Group Project H&M.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "f0a4fa56",
   "metadata": {},
   "outputs": [],
   "source": [
    "import psycopg2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "5c5f7978",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Database connected successfully\n"
     ]
    }
   ],
   "source": [
    "conn = psycopg2.connect(\n",
    "   host=\"localhost\",\n",
    "   database=\"Group Project\",\n",
    "   user=\"postgres\",\n",
    "   password=\"123\")\n",
    "  \n",
    "print(\"Database connected successfully\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "b9ca8dd4",
   "metadata": {},
   "outputs": [],
   "source": [
    "cur = conn.cursor()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "316f259b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b4a48937",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>prod_name</th>\n",
       "      <th>product_type_no</th>\n",
       "      <th>product_type_name</th>\n",
       "      <th>product_group_name</th>\n",
       "      <th>product_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Strap top</td>\n",
       "      <td>253</td>\n",
       "      <td>Vest top</td>\n",
       "      <td>Garment Upper body</td>\n",
       "      <td>10000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Strap top (1)</td>\n",
       "      <td>253</td>\n",
       "      <td>Vest top</td>\n",
       "      <td>Garment Upper body</td>\n",
       "      <td>10000002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>OP T-shirt (Idro)</td>\n",
       "      <td>306</td>\n",
       "      <td>Bra</td>\n",
       "      <td>Underwear</td>\n",
       "      <td>10000003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>20 den 1p Stockings</td>\n",
       "      <td>304</td>\n",
       "      <td>Underwear Tights</td>\n",
       "      <td>Socks &amp; Tights</td>\n",
       "      <td>10000004</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>20 den 1p Stockings</td>\n",
       "      <td>302</td>\n",
       "      <td>Socks</td>\n",
       "      <td>Socks &amp; Tights</td>\n",
       "      <td>10000005</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46787</th>\n",
       "      <td>5pk regular Placement1</td>\n",
       "      <td>302</td>\n",
       "      <td>Socks</td>\n",
       "      <td>Socks &amp; Tights</td>\n",
       "      <td>10046788</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46788</th>\n",
       "      <td>SPORT Malaga tank</td>\n",
       "      <td>253</td>\n",
       "      <td>Vest top</td>\n",
       "      <td>Garment Upper body</td>\n",
       "      <td>10046789</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46789</th>\n",
       "      <td>Cartwheel dress</td>\n",
       "      <td>265</td>\n",
       "      <td>Dress</td>\n",
       "      <td>Garment Full body</td>\n",
       "      <td>10046790</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46790</th>\n",
       "      <td>CLAIRE HAIR CLAW</td>\n",
       "      <td>72</td>\n",
       "      <td>Hair clip</td>\n",
       "      <td>Accessories</td>\n",
       "      <td>10046791</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46791</th>\n",
       "      <td>Lounge dress</td>\n",
       "      <td>265</td>\n",
       "      <td>Dress</td>\n",
       "      <td>Garment Full body</td>\n",
       "      <td>10046792</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>46792 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                    prod_name  product_type_no product_type_name  \\\n",
       "0                   Strap top              253          Vest top   \n",
       "1               Strap top (1)              253          Vest top   \n",
       "2           OP T-shirt (Idro)              306               Bra   \n",
       "3         20 den 1p Stockings              304  Underwear Tights   \n",
       "4         20 den 1p Stockings              302             Socks   \n",
       "...                       ...              ...               ...   \n",
       "46787  5pk regular Placement1              302             Socks   \n",
       "46788       SPORT Malaga tank              253          Vest top   \n",
       "46789         Cartwheel dress              265             Dress   \n",
       "46790        CLAIRE HAIR CLAW               72         Hair clip   \n",
       "46791            Lounge dress              265             Dress   \n",
       "\n",
       "       product_group_name  product_id  \n",
       "0      Garment Upper body    10000001  \n",
       "1      Garment Upper body    10000002  \n",
       "2               Underwear    10000003  \n",
       "3          Socks & Tights    10000004  \n",
       "4          Socks & Tights    10000005  \n",
       "...                   ...         ...  \n",
       "46787      Socks & Tights    10046788  \n",
       "46788  Garment Upper body    10046789  \n",
       "46789   Garment Full body    10046790  \n",
       "46790         Accessories    10046791  \n",
       "46791   Garment Full body    10046792  \n",
       "\n",
       "[46792 rows x 5 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#read data \n",
    "product = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/product.csv')\n",
    "product\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "70b167d1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>product_id</th>\n",
       "      <th>prod_name</th>\n",
       "      <th>product_type_no</th>\n",
       "      <th>product_type_name</th>\n",
       "      <th>product_group_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>10000001</td>\n",
       "      <td>Strap top</td>\n",
       "      <td>253</td>\n",
       "      <td>Vest top</td>\n",
       "      <td>Garment Upper body</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10000002</td>\n",
       "      <td>Strap top (1)</td>\n",
       "      <td>253</td>\n",
       "      <td>Vest top</td>\n",
       "      <td>Garment Upper body</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10000003</td>\n",
       "      <td>OP T-shirt (Idro)</td>\n",
       "      <td>306</td>\n",
       "      <td>Bra</td>\n",
       "      <td>Underwear</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>10000004</td>\n",
       "      <td>20 den 1p Stockings</td>\n",
       "      <td>304</td>\n",
       "      <td>Underwear Tights</td>\n",
       "      <td>Socks &amp; Tights</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10000005</td>\n",
       "      <td>20 den 1p Stockings</td>\n",
       "      <td>302</td>\n",
       "      <td>Socks</td>\n",
       "      <td>Socks &amp; Tights</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46787</th>\n",
       "      <td>10046788</td>\n",
       "      <td>5pk regular Placement1</td>\n",
       "      <td>302</td>\n",
       "      <td>Socks</td>\n",
       "      <td>Socks &amp; Tights</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46788</th>\n",
       "      <td>10046789</td>\n",
       "      <td>SPORT Malaga tank</td>\n",
       "      <td>253</td>\n",
       "      <td>Vest top</td>\n",
       "      <td>Garment Upper body</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46789</th>\n",
       "      <td>10046790</td>\n",
       "      <td>Cartwheel dress</td>\n",
       "      <td>265</td>\n",
       "      <td>Dress</td>\n",
       "      <td>Garment Full body</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46790</th>\n",
       "      <td>10046791</td>\n",
       "      <td>CLAIRE HAIR CLAW</td>\n",
       "      <td>72</td>\n",
       "      <td>Hair clip</td>\n",
       "      <td>Accessories</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46791</th>\n",
       "      <td>10046792</td>\n",
       "      <td>Lounge dress</td>\n",
       "      <td>265</td>\n",
       "      <td>Dress</td>\n",
       "      <td>Garment Full body</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>46792 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       product_id               prod_name  product_type_no product_type_name  \\\n",
       "0        10000001               Strap top              253          Vest top   \n",
       "1        10000002           Strap top (1)              253          Vest top   \n",
       "2        10000003       OP T-shirt (Idro)              306               Bra   \n",
       "3        10000004     20 den 1p Stockings              304  Underwear Tights   \n",
       "4        10000005     20 den 1p Stockings              302             Socks   \n",
       "...           ...                     ...              ...               ...   \n",
       "46787    10046788  5pk regular Placement1              302             Socks   \n",
       "46788    10046789       SPORT Malaga tank              253          Vest top   \n",
       "46789    10046790         Cartwheel dress              265             Dress   \n",
       "46790    10046791        CLAIRE HAIR CLAW               72         Hair clip   \n",
       "46791    10046792            Lounge dress              265             Dress   \n",
       "\n",
       "       product_group_name  \n",
       "0      Garment Upper body  \n",
       "1      Garment Upper body  \n",
       "2               Underwear  \n",
       "3          Socks & Tights  \n",
       "4          Socks & Tights  \n",
       "...                   ...  \n",
       "46787      Socks & Tights  \n",
       "46788  Garment Upper body  \n",
       "46789   Garment Full body  \n",
       "46790         Accessories  \n",
       "46791   Garment Full body  \n",
       "\n",
       "[46792 rows x 5 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "product= product.loc[:, ['product_id','prod_name','product_type_no', 'product_type_name', 'product_group_name']]\n",
    "product = product.drop_duplicates()\n",
    "product= pd.DataFrame(product)\n",
    "product"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9a256dc9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>department_id</th>\n",
       "      <th>department_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>31000001</td>\n",
       "      <td>Jersey Basic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>31000002</td>\n",
       "      <td>Clean Lingerie</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>31000003</td>\n",
       "      <td>Tights basic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>31000004</td>\n",
       "      <td>Baby basics</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>31000005</td>\n",
       "      <td>Casual Lingerie</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>294</th>\n",
       "      <td>31000295</td>\n",
       "      <td>Baby Girl Local Relevance</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>295</th>\n",
       "      <td>31000296</td>\n",
       "      <td>EQ Divided Blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>31000297</td>\n",
       "      <td>Kids Boy Exclusive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>297</th>\n",
       "      <td>31000298</td>\n",
       "      <td>Accessories Other</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>31000299</td>\n",
       "      <td>Blanks</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>299 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     department_id            department_name\n",
       "0         31000001               Jersey Basic\n",
       "1         31000002             Clean Lingerie\n",
       "2         31000003               Tights basic\n",
       "3         31000004                Baby basics\n",
       "4         31000005            Casual Lingerie\n",
       "..             ...                        ...\n",
       "294       31000295  Baby Girl Local Relevance\n",
       "295       31000296            EQ Divided Blue\n",
       "296       31000297         Kids Boy Exclusive\n",
       "297       31000298          Accessories Other\n",
       "298       31000299                     Blanks\n",
       "\n",
       "[299 rows x 2 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "department = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/department.csv')\n",
    "department = department.loc[:, ['department_id','department_name']]\n",
    "department = department.drop_duplicates()\n",
    "department= pd.DataFrame(department)\n",
    "department\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "78a3694a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>graphical_id</th>\n",
       "      <th>graphical_appearance_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20000001</td>\n",
       "      <td>Solid</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>20000002</td>\n",
       "      <td>Stripe</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>20000003</td>\n",
       "      <td>All over pattern</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>20000004</td>\n",
       "      <td>Melange</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>20000005</td>\n",
       "      <td>Transparent</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>20000006</td>\n",
       "      <td>Metallic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>20000007</td>\n",
       "      <td>Application/3D</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>20000008</td>\n",
       "      <td>Denim</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>20000009</td>\n",
       "      <td>Colour blocking</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>20000010</td>\n",
       "      <td>Dot</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>20000011</td>\n",
       "      <td>Other structure</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>20000012</td>\n",
       "      <td>Contrast</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>20000013</td>\n",
       "      <td>Treatment</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>20000014</td>\n",
       "      <td>Check</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>20000015</td>\n",
       "      <td>Chambray</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>20000016</td>\n",
       "      <td>Front print</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>20000017</td>\n",
       "      <td>Glittering/Metallic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>20000018</td>\n",
       "      <td>Mixed solid/pattern</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>20000019</td>\n",
       "      <td>Placement print</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>20000020</td>\n",
       "      <td>Other pattern</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>20000021</td>\n",
       "      <td>Neps</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>20000022</td>\n",
       "      <td>Embroidery</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>20000023</td>\n",
       "      <td>Lace</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>20000024</td>\n",
       "      <td>Jacquard</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>20000025</td>\n",
       "      <td>Unknown</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>20000026</td>\n",
       "      <td>Argyle</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>20000027</td>\n",
       "      <td>Slub</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>20000028</td>\n",
       "      <td>Mesh</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>20000029</td>\n",
       "      <td>Sequin</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>20000030</td>\n",
       "      <td>Hologram</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    graphical_id graphical_appearance_name\n",
       "0       20000001                     Solid\n",
       "1       20000002                    Stripe\n",
       "2       20000003          All over pattern\n",
       "3       20000004                   Melange\n",
       "4       20000005               Transparent\n",
       "5       20000006                  Metallic\n",
       "6       20000007            Application/3D\n",
       "7       20000008                     Denim\n",
       "8       20000009           Colour blocking\n",
       "9       20000010                       Dot\n",
       "10      20000011           Other structure\n",
       "11      20000012                  Contrast\n",
       "12      20000013                 Treatment\n",
       "13      20000014                     Check\n",
       "14      20000015                  Chambray\n",
       "15      20000016               Front print\n",
       "16      20000017       Glittering/Metallic\n",
       "17      20000018       Mixed solid/pattern\n",
       "18      20000019           Placement print\n",
       "19      20000020             Other pattern\n",
       "20      20000021                      Neps\n",
       "21      20000022                Embroidery\n",
       "22      20000023                      Lace\n",
       "23      20000024                  Jacquard\n",
       "24      20000025                   Unknown\n",
       "25      20000026                    Argyle\n",
       "26      20000027                      Slub\n",
       "27      20000028                      Mesh\n",
       "28      20000029                    Sequin\n",
       "29      20000030                  Hologram"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "graphical_appearance = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/graphical.csv')\n",
    "graphical_appearance = graphical_appearance.loc[:, ['graphical_id','graphical_appearance_name']]\n",
    "graphical_appearance = graphical_appearance.drop_duplicates()\n",
    "graphical_appearance = pd.DataFrame(graphical_appearance)\n",
    "graphical_appearance\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "117e7885",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>colour_id</th>\n",
       "      <th>colour_group_code</th>\n",
       "      <th>colour_group_name</th>\n",
       "      <th>perceived_colour_master_id</th>\n",
       "      <th>perceived_colour_master_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>41000001</td>\n",
       "      <td>9</td>\n",
       "      <td>Black</td>\n",
       "      <td>5</td>\n",
       "      <td>Black</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>41000002</td>\n",
       "      <td>10</td>\n",
       "      <td>White</td>\n",
       "      <td>9</td>\n",
       "      <td>White</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>41000003</td>\n",
       "      <td>11</td>\n",
       "      <td>Off White</td>\n",
       "      <td>9</td>\n",
       "      <td>White</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>41000004</td>\n",
       "      <td>12</td>\n",
       "      <td>Light Beige</td>\n",
       "      <td>11</td>\n",
       "      <td>Beige</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>41000005</td>\n",
       "      <td>13</td>\n",
       "      <td>Beige</td>\n",
       "      <td>11</td>\n",
       "      <td>Beige</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>291</th>\n",
       "      <td>41000292</td>\n",
       "      <td>72</td>\n",
       "      <td>Blue</td>\n",
       "      <td>6</td>\n",
       "      <td>Lilac Purple</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>292</th>\n",
       "      <td>41000293</td>\n",
       "      <td>63</td>\n",
       "      <td>Dark Purple</td>\n",
       "      <td>2</td>\n",
       "      <td>Blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>293</th>\n",
       "      <td>41000294</td>\n",
       "      <td>7</td>\n",
       "      <td>Grey</td>\n",
       "      <td>-1</td>\n",
       "      <td>Unknown</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>294</th>\n",
       "      <td>41000295</td>\n",
       "      <td>63</td>\n",
       "      <td>Dark Purple</td>\n",
       "      <td>18</td>\n",
       "      <td>Red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>295</th>\n",
       "      <td>41000296</td>\n",
       "      <td>19</td>\n",
       "      <td>Greenish Khaki</td>\n",
       "      <td>11</td>\n",
       "      <td>Beige</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>296 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     colour_id  colour_group_code colour_group_name  \\\n",
       "0     41000001                  9             Black   \n",
       "1     41000002                 10             White   \n",
       "2     41000003                 11         Off White   \n",
       "3     41000004                 12       Light Beige   \n",
       "4     41000005                 13             Beige   \n",
       "..         ...                ...               ...   \n",
       "291   41000292                 72              Blue   \n",
       "292   41000293                 63       Dark Purple   \n",
       "293   41000294                  7              Grey   \n",
       "294   41000295                 63       Dark Purple   \n",
       "295   41000296                 19    Greenish Khaki   \n",
       "\n",
       "     perceived_colour_master_id perceived_colour_master_name  \n",
       "0                             5                        Black  \n",
       "1                             9                        White  \n",
       "2                             9                        White  \n",
       "3                            11                        Beige  \n",
       "4                            11                        Beige  \n",
       "..                          ...                          ...  \n",
       "291                           6                 Lilac Purple  \n",
       "292                           2                         Blue  \n",
       "293                          -1                      Unknown  \n",
       "294                          18                          Red  \n",
       "295                          11                        Beige  \n",
       "\n",
       "[296 rows x 5 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "color = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/colour.csv')\n",
    "color = color.loc[:, [\"colour_id\",\n",
    "                        \"colour_group_code\",\n",
    "                        \"colour_group_name\",\n",
    "                        \"perceived_colour_master_id\",\n",
    "                        \"perceived_colour_master_name\"]]\n",
    "color = color.drop_duplicates()\n",
    "color = pd.DataFrame(color)\n",
    "color\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "09de54af",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>color_id</th>\n",
       "      <th>color_group_code</th>\n",
       "      <th>color_group_name</th>\n",
       "      <th>perceived_color_master_id</th>\n",
       "      <th>perceived_color_master_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>41000001</td>\n",
       "      <td>9</td>\n",
       "      <td>Black</td>\n",
       "      <td>5</td>\n",
       "      <td>Black</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>41000002</td>\n",
       "      <td>10</td>\n",
       "      <td>White</td>\n",
       "      <td>9</td>\n",
       "      <td>White</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>41000003</td>\n",
       "      <td>11</td>\n",
       "      <td>Off White</td>\n",
       "      <td>9</td>\n",
       "      <td>White</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>41000004</td>\n",
       "      <td>12</td>\n",
       "      <td>Light Beige</td>\n",
       "      <td>11</td>\n",
       "      <td>Beige</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>41000005</td>\n",
       "      <td>13</td>\n",
       "      <td>Beige</td>\n",
       "      <td>11</td>\n",
       "      <td>Beige</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>291</th>\n",
       "      <td>41000292</td>\n",
       "      <td>72</td>\n",
       "      <td>Blue</td>\n",
       "      <td>6</td>\n",
       "      <td>Lilac Purple</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>292</th>\n",
       "      <td>41000293</td>\n",
       "      <td>63</td>\n",
       "      <td>Dark Purple</td>\n",
       "      <td>2</td>\n",
       "      <td>Blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>293</th>\n",
       "      <td>41000294</td>\n",
       "      <td>7</td>\n",
       "      <td>Grey</td>\n",
       "      <td>-1</td>\n",
       "      <td>Unknown</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>294</th>\n",
       "      <td>41000295</td>\n",
       "      <td>63</td>\n",
       "      <td>Dark Purple</td>\n",
       "      <td>18</td>\n",
       "      <td>Red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>295</th>\n",
       "      <td>41000296</td>\n",
       "      <td>19</td>\n",
       "      <td>Greenish Khaki</td>\n",
       "      <td>11</td>\n",
       "      <td>Beige</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>296 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     color_id  color_group_code color_group_name  perceived_color_master_id  \\\n",
       "0    41000001                 9            Black                          5   \n",
       "1    41000002                10            White                          9   \n",
       "2    41000003                11        Off White                          9   \n",
       "3    41000004                12      Light Beige                         11   \n",
       "4    41000005                13            Beige                         11   \n",
       "..        ...               ...              ...                        ...   \n",
       "291  41000292                72             Blue                          6   \n",
       "292  41000293                63      Dark Purple                          2   \n",
       "293  41000294                 7             Grey                         -1   \n",
       "294  41000295                63      Dark Purple                         18   \n",
       "295  41000296                19   Greenish Khaki                         11   \n",
       "\n",
       "    perceived_color_master_name  \n",
       "0                         Black  \n",
       "1                         White  \n",
       "2                         White  \n",
       "3                         Beige  \n",
       "4                         Beige  \n",
       "..                          ...  \n",
       "291                Lilac Purple  \n",
       "292                        Blue  \n",
       "293                     Unknown  \n",
       "294                         Red  \n",
       "295                       Beige  \n",
       "\n",
       "[296 rows x 5 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "color = color.rename(columns={\"colour_id\": \"color_id\", \"colour_group_code\" : \"color_group_code\",\n",
    "                              \"colour_group_name\":\"color_group_name\",\n",
    "                              \"perceived_colour_master_id\" : \"perceived_color_master_id\",\n",
    "                              \"perceived_colour_master_name\" : \"perceived_color_master_name\" })\n",
    "color"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "222e1499",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>section_id</th>\n",
       "      <th>section_name</th>\n",
       "      <th>garment_group_no</th>\n",
       "      <th>garment_group_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>60000001</td>\n",
       "      <td>Womens Everyday Basics</td>\n",
       "      <td>1002</td>\n",
       "      <td>Jersey Basic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>60000002</td>\n",
       "      <td>Womens Lingerie</td>\n",
       "      <td>1017</td>\n",
       "      <td>Under-, Nightwear</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>60000003</td>\n",
       "      <td>Womens Nightwear, Socks &amp; Tigh</td>\n",
       "      <td>1021</td>\n",
       "      <td>Socks and Tights</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>60000004</td>\n",
       "      <td>Baby Essentials &amp; Complements</td>\n",
       "      <td>1002</td>\n",
       "      <td>Jersey Basic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>60000005</td>\n",
       "      <td>Men Underwear</td>\n",
       "      <td>1002</td>\n",
       "      <td>Jersey Basic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>60000191</td>\n",
       "      <td>Divided Complements Other</td>\n",
       "      <td>1016</td>\n",
       "      <td>Trousers Denim</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>191</th>\n",
       "      <td>60000192</td>\n",
       "      <td>Kids Girl</td>\n",
       "      <td>1023</td>\n",
       "      <td>Special Offers</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>192</th>\n",
       "      <td>60000193</td>\n",
       "      <td>Contemporary Street</td>\n",
       "      <td>1001</td>\n",
       "      <td>Unknown</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>193</th>\n",
       "      <td>60000194</td>\n",
       "      <td>Kids Boy</td>\n",
       "      <td>1001</td>\n",
       "      <td>Unknown</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>194</th>\n",
       "      <td>60000195</td>\n",
       "      <td>Divided Complements Other</td>\n",
       "      <td>1019</td>\n",
       "      <td>Accessories</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>195 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     section_id                    section_name  garment_group_no  \\\n",
       "0      60000001          Womens Everyday Basics              1002   \n",
       "1      60000002                 Womens Lingerie              1017   \n",
       "2      60000003  Womens Nightwear, Socks & Tigh              1021   \n",
       "3      60000004   Baby Essentials & Complements              1002   \n",
       "4      60000005                   Men Underwear              1002   \n",
       "..          ...                             ...               ...   \n",
       "190    60000191       Divided Complements Other              1016   \n",
       "191    60000192                       Kids Girl              1023   \n",
       "192    60000193             Contemporary Street              1001   \n",
       "193    60000194                        Kids Boy              1001   \n",
       "194    60000195       Divided Complements Other              1019   \n",
       "\n",
       "    garment_group_name  \n",
       "0         Jersey Basic  \n",
       "1    Under-, Nightwear  \n",
       "2     Socks and Tights  \n",
       "3         Jersey Basic  \n",
       "4         Jersey Basic  \n",
       "..                 ...  \n",
       "190     Trousers Denim  \n",
       "191     Special Offers  \n",
       "192            Unknown  \n",
       "193            Unknown  \n",
       "194        Accessories  \n",
       "\n",
       "[195 rows x 4 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "section = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/section.csv')\n",
    "section = section.loc[:, [\"section_id\",\n",
    "                          \"section_name\",\n",
    "                        \"garment_group_no\",\n",
    "                        \"garment_group_name\"]]\n",
    "section = section.drop_duplicates()\n",
    "section = pd.DataFrame(section)\n",
    "section\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b1677ead",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>index_id</th>\n",
       "      <th>index_name</th>\n",
       "      <th>index_group_no</th>\n",
       "      <th>index_group_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>50000001</td>\n",
       "      <td>Ladieswear</td>\n",
       "      <td>1</td>\n",
       "      <td>Ladieswear</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>50000002</td>\n",
       "      <td>Lingeries/Tights</td>\n",
       "      <td>1</td>\n",
       "      <td>Ladieswear</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>50000003</td>\n",
       "      <td>Baby Sizes 50-98</td>\n",
       "      <td>4</td>\n",
       "      <td>Baby/Children</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>50000004</td>\n",
       "      <td>Menswear</td>\n",
       "      <td>3</td>\n",
       "      <td>Menswear</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>50000005</td>\n",
       "      <td>Ladies Accessories</td>\n",
       "      <td>1</td>\n",
       "      <td>Ladieswear</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>50000006</td>\n",
       "      <td>Sport</td>\n",
       "      <td>26</td>\n",
       "      <td>Sport</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>50000007</td>\n",
       "      <td>Children Sizes 92-140</td>\n",
       "      <td>4</td>\n",
       "      <td>Baby/Children</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>50000008</td>\n",
       "      <td>Divided</td>\n",
       "      <td>2</td>\n",
       "      <td>Divided</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>50000009</td>\n",
       "      <td>Children Sizes 134-170</td>\n",
       "      <td>4</td>\n",
       "      <td>Baby/Children</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>50000010</td>\n",
       "      <td>Children Accessories, Swimwear</td>\n",
       "      <td>4</td>\n",
       "      <td>Baby/Children</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   index_id                      index_name  index_group_no index_group_name\n",
       "0  50000001                      Ladieswear               1       Ladieswear\n",
       "1  50000002                Lingeries/Tights               1       Ladieswear\n",
       "2  50000003                Baby Sizes 50-98               4    Baby/Children\n",
       "3  50000004                        Menswear               3         Menswear\n",
       "4  50000005              Ladies Accessories               1       Ladieswear\n",
       "5  50000006                           Sport              26            Sport\n",
       "6  50000007           Children Sizes 92-140               4    Baby/Children\n",
       "7  50000008                         Divided               2          Divided\n",
       "8  50000009          Children Sizes 134-170               4    Baby/Children\n",
       "9  50000010  Children Accessories, Swimwear               4    Baby/Children"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "index = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/index.csv')\n",
    "index = index.loc[:, ['index_id', 'index_name', 'index_group_no', 'index_group_name']]\n",
    "index = index.drop_duplicates()\n",
    "index = pd.DataFrame(index)\n",
    "index\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "2f275e8f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>index_id</th>\n",
       "      <th>index_name</th>\n",
       "      <th>index_group_id</th>\n",
       "      <th>index_group_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>50000001</td>\n",
       "      <td>Ladieswear</td>\n",
       "      <td>1</td>\n",
       "      <td>Ladieswear</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>50000002</td>\n",
       "      <td>Lingeries/Tights</td>\n",
       "      <td>1</td>\n",
       "      <td>Ladieswear</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>50000003</td>\n",
       "      <td>Baby Sizes 50-98</td>\n",
       "      <td>4</td>\n",
       "      <td>Baby/Children</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>50000004</td>\n",
       "      <td>Menswear</td>\n",
       "      <td>3</td>\n",
       "      <td>Menswear</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>50000005</td>\n",
       "      <td>Ladies Accessories</td>\n",
       "      <td>1</td>\n",
       "      <td>Ladieswear</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>50000006</td>\n",
       "      <td>Sport</td>\n",
       "      <td>26</td>\n",
       "      <td>Sport</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>50000007</td>\n",
       "      <td>Children Sizes 92-140</td>\n",
       "      <td>4</td>\n",
       "      <td>Baby/Children</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>50000008</td>\n",
       "      <td>Divided</td>\n",
       "      <td>2</td>\n",
       "      <td>Divided</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>50000009</td>\n",
       "      <td>Children Sizes 134-170</td>\n",
       "      <td>4</td>\n",
       "      <td>Baby/Children</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>50000010</td>\n",
       "      <td>Children Accessories, Swimwear</td>\n",
       "      <td>4</td>\n",
       "      <td>Baby/Children</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   index_id                      index_name  index_group_id index_group_name\n",
       "0  50000001                      Ladieswear               1       Ladieswear\n",
       "1  50000002                Lingeries/Tights               1       Ladieswear\n",
       "2  50000003                Baby Sizes 50-98               4    Baby/Children\n",
       "3  50000004                        Menswear               3         Menswear\n",
       "4  50000005              Ladies Accessories               1       Ladieswear\n",
       "5  50000006                           Sport              26            Sport\n",
       "6  50000007           Children Sizes 92-140               4    Baby/Children\n",
       "7  50000008                         Divided               2          Divided\n",
       "8  50000009          Children Sizes 134-170               4    Baby/Children\n",
       "9  50000010  Children Accessories, Swimwear               4    Baby/Children"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index = index.rename(columns={\"index_group_no\": \"index_group_id\"})\n",
    "index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "f462bcc1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>FN</th>\n",
       "      <th>fashion_news_frequency</th>\n",
       "      <th>Active</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>NONE</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>True</td>\n",
       "      <td>Regularly</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>137</th>\n",
       "      <td>True</td>\n",
       "      <td>Regularly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>248</th>\n",
       "      <td>False</td>\n",
       "      <td>Regularly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>335</th>\n",
       "      <td>True</td>\n",
       "      <td>NONE</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4744</th>\n",
       "      <td>True</td>\n",
       "      <td>NONE</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5040</th>\n",
       "      <td>True</td>\n",
       "      <td>Monthly</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28322</th>\n",
       "      <td>False</td>\n",
       "      <td>Monthly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>77529</th>\n",
       "      <td>True</td>\n",
       "      <td>Monthly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          FN fashion_news_frequency  Active\n",
       "0      False                   NONE   False\n",
       "4       True              Regularly    True\n",
       "5      False                    NaN   False\n",
       "137     True              Regularly   False\n",
       "248    False              Regularly   False\n",
       "335     True                   NONE   False\n",
       "4744    True                   NONE    True\n",
       "5040    True                Monthly    True\n",
       "28322  False                Monthly   False\n",
       "77529   True                Monthly   False"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fashion_news = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/fashion_news.csv')\n",
    "fashion_news = fashion_news.loc[:, [\"FN\",\n",
    "                        \"fashion_news_frequency\",\n",
    "                                   \"Active\"]]\n",
    "fashion_news = fashion_news.drop_duplicates()\n",
    "fashion_news"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "685c3aa7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>fn_id</th>\n",
       "      <th>FN</th>\n",
       "      <th>fashion_news_frequency</th>\n",
       "      <th>Active</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>900000000</td>\n",
       "      <td>False</td>\n",
       "      <td>NONE</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>900000001</td>\n",
       "      <td>True</td>\n",
       "      <td>Regularly</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>900000002</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>137</th>\n",
       "      <td>900000003</td>\n",
       "      <td>True</td>\n",
       "      <td>Regularly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>248</th>\n",
       "      <td>900000004</td>\n",
       "      <td>False</td>\n",
       "      <td>Regularly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>335</th>\n",
       "      <td>900000005</td>\n",
       "      <td>True</td>\n",
       "      <td>NONE</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4744</th>\n",
       "      <td>900000006</td>\n",
       "      <td>True</td>\n",
       "      <td>NONE</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5040</th>\n",
       "      <td>900000007</td>\n",
       "      <td>True</td>\n",
       "      <td>Monthly</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28322</th>\n",
       "      <td>900000008</td>\n",
       "      <td>False</td>\n",
       "      <td>Monthly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>77529</th>\n",
       "      <td>900000009</td>\n",
       "      <td>True</td>\n",
       "      <td>Monthly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           fn_id     FN fashion_news_frequency  Active\n",
       "0      900000000  False                   NONE   False\n",
       "4      900000001   True              Regularly    True\n",
       "5      900000002  False                    NaN   False\n",
       "137    900000003   True              Regularly   False\n",
       "248    900000004  False              Regularly   False\n",
       "335    900000005   True                   NONE   False\n",
       "4744   900000006   True                   NONE    True\n",
       "5040   900000007   True                Monthly    True\n",
       "28322  900000008  False                Monthly   False\n",
       "77529  900000009   True                Monthly   False"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fashion_news.insert(0, 'fn_id', range(900000000, 900000000 + len(fashion_news)))\n",
    "fashion_news = pd.DataFrame(fashion_news)\n",
    "fashion_news"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "3aca3782",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>fn_id</th>\n",
       "      <th>fn</th>\n",
       "      <th>fashion_news_frequency</th>\n",
       "      <th>active</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>900000000</td>\n",
       "      <td>False</td>\n",
       "      <td>NONE</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>900000001</td>\n",
       "      <td>True</td>\n",
       "      <td>Regularly</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>900000002</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>137</th>\n",
       "      <td>900000003</td>\n",
       "      <td>True</td>\n",
       "      <td>Regularly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>248</th>\n",
       "      <td>900000004</td>\n",
       "      <td>False</td>\n",
       "      <td>Regularly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>335</th>\n",
       "      <td>900000005</td>\n",
       "      <td>True</td>\n",
       "      <td>NONE</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4744</th>\n",
       "      <td>900000006</td>\n",
       "      <td>True</td>\n",
       "      <td>NONE</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5040</th>\n",
       "      <td>900000007</td>\n",
       "      <td>True</td>\n",
       "      <td>Monthly</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28322</th>\n",
       "      <td>900000008</td>\n",
       "      <td>False</td>\n",
       "      <td>Monthly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>77529</th>\n",
       "      <td>900000009</td>\n",
       "      <td>True</td>\n",
       "      <td>Monthly</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           fn_id     fn fashion_news_frequency  active\n",
       "0      900000000  False                   NONE   False\n",
       "4      900000001   True              Regularly    True\n",
       "5      900000002  False                    NaN   False\n",
       "137    900000003   True              Regularly   False\n",
       "248    900000004  False              Regularly   False\n",
       "335    900000005   True                   NONE   False\n",
       "4744   900000006   True                   NONE    True\n",
       "5040   900000007   True                Monthly    True\n",
       "28322  900000008  False                Monthly   False\n",
       "77529  900000009   True                Monthly   False"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fashion_news = fashion_news.rename(columns={\"FN\": \"fn\", \"FN_id\" : \"fn_id\", \"Active\":\"active\"})\n",
    "fashion_news"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "bf564248",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>customer_id</th>\n",
       "      <th>age</th>\n",
       "      <th>club_member_status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>00000dbacae5abe5e23885899a1fa44253a17956c6d1c3...</td>\n",
       "      <td>49.0</td>\n",
       "      <td>ACTIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0000423b00ade91418cceaf3b26c6af3dd342b51fd051e...</td>\n",
       "      <td>25.0</td>\n",
       "      <td>ACTIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...</td>\n",
       "      <td>24.0</td>\n",
       "      <td>ACTIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>00005ca1c9ed5f5146b52ac8639a40ca9d57aeff4d1bd2...</td>\n",
       "      <td>54.0</td>\n",
       "      <td>ACTIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>00006413d8573cd20ed7128e53b7b13819fe5cfc2d801f...</td>\n",
       "      <td>52.0</td>\n",
       "      <td>ACTIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404434</th>\n",
       "      <td>4b9e8490036f8b6631c298802064fccd6c4ff41a5f755f...</td>\n",
       "      <td>21.0</td>\n",
       "      <td>ACTIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404435</th>\n",
       "      <td>4b9eaaf9fc95c429580be86f3b51e8c603907927223823...</td>\n",
       "      <td>34.0</td>\n",
       "      <td>ACTIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404436</th>\n",
       "      <td>4b9eae5f9fc8ebb4cdf45d0af977594dba73d7b97be909...</td>\n",
       "      <td>55.0</td>\n",
       "      <td>ACTIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404437</th>\n",
       "      <td>4b9eb6a6ba2776d99ae241366b13b89a3bb0cbef20f0bc...</td>\n",
       "      <td>58.0</td>\n",
       "      <td>ACTIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404438</th>\n",
       "      <td>4b9ec29639850ce7ec57ca9875cfc5a9d14f92a2c5f313...</td>\n",
       "      <td>22.0</td>\n",
       "      <td>ACTIVE</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>404439 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              customer_id   age  \\\n",
       "0       00000dbacae5abe5e23885899a1fa44253a17956c6d1c3...  49.0   \n",
       "1       0000423b00ade91418cceaf3b26c6af3dd342b51fd051e...  25.0   \n",
       "2       000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...  24.0   \n",
       "3       00005ca1c9ed5f5146b52ac8639a40ca9d57aeff4d1bd2...  54.0   \n",
       "4       00006413d8573cd20ed7128e53b7b13819fe5cfc2d801f...  52.0   \n",
       "...                                                   ...   ...   \n",
       "404434  4b9e8490036f8b6631c298802064fccd6c4ff41a5f755f...  21.0   \n",
       "404435  4b9eaaf9fc95c429580be86f3b51e8c603907927223823...  34.0   \n",
       "404436  4b9eae5f9fc8ebb4cdf45d0af977594dba73d7b97be909...  55.0   \n",
       "404437  4b9eb6a6ba2776d99ae241366b13b89a3bb0cbef20f0bc...  58.0   \n",
       "404438  4b9ec29639850ce7ec57ca9875cfc5a9d14f92a2c5f313...  22.0   \n",
       "\n",
       "       club_member_status  \n",
       "0                  ACTIVE  \n",
       "1                  ACTIVE  \n",
       "2                  ACTIVE  \n",
       "3                  ACTIVE  \n",
       "4                  ACTIVE  \n",
       "...                   ...  \n",
       "404434             ACTIVE  \n",
       "404435             ACTIVE  \n",
       "404436             ACTIVE  \n",
       "404437             ACTIVE  \n",
       "404438             ACTIVE  \n",
       "\n",
       "[404439 rows x 3 columns]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "customer_info = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/customers.csv')\n",
    "customer_info = customer_info.loc[:, [\"customer_id\",\n",
    "                        \"age\",\n",
    "                        \"club_member_status\"]]\n",
    "customer_info = customer_info.drop_duplicates()\n",
    "customer_info = pd.DataFrame(customer_info)\n",
    "customer_info\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "fd87c583",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>t_dat</th>\n",
       "      <th>customer_id</th>\n",
       "      <th>article_id</th>\n",
       "      <th>price</th>\n",
       "      <th>sales_channel_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2018-09-20</td>\n",
       "      <td>000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...</td>\n",
       "      <td>663713001</td>\n",
       "      <td>0.050831</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2018-09-20</td>\n",
       "      <td>000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...</td>\n",
       "      <td>541518023</td>\n",
       "      <td>0.030492</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>2018-09-20</td>\n",
       "      <td>00007d2de826758b65a93dd24ce629ed66842531df6699...</td>\n",
       "      <td>505221004</td>\n",
       "      <td>0.015237</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>2018-09-20</td>\n",
       "      <td>00007d2de826758b65a93dd24ce629ed66842531df6699...</td>\n",
       "      <td>685687003</td>\n",
       "      <td>0.016932</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>2018-09-20</td>\n",
       "      <td>00007d2de826758b65a93dd24ce629ed66842531df6699...</td>\n",
       "      <td>685687004</td>\n",
       "      <td>0.016932</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>529770</th>\n",
       "      <td>2018-09-21</td>\n",
       "      <td>d54b955cbbfce16c1a685add2561ff73fadde0741eab11...</td>\n",
       "      <td>620255001</td>\n",
       "      <td>0.061000</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>529776</th>\n",
       "      <td>2018-09-21</td>\n",
       "      <td>d54b955cbbfce16c1a685add2561ff73fadde0741eab11...</td>\n",
       "      <td>617919009</td>\n",
       "      <td>0.010153</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>529782</th>\n",
       "      <td>2018-09-21</td>\n",
       "      <td>d54b955cbbfce16c1a685add2561ff73fadde0741eab11...</td>\n",
       "      <td>617919011</td>\n",
       "      <td>0.023712</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>529794</th>\n",
       "      <td>2018-09-21</td>\n",
       "      <td>d54b955cbbfce16c1a685add2561ff73fadde0741eab11...</td>\n",
       "      <td>626407003</td>\n",
       "      <td>0.044051</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>529800</th>\n",
       "      <td>2018-09-21</td>\n",
       "      <td>d54d5e6eb2070d5730c26fc7806c88e96499b5719e9a57...</td>\n",
       "      <td>633130006</td>\n",
       "      <td>0.016932</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>79770 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             t_dat                                        customer_id  \\\n",
       "0       2018-09-20  000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...   \n",
       "6       2018-09-20  000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...   \n",
       "12      2018-09-20  00007d2de826758b65a93dd24ce629ed66842531df6699...   \n",
       "18      2018-09-20  00007d2de826758b65a93dd24ce629ed66842531df6699...   \n",
       "24      2018-09-20  00007d2de826758b65a93dd24ce629ed66842531df6699...   \n",
       "...            ...                                                ...   \n",
       "529770  2018-09-21  d54b955cbbfce16c1a685add2561ff73fadde0741eab11...   \n",
       "529776  2018-09-21  d54b955cbbfce16c1a685add2561ff73fadde0741eab11...   \n",
       "529782  2018-09-21  d54b955cbbfce16c1a685add2561ff73fadde0741eab11...   \n",
       "529794  2018-09-21  d54b955cbbfce16c1a685add2561ff73fadde0741eab11...   \n",
       "529800  2018-09-21  d54d5e6eb2070d5730c26fc7806c88e96499b5719e9a57...   \n",
       "\n",
       "        article_id     price  sales_channel_id  \n",
       "0        663713001  0.050831                 2  \n",
       "6        541518023  0.030492                 2  \n",
       "12       505221004  0.015237                 2  \n",
       "18       685687003  0.016932                 2  \n",
       "24       685687004  0.016932                 2  \n",
       "...            ...       ...               ...  \n",
       "529770   620255001  0.061000                 2  \n",
       "529776   617919009  0.010153                 2  \n",
       "529782   617919011  0.023712                 2  \n",
       "529794   626407003  0.044051                 2  \n",
       "529800   633130006  0.016932                 1  \n",
       "\n",
       "[79770 rows x 5 columns]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "trans = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/trans.csv')\n",
    "trans = trans.loc[:, [\"t_dat\",\n",
    "                        \"customer_id\",\n",
    "                        \"article_id\",\n",
    "                        \"price\",\n",
    "                        \"sales_channel_id\"]]\n",
    "trans = trans.drop_duplicates()\n",
    "trans = pd.DataFrame(trans)\n",
    "trans\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "f2824b8b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>article_id</th>\n",
       "      <th>colour_id</th>\n",
       "      <th>department_id</th>\n",
       "      <th>graphical_id</th>\n",
       "      <th>index_id</th>\n",
       "      <th>product_id</th>\n",
       "      <th>section_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>108775015</td>\n",
       "      <td>41000001</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000001</td>\n",
       "      <td>50000001</td>\n",
       "      <td>10000001</td>\n",
       "      <td>60000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>108775015</td>\n",
       "      <td>41000001</td>\n",
       "      <td>31000006</td>\n",
       "      <td>20000001</td>\n",
       "      <td>50000001</td>\n",
       "      <td>10000001</td>\n",
       "      <td>60000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>108775044</td>\n",
       "      <td>41000002</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000001</td>\n",
       "      <td>50000001</td>\n",
       "      <td>10000001</td>\n",
       "      <td>60000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>108775044</td>\n",
       "      <td>41000002</td>\n",
       "      <td>31000006</td>\n",
       "      <td>20000001</td>\n",
       "      <td>50000001</td>\n",
       "      <td>10000001</td>\n",
       "      <td>60000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>108775051</td>\n",
       "      <td>41000003</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000002</td>\n",
       "      <td>50000001</td>\n",
       "      <td>10000002</td>\n",
       "      <td>60000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245042</th>\n",
       "      <td>959461001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>31000007</td>\n",
       "      <td>20000001</td>\n",
       "      <td>50000001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>60000088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245043</th>\n",
       "      <td>959461001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>31000063</td>\n",
       "      <td>20000001</td>\n",
       "      <td>50000001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>60000088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245044</th>\n",
       "      <td>959461001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>31000099</td>\n",
       "      <td>20000001</td>\n",
       "      <td>50000001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>60000088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245045</th>\n",
       "      <td>959461001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>31000127</td>\n",
       "      <td>20000001</td>\n",
       "      <td>50000001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>60000088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245046</th>\n",
       "      <td>959461001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>31000179</td>\n",
       "      <td>20000001</td>\n",
       "      <td>50000001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>60000088</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>245047 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        article_id  colour_id  department_id  graphical_id  index_id  \\\n",
       "0        108775015   41000001       31000001      20000001  50000001   \n",
       "1        108775015   41000001       31000006      20000001  50000001   \n",
       "2        108775044   41000002       31000001      20000001  50000001   \n",
       "3        108775044   41000002       31000006      20000001  50000001   \n",
       "4        108775051   41000003       31000001      20000002  50000001   \n",
       "...            ...        ...            ...           ...       ...   \n",
       "245042   959461001   41000003       31000007      20000001  50000001   \n",
       "245043   959461001   41000003       31000063      20000001  50000001   \n",
       "245044   959461001   41000003       31000099      20000001  50000001   \n",
       "245045   959461001   41000003       31000127      20000001  50000001   \n",
       "245046   959461001   41000003       31000179      20000001  50000001   \n",
       "\n",
       "        product_id  section_id  \n",
       "0         10000001    60000001  \n",
       "1         10000001    60000001  \n",
       "2         10000001    60000001  \n",
       "3         10000001    60000001  \n",
       "4         10000002    60000001  \n",
       "...            ...         ...  \n",
       "245042    10050044    60000088  \n",
       "245043    10050044    60000088  \n",
       "245044    10050044    60000088  \n",
       "245045    10050044    60000088  \n",
       "245046    10050044    60000088  \n",
       "\n",
       "[245047 rows x 7 columns]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Reading data \n",
    "article = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/articlebridge.csv')\n",
    "\n",
    "article\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "2e2c7fce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>article_id</th>\n",
       "      <th>product_id</th>\n",
       "      <th>department_id</th>\n",
       "      <th>graphical_id</th>\n",
       "      <th>colour_id</th>\n",
       "      <th>section_id</th>\n",
       "      <th>index_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>108775015</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000001</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>108775015</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000006</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000001</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>108775044</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000002</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>108775044</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000006</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000002</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>108775051</td>\n",
       "      <td>10000002</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000002</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245042</th>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000007</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245043</th>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000063</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245044</th>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000099</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245045</th>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000127</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245046</th>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000179</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>245047 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        article_id  product_id  department_id  graphical_id  colour_id  \\\n",
       "0        108775015    10000001       31000001      20000001   41000001   \n",
       "1        108775015    10000001       31000006      20000001   41000001   \n",
       "2        108775044    10000001       31000001      20000001   41000002   \n",
       "3        108775044    10000001       31000006      20000001   41000002   \n",
       "4        108775051    10000002       31000001      20000002   41000003   \n",
       "...            ...         ...            ...           ...        ...   \n",
       "245042   959461001    10050044       31000007      20000001   41000003   \n",
       "245043   959461001    10050044       31000063      20000001   41000003   \n",
       "245044   959461001    10050044       31000099      20000001   41000003   \n",
       "245045   959461001    10050044       31000127      20000001   41000003   \n",
       "245046   959461001    10050044       31000179      20000001   41000003   \n",
       "\n",
       "        section_id  index_id  \n",
       "0         60000001  50000001  \n",
       "1         60000001  50000001  \n",
       "2         60000001  50000001  \n",
       "3         60000001  50000001  \n",
       "4         60000001  50000001  \n",
       "...            ...       ...  \n",
       "245042    60000088  50000001  \n",
       "245043    60000088  50000001  \n",
       "245044    60000088  50000001  \n",
       "245045    60000088  50000001  \n",
       "245046    60000088  50000001  \n",
       "\n",
       "[245047 rows x 7 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "article = article.loc[:, [\"article_id\",\n",
    "                           \"product_id\",\n",
    "                           \"department_id\",\n",
    "                           \"graphical_id\",\n",
    "                           \"colour_id\",\n",
    "                           \"section_id\",\n",
    "                            \"index_id\"]]\n",
    "article = article.drop_duplicates()\n",
    "article = pd.DataFrame(article)\n",
    "article"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "ef85bf26",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>article_bridge_id</th>\n",
       "      <th>article_id</th>\n",
       "      <th>product_id</th>\n",
       "      <th>department_id</th>\n",
       "      <th>graphical_id</th>\n",
       "      <th>colour_id</th>\n",
       "      <th>section_id</th>\n",
       "      <th>index_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>440000000</td>\n",
       "      <td>108775015</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000001</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>440000001</td>\n",
       "      <td>108775015</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000006</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000001</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>440000002</td>\n",
       "      <td>108775044</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000002</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>440000003</td>\n",
       "      <td>108775044</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000006</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000002</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>440000004</td>\n",
       "      <td>108775051</td>\n",
       "      <td>10000002</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000002</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245042</th>\n",
       "      <td>440245042</td>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000007</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245043</th>\n",
       "      <td>440245043</td>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000063</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245044</th>\n",
       "      <td>440245044</td>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000099</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245045</th>\n",
       "      <td>440245045</td>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000127</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245046</th>\n",
       "      <td>440245046</td>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000179</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>245047 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        article_bridge_id  article_id  product_id  department_id  \\\n",
       "0               440000000   108775015    10000001       31000001   \n",
       "1               440000001   108775015    10000001       31000006   \n",
       "2               440000002   108775044    10000001       31000001   \n",
       "3               440000003   108775044    10000001       31000006   \n",
       "4               440000004   108775051    10000002       31000001   \n",
       "...                   ...         ...         ...            ...   \n",
       "245042          440245042   959461001    10050044       31000007   \n",
       "245043          440245043   959461001    10050044       31000063   \n",
       "245044          440245044   959461001    10050044       31000099   \n",
       "245045          440245045   959461001    10050044       31000127   \n",
       "245046          440245046   959461001    10050044       31000179   \n",
       "\n",
       "        graphical_id  colour_id  section_id  index_id  \n",
       "0           20000001   41000001    60000001  50000001  \n",
       "1           20000001   41000001    60000001  50000001  \n",
       "2           20000001   41000002    60000001  50000001  \n",
       "3           20000001   41000002    60000001  50000001  \n",
       "4           20000002   41000003    60000001  50000001  \n",
       "...              ...        ...         ...       ...  \n",
       "245042      20000001   41000003    60000088  50000001  \n",
       "245043      20000001   41000003    60000088  50000001  \n",
       "245044      20000001   41000003    60000088  50000001  \n",
       "245045      20000001   41000003    60000088  50000001  \n",
       "245046      20000001   41000003    60000088  50000001  \n",
       "\n",
       "[245047 rows x 8 columns]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "article.insert(0, 'article_bridge_id', range(440000000, 440000000 + len(article)))\n",
    "article"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "6f837ff4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>article_bridge_id</th>\n",
       "      <th>article_id</th>\n",
       "      <th>product_id</th>\n",
       "      <th>department_id</th>\n",
       "      <th>graphical_id</th>\n",
       "      <th>color_id</th>\n",
       "      <th>section_id</th>\n",
       "      <th>index_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>440000000</td>\n",
       "      <td>108775015</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000001</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>440000001</td>\n",
       "      <td>108775015</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000006</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000001</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>440000002</td>\n",
       "      <td>108775044</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000002</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>440000003</td>\n",
       "      <td>108775044</td>\n",
       "      <td>10000001</td>\n",
       "      <td>31000006</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000002</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>440000004</td>\n",
       "      <td>108775051</td>\n",
       "      <td>10000002</td>\n",
       "      <td>31000001</td>\n",
       "      <td>20000002</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000001</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245042</th>\n",
       "      <td>440245042</td>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000007</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245043</th>\n",
       "      <td>440245043</td>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000063</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245044</th>\n",
       "      <td>440245044</td>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000099</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245045</th>\n",
       "      <td>440245045</td>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000127</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245046</th>\n",
       "      <td>440245046</td>\n",
       "      <td>959461001</td>\n",
       "      <td>10050044</td>\n",
       "      <td>31000179</td>\n",
       "      <td>20000001</td>\n",
       "      <td>41000003</td>\n",
       "      <td>60000088</td>\n",
       "      <td>50000001</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>245047 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        article_bridge_id  article_id  product_id  department_id  \\\n",
       "0               440000000   108775015    10000001       31000001   \n",
       "1               440000001   108775015    10000001       31000006   \n",
       "2               440000002   108775044    10000001       31000001   \n",
       "3               440000003   108775044    10000001       31000006   \n",
       "4               440000004   108775051    10000002       31000001   \n",
       "...                   ...         ...         ...            ...   \n",
       "245042          440245042   959461001    10050044       31000007   \n",
       "245043          440245043   959461001    10050044       31000063   \n",
       "245044          440245044   959461001    10050044       31000099   \n",
       "245045          440245045   959461001    10050044       31000127   \n",
       "245046          440245046   959461001    10050044       31000179   \n",
       "\n",
       "        graphical_id  color_id  section_id  index_id  \n",
       "0           20000001  41000001    60000001  50000001  \n",
       "1           20000001  41000001    60000001  50000001  \n",
       "2           20000001  41000002    60000001  50000001  \n",
       "3           20000001  41000002    60000001  50000001  \n",
       "4           20000002  41000003    60000001  50000001  \n",
       "...              ...       ...         ...       ...  \n",
       "245042      20000001  41000003    60000088  50000001  \n",
       "245043      20000001  41000003    60000088  50000001  \n",
       "245044      20000001  41000003    60000088  50000001  \n",
       "245045      20000001  41000003    60000088  50000001  \n",
       "245046      20000001  41000003    60000088  50000001  \n",
       "\n",
       "[245047 rows x 8 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "article = article.rename(columns={\"colour_id\": \"color_id\"})\n",
    "article"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "1db0e814",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>customer_id</th>\n",
       "      <th>fashion_news_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>00000dbacae5abe5e23885899a1fa44253a17956c6d1c3...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0000423b00ade91418cceaf3b26c6af3dd342b51fd051e...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>00005ca1c9ed5f5146b52ac8639a40ca9d57aeff4d1bd2...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>00006413d8573cd20ed7128e53b7b13819fe5cfc2d801f...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404434</th>\n",
       "      <td>4b9e8490036f8b6631c298802064fccd6c4ff41a5f755f...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404435</th>\n",
       "      <td>4b9eaaf9fc95c429580be86f3b51e8c603907927223823...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404436</th>\n",
       "      <td>4b9eae5f9fc8ebb4cdf45d0af977594dba73d7b97be909...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404437</th>\n",
       "      <td>4b9eb6a6ba2776d99ae241366b13b89a3bb0cbef20f0bc...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404438</th>\n",
       "      <td>4b9ec29639850ce7ec57ca9875cfc5a9d14f92a2c5f313...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>404439 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              customer_id  fashion_news_id\n",
       "0       00000dbacae5abe5e23885899a1fa44253a17956c6d1c3...         91000001\n",
       "1       0000423b00ade91418cceaf3b26c6af3dd342b51fd051e...         91000001\n",
       "2       000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...         91000001\n",
       "3       00005ca1c9ed5f5146b52ac8639a40ca9d57aeff4d1bd2...         91000001\n",
       "4       00006413d8573cd20ed7128e53b7b13819fe5cfc2d801f...         91000002\n",
       "...                                                   ...              ...\n",
       "404434  4b9e8490036f8b6631c298802064fccd6c4ff41a5f755f...         91000002\n",
       "404435  4b9eaaf9fc95c429580be86f3b51e8c603907927223823...         91000001\n",
       "404436  4b9eae5f9fc8ebb4cdf45d0af977594dba73d7b97be909...         91000001\n",
       "404437  4b9eb6a6ba2776d99ae241366b13b89a3bb0cbef20f0bc...         91000002\n",
       "404438  4b9ec29639850ce7ec57ca9875cfc5a9d14f92a2c5f313...         91000002\n",
       "\n",
       "[404439 rows x 2 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "customer_bridge = pd.read_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/customer_bridge_new.csv')\n",
    "customer_bridge = customer_bridge.drop_duplicates()\n",
    "customer_bridge = pd.DataFrame(customer_bridge)\n",
    "customer_bridge\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "92a379a3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>customer_id</th>\n",
       "      <th>FN_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>00000dbacae5abe5e23885899a1fa44253a17956c6d1c3...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0000423b00ade91418cceaf3b26c6af3dd342b51fd051e...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>00005ca1c9ed5f5146b52ac8639a40ca9d57aeff4d1bd2...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>00006413d8573cd20ed7128e53b7b13819fe5cfc2d801f...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404434</th>\n",
       "      <td>4b9e8490036f8b6631c298802064fccd6c4ff41a5f755f...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404435</th>\n",
       "      <td>4b9eaaf9fc95c429580be86f3b51e8c603907927223823...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404436</th>\n",
       "      <td>4b9eae5f9fc8ebb4cdf45d0af977594dba73d7b97be909...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404437</th>\n",
       "      <td>4b9eb6a6ba2776d99ae241366b13b89a3bb0cbef20f0bc...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404438</th>\n",
       "      <td>4b9ec29639850ce7ec57ca9875cfc5a9d14f92a2c5f313...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>404439 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              customer_id     FN_id\n",
       "0       00000dbacae5abe5e23885899a1fa44253a17956c6d1c3...  91000001\n",
       "1       0000423b00ade91418cceaf3b26c6af3dd342b51fd051e...  91000001\n",
       "2       000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...  91000001\n",
       "3       00005ca1c9ed5f5146b52ac8639a40ca9d57aeff4d1bd2...  91000001\n",
       "4       00006413d8573cd20ed7128e53b7b13819fe5cfc2d801f...  91000002\n",
       "...                                                   ...       ...\n",
       "404434  4b9e8490036f8b6631c298802064fccd6c4ff41a5f755f...  91000002\n",
       "404435  4b9eaaf9fc95c429580be86f3b51e8c603907927223823...  91000001\n",
       "404436  4b9eae5f9fc8ebb4cdf45d0af977594dba73d7b97be909...  91000001\n",
       "404437  4b9eb6a6ba2776d99ae241366b13b89a3bb0cbef20f0bc...  91000002\n",
       "404438  4b9ec29639850ce7ec57ca9875cfc5a9d14f92a2c5f313...  91000002\n",
       "\n",
       "[404439 rows x 2 columns]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "customer_bridge = customer_bridge.rename(columns={\"fashion_news_id\": \"FN_id\"})\n",
    "customer_bridge"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "32a08158",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>customer_id</th>\n",
       "      <th>fn_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>00000dbacae5abe5e23885899a1fa44253a17956c6d1c3...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0000423b00ade91418cceaf3b26c6af3dd342b51fd051e...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>00005ca1c9ed5f5146b52ac8639a40ca9d57aeff4d1bd2...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>00006413d8573cd20ed7128e53b7b13819fe5cfc2d801f...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404434</th>\n",
       "      <td>4b9e8490036f8b6631c298802064fccd6c4ff41a5f755f...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404435</th>\n",
       "      <td>4b9eaaf9fc95c429580be86f3b51e8c603907927223823...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404436</th>\n",
       "      <td>4b9eae5f9fc8ebb4cdf45d0af977594dba73d7b97be909...</td>\n",
       "      <td>91000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404437</th>\n",
       "      <td>4b9eb6a6ba2776d99ae241366b13b89a3bb0cbef20f0bc...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>404438</th>\n",
       "      <td>4b9ec29639850ce7ec57ca9875cfc5a9d14f92a2c5f313...</td>\n",
       "      <td>91000002</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>404439 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              customer_id     fn_id\n",
       "0       00000dbacae5abe5e23885899a1fa44253a17956c6d1c3...  91000001\n",
       "1       0000423b00ade91418cceaf3b26c6af3dd342b51fd051e...  91000001\n",
       "2       000058a12d5b43e67d225668fa1f8d618c13dc232df0ca...  91000001\n",
       "3       00005ca1c9ed5f5146b52ac8639a40ca9d57aeff4d1bd2...  91000001\n",
       "4       00006413d8573cd20ed7128e53b7b13819fe5cfc2d801f...  91000002\n",
       "...                                                   ...       ...\n",
       "404434  4b9e8490036f8b6631c298802064fccd6c4ff41a5f755f...  91000002\n",
       "404435  4b9eaaf9fc95c429580be86f3b51e8c603907927223823...  91000001\n",
       "404436  4b9eae5f9fc8ebb4cdf45d0af977594dba73d7b97be909...  91000001\n",
       "404437  4b9eb6a6ba2776d99ae241366b13b89a3bb0cbef20f0bc...  91000002\n",
       "404438  4b9ec29639850ce7ec57ca9875cfc5a9d14f92a2c5f313...  91000002\n",
       "\n",
       "[404439 rows x 2 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "customer_bridge = customer_bridge.rename(columns={\"FN_id\": \"fn_id\"})\n",
    "customer_bridge"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "9d3d7834",
   "metadata": {},
   "outputs": [],
   "source": [
    "article.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/article_bridge.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "7138809c",
   "metadata": {},
   "outputs": [],
   "source": [
    "color.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/color.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "623a7129",
   "metadata": {},
   "outputs": [],
   "source": [
    "customer_bridge.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/customer_bridge.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "01505ecb",
   "metadata": {},
   "outputs": [],
   "source": [
    "department.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/department.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "2993b8cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "fashion_news.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/fashion_news.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "01520c5b",
   "metadata": {},
   "outputs": [],
   "source": [
    "graphical_appearance.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/graphical_appearance.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "c162b39c",
   "metadata": {},
   "outputs": [],
   "source": [
    "index.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/index.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "6b5fe35e",
   "metadata": {},
   "outputs": [],
   "source": [
    "section.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/section.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "5439aff8",
   "metadata": {},
   "outputs": [],
   "source": [
    "trans.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/trans.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "8b18dbd7",
   "metadata": {},
   "outputs": [],
   "source": [
    "product.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/product.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "3e6a1212",
   "metadata": {},
   "outputs": [],
   "source": [
    "customer_info.to_csv(r'/Users/minahsu/Desktop/Columbia Work/Spring 2022/SQL/Group Project/tables/Python/Cleaned Table/customer_info.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e3967c74",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bce70eae",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "cba78623",
   "metadata": {},
   "outputs": [],
   "source": [
    "#read data into postgresql\n",
    "#!pip install sqlalchemy\n",
    "from sqlalchemy import create_engine\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "5ef610b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "engine = create_engine(\"postgresql://postgres:123@localhost:5432/Group Project\")\n",
    "con = engine.connect()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "id": "cc5a8bd7",
   "metadata": {},
   "outputs": [],
   "source": [
    "color = pd.DataFrame(color)\n",
    "color.to_sql(name='color',con=con,if_exists='append', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "cf30ecfe",
   "metadata": {},
   "outputs": [],
   "source": [
    "customer_info = pd.DataFrame(customer_info)\n",
    "customer_info.to_sql(name='customer_info',con=con,if_exists='append', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "3769a744",
   "metadata": {},
   "outputs": [],
   "source": [
    "department = pd.DataFrame(department)\n",
    "department.to_sql(name='department',con=con,if_exists='append', index=False)"
   ]
  },
  {
   "cell_type": "raw",
   "id": "21d3e63b",
   "metadata": {},
   "source": [
    "fashion_news = pd.DataFrame(fashion_news)\n",
    "fashion_news.to_sql(name='fashion_news',con=con,if_exists='append', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "8c9213f3",
   "metadata": {},
   "outputs": [],
   "source": [
    "graphical_appearance = pd.DataFrame(graphical_appearance)\n",
    "graphical_appearance.to_sql(name='graphical_appearance',con=con,if_exists='append', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "id": "2fe018fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "index = pd.DataFrame(index)\n",
    "index.to_sql(name='index',con=con,if_exists='append', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "id": "c6e360f4",
   "metadata": {},
   "outputs": [
    {
     "ename": "IntegrityError",
     "evalue": "(psycopg2.errors.UniqueViolation) duplicate key value violates unique constraint \"product_pkey\"\nDETAIL:  Key (product_id)=(10000001) already exists.\n\n[SQL: INSERT INTO product (product_id, prod_name, product_type_no, product_type_name, product_group_name) VALUES (%(product_id)s, %(prod_name)s, %(product_type_no)s, %(product_type_name)s, %(product_group_name)s)]\n[parameters: ({'product_id': 10000001, 'prod_name': 'Strap top', 'product_type_no': 253, 'product_type_name': 'Vest top', 'product_group_name': 'Garment Upper body'}, {'product_id': 10000002, 'prod_name': 'Strap top (1)', 'product_type_no': 253, 'product_type_name': 'Vest top', 'product_group_name': 'Garment Upper body'}, {'product_id': 10000003, 'prod_name': 'OP T-shirt (Idro)', 'product_type_no': 306, 'product_type_name': 'Bra', 'product_group_name': 'Underwear'}, {'product_id': 10000004, 'prod_name': '20 den 1p Stockings', 'product_type_no': 304, 'product_type_name': 'Underwear Tights', 'product_group_name': 'Socks & Tights'}, {'product_id': 10000005, 'prod_name': '20 den 1p Stockings', 'product_type_no': 302, 'product_type_name': 'Socks', 'product_group_name': 'Socks & Tights'}, {'product_id': 10000006, 'prod_name': 'Shape Up 30 den 1p Tights', 'product_type_no': 273, 'product_type_name': 'Leggings/Tights', 'product_group_name': 'Garment Lower body'}, {'product_id': 10000007, 'prod_name': 'Support 40 den 1p Tights', 'product_type_no': 304, 'product_type_name': 'Underwear Tights', 'product_group_name': 'Socks & Tights'}, {'product_id': 10000008, 'prod_name': '200 den 1p Tights', 'product_type_no': 304, 'product_type_name': 'Underwear Tights', 'product_group_name': 'Socks & Tights'}  ... displaying 10 of 46792 total bound parameter sets ...  {'product_id': 10046791, 'prod_name': 'CLAIRE HAIR CLAW', 'product_type_no': 72, 'product_type_name': 'Hair clip', 'product_group_name': 'Accessories'}, {'product_id': 10046792, 'prod_name': 'Lounge dress', 'product_type_no': 265, 'product_type_name': 'Dress', 'product_group_name': 'Garment Full body'})]\n(Background on this error at: https://sqlalche.me/e/14/gkpj)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mUniqueViolation\u001b[0m                           Traceback (most recent call last)",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36m_execute_context\u001b[0;34m(self, dialect, constructor, statement, parameters, execution_options, *args, **kw)\u001b[0m\n\u001b[1;32m   1750\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mevt_handled\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1751\u001b[0;31m                     self.dialect.do_executemany(\n\u001b[0m\u001b[1;32m   1752\u001b[0m                         \u001b[0mcursor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstatement\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/dialects/postgresql/psycopg2.py\u001b[0m in \u001b[0;36mdo_executemany\u001b[0;34m(self, cursor, statement, parameters, context)\u001b[0m\n\u001b[1;32m    961\u001b[0m             \u001b[0mxtras\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_psycopg2_extras\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 962\u001b[0;31m             context._psycopg2_fetched_rows = xtras.execute_values(\n\u001b[0m\u001b[1;32m    963\u001b[0m                 \u001b[0mcursor\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/psycopg2/extras.py\u001b[0m in \u001b[0;36mexecute_values\u001b[0;34m(cur, sql, argslist, template, page_size, fetch)\u001b[0m\n\u001b[1;32m   1269\u001b[0m         \u001b[0mparts\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpost\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1270\u001b[0;31m         \u001b[0mcur\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mb''\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1271\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mfetch\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mUniqueViolation\u001b[0m: duplicate key value violates unique constraint \"product_pkey\"\nDETAIL:  Key (product_id)=(10000001) already exists.\n",
      "\nThe above exception was the direct cause of the following exception:\n",
      "\u001b[0;31mIntegrityError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[0;32m/var/folders/62/t7hrl00s7dv5ch357bbq539r0000gn/T/ipykernel_15629/1906422522.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mproduct\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mproduct\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mproduct\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_sql\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'product'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mcon\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcon\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mif_exists\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'append'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36mto_sql\u001b[0;34m(self, name, con, schema, if_exists, index, index_label, chunksize, dtype, method)\u001b[0m\n\u001b[1;32m   2870\u001b[0m         \u001b[0;32mfrom\u001b[0m \u001b[0mpandas\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mio\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0msql\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2871\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2872\u001b[0;31m         sql.to_sql(\n\u001b[0m\u001b[1;32m   2873\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2874\u001b[0m             \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36mto_sql\u001b[0;34m(frame, name, con, schema, if_exists, index, index_label, chunksize, dtype, method, engine, **engine_kwargs)\u001b[0m\n\u001b[1;32m    715\u001b[0m         )\n\u001b[1;32m    716\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 717\u001b[0;31m     pandas_sql.to_sql(\n\u001b[0m\u001b[1;32m    718\u001b[0m         \u001b[0mframe\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    719\u001b[0m         \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36mto_sql\u001b[0;34m(self, frame, name, if_exists, index, index_label, schema, chunksize, dtype, method, engine, **engine_kwargs)\u001b[0m\n\u001b[1;32m   1759\u001b[0m         )\n\u001b[1;32m   1760\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1761\u001b[0;31m         sql_engine.insert_records(\n\u001b[0m\u001b[1;32m   1762\u001b[0m             \u001b[0mtable\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtable\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1763\u001b[0m             \u001b[0mcon\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconnectable\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36minsert_records\u001b[0;34m(self, table, con, frame, name, index, schema, chunksize, method, **engine_kwargs)\u001b[0m\n\u001b[1;32m   1348\u001b[0m                 \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"inf cannot be used with MySQL\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1349\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1350\u001b[0;31m                 \u001b[0;32mraise\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1351\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1352\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36minsert_records\u001b[0;34m(self, table, con, frame, name, index, schema, chunksize, method, **engine_kwargs)\u001b[0m\n\u001b[1;32m   1338\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1339\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1340\u001b[0;31m             \u001b[0mtable\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minsert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mchunksize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mchunksize\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1341\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSQLAlchemyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1342\u001b[0m             \u001b[0;31m# GH34431\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36minsert\u001b[0;34m(self, chunksize, method)\u001b[0m\n\u001b[1;32m    965\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    966\u001b[0m                 \u001b[0mchunk_iter\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0marr\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstart_i\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mend_i\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0marr\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdata_list\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 967\u001b[0;31m                 \u001b[0mexec_insert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkeys\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mchunk_iter\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    968\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    969\u001b[0m     def _query_iterator(\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36m_execute_insert\u001b[0;34m(self, conn, keys, data_iter)\u001b[0m\n\u001b[1;32m    880\u001b[0m         \"\"\"\n\u001b[1;32m    881\u001b[0m         \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mdict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrow\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mrow\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdata_iter\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 882\u001b[0;31m         \u001b[0mconn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtable\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minsert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    883\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    884\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_execute_insert_multi\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkeys\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata_iter\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36mexecute\u001b[0;34m(self, statement, *multiparams, **params)\u001b[0m\n\u001b[1;32m   1261\u001b[0m             )\n\u001b[1;32m   1262\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1263\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mmeth\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmultiparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_EMPTY_EXECUTION_OPTS\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1264\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1265\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_execute_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmultiparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexecution_options\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/sql/elements.py\u001b[0m in \u001b[0;36m_execute_on_connection\u001b[0;34m(self, connection, multiparams, params, execution_options, _force)\u001b[0m\n\u001b[1;32m    321\u001b[0m     ):\n\u001b[1;32m    322\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0m_force\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msupports_execution\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 323\u001b[0;31m             return connection._execute_clauseelement(\n\u001b[0m\u001b[1;32m    324\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmultiparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexecution_options\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    325\u001b[0m             )\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36m_execute_clauseelement\u001b[0;34m(self, elem, multiparams, params, execution_options)\u001b[0m\n\u001b[1;32m   1450\u001b[0m             \u001b[0mlinting\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdialect\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompiler_linting\u001b[0m \u001b[0;34m|\u001b[0m \u001b[0mcompiler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mWARN_LINTING\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1451\u001b[0m         )\n\u001b[0;32m-> 1452\u001b[0;31m         ret = self._execute_context(\n\u001b[0m\u001b[1;32m   1453\u001b[0m             \u001b[0mdialect\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1454\u001b[0m             \u001b[0mdialect\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecution_ctx_cls\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_init_compiled\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36m_execute_context\u001b[0;34m(self, dialect, constructor, statement, parameters, execution_options, *args, **kw)\u001b[0m\n\u001b[1;32m   1812\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1813\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mBaseException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1814\u001b[0;31m             self._handle_dbapi_exception(\n\u001b[0m\u001b[1;32m   1815\u001b[0m                 \u001b[0me\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstatement\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcursor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1816\u001b[0m             )\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36m_handle_dbapi_exception\u001b[0;34m(self, e, statement, parameters, cursor, context)\u001b[0m\n\u001b[1;32m   1993\u001b[0m                 \u001b[0mutil\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mraise_\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnewraise\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwith_traceback\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mexc_info\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfrom_\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1994\u001b[0m             \u001b[0;32melif\u001b[0m \u001b[0mshould_wrap\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1995\u001b[0;31m                 util.raise_(\n\u001b[0m\u001b[1;32m   1996\u001b[0m                     \u001b[0msqlalchemy_exception\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwith_traceback\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mexc_info\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfrom_\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1997\u001b[0m                 )\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/util/compat.py\u001b[0m in \u001b[0;36mraise_\u001b[0;34m(***failed resolving arguments***)\u001b[0m\n\u001b[1;32m    205\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    206\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 207\u001b[0;31m             \u001b[0;32mraise\u001b[0m \u001b[0mexception\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    208\u001b[0m         \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    209\u001b[0m             \u001b[0;31m# credit to\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36m_execute_context\u001b[0;34m(self, dialect, constructor, statement, parameters, execution_options, *args, **kw)\u001b[0m\n\u001b[1;32m   1749\u001b[0m                             \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1750\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mevt_handled\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1751\u001b[0;31m                     self.dialect.do_executemany(\n\u001b[0m\u001b[1;32m   1752\u001b[0m                         \u001b[0mcursor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstatement\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1753\u001b[0m                     )\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/dialects/postgresql/psycopg2.py\u001b[0m in \u001b[0;36mdo_executemany\u001b[0;34m(self, cursor, statement, parameters, context)\u001b[0m\n\u001b[1;32m    960\u001b[0m                 \u001b[0mkwargs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    961\u001b[0m             \u001b[0mxtras\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_psycopg2_extras\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 962\u001b[0;31m             context._psycopg2_fetched_rows = xtras.execute_values(\n\u001b[0m\u001b[1;32m    963\u001b[0m                 \u001b[0mcursor\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    964\u001b[0m                 \u001b[0mstatement\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/psycopg2/extras.py\u001b[0m in \u001b[0;36mexecute_values\u001b[0;34m(cur, sql, argslist, template, page_size, fetch)\u001b[0m\n\u001b[1;32m   1268\u001b[0m             \u001b[0mparts\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mb','\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1269\u001b[0m         \u001b[0mparts\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpost\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1270\u001b[0;31m         \u001b[0mcur\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mb''\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1271\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mfetch\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1272\u001b[0m             \u001b[0mresult\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcur\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfetchall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mIntegrityError\u001b[0m: (psycopg2.errors.UniqueViolation) duplicate key value violates unique constraint \"product_pkey\"\nDETAIL:  Key (product_id)=(10000001) already exists.\n\n[SQL: INSERT INTO product (product_id, prod_name, product_type_no, product_type_name, product_group_name) VALUES (%(product_id)s, %(prod_name)s, %(product_type_no)s, %(product_type_name)s, %(product_group_name)s)]\n[parameters: ({'product_id': 10000001, 'prod_name': 'Strap top', 'product_type_no': 253, 'product_type_name': 'Vest top', 'product_group_name': 'Garment Upper body'}, {'product_id': 10000002, 'prod_name': 'Strap top (1)', 'product_type_no': 253, 'product_type_name': 'Vest top', 'product_group_name': 'Garment Upper body'}, {'product_id': 10000003, 'prod_name': 'OP T-shirt (Idro)', 'product_type_no': 306, 'product_type_name': 'Bra', 'product_group_name': 'Underwear'}, {'product_id': 10000004, 'prod_name': '20 den 1p Stockings', 'product_type_no': 304, 'product_type_name': 'Underwear Tights', 'product_group_name': 'Socks & Tights'}, {'product_id': 10000005, 'prod_name': '20 den 1p Stockings', 'product_type_no': 302, 'product_type_name': 'Socks', 'product_group_name': 'Socks & Tights'}, {'product_id': 10000006, 'prod_name': 'Shape Up 30 den 1p Tights', 'product_type_no': 273, 'product_type_name': 'Leggings/Tights', 'product_group_name': 'Garment Lower body'}, {'product_id': 10000007, 'prod_name': 'Support 40 den 1p Tights', 'product_type_no': 304, 'product_type_name': 'Underwear Tights', 'product_group_name': 'Socks & Tights'}, {'product_id': 10000008, 'prod_name': '200 den 1p Tights', 'product_type_no': 304, 'product_type_name': 'Underwear Tights', 'product_group_name': 'Socks & Tights'}  ... displaying 10 of 46792 total bound parameter sets ...  {'product_id': 10046791, 'prod_name': 'CLAIRE HAIR CLAW', 'product_type_no': 72, 'product_type_name': 'Hair clip', 'product_group_name': 'Accessories'}, {'product_id': 10046792, 'prod_name': 'Lounge dress', 'product_type_no': 265, 'product_type_name': 'Dress', 'product_group_name': 'Garment Full body'})]\n(Background on this error at: https://sqlalche.me/e/14/gkpj)"
     ]
    }
   ],
   "source": [
    "product = pd.DataFrame(product)\n",
    "product.to_sql(name='product',con=con,if_exists='append', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "id": "29a5c603",
   "metadata": {},
   "outputs": [
    {
     "ename": "IntegrityError",
     "evalue": "(psycopg2.errors.UniqueViolation) duplicate key value violates unique constraint \"section_pkey\"\nDETAIL:  Key (section_id)=(60000001) already exists.\n\n[SQL: INSERT INTO section (section_id, section_name, garment_group_no, garment_group_name) VALUES (%(section_id)s, %(section_name)s, %(garment_group_no)s, %(garment_group_name)s)]\n[parameters: ({'section_id': 60000001, 'section_name': 'Womens Everyday Basics', 'garment_group_no': 1002, 'garment_group_name': 'Jersey Basic'}, {'section_id': 60000002, 'section_name': 'Womens Lingerie', 'garment_group_no': 1017, 'garment_group_name': 'Under-, Nightwear'}, {'section_id': 60000003, 'section_name': 'Womens Nightwear, Socks & Tigh', 'garment_group_no': 1021, 'garment_group_name': 'Socks and Tights'}, {'section_id': 60000004, 'section_name': 'Baby Essentials & Complements', 'garment_group_no': 1002, 'garment_group_name': 'Jersey Basic'}, {'section_id': 60000005, 'section_name': 'Men Underwear', 'garment_group_no': 1002, 'garment_group_name': 'Jersey Basic'}, {'section_id': 60000006, 'section_name': 'Mama', 'garment_group_no': 1005, 'garment_group_name': 'Jersey Fancy'}, {'section_id': 60000007, 'section_name': 'Womens Small accessories', 'garment_group_no': 1019, 'garment_group_name': 'Accessories'}, {'section_id': 60000008, 'section_name': 'Baby Essentials & Complements', 'garment_group_no': 1017, 'garment_group_name': 'Under-, Nightwear'}  ... displaying 10 of 195 total bound parameter sets ...  {'section_id': 60000194, 'section_name': 'Kids Boy', 'garment_group_no': 1001, 'garment_group_name': 'Unknown'}, {'section_id': 60000195, 'section_name': 'Divided Complements Other', 'garment_group_no': 1019, 'garment_group_name': 'Accessories'})]\n(Background on this error at: https://sqlalche.me/e/14/gkpj)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mUniqueViolation\u001b[0m                           Traceback (most recent call last)",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36m_execute_context\u001b[0;34m(self, dialect, constructor, statement, parameters, execution_options, *args, **kw)\u001b[0m\n\u001b[1;32m   1750\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mevt_handled\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1751\u001b[0;31m                     self.dialect.do_executemany(\n\u001b[0m\u001b[1;32m   1752\u001b[0m                         \u001b[0mcursor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstatement\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/dialects/postgresql/psycopg2.py\u001b[0m in \u001b[0;36mdo_executemany\u001b[0;34m(self, cursor, statement, parameters, context)\u001b[0m\n\u001b[1;32m    961\u001b[0m             \u001b[0mxtras\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_psycopg2_extras\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 962\u001b[0;31m             context._psycopg2_fetched_rows = xtras.execute_values(\n\u001b[0m\u001b[1;32m    963\u001b[0m                 \u001b[0mcursor\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/psycopg2/extras.py\u001b[0m in \u001b[0;36mexecute_values\u001b[0;34m(cur, sql, argslist, template, page_size, fetch)\u001b[0m\n\u001b[1;32m   1269\u001b[0m         \u001b[0mparts\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpost\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1270\u001b[0;31m         \u001b[0mcur\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mb''\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1271\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mfetch\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mUniqueViolation\u001b[0m: duplicate key value violates unique constraint \"section_pkey\"\nDETAIL:  Key (section_id)=(60000001) already exists.\n",
      "\nThe above exception was the direct cause of the following exception:\n",
      "\u001b[0;31mIntegrityError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[0;32m/var/folders/62/t7hrl00s7dv5ch357bbq539r0000gn/T/ipykernel_15629/754168463.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0msection\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msection\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0msection\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_sql\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'section'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mcon\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcon\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mif_exists\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'append'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36mto_sql\u001b[0;34m(self, name, con, schema, if_exists, index, index_label, chunksize, dtype, method)\u001b[0m\n\u001b[1;32m   2870\u001b[0m         \u001b[0;32mfrom\u001b[0m \u001b[0mpandas\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mio\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0msql\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2871\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2872\u001b[0;31m         sql.to_sql(\n\u001b[0m\u001b[1;32m   2873\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2874\u001b[0m             \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36mto_sql\u001b[0;34m(frame, name, con, schema, if_exists, index, index_label, chunksize, dtype, method, engine, **engine_kwargs)\u001b[0m\n\u001b[1;32m    715\u001b[0m         )\n\u001b[1;32m    716\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 717\u001b[0;31m     pandas_sql.to_sql(\n\u001b[0m\u001b[1;32m    718\u001b[0m         \u001b[0mframe\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    719\u001b[0m         \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36mto_sql\u001b[0;34m(self, frame, name, if_exists, index, index_label, schema, chunksize, dtype, method, engine, **engine_kwargs)\u001b[0m\n\u001b[1;32m   1759\u001b[0m         )\n\u001b[1;32m   1760\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1761\u001b[0;31m         sql_engine.insert_records(\n\u001b[0m\u001b[1;32m   1762\u001b[0m             \u001b[0mtable\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtable\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1763\u001b[0m             \u001b[0mcon\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconnectable\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36minsert_records\u001b[0;34m(self, table, con, frame, name, index, schema, chunksize, method, **engine_kwargs)\u001b[0m\n\u001b[1;32m   1348\u001b[0m                 \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"inf cannot be used with MySQL\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1349\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1350\u001b[0;31m                 \u001b[0;32mraise\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1351\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1352\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36minsert_records\u001b[0;34m(self, table, con, frame, name, index, schema, chunksize, method, **engine_kwargs)\u001b[0m\n\u001b[1;32m   1338\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1339\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1340\u001b[0;31m             \u001b[0mtable\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minsert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mchunksize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mchunksize\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1341\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSQLAlchemyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1342\u001b[0m             \u001b[0;31m# GH34431\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36minsert\u001b[0;34m(self, chunksize, method)\u001b[0m\n\u001b[1;32m    965\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    966\u001b[0m                 \u001b[0mchunk_iter\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0marr\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstart_i\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mend_i\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0marr\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdata_list\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 967\u001b[0;31m                 \u001b[0mexec_insert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkeys\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mchunk_iter\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    968\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    969\u001b[0m     def _query_iterator(\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/sql.py\u001b[0m in \u001b[0;36m_execute_insert\u001b[0;34m(self, conn, keys, data_iter)\u001b[0m\n\u001b[1;32m    880\u001b[0m         \"\"\"\n\u001b[1;32m    881\u001b[0m         \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mdict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrow\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mrow\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdata_iter\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 882\u001b[0;31m         \u001b[0mconn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtable\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minsert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    883\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    884\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_execute_insert_multi\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkeys\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata_iter\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36mexecute\u001b[0;34m(self, statement, *multiparams, **params)\u001b[0m\n\u001b[1;32m   1261\u001b[0m             )\n\u001b[1;32m   1262\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1263\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mmeth\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmultiparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_EMPTY_EXECUTION_OPTS\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1264\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1265\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_execute_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmultiparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexecution_options\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/sql/elements.py\u001b[0m in \u001b[0;36m_execute_on_connection\u001b[0;34m(self, connection, multiparams, params, execution_options, _force)\u001b[0m\n\u001b[1;32m    321\u001b[0m     ):\n\u001b[1;32m    322\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0m_force\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msupports_execution\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 323\u001b[0;31m             return connection._execute_clauseelement(\n\u001b[0m\u001b[1;32m    324\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmultiparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexecution_options\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    325\u001b[0m             )\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36m_execute_clauseelement\u001b[0;34m(self, elem, multiparams, params, execution_options)\u001b[0m\n\u001b[1;32m   1450\u001b[0m             \u001b[0mlinting\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdialect\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompiler_linting\u001b[0m \u001b[0;34m|\u001b[0m \u001b[0mcompiler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mWARN_LINTING\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1451\u001b[0m         )\n\u001b[0;32m-> 1452\u001b[0;31m         ret = self._execute_context(\n\u001b[0m\u001b[1;32m   1453\u001b[0m             \u001b[0mdialect\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1454\u001b[0m             \u001b[0mdialect\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecution_ctx_cls\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_init_compiled\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36m_execute_context\u001b[0;34m(self, dialect, constructor, statement, parameters, execution_options, *args, **kw)\u001b[0m\n\u001b[1;32m   1812\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1813\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mBaseException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1814\u001b[0;31m             self._handle_dbapi_exception(\n\u001b[0m\u001b[1;32m   1815\u001b[0m                 \u001b[0me\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstatement\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcursor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1816\u001b[0m             )\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36m_handle_dbapi_exception\u001b[0;34m(self, e, statement, parameters, cursor, context)\u001b[0m\n\u001b[1;32m   1993\u001b[0m                 \u001b[0mutil\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mraise_\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnewraise\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwith_traceback\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mexc_info\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfrom_\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1994\u001b[0m             \u001b[0;32melif\u001b[0m \u001b[0mshould_wrap\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1995\u001b[0;31m                 util.raise_(\n\u001b[0m\u001b[1;32m   1996\u001b[0m                     \u001b[0msqlalchemy_exception\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwith_traceback\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mexc_info\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfrom_\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1997\u001b[0m                 )\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/util/compat.py\u001b[0m in \u001b[0;36mraise_\u001b[0;34m(***failed resolving arguments***)\u001b[0m\n\u001b[1;32m    205\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    206\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 207\u001b[0;31m             \u001b[0;32mraise\u001b[0m \u001b[0mexception\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    208\u001b[0m         \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    209\u001b[0m             \u001b[0;31m# credit to\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/engine/base.py\u001b[0m in \u001b[0;36m_execute_context\u001b[0;34m(self, dialect, constructor, statement, parameters, execution_options, *args, **kw)\u001b[0m\n\u001b[1;32m   1749\u001b[0m                             \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1750\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mevt_handled\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1751\u001b[0;31m                     self.dialect.do_executemany(\n\u001b[0m\u001b[1;32m   1752\u001b[0m                         \u001b[0mcursor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstatement\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1753\u001b[0m                     )\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/sqlalchemy/dialects/postgresql/psycopg2.py\u001b[0m in \u001b[0;36mdo_executemany\u001b[0;34m(self, cursor, statement, parameters, context)\u001b[0m\n\u001b[1;32m    960\u001b[0m                 \u001b[0mkwargs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    961\u001b[0m             \u001b[0mxtras\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_psycopg2_extras\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 962\u001b[0;31m             context._psycopg2_fetched_rows = xtras.execute_values(\n\u001b[0m\u001b[1;32m    963\u001b[0m                 \u001b[0mcursor\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    964\u001b[0m                 \u001b[0mstatement\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/psycopg2/extras.py\u001b[0m in \u001b[0;36mexecute_values\u001b[0;34m(cur, sql, argslist, template, page_size, fetch)\u001b[0m\n\u001b[1;32m   1268\u001b[0m             \u001b[0mparts\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mb','\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1269\u001b[0m         \u001b[0mparts\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpost\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1270\u001b[0;31m         \u001b[0mcur\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mb''\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1271\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mfetch\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1272\u001b[0m             \u001b[0mresult\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcur\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfetchall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mIntegrityError\u001b[0m: (psycopg2.errors.UniqueViolation) duplicate key value violates unique constraint \"section_pkey\"\nDETAIL:  Key (section_id)=(60000001) already exists.\n\n[SQL: INSERT INTO section (section_id, section_name, garment_group_no, garment_group_name) VALUES (%(section_id)s, %(section_name)s, %(garment_group_no)s, %(garment_group_name)s)]\n[parameters: ({'section_id': 60000001, 'section_name': 'Womens Everyday Basics', 'garment_group_no': 1002, 'garment_group_name': 'Jersey Basic'}, {'section_id': 60000002, 'section_name': 'Womens Lingerie', 'garment_group_no': 1017, 'garment_group_name': 'Under-, Nightwear'}, {'section_id': 60000003, 'section_name': 'Womens Nightwear, Socks & Tigh', 'garment_group_no': 1021, 'garment_group_name': 'Socks and Tights'}, {'section_id': 60000004, 'section_name': 'Baby Essentials & Complements', 'garment_group_no': 1002, 'garment_group_name': 'Jersey Basic'}, {'section_id': 60000005, 'section_name': 'Men Underwear', 'garment_group_no': 1002, 'garment_group_name': 'Jersey Basic'}, {'section_id': 60000006, 'section_name': 'Mama', 'garment_group_no': 1005, 'garment_group_name': 'Jersey Fancy'}, {'section_id': 60000007, 'section_name': 'Womens Small accessories', 'garment_group_no': 1019, 'garment_group_name': 'Accessories'}, {'section_id': 60000008, 'section_name': 'Baby Essentials & Complements', 'garment_group_no': 1017, 'garment_group_name': 'Under-, Nightwear'}  ... displaying 10 of 195 total bound parameter sets ...  {'section_id': 60000194, 'section_name': 'Kids Boy', 'garment_group_no': 1001, 'garment_group_name': 'Unknown'}, {'section_id': 60000195, 'section_name': 'Divided Complements Other', 'garment_group_no': 1019, 'garment_group_name': 'Accessories'})]\n(Background on this error at: https://sqlalche.me/e/14/gkpj)"
     ]
    }
   ],
   "source": [
    "section = pd.DataFrame(section)\n",
    "section.to_sql(name='section',con=con,if_exists='append', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "bd85bb6c",
   "metadata": {},
   "outputs": [],
   "source": [
    "cur.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3b0841be",
   "metadata": {},
   "outputs": [],
   "source": [
    "#article,customer_bridge,trans have not insert\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}