active_learning_plots.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "RES_PATH = \"data/active_learning/\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_random = pd.read_csv(os.path.join(RES_PATH, \"val_accuracy_list_random2.csv\"))\n",
    "df_unsure = pd.read_csv(os.path.join(RES_PATH, \"val_accuracy_list_unsure.csv\"))\n",
    "df_cluster10 = pd.read_csv(os.path.join(RES_PATH, \"val_accuracy_list_cluster_one_model_10_clusters.csv\"))\n",
    "df_cluster8 = pd.read_csv(os.path.join(RES_PATH, \"val_accuracy_list_cluster_one_model_10_clusters.csv\"))\n",
    "df_cluster6 = pd.read_csv(os.path.join(RES_PATH, \"val_accuracy_list_cluster_one_model_10_clusters.csv\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "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>column</th>\n",
       "      <th>file</th>\n",
       "      <th>region</th>\n",
       "      <th>row_index</th>\n",
       "      <th>tab</th>\n",
       "      <th>template_formula</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.520000</td>\n",
       "      <td>0.620000</td>\n",
       "      <td>0.570000</td>\n",
       "      <td>0.330000</td>\n",
       "      <td>0.670000</td>\n",
       "      <td>0.340000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.510000</td>\n",
       "      <td>0.590000</td>\n",
       "      <td>0.710000</td>\n",
       "      <td>0.280000</td>\n",
       "      <td>0.770000</td>\n",
       "      <td>0.330000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.500000</td>\n",
       "      <td>0.570000</td>\n",
       "      <td>0.530000</td>\n",
       "      <td>0.370000</td>\n",
       "      <td>0.640000</td>\n",
       "      <td>0.270000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.500000</td>\n",
       "      <td>0.730000</td>\n",
       "      <td>0.720000</td>\n",
       "      <td>0.420000</td>\n",
       "      <td>0.730000</td>\n",
       "      <td>0.390000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.580000</td>\n",
       "      <td>0.700000</td>\n",
       "      <td>0.640000</td>\n",
       "      <td>0.380000</td>\n",
       "      <td>0.700000</td>\n",
       "      <td>0.340000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.600000</td>\n",
       "      <td>0.720000</td>\n",
       "      <td>0.770000</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>0.780000</td>\n",
       "      <td>0.410000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.610000</td>\n",
       "      <td>0.740000</td>\n",
       "      <td>0.830000</td>\n",
       "      <td>0.510000</td>\n",
       "      <td>0.850000</td>\n",
       "      <td>0.420000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.550000</td>\n",
       "      <td>0.850000</td>\n",
       "      <td>0.730000</td>\n",
       "      <td>0.520000</td>\n",
       "      <td>0.770000</td>\n",
       "      <td>0.360000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.580000</td>\n",
       "      <td>0.760000</td>\n",
       "      <td>0.710000</td>\n",
       "      <td>0.530000</td>\n",
       "      <td>0.740000</td>\n",
       "      <td>0.470000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.600000</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>0.790000</td>\n",
       "      <td>0.460000</td>\n",
       "      <td>0.840000</td>\n",
       "      <td>0.470000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.590000</td>\n",
       "      <td>0.730000</td>\n",
       "      <td>0.780000</td>\n",
       "      <td>0.580000</td>\n",
       "      <td>0.830000</td>\n",
       "      <td>0.450000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>0.580000</td>\n",
       "      <td>0.720000</td>\n",
       "      <td>0.710000</td>\n",
       "      <td>0.510000</td>\n",
       "      <td>0.750000</td>\n",
       "      <td>0.440000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0.620000</td>\n",
       "      <td>0.710000</td>\n",
       "      <td>0.760000</td>\n",
       "      <td>0.530000</td>\n",
       "      <td>0.780000</td>\n",
       "      <td>0.440000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.722222</td>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.555556</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      column      file    region  row_index       tab  template_formula\n",
       "0   0.520000  0.620000  0.570000   0.330000  0.670000          0.340000\n",
       "1   0.510000  0.590000  0.710000   0.280000  0.770000          0.330000\n",
       "2   0.500000  0.570000  0.530000   0.370000  0.640000          0.270000\n",
       "3   0.500000  0.730000  0.720000   0.420000  0.730000          0.390000\n",
       "4   0.580000  0.700000  0.640000   0.380000  0.700000          0.340000\n",
       "5   0.600000  0.720000  0.770000   0.400000  0.780000          0.410000\n",
       "6   0.610000  0.740000  0.830000   0.510000  0.850000          0.420000\n",
       "7   0.550000  0.850000  0.730000   0.520000  0.770000          0.360000\n",
       "8   0.580000  0.760000  0.710000   0.530000  0.740000          0.470000\n",
       "9   0.600000  0.800000  0.790000   0.460000  0.840000          0.470000\n",
       "10  0.590000  0.730000  0.780000   0.580000  0.830000          0.450000\n",
       "11  0.580000  0.720000  0.710000   0.510000  0.750000          0.440000\n",
       "12  0.620000  0.710000  0.760000   0.530000  0.780000          0.440000\n",
       "13  0.833333  0.833333  0.833333   0.722222  0.833333          0.555556"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_random"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "def apply_avg(row):\n",
    "    a = 0.0\n",
    "    for _, val in row.items():\n",
    "        a += float(val)\n",
    "    return round(a/len(row),3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_random[\"avg\"] = df_random.apply(apply_avg, axis=1)\n",
    "df_unsure[\"avg\"] = df_unsure.apply(apply_avg, axis=1)\n",
    "df_cluster10[\"avg\"] = df_cluster10.apply(apply_avg, axis=1)\n",
    "df_cluster8[\"avg\"] = df_cluster8.apply(apply_avg, axis=1)\n",
    "df_cluster6[\"avg\"] = df_cluster6.apply(apply_avg, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "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>column</th>\n",
       "      <th>file</th>\n",
       "      <th>region</th>\n",
       "      <th>row_index</th>\n",
       "      <th>tab</th>\n",
       "      <th>template_formula</th>\n",
       "      <th>avg</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.520000</td>\n",
       "      <td>0.620000</td>\n",
       "      <td>0.570000</td>\n",
       "      <td>0.330000</td>\n",
       "      <td>0.670000</td>\n",
       "      <td>0.340000</td>\n",
       "      <td>0.508</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.510000</td>\n",
       "      <td>0.590000</td>\n",
       "      <td>0.710000</td>\n",
       "      <td>0.280000</td>\n",
       "      <td>0.770000</td>\n",
       "      <td>0.330000</td>\n",
       "      <td>0.532</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.500000</td>\n",
       "      <td>0.570000</td>\n",
       "      <td>0.530000</td>\n",
       "      <td>0.370000</td>\n",
       "      <td>0.640000</td>\n",
       "      <td>0.270000</td>\n",
       "      <td>0.480</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.500000</td>\n",
       "      <td>0.730000</td>\n",
       "      <td>0.720000</td>\n",
       "      <td>0.420000</td>\n",
       "      <td>0.730000</td>\n",
       "      <td>0.390000</td>\n",
       "      <td>0.582</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.580000</td>\n",
       "      <td>0.700000</td>\n",
       "      <td>0.640000</td>\n",
       "      <td>0.380000</td>\n",
       "      <td>0.700000</td>\n",
       "      <td>0.340000</td>\n",
       "      <td>0.557</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.600000</td>\n",
       "      <td>0.720000</td>\n",
       "      <td>0.770000</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>0.780000</td>\n",
       "      <td>0.410000</td>\n",
       "      <td>0.613</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.610000</td>\n",
       "      <td>0.740000</td>\n",
       "      <td>0.830000</td>\n",
       "      <td>0.510000</td>\n",
       "      <td>0.850000</td>\n",
       "      <td>0.420000</td>\n",
       "      <td>0.660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.550000</td>\n",
       "      <td>0.850000</td>\n",
       "      <td>0.730000</td>\n",
       "      <td>0.520000</td>\n",
       "      <td>0.770000</td>\n",
       "      <td>0.360000</td>\n",
       "      <td>0.630</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.580000</td>\n",
       "      <td>0.760000</td>\n",
       "      <td>0.710000</td>\n",
       "      <td>0.530000</td>\n",
       "      <td>0.740000</td>\n",
       "      <td>0.470000</td>\n",
       "      <td>0.632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.600000</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>0.790000</td>\n",
       "      <td>0.460000</td>\n",
       "      <td>0.840000</td>\n",
       "      <td>0.470000</td>\n",
       "      <td>0.660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.590000</td>\n",
       "      <td>0.730000</td>\n",
       "      <td>0.780000</td>\n",
       "      <td>0.580000</td>\n",
       "      <td>0.830000</td>\n",
       "      <td>0.450000</td>\n",
       "      <td>0.660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>0.580000</td>\n",
       "      <td>0.720000</td>\n",
       "      <td>0.710000</td>\n",
       "      <td>0.510000</td>\n",
       "      <td>0.750000</td>\n",
       "      <td>0.440000</td>\n",
       "      <td>0.618</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0.620000</td>\n",
       "      <td>0.710000</td>\n",
       "      <td>0.760000</td>\n",
       "      <td>0.530000</td>\n",
       "      <td>0.780000</td>\n",
       "      <td>0.440000</td>\n",
       "      <td>0.640</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.722222</td>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.555556</td>\n",
       "      <td>0.769</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      column      file    region  row_index       tab  template_formula    avg\n",
       "0   0.520000  0.620000  0.570000   0.330000  0.670000          0.340000  0.508\n",
       "1   0.510000  0.590000  0.710000   0.280000  0.770000          0.330000  0.532\n",
       "2   0.500000  0.570000  0.530000   0.370000  0.640000          0.270000  0.480\n",
       "3   0.500000  0.730000  0.720000   0.420000  0.730000          0.390000  0.582\n",
       "4   0.580000  0.700000  0.640000   0.380000  0.700000          0.340000  0.557\n",
       "5   0.600000  0.720000  0.770000   0.400000  0.780000          0.410000  0.613\n",
       "6   0.610000  0.740000  0.830000   0.510000  0.850000          0.420000  0.660\n",
       "7   0.550000  0.850000  0.730000   0.520000  0.770000          0.360000  0.630\n",
       "8   0.580000  0.760000  0.710000   0.530000  0.740000          0.470000  0.632\n",
       "9   0.600000  0.800000  0.790000   0.460000  0.840000          0.470000  0.660\n",
       "10  0.590000  0.730000  0.780000   0.580000  0.830000          0.450000  0.660\n",
       "11  0.580000  0.720000  0.710000   0.510000  0.750000          0.440000  0.618\n",
       "12  0.620000  0.710000  0.760000   0.530000  0.780000          0.440000  0.640\n",
       "13  0.833333  0.833333  0.833333   0.722222  0.833333          0.555556  0.769"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_random"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'df' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-11-92a1e0aa7ced>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\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----> 2\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0midx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrow\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0miterrows\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      3\u001b[0m     \u001b[0mdata_list\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mrow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfile\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mregion\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrow_index\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtab\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtemplate_formula\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'df' is not defined"
     ]
    }
   ],
   "source": [
    "data_list = []\n",
    "for idx, row in df.iterrows():\n",
    "    data_list.append([row.column, row.file, row.region, row.row_index, row.tab, row.template_formula])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "ename": "IndexError",
     "evalue": "list index out of range",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mIndexError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-12-809eaf4f0f92>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdata_list\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mIndexError\u001b[0m: list index out of range"
     ]
    }
   ],
   "source": [
    "data_list[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'df' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-13-3e381211f501>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrot\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfigsize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m18\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m: name 'df' is not defined"
     ]
    }
   ],
   "source": [
    "df.plot.bar(rot=0, figsize=(18,10))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "def two_plots(df1, df2, name1, name2):\n",
    "    x1 = [i for i in range(100, 100*(len(df1)+1), 100)]\n",
    "    x2 = [i for i in range(100, 100*(len(df2)+1), 100)]\n",
    "    acc1 = list(df1[\"avg\"])\n",
    "    acc2 = list(df2[\"avg\"])\n",
    "    fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(18,8))\n",
    "    ax1.bar(x1, acc1, width=20)\n",
    "    ax1.set_title(name1)\n",
    "    ax2.bar(x2, acc2, width=20)\n",
    "    ax2.set_title(name2)\n",
    "    plt.xticks(x, x)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1296x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "two_plots(df_random, df_unsure, \"random\", \"unsure\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1296x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "two_plots(df_random, df_cluster10, \"random\", \"cluster_one_model_10_clusters\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1296x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "two_plots(df_unsure, df_cluster8, \"unsure\", \"cluster_one_model_8_clusters\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1296x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "two_plots(df_cluster6, df_cluster8, \"cluster_one_model_6_clusters\", \"cluster_one_model_8_clusters\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1100, 1200, 1300, 1400]\n",
      "[0.508, 0.532, 0.48, 0.582, 0.557, 0.613, 0.66, 0.63, 0.632, 0.66, 0.66, 0.618, 0.64, 0.769]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1296x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "x = [i for i in range(100, 100*(len(df_random)+1), 100)]\n",
    "print(x)\n",
    "acc = list(df_random[\"avg\"])\n",
    "print(acc)\n",
    "fig, ax = plt.subplots(figsize=(18,8))\n",
    "plt.bar(x, acc, width=20)\n",
    "plt.xticks(x, x)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.5.6"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}