Gainsight/Scripts/Jupyter/app_usage.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd \n",
    "import numpy as np \n",
    "import seaborn as sns \n",
    "import matplotlib.pylab as plt \n",
    "import sketch\n",
    "plt.style.use('ggplot')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "pages = pd.read_csv(\"/Users/normrasmussen/Downloads/app_usage.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(59433, 3)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pages.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>School Name</th>\n",
       "      <th>Path</th>\n",
       "      <th>Mar 13 - Apr 11</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Vivvix University for Ad Intel</td>\n",
       "      <td>/courses</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Vivvix University for Ad Intel</td>\n",
       "      <td>/previews</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Vivvix University for Ad Intel</td>\n",
       "      <td>/account_links</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Vivvix University for Ad Intel</td>\n",
       "      <td>/analytics</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Vivvix University for Ad Intel</td>\n",
       "      <td>/settings/general/edit</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Vivvix University for Ad Intel</td>\n",
       "      <td>/apps/integrations</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Vivvix University for Ad Intel</td>\n",
       "      <td>/accounts/general/edit</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Vivvix University for Ad Intel</td>\n",
       "      <td>/people</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Vivvix University for Ad Intel</td>\n",
       "      <td>/settings/authentication</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Vivvix University for Ad Intel</td>\n",
       "      <td>/styling/general/edit</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                       School Name                      Path  Mar 13 - Apr 11\n",
       "0   Vivvix University for Ad Intel                  /courses               25\n",
       "1   Vivvix University for Ad Intel                 /previews               16\n",
       "2   Vivvix University for Ad Intel            /account_links               11\n",
       "3   Vivvix University for Ad Intel                /analytics                8\n",
       "4   Vivvix University for Ad Intel    /settings/general/edit                7\n",
       "5   Vivvix University for Ad Intel        /apps/integrations                4\n",
       "6   Vivvix University for Ad Intel    /accounts/general/edit                4\n",
       "7   Vivvix University for Ad Intel                   /people                3\n",
       "8   Vivvix University for Ad Intel  /settings/authentication                3\n",
       "9   Vivvix University for Ad Intel     /styling/general/edit                2"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pages.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "pages_sum = pd.DataFrame(columns=['Total Views'])\n",
    "pages_sum['Total Views'] = pages.groupby(by='School Name')['Mar 13 - Apr 11'].sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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>Total Views</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>School Name</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Vivvix  for Ad Intel</th>\n",
       "      <td>110</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>'@properties</th>\n",
       "      <td>322</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4 Pillars</th>\n",
       "      <td>112</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AIIM+</th>\n",
       "      <td>528</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ASAPP</th>\n",
       "      <td>153</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>| AgencyBloc</th>\n",
       "      <td>3373</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Académie Évolupharma</th>\n",
       "      <td>253</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Access</th>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ActiveLearner</th>\n",
       "      <td>1907</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ad Intel</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                       Total Views\n",
       "School Name                       \n",
       " Vivvix  for Ad Intel          110\n",
       "'@properties                   322\n",
       "4 Pillars                      112\n",
       "AIIM+                          528\n",
       "ASAPP                          153\n",
       " | AgencyBloc                 3373\n",
       "Académie Évolupharma           253\n",
       "Access                          11\n",
       "ActiveLearner                 1907\n",
       "Ad Intel                         2"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "to_remove = ['Academy', 'academy', 'University', 'university', 'school', 'School', 'Sandbox', 'Knowledge Base']\n",
    "for item in pages_sum.itertuples(index=True):\n",
    "    for word in to_remove:\n",
    "        if word in item[0]:\n",
    "            less = item[0].replace(word, '')\n",
    "            pages_sum.rename(index={item[0]:less}, inplace=True)\n",
    "\n",
    "pages_sum.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "pages_sum.index = pages_sum.index.str.strip()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'Total Views': {'Vivvix  for Ad Intel': 110, \"'@properties\": 322, '4 Pillars': 112, 'AIIM+': 528, 'ASAPP': 153, '| AgencyBloc': 3373, 'Académie Évolupharma': 253, 'Access': 11, 'ActiveLearner': 1907, 'Ad Intel': 765, 'AdCellerant': 5, 'Adkins': 107, 'Agility': 156, 'AgriWebb': 567, 'AgriWebb Brazil': 333, 'Akua Mind Body': 578, 'AlphaSense': 17, 'Altenew': 859, 'Altima Dental': 33, 'American Concrete Pipe Association Learning Center': 2864, 'AnChain.AI': 437, 'AndHealth&#39;s': 2628, 'Andhealth Internal Training': 17, 'Ansley': 116, 'Anthology': 13, 'Anthology Internal': 104, 'Anthology Trial': 418, 'Aquent&#39;s Learning Lab': 16, 'Arrcus': 8, 'Artera': 54, 'Ascend Training by Stenograph': 9, 'AtlasIED': 125, 'Atlassian': 41, 'AutoServe1': 4, 'Autoserve1 New': 1, 'BCNDP Caucus': 26, 'BLVD Mentor Learning Library': 223, 'BNY Mellon OMNI Digital': 364, 'Bartosz&#39;s': 3, 'Bellhop': 118, 'Belmont Farm Nursery': 29, 'BenchSci': 1659, 'Big Ideas Learning': 167, 'Big Ideas Learning  Sandbox': 7, 'BirchStreet': 11, 'BirchStreet Trial': 446, 'Bisla': 402, 'Blacklane Chauffeur Learning': 263, 'Blacklane Dubai Chauffeurs': 272, 'Blacklane Learning &amp; Development': 1913, 'Blackstone Industrial': 42, 'Bolt': 1177, 'BombBomb Studios': 673, 'Bonfire': 19, 'Boon Edam': 164, 'Brand Addition&#39;s': 457, 'Brian&#39;s Starfleet': 3, 'Brighton Science': 1703, 'Bungii Operations': 155, 'CATalyst': 161, 'CHEK Institute': 11138, 'CIBC FirstCaribbean Online and Mobile Banking': 5, 'CIRE': 149, 'CMIC': 200, 'CONCEPT ACADEMY': 468, 'CORE College': 1419, 'CRM Training Courses and Tutorials | Pipedrive Learn': 984, 'CSNews Technology': 1, 'CTAA&#39;s': 1947, 'Canavan Byrne': 1380, 'Capillary': 1473, 'Cappfinity': 108, 'Capstone Scholars Program': 456, 'Cayuse': 99, 'Censis': 1300, 'Channable Internal': 551, 'Channable': 40, 'Chann': 152, 'Chico Electric': 135, 'Cholodecki current': 1, 'Christian': 5, 'Christie&#39;s International Real Estate pl@tform': 273, 'ChurnZero': 41, 'Clay Clerk': 525, 'CloudRadial': 455, 'Cloudticity': 27, 'Cluid Housing': 65, 'Coastal Consulting': 114, 'Cofense': 129, 'Community Fire Prevention': 37, 'Compass': 4327, 'Compass U': 265, 'Competitive Advantage': 48, 'Con-Trol Training System': 816, 'Con-Trol Training System - BambooHR': 179, 'Conlon&#39;s': 598, 'Cook Brother&#39;s Bars': 361, 'Corporate Traveler': 3, 'Curso de Formação': 93, 'CurveBeam': 87, 'DELETE - Airbnb Host Hub': 12, 'DELETE - Airbnb Photography': 13, 'DELETE - BLE Dev': 14, 'DELETE - Bright Line Hub': 24, 'DELETE - Bright Liners Hub': 1020, 'DELETE - Dealerware': 14, 'DELETE - Dynamic Yield': 14, 'DELETE - Gett': 13, 'DELETE - H1 Insights Customer': 21, 'DELETE - H1 Insights Inc': 47, 'DELETE - Happy Culture': 15, 'DELETE - Numerator  for Promotions Intel': 15, 'DELETE - OTHRSource': 16, 'DELETE - PeopleDev': 14, 'DELETE - Pixability&#39;s': 1, 'DELETE - SANDBOX Bright Liners Hub': 28, 'DELETE - The GLAMSQUAD Online Learning Center': 16, 'DELETE - Uber Compliance El Salvador': 14, 'DELETE - Uber Ecuador': 13, 'DELETE - Uber Peru': 19, 'DELETE - Uber Peru Compliance': 14, 'DELETE - Yotpo': 13, 'DV Learning': 601, 'Datawords': 221, 'Dell AMD Learning': 1192, 'Dept Agency': 575, 'Desktop Shipper': 875, 'Devils': 9, 'Dolly': 23, 'DoorDash Shop &amp; Deliver': 10, 'DoorDash&#39;s': 592, 'DoubleVerify': 89, 'Douglas Elliman MyLearning.Elliman.com': 943, 'Doximity Compliance Learning': 27, 'Doximity': 183, 'Dray Alliance': 207, 'EASE': 373, 'EF High  Exchange Year: IEC': 1703, 'EF High  Exchange Year: Staff': 6, 'EF host family resource center': 29, 'EF student learning center': 74, 'ERA Key Realty Services': 66, 'ES&amp;E': 329, 'EXOR &amp; CORVINA': 189, 'ElderSource Ecommerce': 102, 'ElderSource Internal': 16, 'ElderSource Partner': 4, 'Election Protection': 39, 'Embee': 4, 'Encore Healthcare': 290, 'Energy Foundation': 490, 'Engel &amp; Völkers': 566, 'English for Asia': 2270, 'Equip By Equiem': 143, 'Essentium Training Center': 11, 'Everlaw Certification Center': 33, 'Evolve IP': 426, 'Excalibur Data Systems Online Learning': 123, 
     ]
    }
   ],
   "source": [
    "test_dict = pages_sum.to_dict()\n",
    "print(test_dict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "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>Twotal</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>School Name</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>'@properties</th>\n",
       "      <td>322</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4 Pillars</th>\n",
       "      <td>112</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AIIM+</th>\n",
       "      <td>528</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ASAPP</th>\n",
       "      <td>153</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Académie Évolupharma</th>\n",
       "      <td>253</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Yakademy</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Your Pathway Home</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ZENOTI</th>\n",
       "      <td>42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ZU EWC</th>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ZU Sorbet</th>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>489 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                      Twotal\n",
       "School Name                 \n",
       "'@properties             322\n",
       "4 Pillars                112\n",
       "AIIM+                    528\n",
       "ASAPP                    153\n",
       "Académie Évolupharma     253\n",
       "...                      ...\n",
       "Yakademy                   1\n",
       "Your Pathway Home          3\n",
       "ZENOTI                    42\n",
       "ZU EWC                    14\n",
       "ZU Sorbet                  8\n",
       "\n",
       "[489 rows x 1 columns]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pages_three = pd.DataFrame(columns=['Twotal'])\n",
    "pages_three['Twotal'] = pages_sum.groupby(['School Name'])['Total Views'].sum()\n",
    "pages_three.head(-20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "pages_three.loc[pages_three.index == 'Zenjob']\n",
    "acct_list = pages_three.index.to_list()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Bolt Volt\n",
      "Landis LandisU\n",
      "Ocean Oceana\n",
      "Skuad Skool Skuid Skool\n"
     ]
    }
   ],
   "source": [
    "from Levenshtein import distance as lev\n",
    "import itertools\n",
    "\n",
    "acct1 = []\n",
    "comp = []\n",
    "for (\n",
    "    name1,\n",
    "    name2,\n",
    ") in itertools.combinations(acct_list, 2):\n",
    "    # print(name1, name2) - prints all pairs, working so far.\n",
    "    distance = lev(name1, name2)\n",
    "    # print(distance) - successfully returns numbers\n",
    "    if distance > 0 and distance < 2:\n",
    "        print(name1, name2)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Stored 'pages' (DataFrame)\n"
     ]
    }
   ],
   "source": [
    "pages = pages_three\n",
    "%store pages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "arr = pd.read_csv(\"/Users/normrasmussen/Downloads/cust_arr.csv\", index_col=0, header=[0])\n",
    "arr.fillna(0, inplace=True)\n",
    "arr.replace(',','', regex=True, inplace=True)\n",
    "arr['ARR'] = arr['ARR'].astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "arr = arr.drop(axis=1, columns=['Renewaldate Date', 'CSM'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(354, 1)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Stuart']\n",
      "['HelloTech', 'Inc.']\n",
      "['Shopify', 'Inc.']\n",
      "['Hardskills', 'Pte.', 'Ltd']\n",
      "['Shipt']\n",
      "['SPS', 'Commerce']\n",
      "['CDP']\n",
      "['Altenew']\n",
      "['BrightMove']\n",
      "['SITA', 'B.V.', 'c/o', 'Malta', 'International', 'Airport']\n",
      "['Football', 'Marketing', 'Asia']\n",
      "['Prism', 'Maritime']\n",
      "['Skuid']\n",
      "['SmartPM', 'Technologies']\n",
      "['DoorDash,', 'Inc.']\n",
      "['International', 'Care', 'Ltd.']\n",
      "['BrightMove']\n",
      "['Epiphany', 'Healthcare']\n",
      "['Artsy']\n",
      "['Évolupharma,', 'Inc.']\n",
      "['UAB', 'Omnisend']\n",
      "['Epiphany', 'Healthcare']\n",
      "['Artsy']\n",
      "['Renu', 'Contracting', 'Restoration']\n",
      "['Minga']\n",
      "['Renu', 'Contracting', 'Restoration']\n",
      "['Viva', 'Online', 'Services', 'SA']\n",
      "['Health', 'Current']\n",
      "['Cherokee', 'Enterprises,', 'Inc.']\n",
      "['Kinetica']\n",
      "['Innovaccer', 'Inc.']\n",
      "['Bellhop,', 'Inc']\n",
      "['ISOutsource']\n",
      "['Safic-Alcan']\n",
      "['PetalMD']\n",
      "['GomezLee', 'Marketing']\n",
      "['PSC', 'Consulting']\n",
      "['STATCARE', 'URGENT', 'CARE']\n",
      "['Tru', 'Realty']\n",
      "['Netradyne']\n",
      "['H1', 'Insights,', 'Inc.']\n",
      "['Hardskills', 'Pte.', 'Ltd']\n",
      "['BambooHR']\n",
      "['Velocity', 'Risk', 'Underwriters,', 'LLC']\n",
      "['Harri', 'LLC']\n",
      "['Rootstrap']\n",
      "['First', 'Mile']\n",
      "['Lawpath']\n",
      "['Brand', 'Addition']\n",
      "['Roboflow']\n",
      "['Oiltanking', 'GmbH']\n",
      "['Safari', 'Energy']\n",
      "['Larson', 'Texts']\n",
      "['Spring', 'Point']\n",
      "['Legislative', 'Assembly', 'of', 'British', 'Columbia']\n",
      "['National', 'Campus', 'and', 'Community', 'Radio', 'Association']\n",
      "['Psynapse', 'Psychometrics', 'Pty', 'Ltd']\n",
      "['Portnoy,', 'Messinger,', 'Pearl', '&', 'Associates,', 'Inc.']\n",
      "['Trax', 'Technology', 'Solutions', 'Pte', 'Ltd']\n",
      "['Uber', 'London', 'Limited', '(POOL)']\n",
      "['Ansan', 'Industries', 'Ltd.']\n",
      "['connectRN', 'Inc.']\n",
      "['Usdan', 'Summer', 'Camp', 'for', 'the', 'Arts']\n",
      "['Carlson', 'Capital', 'Management']\n",
      "['Safari', 'Energy']\n",
      "['Surmesur']\n",
      "['connectRN', 'Inc.']\n",
      "['ManyChat,', 'Inc.']\n",
      "['Service', 'Coordination', 'Unlimited']\n",
      "['Doximity', 'Inc.']\n",
      "['Starwood', 'Pet', 'Travel']\n",
      "['Future', 'Point', 'of', 'View', '(Tri-Corps)']\n",
      "['Form', 'Energy']\n",
      "['Channable']\n",
      "['Hammer', 'Nutrition']\n",
      "['Uber', 'B.V.', '-', 'Uber', 'LatAm', 'Compliance']\n",
      "['Securonix', 'Inc.']\n",
      "['HopSkipDrive']\n",
      "['Kiwi']\n",
      "['People', 'Untapped']\n",
      "['beqom']\n",
      "['Casio', 'America', 'Inc']\n",
      "['Riviera', 'Partners', 'LLC']\n",
      "['The', 'Latimer', 'Group']\n",
      "['Viveve']\n",
      "['Volt', 'Systems']\n",
      "['OTHRSource']\n",
      "['Viveve']\n",
      "['Material', 'Control', 'Systems,', 'Inc.']\n",
      "['Evolve', 'IP']\n",
      "['Cook', 'Brothers', 'Bars']\n",
      "['STOPit', 'Solutions']\n",
      "['Broche', 'Ballet']\n",
      "['Virtually', 'Human', 'Studio']\n",
      "['BrightLine', 'Eating', 'Solutions', 'LLC']\n",
      "['AgriWebb']\n",
      "['Wingz,', 'Inc.']\n",
      "['Noventiq', 'Holdings', 'plc']\n",
      "['Corporate', 'Traveler', 'UK']\n",
      "['Kadince']\n",
      "['AndHealth']\n",
      "['Swift', 'Medical']\n",
      "['Agility', 'Inc.']\n",
      "['ZyXel', 'Communications', 'Inc']\n",
      "['UX', 'Design', 'Institute']\n",
      "['STATCARE', 'URGENT', 'CARE']\n",
      "['MaRS', 'Discovery', 'District']\n",
      "['Altima', 'Dental', 'Canada']\n",
      "['Aquent']\n",
      "['FeverBee']\n",
      "['Company', 'Nurse']\n",
      "['DoubleVerify']\n",
      "['Pepper', 'Content', 'Inc']\n",
      "['NextHealth']\n",
      "['Community', 'Transportation', 'Association', 'of', 'America']\n",
      "['Teach', 'Plus']\n",
      "['Winchester', 'Carlisle']\n",
      "['Ceres', 'University']\n",
      "['BrandActive', 'International', 'Inc.']\n",
      "['Psychiatry-UK']\n",
      "['Horsepower', 'Brands']\n",
      "['Dept', 'Holding', 'B.V.']\n",
      "['BioLife', 'Solutions,', 'Inc.']\n",
      "['Walmart', 'Inc.']\n",
      "['Conlon', 'Construction']\n",
      "['Nana', 'Technologies', 'Inc.']\n",
      "['Turo,', 'Inc.']\n",
      "['BombBomb']\n",
      "['The', 'Financial', 'Times', 'Limited']\n",
      "['Southeastrans', 'Inc.']\n",
      "['Type', 'A', 'Media']\n",
      "['Jets', 'Gymnastics']\n",
      "['Reconart']\n",
      "['Excalibur', 'Data', 'Systems']\n",
      "['Parkopoly']\n",
      "['Strategos', 'International']\n",
      "['Douglas', 'Elliman', 'Real', 'Estate']\n",
      "['Oodrive']\n",
      "['Swift', 'Medical']\n",
      "['Canavan', 'Byrne']\n",
      "['Dray', 'Alliance', 'Inc.']\n",
      "['CanFi', 'Empowerment', 'Education', 'Corp']\n",
      "['Axios', 'Media', 'Inc.']\n",
      "['Volumental']\n",
      "['Oceana,', 'Inc.']\n",
      "['LaunchThat']\n",
      "['UX', 'Design', 'Institute']\n",
      "['Amyris']\n",
      "['Shine', 'Bright', 'Care', 'LLC']\n",
      "['Alston', 'Construction']\n",
      "['Hello', 'Customer']\n",
      "['S-Docs']\n",
      "['Neil', 'Kelly', 'Company']\n",
      "['Squaretrade', 'Inc.']\n",
      "['Everyday', 'Software,', 'SL']\n",
      "['Webdox', 'CLM']\n",
      "['Hazlett', 'Tree', 'Service']\n",
      "['High', 'Frequency']\n",
      "['CloudRadial']\n",
      "['Ideoclick']\n",
      "['Equiem']\n",
      "['Long', 'Beach', 'Community', 'College', 'District', '-', 'LA', 'SBDC']\n",
      "['enChoice', 'Inc']\n",
      "['Royal', 'Family', 'Kids,', 'Inc.']\n",
      "['SilverCar']\n",
      "['Anchor', 'QEA,', 'LLC']\n",
      "['Maven', 'Clinic']\n",
      "['Flight', 'Centre']\n",
      "['Shoplogix', '(Asia', 'Pacific)', 'Limited', '(Formerly', 'Projection', 'HK)']\n",
      "['North', 'Capital']\n",
      "['Johnson', '&', 'Johnson', 'Surgical', 'Vision,', 'Inc.']\n",
      "['Hexa', 'Assessments', 'dba', 'Talexes']\n",
      "['Raketech', 'Group']\n",
      "['EnsembleIQ']\n",
      "['Ogi']\n",
      "['Grammarly']\n",
      "['PSC', 'Consulting']\n",
      "['Trinity', 'College', 'London']\n",
      "['Estes', 'Construction']\n",
      "['FIVE', 'Holdings,', 'Inc']\n",
      "[\"Women's\", 'Resource', 'Center']\n",
      "['Pablo', '&', \"Rusty's\", 'Coffee']\n",
      "['Lawyers', 'Committee', 'for', 'Civil', 'Rights', 'Under', 'Law']\n",
      "['Richter10.2', 'Media', 'Group']\n",
      "['Venair']\n",
      "['SIT', 'International']\n",
      "['Cultural', 'Care']\n",
      "['DoubleVerify']\n",
      "['Life', 'House']\n",
      "['ASAPP']\n",
      "['GLDN']\n",
      "['Community', 'Fire', 'Prevention']\n",
      "['Capillary', 'Technologies']\n",
      "['Landis']\n",
      "['Blacklane', 'GmbH']\n",
      "['American', 'Concrete', 'Pipe', 'Association']\n",
      "['The', 'CORE', 'Group']\n",
      "['Market', 'Track', 'LLC', 'dba', 'Numerator']\n",
      "['Medical', 'Practice', 'Management', 'Solutions']\n",
      "['Recast', 'Software']\n",
      "['Skan.ai']\n",
      "['Smart', 'Choice']\n",
      "['Hello', 'Insight']\n",
      "['Agility', 'Robotics']\n",
      "['American', 'State', 'Bank']\n",
      "['Transifex', 'Opco', 'LLC']\n",
      "['Cappfinity']\n",
      "['Houwzer,', 'Inc']\n",
      "['Feldman', 'Surveyors']\n",
      "['CognisantMD']\n",
      "['Clay', 'County', 'Clerk', 'of', 'Court', 'and', 'Comptroller', 'Office']\n",
      "['Wiliot']\n",
      "['Jimmy', 'Brings']\n",
      "['AIIM']\n",
      "['Wound', 'Care', 'Advantage']\n",
      "['One', 'Network', 'Enterprises']\n",
      "['Harri', 'LLC']\n",
      "['Community', 'Transportation', 'Association', 'of', 'America']\n",
      "['Puls']\n",
      "['Shopify', 'Inc.']\n",
      "['Semantic', 'Web', 'Company', 'GmbH']\n",
      "['EF', 'Educational', 'Foundation', 'for', 'Foreign', 'Study']\n",
      "['Upland', 'Software', 'Inc.']\n",
      "['Global', 'Systems', 'Engineering']\n",
      "['G2.com,', 'Inc']\n",
      "['Petroleum', 'Analyzer', 'Company']\n",
      "['Quality', 'Built']\n",
      "['Energy', 'Foundation']\n",
      "['ManyChat,', 'Inc.']\n",
      "['People', 'Untapped']\n",
      "['Optimize', 'Wealth', 'Management']\n",
      "['Perchwell']\n",
      "['Rystad', 'Energy']\n",
      "['DesktopShipper']\n",
      "['New', 'England', 'Mechanical', 'Overlay', '(NEMO)']\n",
      "['Scinapsis', 'Analytics', 'Inc.', 'd.b.a.', 'BenchSci']\n",
      "['Eagle', 'Investment', 'Systems', 'LLC']\n",
      "['Falkonry', 'Inc.']\n",
      "['Exor', 'International', '(USA)']\n",
      "['Outside', 'In']\n",
      "['UX', 'Design', 'Institute']\n",
      "['Studex', 'Corporation']\n",
      "['Givergy']\n",
      "['Porch']\n",
      "['StatesServ/Hospicelink']\n",
      "['The', 'a2', 'Milk', 'Company']\n",
      "['Bungii,', 'LLC']\n",
      "['My', 'Food', 'Bag']\n",
      "['Data', 'Words']\n",
      "['Dr.', 'First']\n",
      "['Sidekick', 'Health']\n",
      "['Sirma', 'AI', 'AD,', 'trading', 'as', 'Ontotext']\n",
      "['CHEK', 'Institute']\n",
      "['Universal', 'Technical', 'Resource', 'Services,', 'Inc.']\n",
      "['Falkonry', 'Inc.']\n",
      "['MOLITOR', 'Formations']\n",
      "['Sword', 'Security']\n",
      "['Missouri', 'State', 'Employees', 'Retirement', 'System']\n",
      "['Pickup', 'Now', 'Inc']\n",
      "['Papa', 'Technologies', 'LLC']\n",
      "['Marble', 'Law', 'Firm']\n",
      "['Parchment,', 'Inc.']\n",
      "['Well', 'Health,', 'Inc.', 'dba', 'Artera']\n",
      "['Skuid']\n",
      "['Veriff', 'OÜ']\n",
      "['Soham,', 'Inc.', '(Zenoti)']\n",
      "['Caliza', 'DBA', 'Homesie/Landing']\n",
      "['iAdvize', 'SAS']\n",
      "['Milner', 'International', 'College', 'of', 'English']\n",
      "['Adkins', 'Management', 'and', 'Consulting']\n",
      "['Partender,', 'Inc.']\n",
      "['Hometime']\n",
      "['National', 'Wildlife', 'Federation']\n",
      "['Petland', 'Kennesaw']\n",
      "['Petland', 'Mall', 'of', 'Georgia']\n",
      "['Lash', 'Affair', 'by', 'J.', 'Paris,', 'LLC']\n",
      "['Freshworks,', 'Inc.']\n",
      "['Petland', 'Summerville']\n",
      "['FacilisGroup']\n",
      "['Clay', 'County', 'Clerk', 'of', 'Court', 'and', 'Comptroller', 'Office']\n",
      "['Sweet', 'Cow', 'Ice', 'Cream']\n",
      "['Kovo', 'Inc.']\n",
      "['Anchor', 'Labs,', 'LLC']\n",
      "['HINKLEY,', 'INC.']\n",
      "['Solidus', 'Labs']\n",
      "['Ogi']\n",
      "['LTK']\n",
      "['The', 'CX', 'Company']\n",
      "['Wag', 'Labs,', 'Inc.']\n",
      "['Paramount', 'Commerce']\n",
      "['Akua', 'Mind', '&', 'Body']\n",
      "['Anchain.ai']\n",
      "['Pipedrive,', 'Inc.']\n",
      "['Canavan', 'Byrne']\n",
      "['Alston', 'Construction']\n",
      "['Keystone', 'RV', 'Company']\n",
      "['LJ', 'Hooker', 'Corporation', 'Pty', 'Ltd']\n",
      "['Zenoti(Toni', '&', 'Guy)']\n",
      "['National', 'Contracting', 'Center']\n",
      "['Wild', 'Health']\n",
      "['TripleSeat']\n",
      "['Cloudticity']\n",
      "['OvalEdge']\n",
      "['ForceManager']\n",
      "['Remind']\n",
      "['LoadUp', 'Technologies,', 'LLC']\n",
      "['Zenjob', 'GmbH']\n",
      "['AgencyBloc']\n",
      "['Serge']\n",
      "['English', 'for', 'Asia']\n",
      "['uConnect']\n",
      "['Plan', 'To', 'Protect']\n",
      "['Bonfire', 'Interactive', 'Ltd.']\n",
      "['RogueHire,', 'LLC']\n",
      "['Total', 'Dealer', 'Compliance']\n",
      "['SalesForce,', 'Inc.']\n",
      "['STT', 'Security', '&', 'Investigative', 'Services']\n",
      "['Encore', 'Healthcare']\n",
      "['Engel', '&', 'Völkers', 'Americas,', 'Inc']\n",
      "['Herrmann']\n",
      "['Cayuse']\n",
      "['Ursa', 'Major', 'Technologies']\n",
      "['The', 'Federal', 'Liberal', 'Agency', 'of', 'Canada']\n",
      "['Company', 'Nurse']\n",
      "['WeTravel']\n",
      "['MarketScale']\n",
      "['Mizuno', 'Usa,', 'Inc.']\n",
      "['At', 'World', 'Properties,', 'LLC']\n",
      "['Talener']\n",
      "['Practo', 'PTE', 'Ltd.']\n",
      "['Prenda']\n",
      "['Arrcus']\n",
      "['Yondr', 'USA', 'LLC']\n",
      "['Scrivas']\n",
      "['AutoServe1']\n",
      "['InvestisDigital']\n",
      "['Eldersource']\n",
      "['Dialog']\n",
      "['Own', 'Solutions', 'Financial', 'Services', 'Limited']\n",
      "['Crayon']\n",
      "['Slope', 'Software']\n",
      "['Rokt', 'Pte', 'Ltd']\n",
      "['CyberCube']\n",
      "['Everlaw']\n",
      "['Compass', 'RE']\n",
      "['Solo']\n",
      "['Dolly', 'Inc.']\n",
      "['LTK']\n",
      "['Access', 'E-Forms']\n",
      "['Training', 'Concepts']\n",
      "['Luma', 'Health,', 'Inc.']\n",
      "['FRSecure']\n",
      "['MedicalDirector']\n",
      "nan\n"
     ]
    }
   ],
   "source": [
    "arr.index.astype(str)\n",
    "words = arr.index.str.split()\n",
    "for word in words:\n",
    "    print(word)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "354\n",
      "509\n",
      "nan\n",
      "<class 'str'>\n"
     ]
    }
   ],
   "source": [
    "acct_list = []\n",
    "acct_list = arr.index.to_list()\n",
    "acct_list2 = pages.index.to_list()\n",
    "print(len(acct_list))\n",
    "print(len(acct_list2))\n",
    "\n",
    "for item2 in acct_list2:\n",
    "    acct_list.append(item2)\n",
    "\n",
    "for item in acct_list:\n",
    "    if type(item) == float:\n",
    "        acct_list.remove(item)\n",
    "        item = str(item)\n",
    "        print(item)\n",
    "        print(type(item))\n",
    "        \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SilverCar Silvercar\n",
      "Landis LandisU\n",
      "AIIM AIIM+\n",
      "DesktopShipper Desktop Shipper\n",
      "TripleSeat Tripleseat\n",
      "InvestisDigital Investis Digital\n",
      "Bolt Volt\n",
      "Landis LandisU\n",
      "Ocean Oceana\n",
      "Skuad Skool Skuid Skool\n",
      "10\n"
     ]
    }
   ],
   "source": [
    "tup_list = []\n",
    "for (name1, name2,) in itertools.combinations(acct_list, 2):\n",
    "    distance = lev(name1, name2)\n",
    "    if distance > 0 and distance < 2:\n",
    "        print(name1, name2)\n",
    "        tup_list.append((name1, name2))\n",
    "\n",
    "print(len(tup_list))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "jupyter",
   "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": "3.11.1"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}