IS4800 Final Project.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "SENTIMENT ANALYSIS"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 156,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from numpy import nan\n",
    "import math\n",
    "import text2emotion as te\n",
    "import nltk\n",
    "# nltk.download('omw-1.4')\n",
    "from autocorrect import Speller \n",
    "spell = Speller(lang='en')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 157,
   "metadata": {},
   "outputs": [],
   "source": [
    "def autospell(text):\n",
    "        \"\"\"\n",
    "        correct the spelling of the word.\n",
    "        \"\"\"\n",
    "        spells = [spell(w) for w in (nltk.word_tokenize(text))]\n",
    "        return \" \".join(spells) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 158,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('/Users/nickhiltekwani/Downloads/AI Industry Study (Responses) - Form Responses 1.csv')\n",
    "df = df.drop('Timestamp', axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 159,
   "metadata": {},
   "outputs": [],
   "source": [
    "# no previous question\n",
    "ai_experience = \"If you would like, please describe your experience with AI or knowledge surrounding it\"\n",
    "\n",
    "# Do you feel that your computer or data science undergraduate education has properly prepared you for a career in Al?\n",
    "prepared_for_ai = \"Please expand on the previous question if you are a CS, DS, IS, or Cybersecurity major\"\n",
    "\n",
    "# Regardless of major, do your undergrad courses discuss job opportunities/industries that \n",
    "# you can explore with the tools that course/your major teaches you?\n",
    "discuss_jobs = \"Please expand on the previous question, regardless of major\"\n",
    "\n",
    "# If you are a computer or data science major, do you feel that your courses properly prepared you for your internship? \n",
    "prepared_for_internship = \"If applicable, please expand on the previous question\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "metadata": {},
   "outputs": [],
   "source": [
    "ai_experience_list = df[ai_experience].tolist()\n",
    "prepare_for_ai_list = df[prepared_for_ai].tolist()\n",
    "discuss_jobs_list = df[discuss_jobs].tolist()\n",
    "prepared_for_internship_list = df[prepared_for_internship].tolist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 161,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_ai_experience_list = [item for item in ai_experience_list if not(pd.isnull(item)) == True]\n",
    "new_prepare_for_ai_list = [item for item in prepare_for_ai_list if not(pd.isnull(item)) == True]\n",
    "new_discuss_jobs_list = [item for item in discuss_jobs_list if not(pd.isnull(item)) == True]\n",
    "new_prepared_for_internship_list = [item for item in prepared_for_internship_list if not(pd.isnull(item)) == True]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "25\n",
      "16\n",
      "24\n",
      "5\n"
     ]
    }
   ],
   "source": [
    "print(len(new_ai_experience_list))\n",
    "print(len(new_prepare_for_ai_list))\n",
    "print(len(new_discuss_jobs_list))\n",
    "print(len(new_prepared_for_internship_list))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "metadata": {},
   "outputs": [],
   "source": [
    "lowercase_new_ai_experience_list = [ x.lower() for x in new_ai_experience_list ]\n",
    "lowercase_new_prepare_for_ai_list = [ x.lower() for x in new_prepare_for_ai_list ]\n",
    "lowercase_new_discuss_jobs_list = [ x.lower() for x in new_discuss_jobs_list ]\n",
    "lowercase_new_prepared_for_internship_list = [ x.lower() for x in new_prepared_for_internship_list ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "metadata": {},
   "outputs": [],
   "source": [
    "autospelled_lowercase_new_ai_experience_list = [ autospell(x) for x in lowercase_new_ai_experience_list ]\n",
    "autospelled_lowercase_new_prepare_for_ai_list = [ autospell(x) for x in lowercase_new_prepare_for_ai_list ]\n",
    "autospelled_lowercase_new_discuss_jobs_list = [ autospell(x) for x in lowercase_new_discuss_jobs_list ]\n",
    "autospelled_lowercase_new_prepared_for_internship_list = [ autospell(x) for x in lowercase_new_prepared_for_internship_list ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_ai_experience = autospelled_lowercase_new_ai_experience_list\n",
    "final_prepare_for_ai = autospelled_lowercase_new_prepare_for_ai_list\n",
    "final_discuss_jobs = autospelled_lowercase_new_discuss_jobs_list\n",
    "final_prepared_for_internship = autospelled_lowercase_new_prepared_for_internship_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "metadata": {},
   "outputs": [],
   "source": [
    "ai_experience_scores = [ te.get_emotion(x) for x in final_ai_experience ]\n",
    "prepare_for_ai_scores = [ te.get_emotion(x) for x in final_prepare_for_ai ]\n",
    "discuss_job_scores = [ te.get_emotion(x) for x in final_discuss_jobs ]\n",
    "prepared_for_internship_scores = [ te.get_emotion(x) for x in final_prepared_for_internship ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "metadata": {},
   "outputs": [],
   "source": [
    "ai_experience_scores_df = pd.DataFrame(ai_experience_scores)\n",
    "prepare_for_ai_scores_df = pd.DataFrame(prepare_for_ai_scores)\n",
    "discuss_job_scores_df = pd.DataFrame(discuss_job_scores)\n",
    "prepared_for_internship_scores_df = pd.DataFrame(prepared_for_internship_scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "metadata": {},
   "outputs": [],
   "source": [
    "def prepare_emotion_average(list):\n",
    "    emotions = [\"Happy\", \"Angry\", \"Surprise\", \"Sad\", \"Fear\"]\n",
    "    ret = {}\n",
    "    \n",
    "    for e in emotions:\n",
    "        m = list[e].mean()\n",
    "        s = e\n",
    "        ret[s] = round(m, 3)\n",
    "    \n",
    "    return ret\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AI Experience {'Happy': 0.08, 'Angry': 0.0, 'Surprise': 0.14, 'Sad': 0.11, 'Fear': 0.31} \n",
      "\n",
      "Prepared for AI {'Happy': 0.012, 'Angry': 0.0, 'Surprise': 0.176, 'Sad': 0.128, 'Fear': 0.183} \n",
      "\n",
      "Discuss Job {'Happy': 0.172, 'Angry': 0.0, 'Surprise': 0.204, 'Sad': 0.188, 'Fear': 0.268} \n",
      "\n",
      "Prepared For Internship {'Happy': 0.1, 'Angry': 0.0, 'Surprise': 0.166, 'Sad': 0.1, 'Fear': 0.634} \n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(\"AI Experience\", prepare_emotion_average(ai_experience_scores_df), \"\\n\") \n",
    "print(\"Prepared for AI\", prepare_emotion_average(prepare_for_ai_scores_df), \"\\n\")\n",
    "print(\"Discuss Job\", prepare_emotion_average(discuss_job_scores_df), \"\\n\")\n",
    "print(\"Prepared For Internship\", prepare_emotion_average(prepared_for_internship_scores_df), \"\\n\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "DATA PROCESSING FOR QUIZ SCORES"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "metadata": {},
   "outputs": [],
   "source": [
    "names = df[\"Name\"]\n",
    "python = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [Python]\"]\n",
    "javascript = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [Javascript]\"]\n",
    "java = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [Java]\"]\n",
    "sql = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [SQL]\"]\n",
    "r = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [R]\"]\n",
    "cplus = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [C++]\"]\n",
    "shell = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [Shell Scripting]\"]\n",
    "kcluster = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [K Cluster Analysis]\"]\n",
    "signal = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [Signal Processing]\"]\n",
    "deeplearn = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [Deep Learning]\"]\n",
    "calc = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [Calculus]\"]\n",
    "probstats = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [Probability and Statistics]\"]\n",
    "linearalg = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [Linear Algebra]\"]\n",
    "graphanalysis = df[\"Based on your experience, how important are these skill sets to go into AI jobs? [Graph Analysis]\"]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "metadata": {},
   "outputs": [],
   "source": [
    "list_of_columns = [python, javascript, java, sql, r, cplus, shell, kcluster, signal, deeplearn, calc, probstats, linearalg, graphanalysis]\n",
    "\n",
    "idk = \"Don't Know What This Is\"\n",
    "nr = \"No Relevance\"\n",
    "low = \"Low Importance\"\n",
    "high = \"High Importance\"\n",
    "crucial = \"100% Crucial\"\n",
    "\n",
    "for list in list_of_columns:\n",
    "    list.replace(idk, 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "metadata": {},
   "outputs": [],
   "source": [
    "# scores has 4 values\n",
    "def replace_values(li, scores):\n",
    "    li = li.replace(nr, scores[0])\n",
    "    li = li.replace(low, scores[1])\n",
    "    li = li.replace(high, scores[2])\n",
    "    li = li.replace(crucial, scores[3])\n",
    "    return li\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "python = replace_values(python, [0, .3, .6, 1])\n",
    "javascript = replace_values(javascript, [.3, 1, .3, 0])\n",
    "java = replace_values(java, [.3, 1, .3, 0])\n",
    "sql = replace_values(sql, [0, .3, 1, .3])\n",
    "r = replace_values(r, [0, .3, 1, .3])\n",
    "cplus = replace_values(cplus, [.3, 1, .3, 0])\n",
    "shell = replace_values(shell, [.3, 1, .3, 0])\n",
    "kcluster = replace_values(kcluster, [0, .3, 1, .3])\n",
    "signal = replace_values(signal, [.3, 1, .3, 0])\n",
    "deeplearn = replace_values(deeplearn, [0, .3, 1, .3])\n",
    "calc = replace_values(calc, [1, .3, .3, 0])\n",
    "probstats = replace_values(probstats, [0, .3, .6, 1])\n",
    "linearalg = replace_values(linearalg, [.3, 1, .3, 0])\n",
    "graphanalysis = replace_values(graphanalysis, [.3, 1, .3, 0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 174,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "df_test = pd.DataFrame(columns=['name', 'python', 'javascript', 'java', 'sql', 'r', 'cplus', 'shell', 'kcluster', 'signal', 'deeplearn', 'calc', 'probstats', 'linearalg', 'graphanalysis'])\n",
    "df_test[\"name\"] = names\n",
    "df_test[\"python\"] = python\n",
    "df_test['javascript'] = javascript\n",
    "df_test[\"java\"] = java\n",
    "df_test['sql'] = sql\n",
    "df_test[\"r\"] = r\n",
    "df_test['cplus'] = cplus\n",
    "df_test[\"shell\"] = shell\n",
    "df_test['kcluster'] = kcluster\n",
    "df_test[\"signal\"] = signal\n",
    "df_test['deeplearn'] = deeplearn\n",
    "df_test[\"calc\"] = calc\n",
    "df_test['probstats'] = probstats\n",
    "df_test['linearalg'] = probstats\n",
    "df_test['graphanalysis'] = probstats\n",
    "\n",
    "df_test = df_test.replace(\"Don't Know What This Is\", 0)\n",
    "df_test[\"QUIZ SCORE\"] = df_test.sum(axis=1)\n",
    "df[\"quiz score\"] = df_test[\"QUIZ SCORE\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "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>Name</th>\n",
       "      <th>On a high level, please rank your familiarity with AI as an industry</th>\n",
       "      <th>If you would like, please describe your experience with AI or knowledge surrounding it</th>\n",
       "      <th>Alphabet (Google)</th>\n",
       "      <th>General Motors</th>\n",
       "      <th>IBM</th>\n",
       "      <th>Palantir Technologies</th>\n",
       "      <th>Meta (Facebook)</th>\n",
       "      <th>Johnson &amp; Johnson</th>\n",
       "      <th>Novartis</th>\n",
       "      <th>...</th>\n",
       "      <th>Which industry do you think has the lowest barrier of entry?</th>\n",
       "      <th>University</th>\n",
       "      <th>Major</th>\n",
       "      <th>Age At Time Of Taking this Survey</th>\n",
       "      <th>Undergrad Graduation Year</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Ethnicity</th>\n",
       "      <th>Race</th>\n",
       "      <th>Email</th>\n",
       "      <th>quiz score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Example for Professor</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>Academia/Research</td>\n",
       "      <td>Northeastern</td>\n",
       "      <td>Computer Science</td>\n",
       "      <td>21</td>\n",
       "      <td>2022</td>\n",
       "      <td>Male</td>\n",
       "      <td>Not hispanic or Latino</td>\n",
       "      <td>Asian</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ria bajaj</td>\n",
       "      <td>2</td>\n",
       "      <td>ive heard of it</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>Government (Public Sector)</td>\n",
       "      <td>Northeastern</td>\n",
       "      <td>Economics</td>\n",
       "      <td>22</td>\n",
       "      <td>2022</td>\n",
       "      <td>Female</td>\n",
       "      <td>Not hispanic or Latino</td>\n",
       "      <td>Asian</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Vrishin Sundaram</td>\n",
       "      <td>4</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>...</td>\n",
       "      <td>Government (Public Sector)</td>\n",
       "      <td>BU</td>\n",
       "      <td>Engineering (Other)</td>\n",
       "      <td>19</td>\n",
       "      <td>2024</td>\n",
       "      <td>Male</td>\n",
       "      <td>Not hispanic or Latino</td>\n",
       "      <td>Asian</td>\n",
       "      <td>vrishin@bu.edu</td>\n",
       "      <td>8.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Vidhan Sethi</td>\n",
       "      <td>4</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>Government (Public Sector)</td>\n",
       "      <td>BU</td>\n",
       "      <td>Business (Other)</td>\n",
       "      <td>19</td>\n",
       "      <td>2025</td>\n",
       "      <td>Male</td>\n",
       "      <td>Not hispanic or Latino</td>\n",
       "      <td>Asian</td>\n",
       "      <td>sethividhan@gmail.com</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Arya Shukla</td>\n",
       "      <td>4</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>Academia/Research</td>\n",
       "      <td>Northeastern</td>\n",
       "      <td>Data Science</td>\n",
       "      <td>20</td>\n",
       "      <td>2024</td>\n",
       "      <td>Female</td>\n",
       "      <td>Not hispanic or Latino</td>\n",
       "      <td>Asian</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.3</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",
       "      <td>...</td>\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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>Aparna Shanmugam</td>\n",
       "      <td>3</td>\n",
       "      <td>My dad works in AI and I know it’s artificial ...</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>Government (Public Sector)</td>\n",
       "      <td>Northeastern</td>\n",
       "      <td>Cybersecurity</td>\n",
       "      <td>19</td>\n",
       "      <td>2025</td>\n",
       "      <td>Female</td>\n",
       "      <td>Not hispanic or Latino</td>\n",
       "      <td>Asian</td>\n",
       "      <td>shanmugam.a@northeastern.edu</td>\n",
       "      <td>6.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>61</th>\n",
       "      <td>Srijay Kasturi</td>\n",
       "      <td>4</td>\n",
       "      <td>it’s cool</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>Corporate (Private Sector)</td>\n",
       "      <td>umd</td>\n",
       "      <td>philosophy</td>\n",
       "      <td>21</td>\n",
       "      <td>2023</td>\n",
       "      <td>Male</td>\n",
       "      <td>Not hispanic or Latino</td>\n",
       "      <td>Asian</td>\n",
       "      <td>srijaykasturi@gmail.com</td>\n",
       "      <td>10.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>62</th>\n",
       "      <td>karan desai</td>\n",
       "      <td>4</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>Corporate (Private Sector)</td>\n",
       "      <td>Uiuc</td>\n",
       "      <td>Business (Finance)</td>\n",
       "      <td>23</td>\n",
       "      <td>2022</td>\n",
       "      <td>Male</td>\n",
       "      <td>Not hispanic or Latino</td>\n",
       "      <td>Asian</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>Maya Gogia</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>Academia/Research</td>\n",
       "      <td>BU</td>\n",
       "      <td>Business (Other)</td>\n",
       "      <td>23</td>\n",
       "      <td>2020</td>\n",
       "      <td>Female</td>\n",
       "      <td>Hispanic or latino</td>\n",
       "      <td>Asian</td>\n",
       "      <td>mayagogia22@gmail.com</td>\n",
       "      <td>5.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>roshan</td>\n",
       "      <td>3</td>\n",
       "      <td>Limited.</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>...</td>\n",
       "      <td>Corporate (Private Sector)</td>\n",
       "      <td>BU</td>\n",
       "      <td>Business (Finance)</td>\n",
       "      <td>24</td>\n",
       "      <td>2020</td>\n",
       "      <td>Male</td>\n",
       "      <td>Not hispanic or Latino</td>\n",
       "      <td>Asian, Indian</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>65 rows × 76 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                     Name  \\\n",
       "0   Example for Professor   \n",
       "1               ria bajaj   \n",
       "2       Vrishin Sundaram    \n",
       "3            Vidhan Sethi   \n",
       "4             Arya Shukla   \n",
       "..                    ...   \n",
       "60      Aparna Shanmugam    \n",
       "61         Srijay Kasturi   \n",
       "62           karan desai    \n",
       "63             Maya Gogia   \n",
       "64                roshan    \n",
       "\n",
       "    On a high level, please rank your familiarity with AI as an industry  \\\n",
       "0                                                   3                      \n",
       "1                                                   2                      \n",
       "2                                                   4                      \n",
       "3                                                   4                      \n",
       "4                                                   4                      \n",
       "..                                                ...                      \n",
       "60                                                  3                      \n",
       "61                                                  4                      \n",
       "62                                                  4                      \n",
       "63                                                  3                      \n",
       "64                                                  3                      \n",
       "\n",
       "   If you would like, please describe your experience with AI or knowledge surrounding it  \\\n",
       "0                                                 NaN                                       \n",
       "1                                     ive heard of it                                       \n",
       "2                                                 NaN                                       \n",
       "3                                                 NaN                                       \n",
       "4                                                 NaN                                       \n",
       "..                                                ...                                       \n",
       "60  My dad works in AI and I know it’s artificial ...                                       \n",
       "61                                          it’s cool                                       \n",
       "62                                                NaN                                       \n",
       "63                                                NaN                                       \n",
       "64                                          Limited.                                        \n",
       "\n",
       "    Alphabet (Google)  General Motors  IBM  Palantir Technologies  \\\n",
       "0                   3               3    3                      3   \n",
       "1                   5               5    5                      1   \n",
       "2                   4               5    4                      5   \n",
       "3                   4               4    5                      1   \n",
       "4                   1               4    4                      1   \n",
       "..                ...             ...  ...                    ...   \n",
       "60                  5               5    3                      3   \n",
       "61                  5               4    4                      4   \n",
       "62                  5               4    4                      4   \n",
       "63                  4               3    3                      2   \n",
       "64                  5               5    5                      5   \n",
       "\n",
       "    Meta (Facebook)  Johnson & Johnson   Novartis  ...  \\\n",
       "0                 3                   3         3  ...   \n",
       "1                 5                   5         4  ...   \n",
       "2                 4                   4         5  ...   \n",
       "3                 5                   5         1  ...   \n",
       "4                 1                   5         1  ...   \n",
       "..              ...                 ...       ...  ...   \n",
       "60                5                   5         3  ...   \n",
       "61                5                   3         1  ...   \n",
       "62                5                   4         1  ...   \n",
       "63                4                   3         3  ...   \n",
       "64                5                   5         5  ...   \n",
       "\n",
       "    Which industry do you think has the lowest barrier of entry?  \\\n",
       "0                                   Academia/Research              \n",
       "1                          Government (Public Sector)              \n",
       "2                          Government (Public Sector)              \n",
       "3                          Government (Public Sector)              \n",
       "4                                   Academia/Research              \n",
       "..                                                ...              \n",
       "60                         Government (Public Sector)              \n",
       "61                         Corporate (Private Sector)              \n",
       "62                         Corporate (Private Sector)              \n",
       "63                                  Academia/Research              \n",
       "64                         Corporate (Private Sector)              \n",
       "\n",
       "      University                Major  Age At Time Of Taking this Survey  \\\n",
       "0   Northeastern     Computer Science                                 21   \n",
       "1   Northeastern            Economics                                 22   \n",
       "2             BU  Engineering (Other)                                 19   \n",
       "3             BU     Business (Other)                                 19   \n",
       "4   Northeastern         Data Science                                 20   \n",
       "..           ...                  ...                                ...   \n",
       "60  Northeastern        Cybersecurity                                 19   \n",
       "61           umd           philosophy                                 21   \n",
       "62          Uiuc   Business (Finance)                                 23   \n",
       "63            BU     Business (Other)                                 23   \n",
       "64            BU   Business (Finance)                                 24   \n",
       "\n",
       "    Undergrad Graduation Year     Sex               Ethnicity           Race  \\\n",
       "0                        2022    Male  Not hispanic or Latino          Asian   \n",
       "1                        2022  Female  Not hispanic or Latino          Asian   \n",
       "2                        2024    Male  Not hispanic or Latino          Asian   \n",
       "3                        2025    Male  Not hispanic or Latino          Asian   \n",
       "4                        2024  Female  Not hispanic or Latino          Asian   \n",
       "..                        ...     ...                     ...            ...   \n",
       "60                       2025  Female  Not hispanic or Latino          Asian   \n",
       "61                       2023    Male  Not hispanic or Latino          Asian   \n",
       "62                       2022    Male  Not hispanic or Latino          Asian   \n",
       "63                       2020  Female      Hispanic or latino          Asian   \n",
       "64                       2020    Male  Not hispanic or Latino  Asian, Indian   \n",
       "\n",
       "                           Email  quiz score  \n",
       "0                            NaN         7.7  \n",
       "1                            NaN         6.0  \n",
       "2                 vrishin@bu.edu         8.2  \n",
       "3          sethividhan@gmail.com         8.0  \n",
       "4                            NaN        10.3  \n",
       "..                           ...         ...  \n",
       "60  shanmugam.a@northeastern.edu         6.1  \n",
       "61       srijaykasturi@gmail.com        10.5  \n",
       "62                           NaN         6.7  \n",
       "63         mayagogia22@gmail.com         5.8  \n",
       "64                           NaN        10.2  \n",
       "\n",
       "[65 rows x 76 columns]"
      ]
     },
     "execution_count": 175,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}