ir_part2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 159,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from numpy import linalg as LA\n",
    "import pandas as pd\n",
    "\n",
    "from string import punctuation\n",
    "import re\n",
    "import nltk\n",
    "from nltk.stem.porter import PorterStemmer\n",
    "p_stemmer = PorterStemmer()\n",
    "from nltk.tokenize import word_tokenize\n",
    "from nltk.corpus import stopwords\n",
    "stop_words = set(stopwords.words('english'))\n",
    "import itertools\n",
    "from collections import defaultdict\n",
    "import streamlit as st"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "metadata": {},
   "outputs": [],
   "source": [
    "# reads the file\n",
    "df = pd.read_csv(\"walmart-products-modified.csv\", encoding='latin1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 161,
   "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>rating</th>\n",
       "      <th>type_of</th>\n",
       "      <th>price</th>\n",
       "      <th>comments</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Eliminator Ant, Roach &amp; Spider Killer4, 20 oz,...</td>\n",
       "      <td>4.0840</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>3.48</td>\n",
       "      <td>Covered one up in phone. The roach crawled out...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Spiderman Party Blowers, 8ct</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Novelty &amp; Gag Toys</td>\n",
       "      <td>3.74</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>TERRO Spider and Ant Killer Aerosol Spray, 16 ...</td>\n",
       "      <td>4.5333</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>4.97</td>\n",
       "      <td>EXTREMELY disappointed. Raid worked way faster...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Hot Shot Fresh Floral Scent Ant, Roach &amp; Spide...</td>\n",
       "      <td>4.1032</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>6.36</td>\n",
       "      <td>Sprayed them directly 10 times. did nothing!</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Eliminator Ant, Roach &amp; Spider Killer4, Aeroso...</td>\n",
       "      <td>4.3548</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>5.98</td>\n",
       "      <td>It does somewhat kill on contact but it's real...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                name  rating  \\\n",
       "0  Eliminator Ant, Roach & Spider Killer4, 20 oz,...  4.0840   \n",
       "1                       Spiderman Party Blowers, 8ct     NaN   \n",
       "2  TERRO Spider and Ant Killer Aerosol Spray, 16 ...  4.5333   \n",
       "3  Hot Shot Fresh Floral Scent Ant, Roach & Spide...  4.1032   \n",
       "4  Eliminator Ant, Roach & Spider Killer4, Aeroso...  4.3548   \n",
       "\n",
       "                      type_of  price  \\\n",
       "0  Pest Bait, Traps & Killers   3.48   \n",
       "1          Novelty & Gag Toys   3.74   \n",
       "2  Pest Bait, Traps & Killers   4.97   \n",
       "3  Pest Bait, Traps & Killers   6.36   \n",
       "4  Pest Bait, Traps & Killers   5.98   \n",
       "\n",
       "                                            comments  \n",
       "0  Covered one up in phone. The roach crawled out...  \n",
       "1                                                NaN  \n",
       "2  EXTREMELY disappointed. Raid worked way faster...  \n",
       "3       Sprayed them directly 10 times. did nothing!  \n",
       "4  It does somewhat kill on contact but it's real...  "
      ]
     },
     "execution_count": 161,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "862"
      ]
     },
     "execution_count": 162,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "metadata": {},
   "outputs": [],
   "source": [
    "# the different zones (tables) to create the inverted-indexes\n",
    "terms_dictionary_for_zone = {\n",
    "        'name': { },\n",
    "         'type_of': { },\n",
    "         'comments': { }\n",
    "         }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "metadata": {},
   "outputs": [],
   "source": [
    "def stemmed_inverted_index_from_data(\n",
    "    \n",
    "    \n",
    "    # the dataframe\n",
    "    doc_database # list[str,]\n",
    "):\n",
    "    terms_dictionary_for_zone = {\n",
    "            'name': { },\n",
    "            'type_of': { },\n",
    "            'comments': { }\n",
    "            }\n",
    "    for zone in doc_database.columns:\n",
    "        # only doing indexing for the chosen zones above\n",
    "        if zone in terms_dictionary_for_zone.keys():\n",
    "            # saving docID and the row content for the chosen zones\n",
    "            for docID, doc in enumerate(df[zone]): # int, str; list[(int, str), ]\n",
    "                \n",
    "                # tokenises the words in the row of the selected zone based on NLTK vocab\n",
    "                sentence_doc = word_tokenize(str(doc)) # list[str,];\n",
    "                # stems all words in doc\n",
    "                sentence_str_1 = [p_stemmer.stem(word_tk) for word_tk in sentence_doc]  # list[str,]\n",
    "                # joins the stemmed tokens back into a sentence for further procesing\n",
    "                sentence_str_1 = \" \".join(sentence_str_1) # str\n",
    "\n",
    "                # subs all symbols/punctuations (including space) with a space (' '); excludes digits\n",
    "                sentence_str_1 = re.sub(r'\\W+', ' ',sentence_str_1)\n",
    "                # subs all digits with a space (' '); a sequence of digits (without space) is given one (' ')\n",
    "                sentence_str_1 = re.sub(r'\\d+', ' ',sentence_str_1)\n",
    "                # subs all symbols AND digits (including spaces) with a space (' '); includes digits\n",
    "                sentence_str_1 = re.sub(r'[^a-zA-Z]', ' ',sentence_str_1)\n",
    "                # compiles a pattern and subs out the pattern in sentence_str_1 with ' '\n",
    "                sentence_str_1 = re.compile('(\\s*)pron(\\s*)').sub(' ', sentence_str_1)\n",
    "\n",
    "                # tokenize to clean up one more time if 're' has introduced and garbage\n",
    "                sentence_doc_1 = word_tokenize(sentence_str_1) # list[str,]\n",
    "                # strip removes whitespace at beginning and end of string (not in between)\n",
    "                sentence_str_2 = [str(word_tk_1).strip() for word_tk_1 in sentence_doc_1] # list[str,]\n",
    "                # strings with >=2 chars only\n",
    "                sentence_str_2  = [word_str for word_str in sentence_str_2 if len(word_str) >= 2] # list[str,]\n",
    "                # strings which are not symbols/punctuations\n",
    "                sentence_str_2 = [word_str for word_str in sentence_str_2  if word_str not in punctuation]\n",
    "                # strings which are not stop-words; check with: Spacy_Eng.vocab['word'].is_stop\n",
    "                sentence_str_2 = [word_str for word_str in sentence_str_2 if word_str not in stop_words]\n",
    "\n",
    "                for term in sentence_str_2: # 'str'\n",
    "                    # for each zone the term increased in doc freq and appends the posting list if term exists\n",
    "                        if term in terms_dictionary_for_zone[zone]: # previously from this doc or other docs\n",
    "                            # print(term, terms_dictionary_for_zone[zone], type(terms_dictionary_for_zone[zone][term][1]))\n",
    "                            if docID in terms_dictionary_for_zone[zone][term][1].keys(): # previously from this doc\n",
    "                                org_val = terms_dictionary_for_zone[zone][term][1][docID]\n",
    "                                terms_dictionary_for_zone[zone][term][1].update({docID : org_val+1})\n",
    "                            else: # from other docs\n",
    "                                terms_dictionary_for_zone[zone][term][1].update({docID : 1})\n",
    "                                terms_dictionary_for_zone[zone][term][0] += 1\n",
    "                                \n",
    "\n",
    "                                \n",
    "                            # terms_dictionary_for_zone[zone][term][1].append([docID, ]) # list[int,]\n",
    "                            # if docID not in terms_dictionary_for_zone[zone][term][1].keys():\n",
    "                            #     terms_dictionary_for_zone[zone][term][0] += 1 # int; doc freq\n",
    "                        # if term doesnt exist, put doc freq as 1 and append the first posting list\n",
    "                        else: # previously non-existant\n",
    "                            terms_dictionary_for_zone[zone][term] =[[],{}] # list[[int], [int, ]]; list[[doc freq], [docIds,]]\n",
    "                            terms_dictionary_for_zone[zone][term][0] = 1 # int; doc freq\n",
    "                            terms_dictionary_for_zone[zone][term][1].update({docID : 1})\n",
    "                            # print(type(terms_dictionary_for_zone[zone][term][1]))\n",
    "    # return the inverted-index dictionary\n",
    "    return terms_dictionary_for_zone"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "metadata": {},
   "outputs": [],
   "source": [
    "# # Test case\n",
    "# doc1 = {\n",
    "#     'name': 'Fuji',\n",
    "#     'rating': '4.5',\n",
    "#     'type_of': 'apple',\n",
    "#     'category': 'fruit',\n",
    "#     'price': '2.50',\n",
    "#     'comments': 'this is an apple, it is kind of fresh but also small, smaller than a grape'\n",
    "# }\n",
    "# doc2 = {\n",
    "#     'name': 'mcIntosh',\n",
    "#     'rating': '3.6',\n",
    "#     'type_of': 'apple',\n",
    "#     'category': 'fruit',\n",
    "#     'price': '3.50',\n",
    "#     'comments': 'it was not as sweet as i hoped'\n",
    "# }\n",
    "# doc3 = {\n",
    "#     'name': 'concord',\n",
    "#     'rating': '4.8',\n",
    "#     'type_of': 'grape',\n",
    "#     'category': 'fruit',\n",
    "#     'price': '4.50',\n",
    "#     'comments': 'trying grapes for the first time, not too bad'\n",
    "# }\n",
    "# doc4 = {\n",
    "#     'name': 'Red anjou',\n",
    "#     'rating': '4.5',\n",
    "#     'type_of': 'pear',\n",
    "#     'category': 'fruit',\n",
    "#     'price': '1.50',\n",
    "#     'comments': 'the shape of the peach is appealing, haha'\n",
    "# }\n",
    "\n",
    "\n",
    "# doc_database_list = [doc1, doc2, doc3, doc4] # list[dict, ]\n",
    "\n",
    "# doc_database = defaultdict(list) # defaultdict({key: list[str, ]})\n",
    "# for doc in doc_database_list:\n",
    "#     for key, val in doc.items():\n",
    "#         doc_database[key].append(val)\n",
    "# doc_database\n",
    "\n",
    "# my_dict = {}\n",
    "# for doc in doc_database_list:\n",
    "#     for key, val in doc.items():\n",
    "#         if key not in my_dict.keys():\n",
    "#             my_dict.update({key: [val]})\n",
    "#         else:\n",
    "#             my_dict[key].append(val)\n",
    "# my_dict\n",
    "\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "metadata": {},
   "outputs": [],
   "source": [
    "inverted_index_zonal_dictionary = stemmed_inverted_index_from_data(df)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1275"
      ]
     },
     "execution_count": 167,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(inverted_index_zonal_dictionary['name'].keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "metadata": {},
   "outputs": [],
   "source": [
    "def query_processing(\n",
    "    query # str\n",
    "):\n",
    "    posting_list = [] # list[]\n",
    "    # split long string of query terms into into different individual terms based on whitespace\n",
    "    # query_terms = query.split() #list[str, ]\n",
    "    # each_term = 0 # int\n",
    "                \n",
    "    # tokenises the words in the row of the selected zone based on NLTK vocab\n",
    "    sentence_doc = word_tokenize(str(query)) # list[str,];\n",
    "    # stems all words in doc\n",
    "    sentence_str_1 = [p_stemmer.stem(word_tk) for word_tk in sentence_doc]  # list[str,]\n",
    "    # joins the stemmed tokens back into a sentence for further procesing\n",
    "    sentence_str_1 = \" \".join(sentence_str_1) # str\n",
    "\n",
    "    # subs all symbols/punctuations (including space) with a space (' '); excludes digits\n",
    "    sentence_str_1 = re.sub(r'\\W+', ' ',sentence_str_1)\n",
    "    # subs all digits with a space (' '); a sequence of digits (without space) is given one (' ')\n",
    "    sentence_str_1 = re.sub(r'\\d+', ' ',sentence_str_1)\n",
    "    # subs all symbols AND digits (including spaces) with a space (' '); includes digits\n",
    "    sentence_str_1 = re.sub(r'[^a-zA-Z]', ' ',sentence_str_1)\n",
    "    # compiles a pattern and subs out the pattern in sentence_str_1 with ' '\n",
    "    sentence_str_1 = re.compile('(\\s*)pron(\\s*)').sub(' ', sentence_str_1)\n",
    "\n",
    "    # tokenize to clean up one more time if 're' has introduced and garbage\n",
    "    sentence_doc_1 = word_tokenize(sentence_str_1) # list[str,]\n",
    "    # strip removes whitespace at beginning and end of string (not in between)\n",
    "    sentence_str_2 = [str(word_tk_1).strip() for word_tk_1 in sentence_doc_1] # list[str,]\n",
    "    # strings with >=2 chars only\n",
    "    sentence_str_2  = [word_str for word_str in sentence_str_2 if len(word_str) >= 2] # list[str,]\n",
    "    # strings which are not symbols/punctuations\n",
    "    sentence_str_2 = [word_str for word_str in sentence_str_2  if word_str not in punctuation]\n",
    "    # strings which are not stop-words; check with: Spacy_Eng.vocab['word'].is_stop\n",
    "    sentence_str_2 = [word_str for word_str in sentence_str_2 if word_str not in stop_words]\n",
    "\n",
    "    \n",
    "    for term in sentence_str_2[:]: # str       \n",
    "        # for individual terms compute edit distance with each term in the 'name' inverted-index dictionary\n",
    "        # this is useful if there is a typo in one or multiple of the query terms\n",
    "        edit_dist_list = [[key, nltk.edit_distance(term, key)]  for key in inverted_index_zonal_dictionary['name']] # list[[str, double], ]\n",
    "        edit_dist_list_1 = list(zip(*edit_dist_list)) # list[(str,)(double,)]\n",
    "        # choose the min edit distance as the closest term match in the inverted-index dictionary\n",
    "        if min(edit_dist_list_1[1]) >=2:\n",
    "            print('No matching results')\n",
    "            return 0\n",
    "\n",
    "\n",
    "        internal_query = edit_dist_list_1[0][edit_dist_list_1[1].index(min(edit_dist_list_1[1]))] # str\n",
    "\n",
    "\n",
    "        # from the term matched in the inverted-index, append, its posting list to 'posting-list'\n",
    "        posting_list.append(inverted_index_zonal_dictionary['name'][internal_query][1]) # list[[int, ], ]\n",
    "        # each_term +=1\n",
    "\n",
    "    return posting_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "metadata": {},
   "outputs": [],
   "source": [
    "def tf_df(posting_list):\n",
    "    \n",
    "    # for multiple query terms, we also get (OR query)\n",
    "    posting_list_combined = set(list(itertools.chain(*posting_list))) # list[int, ]\n",
    "    # print(posting_list_combined)\n",
    "    # posting_list_combined_for_or_low_priority = set(posting_list_combined) # set[int, ]\n",
    "\n",
    "\n",
    "    ### tf|term,doc\n",
    "    term_freq_given_doc_term = {}\n",
    "    for docID in posting_list_combined:\n",
    "        for i in range(0, len(posting_list), 1):\n",
    "            if docID not in term_freq_given_doc_term.keys():\n",
    "                if docID not in posting_list[i]:\n",
    "                    term_freq_given_doc_term.update({docID : [0]})\n",
    "                else:\n",
    "                    term_freq_given_doc_term.update({docID : [posting_list[i][docID]]})\n",
    "            else:\n",
    "                if docID not in posting_list[i]:\n",
    "                    term_freq_given_doc_term[docID].append(0)\n",
    "                else:\n",
    "                    term_freq_given_doc_term[docID].append(posting_list[i][docID])\n",
    "    \n",
    "    \n",
    "    ### df|term\n",
    "    doc_freq_given_terms = []\n",
    "    for i in range(0, len(posting_list), 1):\n",
    "        doc_freq_given_terms.append(len(posting_list[i]))\n",
    "\n",
    "\n",
    "    return term_freq_given_doc_term, doc_freq_given_terms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "metadata": {},
   "outputs": [],
   "source": [
    "def doc_scoring(term_f, doc_f):\n",
    "    score = {}\n",
    "    doc_score = {}\n",
    "    for key, val in term_f.items():\n",
    "        for i in range(0, len(val), 1):\n",
    "            if key not in score.keys():\n",
    "                tf_idf = (1 + np.log10(val[i])) * (np.log10(df.shape[0]/doc_f[i]))\n",
    "                if tf_idf > -9999:\n",
    "                    score.update({key : [tf_idf]})\n",
    "                else:\n",
    "                    score.update({key : [0]})\n",
    "            else:\n",
    "                tf_idf = (1 + np.log10(val[i])) * (np.log10(df.shape[0]/doc_f[i]))\n",
    "                if tf_idf > -9999:\n",
    "                    score[key].append(tf_idf)\n",
    "                else:\n",
    "                    score[key].append(0)\n",
    "    \n",
    "    for key, val in score.items():\n",
    "        doc_score.update({key : sum(val)})\n",
    "\n",
    "\n",
    "    return score, dict(sorted(doc_score.items(), key = lambda x : x[1], reverse= True))\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{0: 3.615742026546119, 4: 3.615742026546119, 82: 3.615742026546119, 797: 1.709555169685661, 129: 1.5057548917509769, 813: 1.5057548917509769, 307: 1.5057548917509769, 853: 1.5057548917509769, 2: 1.1573560154410691, 3: 1.1573560154410691, 5: 1.1573560154410691, 6: 1.1573560154410691, 7: 1.1573560154410691, 257: 1.1573560154410691, 265: 1.1573560154410691, 138: 1.1573560154410691, 139: 1.1573560154410691, 141: 1.1573560154410691, 14: 1.1573560154410691, 20: 1.1573560154410691, 151: 1.1573560154410691, 26: 1.1573560154410691, 283: 1.1573560154410691, 794: 1.1573560154410691, 30: 1.1573560154410691, 415: 1.1573560154410691, 674: 1.1573560154410691, 35: 1.1573560154410691, 163: 1.1573560154410691, 294: 1.1573560154410691, 557: 1.1573560154410691, 174: 1.1573560154410691, 430: 1.1573560154410691, 306: 1.1573560154410691, 563: 1.1573560154410691, 571: 1.1573560154410691, 449: 1.1573560154410691, 837: 1.1573560154410691, 332: 1.1573560154410691, 845: 1.1573560154410691, 336: 1.1573560154410691, 339: 1.1573560154410691, 340: 1.1573560154410691, 342: 1.1573560154410691, 217: 1.1573560154410691, 345: 1.1573560154410691, 474: 1.1573560154410691, 603: 1.1573560154410691, 729: 1.1573560154410691, 730: 1.1573560154410691, 223: 1.1573560154410691, 483: 1.1573560154410691, 101: 1.1573560154410691, 614: 1.1573560154410691, 105: 1.1573560154410691, 368: 1.1573560154410691, 118: 1.1573560154410691, 504: 1.1573560154410691, 762: 1.1573560154410691, 764: 1.1573560154410691}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Shiva\\.conda\\envs\\nlp_env\\lib\\site-packages\\ipykernel_launcher.py:7: RuntimeWarning: divide by zero encountered in log10\n",
      "  import sys\n"
     ]
    }
   ],
   "source": [
    "query = 'eliminator ant' # 'str' typo; on both terms\n",
    "pl= query_processing(query)\n",
    "term_f, doc_f = tf_df(pl)\n",
    "score, doc_score = doc_scoring(term_f,doc_f)\n",
    "# print(term_f, doc_f)\n",
    "print(doc_score)    \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_10_docID = list(doc_score.keys())[0:10]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "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>rating</th>\n",
       "      <th>type_of</th>\n",
       "      <th>price</th>\n",
       "      <th>comments</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Eliminator Ant, Roach &amp; Spider Killer4, 20 oz,...</td>\n",
       "      <td>4.0840</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>3.48</td>\n",
       "      <td>Covered one up in phone. The roach crawled out...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Eliminator Ant, Roach &amp; Spider Killer4, Aeroso...</td>\n",
       "      <td>4.3548</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>5.98</td>\n",
       "      <td>It does somewhat kill on contact but it's real...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>82</th>\n",
       "      <td>Eliminator Ant, Flea &amp; Tick Killer Plus Granul...</td>\n",
       "      <td>4.0804</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>6.48</td>\n",
       "      <td>I bought it because I was expecting it to kill...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>797</th>\n",
       "      <td>TERRO T600 Ant Dust - Kills fire ants, carpent...</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>18.49</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>129</th>\n",
       "      <td>Ortho Home Defense Max Ant, Roach and Spider, ...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>10.80</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>813</th>\n",
       "      <td>Disney Avengers Campus Spider-Bot Ant Man Wasp...</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>Action Figures</td>\n",
       "      <td>44.99</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>307</th>\n",
       "      <td>Raid Ant &amp; Roach Killer - Fragrance-Free - Spr...</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>41.92</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>853</th>\n",
       "      <td>Disney Avengers Campus Spider-Bot Ant Man Tact...</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>Action Figures</td>\n",
       "      <td>44.99</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>TERRO Spider and Ant Killer Aerosol Spray, 16 ...</td>\n",
       "      <td>4.5333</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>4.97</td>\n",
       "      <td>EXTREMELY disappointed. Raid worked way faster...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Hot Shot Fresh Floral Scent Ant, Roach &amp; Spide...</td>\n",
       "      <td>4.1032</td>\n",
       "      <td>Pest Bait, Traps &amp; Killers</td>\n",
       "      <td>6.36</td>\n",
       "      <td>Sprayed them directly 10 times. did nothing!</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                  name  rating  \\\n",
       "0    Eliminator Ant, Roach & Spider Killer4, 20 oz,...  4.0840   \n",
       "4    Eliminator Ant, Roach & Spider Killer4, Aeroso...  4.3548   \n",
       "82   Eliminator Ant, Flea & Tick Killer Plus Granul...  4.0804   \n",
       "797  TERRO T600 Ant Dust - Kills fire ants, carpent...  0.0000   \n",
       "129  Ortho Home Defense Max Ant, Roach and Spider, ...     NaN   \n",
       "813  Disney Avengers Campus Spider-Bot Ant Man Wasp...  0.0000   \n",
       "307  Raid Ant & Roach Killer - Fragrance-Free - Spr...  0.0000   \n",
       "853  Disney Avengers Campus Spider-Bot Ant Man Tact...  0.0000   \n",
       "2    TERRO Spider and Ant Killer Aerosol Spray, 16 ...  4.5333   \n",
       "3    Hot Shot Fresh Floral Scent Ant, Roach & Spide...  4.1032   \n",
       "\n",
       "                        type_of  price  \\\n",
       "0    Pest Bait, Traps & Killers   3.48   \n",
       "4    Pest Bait, Traps & Killers   5.98   \n",
       "82   Pest Bait, Traps & Killers   6.48   \n",
       "797  Pest Bait, Traps & Killers  18.49   \n",
       "129  Pest Bait, Traps & Killers  10.80   \n",
       "813              Action Figures  44.99   \n",
       "307  Pest Bait, Traps & Killers  41.92   \n",
       "853              Action Figures  44.99   \n",
       "2    Pest Bait, Traps & Killers   4.97   \n",
       "3    Pest Bait, Traps & Killers   6.36   \n",
       "\n",
       "                                              comments  \n",
       "0    Covered one up in phone. The roach crawled out...  \n",
       "4    It does somewhat kill on contact but it's real...  \n",
       "82   I bought it because I was expecting it to kill...  \n",
       "797                                                NaN  \n",
       "129                                                NaN  \n",
       "813                                                NaN  \n",
       "307                                                NaN  \n",
       "853                                                NaN  \n",
       "2    EXTREMELY disappointed. Raid worked way faster...  \n",
       "3         Sprayed them directly 10 times. did nothing!  "
      ]
     },
     "execution_count": 173,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[top_10_docID,:]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "PART 2 - Cosine similarity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 174,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_2 = df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Eliminator Ant, Roach & Spider Killer4, 20 oz, Kills Insects & Spiders'"
      ]
     },
     "execution_count": 175,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "query_1 = df.loc[0, 'name']\n",
    "query_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 176,
   "metadata": {},
   "outputs": [],
   "source": [
    "inverted_index_zonal_dictionary_second = stemmed_inverted_index_from_data(df_2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 177,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1275"
      ]
     },
     "execution_count": 177,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(inverted_index_zonal_dictionary_second['name'].keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "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>elimin</th>\n",
       "      <th>ant</th>\n",
       "      <th>roach</th>\n",
       "      <th>spider</th>\n",
       "      <th>killer</th>\n",
       "      <th>oz</th>\n",
       "      <th>kill</th>\n",
       "      <th>insect</th>\n",
       "      <th>spiderman</th>\n",
       "      <th>parti</th>\n",
       "      <th>...</th>\n",
       "      <th>bring</th>\n",
       "      <th>tradit</th>\n",
       "      <th>flip</th>\n",
       "      <th>indestruct</th>\n",
       "      <th>chew</th>\n",
       "      <th>proof</th>\n",
       "      <th>rip</th>\n",
       "      <th>nontox</th>\n",
       "      <th>washabl</th>\n",
       "      <th>newborn</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 1275 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   elimin  ant  roach  spider  killer   oz  kill  insect  spiderman  parti  \\\n",
       "0     0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "\n",
       "   ...  bring  tradit  flip  indestruct  chew  proof  rip  nontox  washabl  \\\n",
       "0  ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "\n",
       "   newborn  \n",
       "0      0.0  \n",
       "\n",
       "[1 rows x 1275 columns]"
      ]
     },
     "execution_count": 178,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "zero_data = np.zeros(shape=(1,len(inverted_index_zonal_dictionary_second['name'].keys())))\n",
    "initiate_query_bow = pd.DataFrame(zero_data, columns = inverted_index_zonal_dictionary_second['name'].keys())\n",
    "initiate_query_bow"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 179,
   "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>elimin</th>\n",
       "      <th>ant</th>\n",
       "      <th>roach</th>\n",
       "      <th>spider</th>\n",
       "      <th>killer</th>\n",
       "      <th>oz</th>\n",
       "      <th>kill</th>\n",
       "      <th>insect</th>\n",
       "      <th>spiderman</th>\n",
       "      <th>parti</th>\n",
       "      <th>...</th>\n",
       "      <th>bring</th>\n",
       "      <th>tradit</th>\n",
       "      <th>flip</th>\n",
       "      <th>indestruct</th>\n",
       "      <th>chew</th>\n",
       "      <th>proof</th>\n",
       "      <th>rip</th>\n",
       "      <th>nontox</th>\n",
       "      <th>washabl</th>\n",
       "      <th>newborn</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>857</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>858</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>859</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>860</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>861</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>862 rows × 1275 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     elimin  ant  roach  spider  killer   oz  kill  insect  spiderman  parti  \\\n",
       "0       0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "1       0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "2       0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "3       0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "4       0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "..      ...  ...    ...     ...     ...  ...   ...     ...        ...    ...   \n",
       "857     0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "858     0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "859     0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "860     0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "861     0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "\n",
       "     ...  bring  tradit  flip  indestruct  chew  proof  rip  nontox  washabl  \\\n",
       "0    ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "1    ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "2    ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "3    ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "4    ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "..   ...    ...     ...   ...         ...   ...    ...  ...     ...      ...   \n",
       "857  ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "858  ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "859  ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "860  ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "861  ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "\n",
       "     newborn  \n",
       "0        0.0  \n",
       "1        0.0  \n",
       "2        0.0  \n",
       "3        0.0  \n",
       "4        0.0  \n",
       "..       ...  \n",
       "857      0.0  \n",
       "858      0.0  \n",
       "859      0.0  \n",
       "860      0.0  \n",
       "861      0.0  \n",
       "\n",
       "[862 rows x 1275 columns]"
      ]
     },
     "execution_count": 179,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "zero_data = np.zeros(shape=(len(df_2),len(inverted_index_zonal_dictionary_second['name'].keys())))\n",
    "initiate_bow = pd.DataFrame(zero_data, columns = inverted_index_zonal_dictionary_second['name'].keys())\n",
    "initiate_bow"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 180,
   "metadata": {},
   "outputs": [],
   "source": [
    "def BOW(doc_database, bow):\n",
    "    terms_dictionary_for_zone = {\n",
    "            'name': { },\n",
    "            # 'type_of': { },\n",
    "            # 'comments': { }\n",
    "            }\n",
    "    L2_norm_doc = []\n",
    "    for zone in doc_database.columns:\n",
    "        # only doing indexing for the chosen zones above\n",
    "        if zone in terms_dictionary_for_zone.keys():\n",
    "            # saving docID and the row content for the chosen zones\n",
    "            for docID, doc in enumerate(df_2[zone]): # int, str; list[(int, str), ]\n",
    "                 \n",
    "                # tokenises the words in the row of the selected zone based on NLTK vocab\n",
    "                sentence_doc = word_tokenize(str(doc)) # list[str,];\n",
    "                # stems all words in doc\n",
    "                sentence_str_1 = [p_stemmer.stem(word_tk) for word_tk in sentence_doc]  # list[str,]\n",
    "                # joins the stemmed tokens back into a sentence for further procesing\n",
    "                sentence_str_1 = \" \".join(sentence_str_1) # str\n",
    "\n",
    "                # subs all symbols/punctuations (including space) with a space (' '); excludes digits\n",
    "                sentence_str_1 = re.sub(r'\\W+', ' ',sentence_str_1)\n",
    "                # subs all digits with a space (' '); a sequence of digits (without space) is given one (' ')\n",
    "                sentence_str_1 = re.sub(r'\\d+', ' ',sentence_str_1)\n",
    "                # subs all symbols AND digits (including spaces) with a space (' '); includes digits\n",
    "                sentence_str_1 = re.sub(r'[^a-zA-Z]', ' ',sentence_str_1)\n",
    "                # compiles a pattern and subs out the pattern in sentence_str_1 with ' '\n",
    "                sentence_str_1 = re.compile('(\\s*)pron(\\s*)').sub(' ', sentence_str_1)\n",
    "\n",
    "                # tokenize to clean up one more time if 're' has introduced and garbage\n",
    "                sentence_doc_1 = word_tokenize(sentence_str_1) # list[str,]\n",
    "                # strip removes whitespace at beginning and end of string (not in between)\n",
    "                sentence_str_2 = [str(word_tk_1).strip() for word_tk_1 in sentence_doc_1] # list[str,]\n",
    "                # strings with >=2 chars only\n",
    "                sentence_str_2  = [word_str for word_str in sentence_str_2 if len(word_str) >= 2] # list[str,]\n",
    "                # strings which are not symbols/punctuations\n",
    "                sentence_str_2 = [word_str for word_str in sentence_str_2  if word_str not in punctuation]\n",
    "                # strings which are not stop-words; check with: Spacy_Eng.vocab['word'].is_stop\n",
    "                sentence_str_2 = [word_str for word_str in sentence_str_2 if word_str not in stop_words]\n",
    "\n",
    "                for term in sentence_str_2: # 'str'\n",
    "                    # for each zone the term increased in doc freq and appends the posting list if term exists\n",
    "                    if term in bow.columns:\n",
    "                        bow.loc[docID, term] += 1\n",
    "                L2_norm_doc.append(LA.norm(bow.loc[docID, :].to_numpy()))\n",
    "                \n",
    "\n",
    "\n",
    "                \n",
    "    return bow, L2_norm_doc\n",
    "      "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 181,
   "metadata": {},
   "outputs": [],
   "source": [
    "def query_BOW(doc, q_bow):\n",
    "                 \n",
    "    # tokenises the words in the row of the selected zone based on NLTK vocab\n",
    "    sentence_doc = word_tokenize(str(doc)) # list[str,];\n",
    "    # stems all words in doc\n",
    "    sentence_str_1 = [p_stemmer.stem(word_tk) for word_tk in sentence_doc]  # list[str,]\n",
    "    # joins the stemmed tokens back into a sentence for further procesing\n",
    "    sentence_str_1 = \" \".join(sentence_str_1) # str\n",
    "\n",
    "    # subs all symbols/punctuations (including space) with a space (' '); excludes digits\n",
    "    sentence_str_1 = re.sub(r'\\W+', ' ',sentence_str_1)\n",
    "    # subs all digits with a space (' '); a sequence of digits (without space) is given one (' ')\n",
    "    sentence_str_1 = re.sub(r'\\d+', ' ',sentence_str_1)\n",
    "    # subs all symbols AND digits (including spaces) with a space (' '); includes digits\n",
    "    sentence_str_1 = re.sub(r'[^a-zA-Z]', ' ',sentence_str_1)\n",
    "    # compiles a pattern and subs out the pattern in sentence_str_1 with ' '\n",
    "    sentence_str_1 = re.compile('(\\s*)pron(\\s*)').sub(' ', sentence_str_1)\n",
    "\n",
    "    # tokenize to clean up one more time if 're' has introduced and garbage\n",
    "    sentence_doc_1 = word_tokenize(sentence_str_1) # list[str,]\n",
    "    # strip removes whitespace at beginning and end of string (not in between)\n",
    "    sentence_str_2 = [str(word_tk_1).strip() for word_tk_1 in sentence_doc_1] # list[str,]\n",
    "    # strings with >=2 chars only\n",
    "    sentence_str_2  = [word_str for word_str in sentence_str_2 if len(word_str) >= 2] # list[str,]\n",
    "    # strings which are not symbols/punctuations\n",
    "    sentence_str_2 = [word_str for word_str in sentence_str_2  if word_str not in punctuation]\n",
    "    # strings which are not stop-words; check with: Spacy_Eng.vocab['word'].is_stop\n",
    "    sentence_str_2 = [word_str for word_str in sentence_str_2 if word_str not in stop_words]\n",
    "\n",
    "    for term in sentence_str_2: # 'str'\n",
    "        # for each zone the term increased in doc freq and appends the posting list if term exists\n",
    "        if term in bow.columns:\n",
    "            q_bow.loc[0, term] += 1\n",
    "    \n",
    "    L2_norm_query = LA.norm(q_bow.to_numpy())\n",
    "    return q_bow, L2_norm_query\n",
    "      "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 182,
   "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>elimin</th>\n",
       "      <th>ant</th>\n",
       "      <th>roach</th>\n",
       "      <th>spider</th>\n",
       "      <th>killer</th>\n",
       "      <th>oz</th>\n",
       "      <th>kill</th>\n",
       "      <th>insect</th>\n",
       "      <th>spiderman</th>\n",
       "      <th>parti</th>\n",
       "      <th>...</th>\n",
       "      <th>bring</th>\n",
       "      <th>tradit</th>\n",
       "      <th>flip</th>\n",
       "      <th>indestruct</th>\n",
       "      <th>chew</th>\n",
       "      <th>proof</th>\n",
       "      <th>rip</th>\n",
       "      <th>nontox</th>\n",
       "      <th>washabl</th>\n",
       "      <th>newborn</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>857</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>858</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>859</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>860</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>861</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>862 rows × 1275 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     elimin  ant  roach  spider  killer   oz  kill  insect  spiderman  parti  \\\n",
       "0       1.0  1.0    1.0     2.0     1.0  1.0   1.0     1.0        0.0    0.0   \n",
       "1       0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        1.0    1.0   \n",
       "2       0.0  1.0    0.0     1.0     1.0  0.0   0.0     0.0        0.0    0.0   \n",
       "3       0.0  1.0    1.0     1.0     1.0  1.0   0.0     0.0        0.0    0.0   \n",
       "4       1.0  1.0    1.0     1.0     1.0  0.0   0.0     0.0        0.0    0.0   \n",
       "..      ...  ...    ...     ...     ...  ...   ...     ...        ...    ...   \n",
       "857     0.0  0.0    0.0     1.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "858     0.0  0.0    0.0     0.0     0.0  0.0   0.0     0.0        1.0    0.0   \n",
       "859     0.0  0.0    0.0     1.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "860     0.0  0.0    0.0     2.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "861     0.0  0.0    0.0     1.0     0.0  0.0   0.0     0.0        0.0    0.0   \n",
       "\n",
       "     ...  bring  tradit  flip  indestruct  chew  proof  rip  nontox  washabl  \\\n",
       "0    ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "1    ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "2    ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "3    ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "4    ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "..   ...    ...     ...   ...         ...   ...    ...  ...     ...      ...   \n",
       "857  ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "858  ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "859  ...    1.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "860  ...    0.0     1.0   1.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "861  ...    0.0     0.0   0.0         2.0   2.0    2.0  1.0     1.0      1.0   \n",
       "\n",
       "     newborn  \n",
       "0        0.0  \n",
       "1        0.0  \n",
       "2        0.0  \n",
       "3        0.0  \n",
       "4        0.0  \n",
       "..       ...  \n",
       "857      0.0  \n",
       "858      0.0  \n",
       "859      0.0  \n",
       "860      0.0  \n",
       "861      1.0  \n",
       "\n",
       "[862 rows x 1275 columns]"
      ]
     },
     "execution_count": 182,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bow, L2_norm_doc = BOW(df_2, initiate_bow)\n",
    "bow"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 183,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[3.3166247903554,\n",
       " 2.0,\n",
       " 2.6457513110645907,\n",
       " 3.3166247903554,\n",
       " 2.8284271247461903,\n",
       " 2.8284271247461903,\n",
       " 2.8284271247461903,\n",
       " 4.242640687119285,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 2.0,\n",
       " 2.449489742783178,\n",
       " 3.605551275463989,\n",
       " 2.0,\n",
       " 3.4641016151377544,\n",
       " 3.0,\n",
       " 3.0,\n",
       " 3.605551275463989,\n",
       " 2.8284271247461903,\n",
       " 3.1622776601683795,\n",
       " 5.0,\n",
       " 2.449489742783178,\n",
       " 2.23606797749979,\n",
       " 2.23606797749979,\n",
       " 2.23606797749979,\n",
       " 3.605551275463989,\n",
       " 4.58257569495584,\n",
       " 3.1622776601683795,\n",
       " 2.6457513110645907,\n",
       " 4.358898943540674,\n",
       " 3.4641016151377544,\n",
       " 2.8284271247461903,\n",
       " 2.23606797749979,\n",
       " 5.744562646538029,\n",
       " 5.196152422706632,\n",
       " 5.0,\n",
       " 3.0,\n",
       " 3.1622776601683795,\n",
       " 2.6457513110645907,\n",
       " 2.23606797749979,\n",
       " 2.23606797749979,\n",
       " 5.656854249492381,\n",
       " 2.449489742783178,\n",
       " 2.449489742783178,\n",
       " 4.47213595499958,\n",
       " 2.6457513110645907,\n",
       " 2.23606797749979,\n",
       " 2.23606797749979,\n",
       " 3.0,\n",
       " 2.6457513110645907,\n",
       " 3.4641016151377544,\n",
       " 3.4641016151377544,\n",
       " 3.872983346207417,\n",
       " 3.4641016151377544,\n",
       " 5.0990195135927845,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 2.0,\n",
       " 3.1622776601683795,\n",
       " 4.123105625617661,\n",
       " 3.3166247903554,\n",
       " 3.1622776601683795,\n",
       " 3.7416573867739413,\n",
       " 2.6457513110645907,\n",
       " 3.605551275463989,\n",
       " 2.8284271247461903,\n",
       " 3.1622776601683795,\n",
       " 4.795831523312719,\n",
       " 3.0,\n",
       " 2.6457513110645907,\n",
       " 3.3166247903554,\n",
       " 2.6457513110645907,\n",
       " 2.8284271247461903,\n",
       " 3.7416573867739413,\n",
       " 4.123105625617661,\n",
       " 3.0,\n",
       " 3.605551275463989,\n",
       " 4.242640687119285,\n",
       " 3.3166247903554,\n",
       " 2.23606797749979,\n",
       " 2.8284271247461903,\n",
       " 2.0,\n",
       " 2.8284271247461903,\n",
       " 2.8284271247461903,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 2.8284271247461903,\n",
       " 2.6457513110645907,\n",
       " 3.4641016151377544,\n",
       " 2.6457513110645907,\n",
       " 2.6457513110645907,\n",
       " 2.6457513110645907,\n",
       " 3.4641016151377544,\n",
       " 3.872983346207417,\n",
       " 3.4641016151377544,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 2.6457513110645907,\n",
       " 2.8284271247461903,\n",
       " 3.4641016151377544,\n",
       " 3.605551275463989,\n",
       " 2.6457513110645907,\n",
       " 2.6457513110645907,\n",
       " 4.358898943540674,\n",
       " 2.8284271247461903,\n",
       " 3.4641016151377544,\n",
       " 3.605551275463989,\n",
       " 4.242640687119285,\n",
       " 2.449489742783178,\n",
       " 2.6457513110645907,\n",
       " 2.449489742783178,\n",
       " 2.23606797749979,\n",
       " 3.3166247903554,\n",
       " 3.7416573867739413,\n",
       " 4.242640687119285,\n",
       " 2.23606797749979,\n",
       " 3.4641016151377544,\n",
       " 3.1622776601683795,\n",
       " 3.7416573867739413,\n",
       " 2.23606797749979,\n",
       " 2.8284271247461903,\n",
       " 2.23606797749979,\n",
       " 2.8284271247461903,\n",
       " 2.23606797749979,\n",
       " 2.449489742783178,\n",
       " 2.449489742783178,\n",
       " 2.449489742783178,\n",
       " 2.23606797749979,\n",
       " 3.1622776601683795,\n",
       " 3.7416573867739413,\n",
       " 3.0,\n",
       " 2.6457513110645907,\n",
       " 3.4641016151377544,\n",
       " 3.1622776601683795,\n",
       " 3.1622776601683795,\n",
       " 3.872983346207417,\n",
       " 3.4641016151377544,\n",
       " 2.8284271247461903,\n",
       " 5.0,\n",
       " 3.4641016151377544,\n",
       " 3.3166247903554,\n",
       " 3.7416573867739413,\n",
       " 2.8284271247461903,\n",
       " 3.872983346207417,\n",
       " 3.1622776601683795,\n",
       " 2.8284271247461903,\n",
       " 7.14142842854285,\n",
       " 3.872983346207417,\n",
       " 4.0,\n",
       " 3.872983346207417,\n",
       " 4.0,\n",
       " 4.69041575982343,\n",
       " 3.4641016151377544,\n",
       " 3.1622776601683795,\n",
       " 3.0,\n",
       " 3.4641016151377544,\n",
       " 3.1622776601683795,\n",
       " 2.8284271247461903,\n",
       " 3.7416573867739413,\n",
       " 3.1622776601683795,\n",
       " 4.358898943540674,\n",
       " 2.6457513110645907,\n",
       " 2.8284271247461903,\n",
       " 3.605551275463989,\n",
       " 2.8284271247461903,\n",
       " 4.123105625617661,\n",
       " 3.1622776601683795,\n",
       " 4.0,\n",
       " 2.0,\n",
       " 4.0,\n",
       " 2.23606797749979,\n",
       " 2.6457513110645907,\n",
       " 4.123105625617661,\n",
       " 5.5677643628300215,\n",
       " 4.58257569495584,\n",
       " 3.872983346207417,\n",
       " 2.23606797749979,\n",
       " 4.242640687119285,\n",
       " 4.0,\n",
       " 3.0,\n",
       " 3.3166247903554,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 3.0,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 2.449489742783178,\n",
       " 2.6457513110645907,\n",
       " 3.7416573867739413,\n",
       " 4.123105625617661,\n",
       " 3.872983346207417,\n",
       " 2.8284271247461903,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 4.47213595499958,\n",
       " 4.795831523312719,\n",
       " 3.7416573867739413,\n",
       " 3.605551275463989,\n",
       " 2.8284271247461903,\n",
       " 2.449489742783178,\n",
       " 3.3166247903554,\n",
       " 3.605551275463989,\n",
       " 5.5677643628300215,\n",
       " 3.0,\n",
       " 4.123105625617661,\n",
       " 2.0,\n",
       " 3.872983346207417,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 3.0,\n",
       " 1.4142135623730951,\n",
       " 2.0,\n",
       " 3.3166247903554,\n",
       " 5.0990195135927845,\n",
       " 3.0,\n",
       " 3.605551275463989,\n",
       " 4.47213595499958,\n",
       " 4.47213595499958,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 2.8284271247461903,\n",
       " 4.358898943540674,\n",
       " 3.7416573867739413,\n",
       " 2.0,\n",
       " 3.605551275463989,\n",
       " 3.4641016151377544,\n",
       " 3.0,\n",
       " 3.7416573867739413,\n",
       " 2.8284271247461903,\n",
       " 2.8284271247461903,\n",
       " 3.0,\n",
       " 3.605551275463989,\n",
       " 4.0,\n",
       " 2.8284271247461903,\n",
       " 3.1622776601683795,\n",
       " 4.123105625617661,\n",
       " 3.0,\n",
       " 3.605551275463989,\n",
       " 4.242640687119285,\n",
       " 4.898979485566356,\n",
       " 4.47213595499958,\n",
       " 2.449489742783178,\n",
       " 2.23606797749979,\n",
       " 3.0,\n",
       " 3.1622776601683795,\n",
       " 3.4641016151377544,\n",
       " 4.123105625617661,\n",
       " 3.0,\n",
       " 3.4641016151377544,\n",
       " 2.6457513110645907,\n",
       " 2.8284271247461903,\n",
       " 3.4641016151377544,\n",
       " 3.4641016151377544,\n",
       " 2.6457513110645907,\n",
       " 5.0990195135927845,\n",
       " 4.58257569495584,\n",
       " 3.7416573867739413,\n",
       " 3.7416573867739413,\n",
       " 3.4641016151377544,\n",
       " 5.196152422706632,\n",
       " 3.3166247903554,\n",
       " 3.0,\n",
       " 4.123105625617661,\n",
       " 5.0990195135927845,\n",
       " 3.0,\n",
       " 4.0,\n",
       " 3.0,\n",
       " 1.7320508075688772,\n",
       " 3.4641016151377544,\n",
       " 2.6457513110645907,\n",
       " 3.872983346207417,\n",
       " 3.605551275463989,\n",
       " 3.0,\n",
       " 3.4641016151377544,\n",
       " 3.605551275463989,\n",
       " 3.3166247903554,\n",
       " 2.8284271247461903,\n",
       " 2.8284271247461903,\n",
       " 3.4641016151377544,\n",
       " 2.0,\n",
       " 3.0,\n",
       " 5.385164807134504,\n",
       " 5.0990195135927845,\n",
       " 2.449489742783178,\n",
       " 3.605551275463989,\n",
       " 3.0,\n",
       " 3.4641016151377544,\n",
       " 2.6457513110645907,\n",
       " 4.242640687119285,\n",
       " 3.605551275463989,\n",
       " 3.605551275463989,\n",
       " 3.0,\n",
       " 4.358898943540674,\n",
       " 2.6457513110645907,\n",
       " 3.3166247903554,\n",
       " 3.0,\n",
       " 3.7416573867739413,\n",
       " 3.1622776601683795,\n",
       " 3.605551275463989,\n",
       " 3.0,\n",
       " 2.23606797749979,\n",
       " 3.3166247903554,\n",
       " 2.8284271247461903,\n",
       " 3.4641016151377544,\n",
       " 3.7416573867739413,\n",
       " 4.795831523312719,\n",
       " 3.1622776601683795,\n",
       " 2.8284271247461903,\n",
       " 3.0,\n",
       " 3.7416573867739413,\n",
       " 4.47213595499958,\n",
       " 2.6457513110645907,\n",
       " 3.4641016151377544,\n",
       " 2.8284271247461903,\n",
       " 3.0,\n",
       " 2.6457513110645907,\n",
       " 2.0,\n",
       " 2.0,\n",
       " 1.7320508075688772,\n",
       " 1.7320508075688772,\n",
       " 3.7416573867739413,\n",
       " 4.123105625617661,\n",
       " 6.855654600401044,\n",
       " 2.0,\n",
       " 2.23606797749979,\n",
       " 2.449489742783178,\n",
       " 5.5677643628300215,\n",
       " 3.4641016151377544,\n",
       " 3.605551275463989,\n",
       " 2.6457513110645907,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 4.123105625617661,\n",
       " 2.6457513110645907,\n",
       " 4.47213595499958,\n",
       " 3.3166247903554,\n",
       " 3.605551275463989,\n",
       " 3.7416573867739413,\n",
       " 5.0990195135927845,\n",
       " 4.242640687119285,\n",
       " 5.830951894845301,\n",
       " 3.1622776601683795,\n",
       " 3.1622776601683795,\n",
       " 7.14142842854285,\n",
       " 3.1622776601683795,\n",
       " 2.8284271247461903,\n",
       " 2.8284271247461903,\n",
       " 3.872983346207417,\n",
       " 4.898979485566356,\n",
       " 2.8284271247461903,\n",
       " 3.605551275463989,\n",
       " 3.3166247903554,\n",
       " 2.449489742783178,\n",
       " 3.0,\n",
       " 3.1622776601683795,\n",
       " 2.8284271247461903,\n",
       " 3.3166247903554,\n",
       " 5.916079783099616,\n",
       " 3.0,\n",
       " 3.1622776601683795,\n",
       " 3.872983346207417,\n",
       " 3.872983346207417,\n",
       " 2.449489742783178,\n",
       " 3.0,\n",
       " 3.605551275463989,\n",
       " 2.0,\n",
       " 5.916079783099616,\n",
       " 4.123105625617661,\n",
       " 3.872983346207417,\n",
       " 3.7416573867739413,\n",
       " 3.605551275463989,\n",
       " 6.4031242374328485,\n",
       " 6.082762530298219,\n",
       " 3.0,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 3.1622776601683795,\n",
       " 2.6457513110645907,\n",
       " 3.0,\n",
       " 3.872983346207417,\n",
       " 3.0,\n",
       " 2.8284271247461903,\n",
       " 3.0,\n",
       " 2.449489742783178,\n",
       " 8.18535277187245,\n",
       " 3.3166247903554,\n",
       " 3.7416573867739413,\n",
       " 6.708203932499369,\n",
       " 7.0710678118654755,\n",
       " 4.358898943540674,\n",
       " 3.1622776601683795,\n",
       " 3.0,\n",
       " 2.8284271247461903,\n",
       " 3.1622776601683795,\n",
       " 2.6457513110645907,\n",
       " 2.23606797749979,\n",
       " 3.1622776601683795,\n",
       " 4.69041575982343,\n",
       " 4.47213595499958,\n",
       " 5.5677643628300215,\n",
       " 2.6457513110645907,\n",
       " 2.6457513110645907,\n",
       " 2.8284271247461903,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 2.8284271247461903,\n",
       " 2.0,\n",
       " 3.1622776601683795,\n",
       " 3.605551275463989,\n",
       " 2.23606797749979,\n",
       " 2.6457513110645907,\n",
       " 2.6457513110645907,\n",
       " 4.123105625617661,\n",
       " 5.744562646538029,\n",
       " 6.324555320336759,\n",
       " 3.3166247903554,\n",
       " 3.4641016151377544,\n",
       " 5.0,\n",
       " 2.8284271247461903,\n",
       " 3.872983346207417,\n",
       " 4.58257569495584,\n",
       " 2.6457513110645907,\n",
       " 4.69041575982343,\n",
       " 3.1622776601683795,\n",
       " 3.1622776601683795,\n",
       " 3.1622776601683795,\n",
       " 7.0710678118654755,\n",
       " 2.449489742783178,\n",
       " 3.3166247903554,\n",
       " 2.6457513110645907,\n",
       " 5.477225575051661,\n",
       " 2.23606797749979,\n",
       " 3.605551275463989,\n",
       " 2.8284271247461903,\n",
       " 4.795831523312719,\n",
       " 2.0,\n",
       " 3.3166247903554,\n",
       " 4.242640687119285,\n",
       " 3.605551275463989,\n",
       " 3.4641016151377544,\n",
       " 6.4031242374328485,\n",
       " 5.0990195135927845,\n",
       " 6.0,\n",
       " 8.246211251235321,\n",
       " 3.0,\n",
       " 4.123105625617661,\n",
       " 6.855654600401044,\n",
       " 2.23606797749979,\n",
       " 3.3166247903554,\n",
       " 4.795831523312719,\n",
       " 3.1622776601683795,\n",
       " 4.0,\n",
       " 3.0,\n",
       " 4.123105625617661,\n",
       " 3.3166247903554,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 4.123105625617661,\n",
       " 3.3166247903554,\n",
       " 3.605551275463989,\n",
       " 4.242640687119285,\n",
       " 3.1622776601683795,\n",
       " 2.6457513110645907,\n",
       " 3.605551275463989,\n",
       " 4.47213595499958,\n",
       " 3.0,\n",
       " 3.605551275463989,\n",
       " 2.6457513110645907,\n",
       " 2.8284271247461903,\n",
       " 2.6457513110645907,\n",
       " 2.6457513110645907,\n",
       " 3.7416573867739413,\n",
       " 3.7416573867739413,\n",
       " 3.3166247903554,\n",
       " 3.1622776601683795,\n",
       " 3.0,\n",
       " 3.1622776601683795,\n",
       " 2.23606797749979,\n",
       " 4.58257569495584,\n",
       " 3.1622776601683795,\n",
       " 3.4641016151377544,\n",
       " 6.164414002968976,\n",
       " 3.605551275463989,\n",
       " 2.6457513110645907,\n",
       " 3.7416573867739413,\n",
       " 3.0,\n",
       " 3.0,\n",
       " 3.4641016151377544,\n",
       " 3.0,\n",
       " 3.3166247903554,\n",
       " 3.1622776601683795,\n",
       " 3.1622776601683795,\n",
       " 3.4641016151377544,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 3.1622776601683795,\n",
       " 3.1622776601683795,\n",
       " 3.7416573867739413,\n",
       " 2.23606797749979,\n",
       " 2.6457513110645907,\n",
       " 3.4641016151377544,\n",
       " 3.605551275463989,\n",
       " 4.47213595499958,\n",
       " 2.6457513110645907,\n",
       " 3.0,\n",
       " 6.4031242374328485,\n",
       " 4.47213595499958,\n",
       " 3.0,\n",
       " 3.7416573867739413,\n",
       " 3.872983346207417,\n",
       " 3.1622776601683795,\n",
       " 4.242640687119285,\n",
       " 3.7416573867739413,\n",
       " 3.605551275463989,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 3.872983346207417,\n",
       " 3.3166247903554,\n",
       " 3.4641016151377544,\n",
       " 4.242640687119285,\n",
       " 3.0,\n",
       " 4.795831523312719,\n",
       " 3.872983346207417,\n",
       " 3.1622776601683795,\n",
       " 3.0,\n",
       " 6.6332495807108,\n",
       " 3.3166247903554,\n",
       " 3.0,\n",
       " 2.449489742783178,\n",
       " 4.242640687119285,\n",
       " 3.3166247903554,\n",
       " 3.0,\n",
       " 2.8284271247461903,\n",
       " 3.4641016151377544,\n",
       " 3.4641016151377544,\n",
       " 2.8284271247461903,\n",
       " 3.3166247903554,\n",
       " 3.1622776601683795,\n",
       " 5.656854249492381,\n",
       " 4.123105625617661,\n",
       " 3.0,\n",
       " 4.0,\n",
       " 3.4641016151377544,\n",
       " 2.449489742783178,\n",
       " 3.1622776601683795,\n",
       " 3.605551275463989,\n",
       " 3.0,\n",
       " 2.23606797749979,\n",
       " 4.0,\n",
       " 4.0,\n",
       " 5.0990195135927845,\n",
       " 3.0,\n",
       " 6.0,\n",
       " 2.6457513110645907,\n",
       " 5.477225575051661,\n",
       " 3.0,\n",
       " 3.605551275463989,\n",
       " 2.449489742783178,\n",
       " 4.47213595499958,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 5.744562646538029,\n",
       " 3.0,\n",
       " 2.0,\n",
       " 2.449489742783178,\n",
       " 4.358898943540674,\n",
       " 2.449489742783178,\n",
       " 3.7416573867739413,\n",
       " 2.449489742783178,\n",
       " 4.898979485566356,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 2.8284271247461903,\n",
       " 2.6457513110645907,\n",
       " 3.605551275463989,\n",
       " 3.1622776601683795,\n",
       " 3.0,\n",
       " 3.7416573867739413,\n",
       " 3.0,\n",
       " 4.242640687119285,\n",
       " 3.3166247903554,\n",
       " 2.6457513110645907,\n",
       " 2.8284271247461903,\n",
       " 3.3166247903554,\n",
       " 2.6457513110645907,\n",
       " 3.7416573867739413,\n",
       " 5.477225575051661,\n",
       " 2.23606797749979,\n",
       " 1.7320508075688772,\n",
       " 4.0,\n",
       " 4.58257569495584,\n",
       " 4.47213595499958,\n",
       " 2.8284271247461903,\n",
       " 6.082762530298219,\n",
       " 3.605551275463989,\n",
       " 5.0,\n",
       " 2.6457513110645907,\n",
       " 3.4641016151377544,\n",
       " 3.872983346207417,\n",
       " 2.449489742783178,\n",
       " 2.6457513110645907,\n",
       " 3.1622776601683795,\n",
       " 2.23606797749979,\n",
       " 3.7416573867739413,\n",
       " 3.0,\n",
       " 3.3166247903554,\n",
       " 3.605551275463989,\n",
       " 4.242640687119285,\n",
       " 3.0,\n",
       " 3.0,\n",
       " 4.242640687119285,\n",
       " 2.0,\n",
       " 5.830951894845301,\n",
       " 2.8284271247461903,\n",
       " 2.0,\n",
       " 3.4641016151377544,\n",
       " 3.605551275463989,\n",
       " 3.872983346207417,\n",
       " 4.123105625617661,\n",
       " 4.47213595499958,\n",
       " 2.23606797749979,\n",
       " 1.7320508075688772,\n",
       " 3.605551275463989,\n",
       " 3.7416573867739413,\n",
       " 2.449489742783178,\n",
       " 3.0,\n",
       " 5.385164807134504,\n",
       " 2.6457513110645907,\n",
       " 2.23606797749979,\n",
       " 4.795831523312719,\n",
       " 3.0,\n",
       " 3.4641016151377544,\n",
       " 3.4641016151377544,\n",
       " 2.8284271247461903,\n",
       " 3.7416573867739413,\n",
       " 3.0,\n",
       " 4.123105625617661,\n",
       " 3.1622776601683795,\n",
       " 5.0990195135927845,\n",
       " 3.605551275463989,\n",
       " 3.605551275463989,\n",
       " 3.3166247903554,\n",
       " 4.58257569495584,\n",
       " 5.0,\n",
       " 4.58257569495584,\n",
       " 3.872983346207417,\n",
       " 3.0,\n",
       " 3.4641016151377544,\n",
       " 3.7416573867739413,\n",
       " 2.449489742783178,\n",
       " 3.7416573867739413,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 2.449489742783178,\n",
       " 4.0,\n",
       " 2.23606797749979,\n",
       " 3.0,\n",
       " 3.3166247903554,\n",
       " 2.0,\n",
       " 2.449489742783178,\n",
       " 3.1622776601683795,\n",
       " 6.6332495807108,\n",
       " 3.4641016151377544,\n",
       " 4.47213595499958,\n",
       " 4.58257569495584,\n",
       " 4.898979485566356,\n",
       " 4.358898943540674,\n",
       " 2.6457513110645907,\n",
       " 4.898979485566356,\n",
       " 4.242640687119285,\n",
       " 6.708203932499369,\n",
       " 3.605551275463989,\n",
       " 3.605551275463989,\n",
       " 4.47213595499958,\n",
       " 4.242640687119285,\n",
       " 2.449489742783178,\n",
       " 4.123105625617661,\n",
       " 3.7416573867739413,\n",
       " 4.242640687119285,\n",
       " 3.0,\n",
       " 3.0,\n",
       " 3.3166247903554,\n",
       " 3.0,\n",
       " 2.0,\n",
       " 3.872983346207417,\n",
       " 3.872983346207417,\n",
       " 2.23606797749979,\n",
       " 2.8284271247461903,\n",
       " 3.3166247903554,\n",
       " 3.605551275463989,\n",
       " 3.0,\n",
       " 3.872983346207417,\n",
       " 4.0,\n",
       " 3.605551275463989,\n",
       " 3.0,\n",
       " 2.0,\n",
       " 4.242640687119285,\n",
       " 3.3166247903554,\n",
       " 2.449489742783178,\n",
       " 3.3166247903554,\n",
       " 2.8284271247461903,\n",
       " 3.0,\n",
       " 2.23606797749979,\n",
       " 2.6457513110645907,\n",
       " 3.7416573867739413,\n",
       " 2.0,\n",
       " 3.0,\n",
       " 2.8284271247461903,\n",
       " 3.1622776601683795,\n",
       " 3.605551275463989,\n",
       " 4.123105625617661,\n",
       " 4.69041575982343,\n",
       " 6.48074069840786,\n",
       " 3.1622776601683795,\n",
       " 3.7416573867739413,\n",
       " 3.1622776601683795,\n",
       " 2.449489742783178,\n",
       " 2.8284271247461903,\n",
       " 3.872983346207417,\n",
       " 3.0,\n",
       " 4.69041575982343,\n",
       " 4.242640687119285,\n",
       " 3.4641016151377544,\n",
       " 2.8284271247461903,\n",
       " 3.1622776601683795,\n",
       " 3.7416573867739413,\n",
       " 4.0,\n",
       " 3.4641016151377544,\n",
       " 3.1622776601683795,\n",
       " 2.0,\n",
       " 2.6457513110645907,\n",
       " 3.872983346207417,\n",
       " 2.23606797749979,\n",
       " 4.242640687119285,\n",
       " 4.47213595499958,\n",
       " 2.449489742783178,\n",
       " 2.0,\n",
       " 3.1622776601683795,\n",
       " 3.872983346207417,\n",
       " 3.872983346207417,\n",
       " 3.3166247903554,\n",
       " 2.0,\n",
       " 3.4641016151377544,\n",
       " 3.1622776601683795,\n",
       " 4.358898943540674,\n",
       " 3.1622776601683795,\n",
       " 4.123105625617661,\n",
       " 4.795831523312719,\n",
       " 3.3166247903554,\n",
       " 2.8284271247461903,\n",
       " 4.0,\n",
       " 3.7416573867739413,\n",
       " 5.0,\n",
       " 4.795831523312719,\n",
       " 1.7320508075688772,\n",
       " 3.605551275463989,\n",
       " 3.0,\n",
       " 3.0,\n",
       " 6.0,\n",
       " 4.58257569495584,\n",
       " 4.58257569495584,\n",
       " 3.3166247903554,\n",
       " 4.123105625617661,\n",
       " 4.47213595499958,\n",
       " 3.7416573867739413,\n",
       " 3.3166247903554,\n",
       " 2.8284271247461903,\n",
       " 2.23606797749979,\n",
       " 3.0,\n",
       " 4.0,\n",
       " 3.3166247903554,\n",
       " 3.3166247903554,\n",
       " 4.0,\n",
       " 2.8284271247461903,\n",
       " 3.0,\n",
       " 3.3166247903554,\n",
       " 4.58257569495584,\n",
       " 3.1622776601683795,\n",
       " 3.7416573867739413,\n",
       " 3.0,\n",
       " 2.0,\n",
       " 3.0,\n",
       " 5.291502622129181,\n",
       " 1.7320508075688772,\n",
       " 2.0,\n",
       " 2.8284271247461903,\n",
       " 2.449489742783178,\n",
       " 2.6457513110645907,\n",
       " 2.449489742783178,\n",
       " 3.0,\n",
       " 4.0,\n",
       " 2.23606797749979,\n",
       " 3.1622776601683795,\n",
       " 4.0,\n",
       " 3.1622776601683795,\n",
       " 4.242640687119285,\n",
       " 3.0,\n",
       " 3.1622776601683795,\n",
       " 5.0990195135927845,\n",
       " 3.0,\n",
       " 3.4641016151377544,\n",
       " 4.0,\n",
       " 3.0,\n",
       " 2.8284271247461903,\n",
       " 2.449489742783178,\n",
       " 3.872983346207417,\n",
       " 3.4641016151377544,\n",
       " 3.605551275463989,\n",
       " 3.3166247903554,\n",
       " 4.58257569495584,\n",
       " 3.1622776601683795,\n",
       " 3.3166247903554,\n",
       " 2.449489742783178,\n",
       " 4.795831523312719,\n",
       " 2.449489742783178,\n",
       " 4.242640687119285,\n",
       " 2.8284271247461903,\n",
       " 3.605551275463989,\n",
       " 5.916079783099616,\n",
       " 3.4641016151377544,\n",
       " 4.795831523312719,\n",
       " 2.23606797749979,\n",
       " 2.6457513110645907,\n",
       " 3.605551275463989,\n",
       " 3.605551275463989,\n",
       " 2.8284271247461903,\n",
       " 4.123105625617661,\n",
       " 4.58257569495584,\n",
       " 3.3166247903554,\n",
       " 4.0,\n",
       " 5.477225575051661,\n",
       " 2.8284271247461903,\n",
       " 3.1622776601683795,\n",
       " 4.795831523312719,\n",
       " 5.291502622129181,\n",
       " 3.7416573867739413,\n",
       " 2.449489742783178,\n",
       " 3.605551275463989,\n",
       " 2.0,\n",
       " 2.23606797749979,\n",
       " 3.872983346207417,\n",
       " 4.358898943540674,\n",
       " 3.1622776601683795,\n",
       " 4.47213595499958,\n",
       " 3.605551275463989,\n",
       " 2.23606797749979,\n",
       " 2.8284271247461903,\n",
       " 3.605551275463989,\n",
       " 2.23606797749979,\n",
       " 4.123105625617661,\n",
       " 2.8284271247461903,\n",
       " 3.605551275463989,\n",
       " 2.449489742783178,\n",
       " 2.8284271247461903,\n",
       " 2.6457513110645907,\n",
       " 3.0,\n",
       " 4.0,\n",
       " 5.0990195135927845]"
      ]
     },
     "execution_count": 183,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "L2_norm_doc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 184,
   "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>elimin</th>\n",
       "      <th>ant</th>\n",
       "      <th>roach</th>\n",
       "      <th>spider</th>\n",
       "      <th>killer</th>\n",
       "      <th>oz</th>\n",
       "      <th>kill</th>\n",
       "      <th>insect</th>\n",
       "      <th>spiderman</th>\n",
       "      <th>parti</th>\n",
       "      <th>...</th>\n",
       "      <th>bring</th>\n",
       "      <th>tradit</th>\n",
       "      <th>flip</th>\n",
       "      <th>indestruct</th>\n",
       "      <th>chew</th>\n",
       "      <th>proof</th>\n",
       "      <th>rip</th>\n",
       "      <th>nontox</th>\n",
       "      <th>washabl</th>\n",
       "      <th>newborn</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 1275 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   elimin  ant  roach  spider  killer   oz  kill  insect  spiderman  parti  \\\n",
       "0     1.0  1.0    1.0     2.0     1.0  1.0   1.0     1.0        0.0    0.0   \n",
       "\n",
       "   ...  bring  tradit  flip  indestruct  chew  proof  rip  nontox  washabl  \\\n",
       "0  ...    0.0     0.0   0.0         0.0   0.0    0.0  0.0     0.0      0.0   \n",
       "\n",
       "   newborn  \n",
       "0      0.0  \n",
       "\n",
       "[1 rows x 1275 columns]"
      ]
     },
     "execution_count": 184,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "query_bow, L2_norm_query  = query_BOW(query_1, initiate_query_bow)\n",
    "query_bow"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 185,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3.3166247903554"
      ]
     },
     "execution_count": 185,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "L2_norm_query"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 186,
   "metadata": {},
   "outputs": [],
   "source": [
    "L2_reciprocal = np.multiply(L2_norm_query,L2_norm_doc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([11.        ,  6.63324958,  8.77496439, 11.        ,  9.38083152,\n",
       "        9.38083152,  9.38083152, 14.07124728, 10.48808848, 11.        ,\n",
       "        6.63324958,  8.1240384 , 11.95826074,  6.63324958, 11.48912529,\n",
       "        9.94987437,  9.94987437, 11.95826074,  9.38083152, 10.48808848,\n",
       "       16.58312395,  8.1240384 ,  7.41619849,  7.41619849,  7.41619849,\n",
       "       11.95826074, 15.19868415, 10.48808848,  8.77496439, 14.45683229,\n",
       "       11.48912529,  9.38083152,  7.41619849, 19.05255888, 17.23368794,\n",
       "       16.58312395,  9.94987437, 10.48808848,  8.77496439,  7.41619849,\n",
       "        7.41619849, 18.76166304,  8.1240384 ,  8.1240384 , 14.83239697,\n",
       "        8.77496439,  7.41619849,  7.41619849,  9.94987437,  8.77496439,\n",
       "       11.48912529, 11.48912529, 12.84523258, 11.48912529, 16.91153453,\n",
       "       10.48808848, 11.        ,  6.63324958, 10.48808848, 13.67479433,\n",
       "       11.        , 10.48808848, 12.40967365,  8.77496439, 11.95826074,\n",
       "        9.38083152, 10.48808848, 15.90597372,  9.94987437,  8.77496439,\n",
       "       11.        ,  8.77496439,  9.38083152, 12.40967365, 13.67479433,\n",
       "        9.94987437, 11.95826074, 14.07124728, 11.        ,  7.41619849,\n",
       "        9.38083152,  6.63324958,  9.38083152,  9.38083152, 10.48808848,\n",
       "       11.        ,  9.38083152,  8.77496439, 11.48912529,  8.77496439,\n",
       "        8.77496439,  8.77496439, 11.48912529, 12.84523258, 11.48912529,\n",
       "       10.48808848, 11.        ,  8.77496439,  9.38083152, 11.48912529,\n",
       "       11.95826074,  8.77496439,  8.77496439, 14.45683229,  9.38083152,\n",
       "       11.48912529, 11.95826074, 14.07124728,  8.1240384 ,  8.77496439,\n",
       "        8.1240384 ,  7.41619849, 11.        , 12.40967365, 14.07124728,\n",
       "        7.41619849, 11.48912529, 10.48808848, 12.40967365,  7.41619849,\n",
       "        9.38083152,  7.41619849,  9.38083152,  7.41619849,  8.1240384 ,\n",
       "        8.1240384 ,  8.1240384 ,  7.41619849, 10.48808848, 12.40967365,\n",
       "        9.94987437,  8.77496439, 11.48912529, 10.48808848, 10.48808848,\n",
       "       12.84523258, 11.48912529,  9.38083152, 16.58312395, 11.48912529,\n",
       "       11.        , 12.40967365,  9.38083152, 12.84523258, 10.48808848,\n",
       "        9.38083152, 23.68543856, 12.84523258, 13.26649916, 12.84523258,\n",
       "       13.26649916, 15.55634919, 11.48912529, 10.48808848,  9.94987437,\n",
       "       11.48912529, 10.48808848,  9.38083152, 12.40967365, 10.48808848,\n",
       "       14.45683229,  8.77496439,  9.38083152, 11.95826074,  9.38083152,\n",
       "       13.67479433, 10.48808848, 13.26649916,  6.63324958, 13.26649916,\n",
       "        7.41619849,  8.77496439, 13.67479433, 18.46618531, 15.19868415,\n",
       "       12.84523258,  7.41619849, 14.07124728, 13.26649916,  9.94987437,\n",
       "       11.        , 10.48808848, 11.        ,  9.94987437, 11.        ,\n",
       "       11.        ,  8.1240384 ,  8.77496439, 12.40967365, 13.67479433,\n",
       "       12.84523258,  9.38083152, 11.        , 11.        , 14.83239697,\n",
       "       15.90597372, 12.40967365, 11.95826074,  9.38083152,  8.1240384 ,\n",
       "       11.        , 11.95826074, 18.46618531,  9.94987437, 13.67479433,\n",
       "        6.63324958, 12.84523258, 10.48808848, 11.        ,  9.94987437,\n",
       "        4.69041576,  6.63324958, 11.        , 16.91153453,  9.94987437,\n",
       "       11.95826074, 14.83239697, 14.83239697, 11.        , 11.        ,\n",
       "       11.        , 11.        ,  9.38083152, 14.45683229, 12.40967365,\n",
       "        6.63324958, 11.95826074, 11.48912529,  9.94987437, 12.40967365,\n",
       "        9.38083152,  9.38083152,  9.94987437, 11.95826074, 13.26649916,\n",
       "        9.38083152, 10.48808848, 13.67479433,  9.94987437, 11.95826074,\n",
       "       14.07124728, 16.24807681, 14.83239697,  8.1240384 ,  7.41619849,\n",
       "        9.94987437, 10.48808848, 11.48912529, 13.67479433,  9.94987437,\n",
       "       11.48912529,  8.77496439,  9.38083152, 11.48912529, 11.48912529,\n",
       "        8.77496439, 16.91153453, 15.19868415, 12.40967365, 12.40967365,\n",
       "       11.48912529, 17.23368794, 11.        ,  9.94987437, 13.67479433,\n",
       "       16.91153453,  9.94987437, 13.26649916,  9.94987437,  5.74456265,\n",
       "       11.48912529,  8.77496439, 12.84523258, 11.95826074,  9.94987437,\n",
       "       11.48912529, 11.95826074, 11.        ,  9.38083152,  9.38083152,\n",
       "       11.48912529,  6.63324958,  9.94987437, 17.8605711 , 16.91153453,\n",
       "        8.1240384 , 11.95826074,  9.94987437, 11.48912529,  8.77496439,\n",
       "       14.07124728, 11.95826074, 11.95826074,  9.94987437, 14.45683229,\n",
       "        8.77496439, 11.        ,  9.94987437, 12.40967365, 10.48808848,\n",
       "       11.95826074,  9.94987437,  7.41619849, 11.        ,  9.38083152,\n",
       "       11.48912529, 12.40967365, 15.90597372, 10.48808848,  9.38083152,\n",
       "        9.94987437, 12.40967365, 14.83239697,  8.77496439, 11.48912529,\n",
       "        9.38083152,  9.94987437,  8.77496439,  6.63324958,  6.63324958,\n",
       "        5.74456265,  5.74456265, 12.40967365, 13.67479433, 22.737634  ,\n",
       "        6.63324958,  7.41619849,  8.1240384 , 18.46618531, 11.48912529,\n",
       "       11.95826074,  8.77496439, 11.        , 11.        , 13.67479433,\n",
       "        8.77496439, 14.83239697, 11.        , 11.95826074, 12.40967365,\n",
       "       16.91153453, 14.07124728, 19.33907961, 10.48808848, 10.48808848,\n",
       "       23.68543856, 10.48808848,  9.38083152,  9.38083152, 12.84523258,\n",
       "       16.24807681,  9.38083152, 11.95826074, 11.        ,  8.1240384 ,\n",
       "        9.94987437, 10.48808848,  9.38083152, 11.        , 19.62141687,\n",
       "        9.94987437, 10.48808848, 12.84523258, 12.84523258,  8.1240384 ,\n",
       "        9.94987437, 11.95826074,  6.63324958, 19.62141687, 13.67479433,\n",
       "       12.84523258, 12.40967365, 11.95826074, 21.23676058, 20.174241  ,\n",
       "        9.94987437, 11.        , 11.        , 10.48808848,  8.77496439,\n",
       "        9.94987437, 12.84523258,  9.94987437,  9.38083152,  9.94987437,\n",
       "        8.1240384 , 27.14774392, 11.        , 12.40967365, 22.24859546,\n",
       "       23.4520788 , 14.45683229, 10.48808848,  9.94987437,  9.38083152,\n",
       "       10.48808848,  8.77496439,  7.41619849, 10.48808848, 15.55634919,\n",
       "       14.83239697, 18.46618531,  8.77496439,  8.77496439,  9.38083152,\n",
       "       10.48808848, 11.        ,  9.38083152,  6.63324958, 10.48808848,\n",
       "       11.95826074,  7.41619849,  8.77496439,  8.77496439, 13.67479433,\n",
       "       19.05255888, 20.97617696, 11.        , 11.48912529, 16.58312395,\n",
       "        9.38083152, 12.84523258, 15.19868415,  8.77496439, 15.55634919,\n",
       "       10.48808848, 10.48808848, 10.48808848, 23.4520788 ,  8.1240384 ,\n",
       "       11.        ,  8.77496439, 18.16590212,  7.41619849, 11.95826074,\n",
       "        9.38083152, 15.90597372,  6.63324958, 11.        , 14.07124728,\n",
       "       11.95826074, 11.48912529, 21.23676058, 16.91153453, 19.89974874,\n",
       "       27.34958866,  9.94987437, 13.67479433, 22.737634  ,  7.41619849,\n",
       "       11.        , 15.90597372, 10.48808848, 13.26649916,  9.94987437,\n",
       "       13.67479433, 11.        , 10.48808848, 11.        , 13.67479433,\n",
       "       11.        , 11.95826074, 14.07124728, 10.48808848,  8.77496439,\n",
       "       11.95826074, 14.83239697,  9.94987437, 11.95826074,  8.77496439,\n",
       "        9.38083152,  8.77496439,  8.77496439, 12.40967365, 12.40967365,\n",
       "       11.        , 10.48808848,  9.94987437, 10.48808848,  7.41619849,\n",
       "       15.19868415, 10.48808848, 11.48912529, 20.4450483 , 11.95826074,\n",
       "        8.77496439, 12.40967365,  9.94987437,  9.94987437, 11.48912529,\n",
       "        9.94987437, 11.        , 10.48808848, 10.48808848, 11.48912529,\n",
       "       11.        , 11.        , 10.48808848, 10.48808848, 12.40967365,\n",
       "        7.41619849,  8.77496439, 11.48912529, 11.95826074, 14.83239697,\n",
       "        8.77496439,  9.94987437, 21.23676058, 14.83239697,  9.94987437,\n",
       "       12.40967365, 12.84523258, 10.48808848, 14.07124728, 12.40967365,\n",
       "       11.95826074, 11.        , 11.        , 12.84523258, 11.        ,\n",
       "       11.48912529, 14.07124728,  9.94987437, 15.90597372, 12.84523258,\n",
       "       10.48808848,  9.94987437, 22.        , 11.        ,  9.94987437,\n",
       "        8.1240384 , 14.07124728, 11.        ,  9.94987437,  9.38083152,\n",
       "       11.48912529, 11.48912529,  9.38083152, 11.        , 10.48808848,\n",
       "       18.76166304, 13.67479433,  9.94987437, 13.26649916, 11.48912529,\n",
       "        8.1240384 , 10.48808848, 11.95826074,  9.94987437,  7.41619849,\n",
       "       13.26649916, 13.26649916, 16.91153453,  9.94987437, 19.89974874,\n",
       "        8.77496439, 18.16590212,  9.94987437, 11.95826074,  8.1240384 ,\n",
       "       14.83239697, 10.48808848, 11.        , 19.05255888,  9.94987437,\n",
       "        6.63324958,  8.1240384 , 14.45683229,  8.1240384 , 12.40967365,\n",
       "        8.1240384 , 16.24807681, 11.        , 11.        ,  9.38083152,\n",
       "        8.77496439, 11.95826074, 10.48808848,  9.94987437, 12.40967365,\n",
       "        9.94987437, 14.07124728, 11.        ,  8.77496439,  9.38083152,\n",
       "       11.        ,  8.77496439, 12.40967365, 18.16590212,  7.41619849,\n",
       "        5.74456265, 13.26649916, 15.19868415, 14.83239697,  9.38083152,\n",
       "       20.174241  , 11.95826074, 16.58312395,  8.77496439, 11.48912529,\n",
       "       12.84523258,  8.1240384 ,  8.77496439, 10.48808848,  7.41619849,\n",
       "       12.40967365,  9.94987437, 11.        , 11.95826074, 14.07124728,\n",
       "        9.94987437,  9.94987437, 14.07124728,  6.63324958, 19.33907961,\n",
       "        9.38083152,  6.63324958, 11.48912529, 11.95826074, 12.84523258,\n",
       "       13.67479433, 14.83239697,  7.41619849,  5.74456265, 11.95826074,\n",
       "       12.40967365,  8.1240384 ,  9.94987437, 17.8605711 ,  8.77496439,\n",
       "        7.41619849, 15.90597372,  9.94987437, 11.48912529, 11.48912529,\n",
       "        9.38083152, 12.40967365,  9.94987437, 13.67479433, 10.48808848,\n",
       "       16.91153453, 11.95826074, 11.95826074, 11.        , 15.19868415,\n",
       "       16.58312395, 15.19868415, 12.84523258,  9.94987437, 11.48912529,\n",
       "       12.40967365,  8.1240384 , 12.40967365, 11.        , 11.        ,\n",
       "       10.48808848, 11.        ,  8.1240384 , 13.26649916,  7.41619849,\n",
       "        9.94987437, 11.        ,  6.63324958,  8.1240384 , 10.48808848,\n",
       "       22.        , 11.48912529, 14.83239697, 15.19868415, 16.24807681,\n",
       "       14.45683229,  8.77496439, 16.24807681, 14.07124728, 22.24859546,\n",
       "       11.95826074, 11.95826074, 14.83239697, 14.07124728,  8.1240384 ,\n",
       "       13.67479433, 12.40967365, 14.07124728,  9.94987437,  9.94987437,\n",
       "       11.        ,  9.94987437,  6.63324958, 12.84523258, 12.84523258,\n",
       "        7.41619849,  9.38083152, 11.        , 11.95826074,  9.94987437,\n",
       "       12.84523258, 13.26649916, 11.95826074,  9.94987437,  6.63324958,\n",
       "       14.07124728, 11.        ,  8.1240384 , 11.        ,  9.38083152,\n",
       "        9.94987437,  7.41619849,  8.77496439, 12.40967365,  6.63324958,\n",
       "        9.94987437,  9.38083152, 10.48808848, 11.95826074, 13.67479433,\n",
       "       15.55634919, 21.49418526, 10.48808848, 12.40967365, 10.48808848,\n",
       "        8.1240384 ,  9.38083152, 12.84523258,  9.94987437, 15.55634919,\n",
       "       14.07124728, 11.48912529,  9.38083152, 10.48808848, 12.40967365,\n",
       "       13.26649916, 11.48912529, 10.48808848,  6.63324958,  8.77496439,\n",
       "       12.84523258,  7.41619849, 14.07124728, 14.83239697,  8.1240384 ,\n",
       "        6.63324958, 10.48808848, 12.84523258, 12.84523258, 11.        ,\n",
       "        6.63324958, 11.48912529, 10.48808848, 14.45683229, 10.48808848,\n",
       "       13.67479433, 15.90597372, 11.        ,  9.38083152, 13.26649916,\n",
       "       12.40967365, 16.58312395, 15.90597372,  5.74456265, 11.95826074,\n",
       "        9.94987437,  9.94987437, 19.89974874, 15.19868415, 15.19868415,\n",
       "       11.        , 13.67479433, 14.83239697, 12.40967365, 11.        ,\n",
       "        9.38083152,  7.41619849,  9.94987437, 13.26649916, 11.        ,\n",
       "       11.        , 13.26649916,  9.38083152,  9.94987437, 11.        ,\n",
       "       15.19868415, 10.48808848, 12.40967365,  9.94987437,  6.63324958,\n",
       "        9.94987437, 17.54992877,  5.74456265,  6.63324958,  9.38083152,\n",
       "        8.1240384 ,  8.77496439,  8.1240384 ,  9.94987437, 13.26649916,\n",
       "        7.41619849, 10.48808848, 13.26649916, 10.48808848, 14.07124728,\n",
       "        9.94987437, 10.48808848, 16.91153453,  9.94987437, 11.48912529,\n",
       "       13.26649916,  9.94987437,  9.38083152,  8.1240384 , 12.84523258,\n",
       "       11.48912529, 11.95826074, 11.        , 15.19868415, 10.48808848,\n",
       "       11.        ,  8.1240384 , 15.90597372,  8.1240384 , 14.07124728,\n",
       "        9.38083152, 11.95826074, 19.62141687, 11.48912529, 15.90597372,\n",
       "        7.41619849,  8.77496439, 11.95826074, 11.95826074,  9.38083152,\n",
       "       13.67479433, 15.19868415, 11.        , 13.26649916, 18.16590212,\n",
       "        9.38083152, 10.48808848, 15.90597372, 17.54992877, 12.40967365,\n",
       "        8.1240384 , 11.95826074,  6.63324958,  7.41619849, 12.84523258,\n",
       "       14.45683229, 10.48808848, 14.83239697, 11.95826074,  7.41619849,\n",
       "        9.38083152, 11.95826074,  7.41619849, 13.67479433,  9.38083152,\n",
       "       11.95826074,  8.1240384 ,  9.38083152,  8.77496439,  9.94987437,\n",
       "       13.26649916, 16.91153453])"
      ]
     },
     "execution_count": 187,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "L2_reciprocal"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 188,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.09090909, 0.15075567, 0.11396058, 0.09090909, 0.10660036,\n",
       "       0.10660036, 0.10660036, 0.07106691, 0.09534626, 0.09090909,\n",
       "       0.15075567, 0.12309149, 0.0836242 , 0.15075567, 0.08703883,\n",
       "       0.10050378, 0.10050378, 0.0836242 , 0.10660036, 0.09534626,\n",
       "       0.06030227, 0.12309149, 0.13483997, 0.13483997, 0.13483997,\n",
       "       0.0836242 , 0.06579517, 0.09534626, 0.11396058, 0.06917145,\n",
       "       0.08703883, 0.10660036, 0.13483997, 0.05248639, 0.05802589,\n",
       "       0.06030227, 0.10050378, 0.09534626, 0.11396058, 0.13483997,\n",
       "       0.13483997, 0.05330018, 0.12309149, 0.12309149, 0.06741999,\n",
       "       0.11396058, 0.13483997, 0.13483997, 0.10050378, 0.11396058,\n",
       "       0.08703883, 0.08703883, 0.07784989, 0.08703883, 0.05913124,\n",
       "       0.09534626, 0.09090909, 0.15075567, 0.09534626, 0.07312724,\n",
       "       0.09090909, 0.09534626, 0.0805823 , 0.11396058, 0.0836242 ,\n",
       "       0.10660036, 0.09534626, 0.06286946, 0.10050378, 0.11396058,\n",
       "       0.09090909, 0.11396058, 0.10660036, 0.0805823 , 0.07312724,\n",
       "       0.10050378, 0.0836242 , 0.07106691, 0.09090909, 0.13483997,\n",
       "       0.10660036, 0.15075567, 0.10660036, 0.10660036, 0.09534626,\n",
       "       0.09090909, 0.10660036, 0.11396058, 0.08703883, 0.11396058,\n",
       "       0.11396058, 0.11396058, 0.08703883, 0.07784989, 0.08703883,\n",
       "       0.09534626, 0.09090909, 0.11396058, 0.10660036, 0.08703883,\n",
       "       0.0836242 , 0.11396058, 0.11396058, 0.06917145, 0.10660036,\n",
       "       0.08703883, 0.0836242 , 0.07106691, 0.12309149, 0.11396058,\n",
       "       0.12309149, 0.13483997, 0.09090909, 0.0805823 , 0.07106691,\n",
       "       0.13483997, 0.08703883, 0.09534626, 0.0805823 , 0.13483997,\n",
       "       0.10660036, 0.13483997, 0.10660036, 0.13483997, 0.12309149,\n",
       "       0.12309149, 0.12309149, 0.13483997, 0.09534626, 0.0805823 ,\n",
       "       0.10050378, 0.11396058, 0.08703883, 0.09534626, 0.09534626,\n",
       "       0.07784989, 0.08703883, 0.10660036, 0.06030227, 0.08703883,\n",
       "       0.09090909, 0.0805823 , 0.10660036, 0.07784989, 0.09534626,\n",
       "       0.10660036, 0.04222003, 0.07784989, 0.07537784, 0.07784989,\n",
       "       0.07537784, 0.06428243, 0.08703883, 0.09534626, 0.10050378,\n",
       "       0.08703883, 0.09534626, 0.10660036, 0.0805823 , 0.09534626,\n",
       "       0.06917145, 0.11396058, 0.10660036, 0.0836242 , 0.10660036,\n",
       "       0.07312724, 0.09534626, 0.07537784, 0.15075567, 0.07537784,\n",
       "       0.13483997, 0.11396058, 0.07312724, 0.05415304, 0.06579517,\n",
       "       0.07784989, 0.13483997, 0.07106691, 0.07537784, 0.10050378,\n",
       "       0.09090909, 0.09534626, 0.09090909, 0.10050378, 0.09090909,\n",
       "       0.09090909, 0.12309149, 0.11396058, 0.0805823 , 0.07312724,\n",
       "       0.07784989, 0.10660036, 0.09090909, 0.09090909, 0.06741999,\n",
       "       0.06286946, 0.0805823 , 0.0836242 , 0.10660036, 0.12309149,\n",
       "       0.09090909, 0.0836242 , 0.05415304, 0.10050378, 0.07312724,\n",
       "       0.15075567, 0.07784989, 0.09534626, 0.09090909, 0.10050378,\n",
       "       0.21320072, 0.15075567, 0.09090909, 0.05913124, 0.10050378,\n",
       "       0.0836242 , 0.06741999, 0.06741999, 0.09090909, 0.09090909,\n",
       "       0.09090909, 0.09090909, 0.10660036, 0.06917145, 0.0805823 ,\n",
       "       0.15075567, 0.0836242 , 0.08703883, 0.10050378, 0.0805823 ,\n",
       "       0.10660036, 0.10660036, 0.10050378, 0.0836242 , 0.07537784,\n",
       "       0.10660036, 0.09534626, 0.07312724, 0.10050378, 0.0836242 ,\n",
       "       0.07106691, 0.06154575, 0.06741999, 0.12309149, 0.13483997,\n",
       "       0.10050378, 0.09534626, 0.08703883, 0.07312724, 0.10050378,\n",
       "       0.08703883, 0.11396058, 0.10660036, 0.08703883, 0.08703883,\n",
       "       0.11396058, 0.05913124, 0.06579517, 0.0805823 , 0.0805823 ,\n",
       "       0.08703883, 0.05802589, 0.09090909, 0.10050378, 0.07312724,\n",
       "       0.05913124, 0.10050378, 0.07537784, 0.10050378, 0.17407766,\n",
       "       0.08703883, 0.11396058, 0.07784989, 0.0836242 , 0.10050378,\n",
       "       0.08703883, 0.0836242 , 0.09090909, 0.10660036, 0.10660036,\n",
       "       0.08703883, 0.15075567, 0.10050378, 0.05598925, 0.05913124,\n",
       "       0.12309149, 0.0836242 , 0.10050378, 0.08703883, 0.11396058,\n",
       "       0.07106691, 0.0836242 , 0.0836242 , 0.10050378, 0.06917145,\n",
       "       0.11396058, 0.09090909, 0.10050378, 0.0805823 , 0.09534626,\n",
       "       0.0836242 , 0.10050378, 0.13483997, 0.09090909, 0.10660036,\n",
       "       0.08703883, 0.0805823 , 0.06286946, 0.09534626, 0.10660036,\n",
       "       0.10050378, 0.0805823 , 0.06741999, 0.11396058, 0.08703883,\n",
       "       0.10660036, 0.10050378, 0.11396058, 0.15075567, 0.15075567,\n",
       "       0.17407766, 0.17407766, 0.0805823 , 0.07312724, 0.04397995,\n",
       "       0.15075567, 0.13483997, 0.12309149, 0.05415304, 0.08703883,\n",
       "       0.0836242 , 0.11396058, 0.09090909, 0.09090909, 0.07312724,\n",
       "       0.11396058, 0.06741999, 0.09090909, 0.0836242 , 0.0805823 ,\n",
       "       0.05913124, 0.07106691, 0.05170877, 0.09534626, 0.09534626,\n",
       "       0.04222003, 0.09534626, 0.10660036, 0.10660036, 0.07784989,\n",
       "       0.06154575, 0.10660036, 0.0836242 , 0.09090909, 0.12309149,\n",
       "       0.10050378, 0.09534626, 0.10660036, 0.09090909, 0.05096472,\n",
       "       0.10050378, 0.09534626, 0.07784989, 0.07784989, 0.12309149,\n",
       "       0.10050378, 0.0836242 , 0.15075567, 0.05096472, 0.07312724,\n",
       "       0.07784989, 0.0805823 , 0.0836242 , 0.04708816, 0.04956816,\n",
       "       0.10050378, 0.09090909, 0.09090909, 0.09534626, 0.11396058,\n",
       "       0.10050378, 0.07784989, 0.10050378, 0.10660036, 0.10050378,\n",
       "       0.12309149, 0.03683547, 0.09090909, 0.0805823 , 0.04494666,\n",
       "       0.04264014, 0.06917145, 0.09534626, 0.10050378, 0.10660036,\n",
       "       0.09534626, 0.11396058, 0.13483997, 0.09534626, 0.06428243,\n",
       "       0.06741999, 0.05415304, 0.11396058, 0.11396058, 0.10660036,\n",
       "       0.09534626, 0.09090909, 0.10660036, 0.15075567, 0.09534626,\n",
       "       0.0836242 , 0.13483997, 0.11396058, 0.11396058, 0.07312724,\n",
       "       0.05248639, 0.04767313, 0.09090909, 0.08703883, 0.06030227,\n",
       "       0.10660036, 0.07784989, 0.06579517, 0.11396058, 0.06428243,\n",
       "       0.09534626, 0.09534626, 0.09534626, 0.04264014, 0.12309149,\n",
       "       0.09090909, 0.11396058, 0.05504819, 0.13483997, 0.0836242 ,\n",
       "       0.10660036, 0.06286946, 0.15075567, 0.09090909, 0.07106691,\n",
       "       0.0836242 , 0.08703883, 0.04708816, 0.05913124, 0.05025189,\n",
       "       0.03656362, 0.10050378, 0.07312724, 0.04397995, 0.13483997,\n",
       "       0.09090909, 0.06286946, 0.09534626, 0.07537784, 0.10050378,\n",
       "       0.07312724, 0.09090909, 0.09534626, 0.09090909, 0.07312724,\n",
       "       0.09090909, 0.0836242 , 0.07106691, 0.09534626, 0.11396058,\n",
       "       0.0836242 , 0.06741999, 0.10050378, 0.0836242 , 0.11396058,\n",
       "       0.10660036, 0.11396058, 0.11396058, 0.0805823 , 0.0805823 ,\n",
       "       0.09090909, 0.09534626, 0.10050378, 0.09534626, 0.13483997,\n",
       "       0.06579517, 0.09534626, 0.08703883, 0.0489116 , 0.0836242 ,\n",
       "       0.11396058, 0.0805823 , 0.10050378, 0.10050378, 0.08703883,\n",
       "       0.10050378, 0.09090909, 0.09534626, 0.09534626, 0.08703883,\n",
       "       0.09090909, 0.09090909, 0.09534626, 0.09534626, 0.0805823 ,\n",
       "       0.13483997, 0.11396058, 0.08703883, 0.0836242 , 0.06741999,\n",
       "       0.11396058, 0.10050378, 0.04708816, 0.06741999, 0.10050378,\n",
       "       0.0805823 , 0.07784989, 0.09534626, 0.07106691, 0.0805823 ,\n",
       "       0.0836242 , 0.09090909, 0.09090909, 0.07784989, 0.09090909,\n",
       "       0.08703883, 0.07106691, 0.10050378, 0.06286946, 0.07784989,\n",
       "       0.09534626, 0.10050378, 0.04545455, 0.09090909, 0.10050378,\n",
       "       0.12309149, 0.07106691, 0.09090909, 0.10050378, 0.10660036,\n",
       "       0.08703883, 0.08703883, 0.10660036, 0.09090909, 0.09534626,\n",
       "       0.05330018, 0.07312724, 0.10050378, 0.07537784, 0.08703883,\n",
       "       0.12309149, 0.09534626, 0.0836242 , 0.10050378, 0.13483997,\n",
       "       0.07537784, 0.07537784, 0.05913124, 0.10050378, 0.05025189,\n",
       "       0.11396058, 0.05504819, 0.10050378, 0.0836242 , 0.12309149,\n",
       "       0.06741999, 0.09534626, 0.09090909, 0.05248639, 0.10050378,\n",
       "       0.15075567, 0.12309149, 0.06917145, 0.12309149, 0.0805823 ,\n",
       "       0.12309149, 0.06154575, 0.09090909, 0.09090909, 0.10660036,\n",
       "       0.11396058, 0.0836242 , 0.09534626, 0.10050378, 0.0805823 ,\n",
       "       0.10050378, 0.07106691, 0.09090909, 0.11396058, 0.10660036,\n",
       "       0.09090909, 0.11396058, 0.0805823 , 0.05504819, 0.13483997,\n",
       "       0.17407766, 0.07537784, 0.06579517, 0.06741999, 0.10660036,\n",
       "       0.04956816, 0.0836242 , 0.06030227, 0.11396058, 0.08703883,\n",
       "       0.07784989, 0.12309149, 0.11396058, 0.09534626, 0.13483997,\n",
       "       0.0805823 , 0.10050378, 0.09090909, 0.0836242 , 0.07106691,\n",
       "       0.10050378, 0.10050378, 0.07106691, 0.15075567, 0.05170877,\n",
       "       0.10660036, 0.15075567, 0.08703883, 0.0836242 , 0.07784989,\n",
       "       0.07312724, 0.06741999, 0.13483997, 0.17407766, 0.0836242 ,\n",
       "       0.0805823 , 0.12309149, 0.10050378, 0.05598925, 0.11396058,\n",
       "       0.13483997, 0.06286946, 0.10050378, 0.08703883, 0.08703883,\n",
       "       0.10660036, 0.0805823 , 0.10050378, 0.07312724, 0.09534626,\n",
       "       0.05913124, 0.0836242 , 0.0836242 , 0.09090909, 0.06579517,\n",
       "       0.06030227, 0.06579517, 0.07784989, 0.10050378, 0.08703883,\n",
       "       0.0805823 , 0.12309149, 0.0805823 , 0.09090909, 0.09090909,\n",
       "       0.09534626, 0.09090909, 0.12309149, 0.07537784, 0.13483997,\n",
       "       0.10050378, 0.09090909, 0.15075567, 0.12309149, 0.09534626,\n",
       "       0.04545455, 0.08703883, 0.06741999, 0.06579517, 0.06154575,\n",
       "       0.06917145, 0.11396058, 0.06154575, 0.07106691, 0.04494666,\n",
       "       0.0836242 , 0.0836242 , 0.06741999, 0.07106691, 0.12309149,\n",
       "       0.07312724, 0.0805823 , 0.07106691, 0.10050378, 0.10050378,\n",
       "       0.09090909, 0.10050378, 0.15075567, 0.07784989, 0.07784989,\n",
       "       0.13483997, 0.10660036, 0.09090909, 0.0836242 , 0.10050378,\n",
       "       0.07784989, 0.07537784, 0.0836242 , 0.10050378, 0.15075567,\n",
       "       0.07106691, 0.09090909, 0.12309149, 0.09090909, 0.10660036,\n",
       "       0.10050378, 0.13483997, 0.11396058, 0.0805823 , 0.15075567,\n",
       "       0.10050378, 0.10660036, 0.09534626, 0.0836242 , 0.07312724,\n",
       "       0.06428243, 0.04652421, 0.09534626, 0.0805823 , 0.09534626,\n",
       "       0.12309149, 0.10660036, 0.07784989, 0.10050378, 0.06428243,\n",
       "       0.07106691, 0.08703883, 0.10660036, 0.09534626, 0.0805823 ,\n",
       "       0.07537784, 0.08703883, 0.09534626, 0.15075567, 0.11396058,\n",
       "       0.07784989, 0.13483997, 0.07106691, 0.06741999, 0.12309149,\n",
       "       0.15075567, 0.09534626, 0.07784989, 0.07784989, 0.09090909,\n",
       "       0.15075567, 0.08703883, 0.09534626, 0.06917145, 0.09534626,\n",
       "       0.07312724, 0.06286946, 0.09090909, 0.10660036, 0.07537784,\n",
       "       0.0805823 , 0.06030227, 0.06286946, 0.17407766, 0.0836242 ,\n",
       "       0.10050378, 0.10050378, 0.05025189, 0.06579517, 0.06579517,\n",
       "       0.09090909, 0.07312724, 0.06741999, 0.0805823 , 0.09090909,\n",
       "       0.10660036, 0.13483997, 0.10050378, 0.07537784, 0.09090909,\n",
       "       0.09090909, 0.07537784, 0.10660036, 0.10050378, 0.09090909,\n",
       "       0.06579517, 0.09534626, 0.0805823 , 0.10050378, 0.15075567,\n",
       "       0.10050378, 0.05698029, 0.17407766, 0.15075567, 0.10660036,\n",
       "       0.12309149, 0.11396058, 0.12309149, 0.10050378, 0.07537784,\n",
       "       0.13483997, 0.09534626, 0.07537784, 0.09534626, 0.07106691,\n",
       "       0.10050378, 0.09534626, 0.05913124, 0.10050378, 0.08703883,\n",
       "       0.07537784, 0.10050378, 0.10660036, 0.12309149, 0.07784989,\n",
       "       0.08703883, 0.0836242 , 0.09090909, 0.06579517, 0.09534626,\n",
       "       0.09090909, 0.12309149, 0.06286946, 0.12309149, 0.07106691,\n",
       "       0.10660036, 0.0836242 , 0.05096472, 0.08703883, 0.06286946,\n",
       "       0.13483997, 0.11396058, 0.0836242 , 0.0836242 , 0.10660036,\n",
       "       0.07312724, 0.06579517, 0.09090909, 0.07537784, 0.05504819,\n",
       "       0.10660036, 0.09534626, 0.06286946, 0.05698029, 0.0805823 ,\n",
       "       0.12309149, 0.0836242 , 0.15075567, 0.13483997, 0.07784989,\n",
       "       0.06917145, 0.09534626, 0.06741999, 0.0836242 , 0.13483997,\n",
       "       0.10660036, 0.0836242 , 0.13483997, 0.07312724, 0.10660036,\n",
       "       0.0836242 , 0.12309149, 0.10660036, 0.11396058, 0.10050378,\n",
       "       0.07537784, 0.05913124])"
      ]
     },
     "execution_count": 188,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "L2_product = 1/L2_reciprocal\n",
    "L2_product"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 189,
   "metadata": {},
   "outputs": [],
   "source": [
    "query_matrix = query_bow.to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 190,
   "metadata": {},
   "outputs": [],
   "source": [
    "doc_matrix = bow.to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 191,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([11.,  0.,  4.,  6.,  6.,  6.,  6.,  6.,  3.,  2.,  2.,  2.,  4.,\n",
       "        2.,  7.,  2.,  4.,  0.,  2.,  4.,  6.,  2.,  3.,  0.,  2.,  4.,\n",
       "        8.,  4.,  2.,  2.,  5.,  2.,  2.,  3.,  6.,  5.,  2.,  2.,  0.,\n",
       "        0.,  2.,  2.,  0.,  4.,  4.,  4.,  2.,  2.,  2.,  2.,  2.,  0.,\n",
       "        2.,  0.,  2.,  2.,  2.,  0.,  0.,  4.,  2.,  2.,  2.,  2.,  0.,\n",
       "        2.,  2.,  6.,  2.,  2.,  2.,  2.,  2.,  2.,  4.,  2.,  4.,  2.,\n",
       "        0.,  0.,  0.,  0.,  3.,  0.,  0.,  2.,  0.,  2.,  0.,  0.,  2.,\n",
       "        0.,  2.,  2.,  2.,  4.,  0.,  2.,  2.,  2.,  2.,  6.,  2.,  4.,\n",
       "        0.,  5.,  2.,  4.,  2.,  2.,  2.,  0.,  0.,  2.,  4.,  0.,  2.,\n",
       "        2.,  6.,  0.,  0.,  0.,  0.,  0.,  3.,  2.,  2.,  2.,  2.,  6.,\n",
       "        2.,  3.,  2.,  0.,  2.,  2.,  2.,  4.,  6.,  5.,  2.,  6.,  0.,\n",
       "        4.,  4.,  2.,  8.,  2.,  2.,  2.,  2.,  7.,  2.,  0.,  2.,  4.,\n",
       "        2.,  2.,  2.,  2.,  4.,  2.,  3.,  6.,  0.,  3.,  2.,  4.,  0.,\n",
       "        2.,  3.,  1.,  4.,  0.,  7.,  2.,  3.,  4.,  4.,  4.,  2.,  2.,\n",
       "        2.,  2.,  2.,  2.,  4.,  2.,  4.,  4.,  4.,  1.,  2.,  0.,  4.,\n",
       "        4.,  2.,  2.,  2.,  2.,  2.,  4.,  6.,  2.,  4.,  2.,  4.,  0.,\n",
       "        4.,  2.,  0.,  0.,  2.,  2.,  2.,  0.,  6.,  3.,  2.,  2.,  4.,\n",
       "        2.,  2.,  4.,  4.,  1.,  2.,  4.,  2.,  4.,  2.,  2.,  2.,  4.,\n",
       "        2.,  2.,  2.,  4.,  0.,  2.,  4.,  4.,  4.,  2.,  2.,  2.,  2.,\n",
       "        2.,  4.,  2.,  2.,  0.,  2.,  2.,  0.,  2.,  2.,  7.,  0.,  4.,\n",
       "        4.,  2.,  2.,  2.,  2.,  7.,  0.,  4.,  2.,  0.,  2.,  0.,  4.,\n",
       "        2.,  2.,  2.,  4.,  2.,  2.,  2.,  2.,  2.,  2.,  5.,  2.,  2.,\n",
       "        2.,  1.,  2.,  0.,  4.,  2.,  2.,  2.,  4.,  2.,  2.,  2.,  2.,\n",
       "        2.,  2.,  3.,  2.,  2.,  0.,  4.,  8.,  7.,  4.,  0.,  0.,  2.,\n",
       "        2.,  2.,  2.,  1.,  0.,  2.,  2.,  2.,  2.,  2.,  2.,  4.,  8.,\n",
       "        2.,  3.,  0.,  6.,  4.,  0.,  2.,  6.,  4.,  0.,  2.,  3.,  2.,\n",
       "        0.,  8.,  6.,  4.,  5.,  0.,  4.,  5.,  0.,  4.,  0.,  0.,  0.,\n",
       "        2.,  2.,  2.,  2.,  4.,  2.,  2.,  2.,  6.,  2.,  4.,  4.,  2.,\n",
       "        0.,  2.,  2.,  2.,  3.,  0.,  4.,  0.,  2.,  4.,  4.,  2.,  2.,\n",
       "        2.,  2.,  0.,  2.,  4.,  2.,  0.,  2.,  0.,  0.,  2.,  4.,  8.,\n",
       "        8.,  0.,  0.,  2.,  2.,  2.,  4.,  2.,  2.,  2.,  4.,  6.,  2.,\n",
       "        0.,  2.,  2.,  0.,  2.,  2.,  2.,  4.,  2.,  2.,  3.,  4.,  4.,\n",
       "        8.,  2.,  4.,  4.,  2.,  2.,  2.,  2.,  2.,  4.,  2.,  0.,  8.,\n",
       "        2.,  4.,  2.,  2.,  2.,  2.,  2.,  4.,  2.,  4.,  4.,  4.,  2.,\n",
       "        8.,  2.,  3.,  8.,  2.,  0.,  8.,  5.,  3.,  2.,  2.,  2.,  2.,\n",
       "        4.,  2.,  2.,  2.,  4.,  2.,  2.,  2.,  2.,  2.,  2.,  4.,  2.,\n",
       "        4.,  2.,  2.,  0.,  3.,  0.,  5.,  2.,  2.,  2.,  2.,  2.,  4.,\n",
       "        2.,  0.,  5.,  0.,  2.,  0.,  2.,  2.,  4.,  0.,  0.,  4.,  2.,\n",
       "        0.,  2.,  2.,  2.,  2.,  4.,  2.,  0.,  4.,  4.,  4.,  2.,  2.,\n",
       "        8.,  4.,  2.,  2.,  2.,  0.,  2.,  2.,  2.,  2.,  0.,  4.,  2.,\n",
       "        4.,  2.,  4.,  2.,  2.,  2.,  2.,  3.,  2.,  0.,  0.,  4.,  2.,\n",
       "        2.,  2.,  4.,  4.,  2.,  2.,  2.,  2.,  6.,  2.,  2.,  4.,  2.,\n",
       "        3.,  4.,  2.,  3.,  4.,  4.,  4.,  3.,  2.,  2.,  2.,  4.,  2.,\n",
       "        0.,  2.,  2.,  0.,  4.,  2.,  2.,  2.,  2.,  0.,  4.,  2.,  4.,\n",
       "        2.,  2.,  2.,  2.,  2.,  2.,  2.,  4.,  0.,  2.,  0.,  2.,  3.,\n",
       "        2.,  2.,  4.,  6.,  2.,  2.,  4.,  2.,  6.,  0.,  6.,  4.,  4.,\n",
       "        2.,  0.,  0.,  2.,  2.,  6.,  2.,  2.,  2.,  2.,  2.,  2.,  2.,\n",
       "        2.,  6.,  0.,  5.,  2.,  2.,  2.,  2.,  4.,  2.,  2.,  2.,  0.,\n",
       "        2.,  2.,  2.,  2.,  2.,  0.,  2.,  4.,  2.,  0.,  2.,  4.,  4.,\n",
       "        2.,  6.,  4.,  4.,  2.,  2.,  2.,  2.,  2.,  6.,  0.,  2.,  0.,\n",
       "        2.,  2.,  2.,  2.,  2.,  2.,  2.,  2.,  2.,  0.,  2.,  2.,  2.,\n",
       "        2.,  2.,  3.,  2.,  4.,  5.,  2.,  2.,  2.,  2.,  0.,  3.,  2.,\n",
       "        2.,  6.,  4.,  2.,  0.,  4.,  2.,  2.,  0.,  0.,  2.,  0.,  0.,\n",
       "        4.,  2.,  2.,  2.,  2.,  0.,  0.,  4.,  4.,  2.,  0.,  0.,  4.,\n",
       "        2.,  3.,  2.,  2.,  2.,  2.,  4.,  2.,  2.,  0.,  2.,  2.,  4.,\n",
       "        4.,  8.,  2.,  4.,  4.,  2.,  4.,  4.,  3.,  2.,  4.,  2.,  2.,\n",
       "        2.,  8.,  6.,  2.,  2.,  0.,  2.,  4.,  0.,  4.,  6.,  2.,  2.,\n",
       "        2.,  4.,  0.,  2.,  2.,  2.,  0.,  2.,  2.,  4.,  4.,  2.,  2.,\n",
       "        2.,  2.,  2.,  4.,  2.,  0.,  2.,  4.,  5.,  0.,  4.,  0.,  2.,\n",
       "        2.,  2.,  2.,  0.,  2.,  2.,  2.,  2.,  2.,  4.,  2.,  2.,  2.,\n",
       "        0.,  2.,  2.,  2.,  2.,  2.,  2.,  2.,  2.,  2.,  2.,  2.,  2.,\n",
       "        2.,  6.,  0.,  4.,  6.,  2.,  2.,  2.,  0.,  2.,  2.,  2.,  2.,\n",
       "        2.,  0.,  2.,  4.,  4.,  4.,  0.,  4.,  2.,  2.,  2.,  4.,  2.,\n",
       "        2.,  4.,  4.,  8.,  4.,  4.,  1.,  2.,  2.,  2.,  5.,  2.,  4.,\n",
       "        0.,  2.,  4.,  2.,  0.,  5.,  2.,  2.,  2.,  2.,  0.,  0.,  0.,\n",
       "        8.,  0.,  2.,  2.,  2.,  0.,  3.,  1.,  4.,  2.,  2.,  2.,  2.,\n",
       "        0.,  2.,  4.,  2.])"
      ]
     },
     "execution_count": 191,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dot_pdt = np.dot(doc_matrix, query_matrix.T)\n",
    "dot_pdt = dot_pdt.flatten()\n",
    "dot_pdt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 192,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{0: 1.0,\n",
       " 101: 0.6837634587578276,\n",
       " 449: 0.6741998624632421,\n",
       " 306: 0.6446583712203042,\n",
       " 339: 0.6446583712203042,\n",
       " 729: 0.6446583712203042,\n",
       " 4: 0.6396021490668312,\n",
       " 5: 0.6396021490668312,\n",
       " 6: 0.6396021490668312,\n",
       " 14: 0.6092717958449425,\n",
       " 603: 0.5720775535473555,\n",
       " 845: 0.5533715710928597,\n",
       " 3: 0.5454545454545454,\n",
       " 332: 0.5454545454545454,\n",
       " 829: 0.533001790889026,\n",
       " 26: 0.5263613559678152,\n",
       " 163: 0.5017452060042544,\n",
       " 43: 0.492365963917331,\n",
       " 186: 0.492365963917331,\n",
       " 118: 0.48349377841522817,\n",
       " 129: 0.48349377841522817,\n",
       " 141: 0.48349377841522817,\n",
       " 174: 0.4605661864718383,\n",
       " 257: 0.4605661864718383,\n",
       " 2: 0.4558423058385518,\n",
       " 45: 0.4558423058385518,\n",
       " 396: 0.4558423058385518,\n",
       " 730: 0.45226701686664544,\n",
       " 794: 0.45226701686664544,\n",
       " 797: 0.45226701686664544,\n",
       " 151: 0.44997704257325744,\n",
       " 307: 0.4400862294233521,\n",
       " 541: 0.4387634544762784,\n",
       " 638: 0.4387634544762784,\n",
       " 30: 0.4351941398892446,\n",
       " 105: 0.4351941398892446,\n",
       " 139: 0.4351941398892446,\n",
       " 7: 0.4264014327112209,\n",
       " 612: 0.4264014327112209,\n",
       " 137: 0.42640143271122083,\n",
       " 347: 0.42640143271122083,\n",
       " 635: 0.42640143271122083,\n",
       " 721: 0.42640143271122083,\n",
       " 820: 0.42640143271122083,\n",
       " 265: 0.4139186771923578,\n",
       " 822: 0.40771775315010045,\n",
       " 22: 0.40451991747794525,\n",
       " 170: 0.40451991747794525,\n",
       " 176: 0.40451991747794525,\n",
       " 216: 0.40451991747794525,\n",
       " 326: 0.40451991747794525,\n",
       " 549: 0.40451991747794525,\n",
       " 593: 0.40451991747794525,\n",
       " 677: 0.40451991747794525,\n",
       " 738: 0.40451991747794525,\n",
       " 474: 0.4029114820126901,\n",
       " 16: 0.40201512610368484,\n",
       " 179: 0.40201512610368484,\n",
       " 355: 0.40201512610368484,\n",
       " 522: 0.40201512610368484,\n",
       " 557: 0.40201512610368484,\n",
       " 761: 0.40201512610368484,\n",
       " 646: 0.39477101697586137,\n",
       " 19: 0.38138503569823695,\n",
       " 27: 0.38138503569823695,\n",
       " 95: 0.38138503569823695,\n",
       " 144: 0.38138503569823695,\n",
       " 308: 0.38138503569823695,\n",
       " 344: 0.38138503569823695,\n",
       " 361: 0.38138503569823695,\n",
       " 416: 0.38138503569823695,\n",
       " 425: 0.38138503569823695,\n",
       " 492: 0.38138503569823695,\n",
       " 639: 0.38138503569823695,\n",
       " 719: 0.38138503569823695,\n",
       " 796: 0.38138503569823695,\n",
       " 67: 0.377216768077159,\n",
       " 442: 0.37670528747840887,\n",
       " 507: 0.37670528747840887,\n",
       " 716: 0.37219368415938836,\n",
       " 124: 0.36927447293799825,\n",
       " 208: 0.36363636363636365,\n",
       " 220: 0.36363636363636365,\n",
       " 333: 0.36363636363636365,\n",
       " 430: 0.36363636363636365,\n",
       " 438: 0.36363636363636365,\n",
       " 701: 0.36363636363636365,\n",
       " 20: 0.36181361349331637,\n",
       " 138: 0.36181361349331637,\n",
       " 389: 0.3595732599803958,\n",
       " 340: 0.35478743759344955,\n",
       " 324: 0.351839597706834,\n",
       " 448: 0.351839597706834,\n",
       " 155: 0.3481553119113957,\n",
       " 227: 0.3481553119113957,\n",
       " 260: 0.3481553119113957,\n",
       " 305: 0.3481553119113957,\n",
       " 320: 0.3481553119113957,\n",
       " 321: 0.3481553119113957,\n",
       " 329: 0.3481553119113957,\n",
       " 418: 0.3481553119113957,\n",
       " 489: 0.3481553119113957,\n",
       " 502: 0.3481553119113957,\n",
       " 520: 0.3481553119113957,\n",
       " 535: 0.3481553119113957,\n",
       " 536: 0.3481553119113957,\n",
       " 544: 0.3481553119113957,\n",
       " 590: 0.3481553119113957,\n",
       " 758: 0.3481553119113957,\n",
       " 787: 0.3481553119113957,\n",
       " 810: 0.3481553119113957,\n",
       " 823: 0.3481553119113957,\n",
       " 34: 0.34815531191139565,\n",
       " 131: 0.3418817293789138,\n",
       " 413: 0.3418817293789138,\n",
       " 472: 0.3418817293789138,\n",
       " 390: 0.34112114616897665,\n",
       " 428: 0.34112114616897665,\n",
       " 146: 0.3377602647365992,\n",
       " 12: 0.3344968040028363,\n",
       " 25: 0.3344968040028363,\n",
       " 76: 0.3344968040028363,\n",
       " 201: 0.3344968040028363,\n",
       " 233: 0.3344968040028363,\n",
       " 276: 0.3344968040028363,\n",
       " 410: 0.3344968040028363,\n",
       " 440: 0.3344968040028363,\n",
       " 468: 0.3344968040028363,\n",
       " 503: 0.3344968040028363,\n",
       " 547: 0.3344968040028363,\n",
       " 596: 0.3344968040028363,\n",
       " 697: 0.3344968040028363,\n",
       " 811: 0.3344968040028363,\n",
       " 821: 0.3344968040028363,\n",
       " 588: 0.33028912953790823,\n",
       " 668: 0.3289758474798845,\n",
       " 202: 0.3249182166443294,\n",
       " 328: 0.3249182166443294,\n",
       " 401: 0.3249182166443294,\n",
       " 188: 0.3223291856101521,\n",
       " 224: 0.3223291856101521,\n",
       " 229: 0.3223291856101521,\n",
       " 259: 0.3223291856101521,\n",
       " 388: 0.3223291856101521,\n",
       " 499: 0.3223291856101521,\n",
       " 569: 0.3223291856101521,\n",
       " 579: 0.3223291856101521,\n",
       " 587: 0.3223291856101521,\n",
       " 636: 0.3223291856101521,\n",
       " 681: 0.3223291856101521,\n",
       " 708: 0.3223291856101521,\n",
       " 718: 0.3223291856101521,\n",
       " 82: 0.3198010745334156,\n",
       " 162: 0.3198010745334156,\n",
       " 584: 0.3198010745334156,\n",
       " 837: 0.3143473067309658,\n",
       " 143: 0.3113995776646092,\n",
       " 190: 0.3113995776646092,\n",
       " 206: 0.3113995776646092,\n",
       " 272: 0.3113995776646092,\n",
       " 362: 0.3113995776646092,\n",
       " 370: 0.3113995776646092,\n",
       " 381: 0.3113995776646092,\n",
       " 518: 0.3113995776646092,\n",
       " 619: 0.3113995776646092,\n",
       " 689: 0.3113995776646092,\n",
       " 722: 0.3113995776646092,\n",
       " 735: 0.3113995776646092,\n",
       " 742: 0.3113995776646092,\n",
       " 809: 0.3113995776646092,\n",
       " 359: 0.30578831486257535,\n",
       " 10: 0.30151134457776363,\n",
       " 13: 0.30151134457776363,\n",
       " 35: 0.30151134457776363,\n",
       " 167: 0.30151134457776363,\n",
       " 178: 0.30151134457776363,\n",
       " 205: 0.30151134457776363,\n",
       " 267: 0.30151134457776363,\n",
       " 281: 0.30151134457776363,\n",
       " 301: 0.30151134457776363,\n",
       " 318: 0.30151134457776363,\n",
       " 319: 0.30151134457776363,\n",
       " 325: 0.30151134457776363,\n",
       " 367: 0.30151134457776363,\n",
       " 408: 0.30151134457776363,\n",
       " 437: 0.30151134457776363,\n",
       " 550: 0.30151134457776363,\n",
       " 551: 0.30151134457776363,\n",
       " 553: 0.30151134457776363,\n",
       " 565: 0.30151134457776363,\n",
       " 591: 0.30151134457776363,\n",
       " 616: 0.30151134457776363,\n",
       " 662: 0.30151134457776363,\n",
       " 696: 0.30151134457776363,\n",
       " 709: 0.30151134457776363,\n",
       " 723: 0.30151134457776363,\n",
       " 740: 0.30151134457776363,\n",
       " 745: 0.30151134457776363,\n",
       " 776: 0.30151134457776363,\n",
       " 784: 0.30151134457776363,\n",
       " 788: 0.30151134457776363,\n",
       " 860: 0.30151134457776363,\n",
       " 595: 0.29740895825796587,\n",
       " 59: 0.29250896965085227,\n",
       " 74: 0.29250896965085227,\n",
       " 172: 0.29250896965085227,\n",
       " 189: 0.29250896965085227,\n",
       " 204: 0.29250896965085227,\n",
       " 237: 0.29250896965085227,\n",
       " 248: 0.29250896965085227,\n",
       " 323: 0.29250896965085227,\n",
       " 414: 0.29250896965085227,\n",
       " 445: 0.29250896965085227,\n",
       " 455: 0.29250896965085227,\n",
       " 459: 0.29250896965085227,\n",
       " 714: 0.29250896965085227,\n",
       " 750: 0.29250896965085227,\n",
       " 853: 0.29250896965085227,\n",
       " 8: 0.2860387767736777,\n",
       " 546: 0.2860387767736777,\n",
       " 107: 0.2842676218074806,\n",
       " 114: 0.2842676218074806,\n",
       " 177: 0.2842676218074806,\n",
       " 240: 0.2842676218074806,\n",
       " 290: 0.2842676218074806,\n",
       " 341: 0.2842676218074806,\n",
       " 439: 0.2842676218074806,\n",
       " 531: 0.2842676218074806,\n",
       " 678: 0.2842676218074806,\n",
       " 725: 0.2842676218074806,\n",
       " 737: 0.2842676218074806,\n",
       " 283: 0.2799462554779272,\n",
       " 103: 0.27668578554642986,\n",
       " 160: 0.27668578554642986,\n",
       " 223: 0.27668578554642986,\n",
       " 294: 0.27668578554642986,\n",
       " 450: 0.2727272727272727,\n",
       " 703: 0.2727272727272727,\n",
       " 24: 0.26967994498529685,\n",
       " 32: 0.26967994498529685,\n",
       " 40: 0.26967994498529685,\n",
       " 44: 0.26967994498529685,\n",
       " 46: 0.26967994498529685,\n",
       " 47: 0.26967994498529685,\n",
       " 127: 0.26967994498529685,\n",
       " 194: 0.26967994498529685,\n",
       " 242: 0.26967994498529685,\n",
       " 244: 0.26967994498529685,\n",
       " 302: 0.26967994498529685,\n",
       " 397: 0.26967994498529685,\n",
       " 400: 0.26967994498529685,\n",
       " 411: 0.26967994498529685,\n",
       " 433: 0.26967994498529685,\n",
       " 466: 0.26967994498529685,\n",
       " 479: 0.26967994498529685,\n",
       " 500: 0.26967994498529685,\n",
       " 504: 0.26967994498529685,\n",
       " 508: 0.26967994498529685,\n",
       " 589: 0.26967994498529685,\n",
       " 604: 0.26967994498529685,\n",
       " 622: 0.26967994498529685,\n",
       " 630: 0.26967994498529685,\n",
       " 667: 0.26967994498529685,\n",
       " 690: 0.26967994498529685,\n",
       " 706: 0.26967994498529685,\n",
       " 771: 0.26967994498529685,\n",
       " 849: 0.26967994498529685,\n",
       " 480: 0.2631806779839076,\n",
       " 764: 0.2631806779839076,\n",
       " 813: 0.2631806779839076,\n",
       " 831: 0.2631806779839076,\n",
       " 342: 0.2585438449975096,\n",
       " 614: 0.2585438449975096,\n",
       " 715: 0.25712973861328997,\n",
       " 195: 0.25147784538477264,\n",
       " 436: 0.25147784538477264,\n",
       " 631: 0.25147784538477264,\n",
       " 751: 0.25147784538477264,\n",
       " 757: 0.25147784538477264,\n",
       " 817: 0.25147784538477264,\n",
       " 824: 0.25147784538477264,\n",
       " 762: 0.251259453814803,\n",
       " 851: 0.2508726030021272,\n",
       " 11: 0.2461829819586655,\n",
       " 21: 0.2461829819586655,\n",
       " 108: 0.2461829819586655,\n",
       " 110: 0.2461829819586655,\n",
       " 125: 0.2461829819586655,\n",
       " 126: 0.2461829819586655,\n",
       " 199: 0.2461829819586655,\n",
       " 241: 0.2461829819586655,\n",
       " 243: 0.2461829819586655,\n",
       " 285: 0.2461829819586655,\n",
       " 354: 0.2461829819586655,\n",
       " 429: 0.2461829819586655,\n",
       " 545: 0.2461829819586655,\n",
       " 566: 0.2461829819586655,\n",
       " 570: 0.2461829819586655,\n",
       " 571: 0.2461829819586655,\n",
       " 601: 0.2461829819586655,\n",
       " 626: 0.2461829819586655,\n",
       " 651: 0.2461829819586655,\n",
       " 657: 0.2461829819586655,\n",
       " 663: 0.2461829819586655,\n",
       " 679: 0.2461829819586655,\n",
       " 702: 0.2461829819586655,\n",
       " 720: 0.2461829819586655,\n",
       " 739: 0.2461829819586655,\n",
       " 790: 0.2461829819586655,\n",
       " 792: 0.2461829819586655,\n",
       " 808: 0.2461829819586655,\n",
       " 816: 0.2461829819586655,\n",
       " 818: 0.2461829819586655,\n",
       " 840: 0.2461829819586655,\n",
       " 856: 0.2461829819586655,\n",
       " 483: 0.24455799402225925,\n",
       " 419: 0.24120907566221092,\n",
       " 597: 0.24120907566221092,\n",
       " 552: 0.23652495839563303,\n",
       " 640: 0.23652495839563303,\n",
       " 28: 0.2279211529192759,\n",
       " 49: 0.2279211529192759,\n",
       " 63: 0.2279211529192759,\n",
       " 69: 0.2279211529192759,\n",
       " 71: 0.2279211529192759,\n",
       " 87: 0.2279211529192759,\n",
       " 90: 0.2279211529192759,\n",
       " 97: 0.2279211529192759,\n",
       " 102: 0.2279211529192759,\n",
       " 109: 0.2279211529192759,\n",
       " 161: 0.2279211529192759,\n",
       " 187: 0.2279211529192759,\n",
       " 255: 0.2279211529192759,\n",
       " 295: 0.2279211529192759,\n",
       " 313: 0.2279211529192759,\n",
       " 317: 0.2279211529192759,\n",
       " 331: 0.2279211529192759,\n",
       " 335: 0.2279211529192759,\n",
       " 402: 0.2279211529192759,\n",
       " 412: 0.2279211529192759,\n",
       " 423: 0.2279211529192759,\n",
       " 431: 0.2279211529192759,\n",
       " 464: 0.2279211529192759,\n",
       " 469: 0.2279211529192759,\n",
       " 485: 0.2279211529192759,\n",
       " 505: 0.2279211529192759,\n",
       " 555: 0.2279211529192759,\n",
       " 575: 0.2279211529192759,\n",
       " 583: 0.2279211529192759,\n",
       " 586: 0.2279211529192759,\n",
       " 598: 0.2279211529192759,\n",
       " 602: 0.2279211529192759,\n",
       " 671: 0.2279211529192759,\n",
       " 707: 0.2279211529192759,\n",
       " 734: 0.2279211529192759,\n",
       " 791: 0.2279211529192759,\n",
       " 826: 0.2279211529192759,\n",
       " 834: 0.22019275302527214,\n",
       " 165: 0.2193817272381392,\n",
       " 18: 0.21320071635561041,\n",
       " 31: 0.21320071635561041,\n",
       " 65: 0.21320071635561041,\n",
       " 72: 0.21320071635561041,\n",
       " 98: 0.21320071635561041,\n",
       " 145: 0.21320071635561041,\n",
       " 157: 0.21320071635561041,\n",
       " 198: 0.21320071635561041,\n",
       " 222: 0.21320071635561041,\n",
       " 230: 0.21320071635561041,\n",
       " 231: 0.21320071635561041,\n",
       " 235: 0.21320071635561041,\n",
       " 252: 0.21320071635561041,\n",
       " 278: 0.21320071635561041,\n",
       " 279: 0.21320071635561041,\n",
       " 351: 0.21320071635561041,\n",
       " 357: 0.21320071635561041,\n",
       " 394: 0.21320071635561041,\n",
       " 404: 0.21320071635561041,\n",
       " 407: 0.21320071635561041,\n",
       " 420: 0.21320071635561041,\n",
       " 435: 0.21320071635561041,\n",
       " 470: 0.21320071635561041,\n",
       " 534: 0.21320071635561041,\n",
       " 537: 0.21320071635561041,\n",
       " 574: 0.21320071635561041,\n",
       " 615: 0.21320071635561041,\n",
       " 691: 0.21320071635561041,\n",
       " 704: 0.21320071635561041,\n",
       " 727: 0.21320071635561041,\n",
       " 753: 0.21320071635561041,\n",
       " 777: 0.21320071635561041,\n",
       " 789: 0.21320071635561041,\n",
       " 835: 0.21320071635561041,\n",
       " 854: 0.21320071635561041,\n",
       " 857: 0.21320071635561041,\n",
       " 345: 0.2111001654603745,\n",
       " 415: 0.2099455524325912,\n",
       " 563: 0.2099455524325912,\n",
       " 217: 0.20225995873897262,\n",
       " 336: 0.20225995873897262,\n",
       " 15: 0.20100756305184242,\n",
       " 36: 0.20100756305184242,\n",
       " 48: 0.20100756305184242,\n",
       " 68: 0.20100756305184242,\n",
       " 75: 0.20100756305184242,\n",
       " 130: 0.20100756305184242,\n",
       " 154: 0.20100756305184242,\n",
       " 183: 0.20100756305184242,\n",
       " 203: 0.20100756305184242,\n",
       " 209: 0.20100756305184242,\n",
       " 214: 0.20100756305184242,\n",
       " 228: 0.20100756305184242,\n",
       " 232: 0.20100756305184242,\n",
       " 245: 0.20100756305184242,\n",
       " 249: 0.20100756305184242,\n",
       " 263: 0.20100756305184242,\n",
       " 268: 0.20100756305184242,\n",
       " 274: 0.20100756305184242,\n",
       " 282: 0.20100756305184242,\n",
       " 293: 0.20100756305184242,\n",
       " 297: 0.20100756305184242,\n",
       " 360: 0.20100756305184242,\n",
       " 365: 0.20100756305184242,\n",
       " 375: 0.20100756305184242,\n",
       " 380: 0.20100756305184242,\n",
       " 382: 0.20100756305184242,\n",
       " 384: 0.20100756305184242,\n",
       " 393: 0.20100756305184242,\n",
       " 446: 0.20100756305184242,\n",
       " 454: 0.20100756305184242,\n",
       " 467: 0.20100756305184242,\n",
       " 477: 0.20100756305184242,\n",
       " 487: 0.20100756305184242,\n",
       " 488: 0.20100756305184242,\n",
       " 506: 0.20100756305184242,\n",
       " 509: 0.20100756305184242,\n",
       " 526: 0.20100756305184242,\n",
       " 533: 0.20100756305184242,\n",
       " 542: 0.20100756305184242,\n",
       " 548: 0.20100756305184242,\n",
       " 564: 0.20100756305184242,\n",
       " 578: 0.20100756305184242,\n",
       " 606: 0.20100756305184242,\n",
       " 610: 0.20100756305184242,\n",
       " 611: 0.20100756305184242,\n",
       " 627: 0.20100756305184242,\n",
       " 632: 0.20100756305184242,\n",
       " 637: 0.20100756305184242,\n",
       " 648: 0.20100756305184242,\n",
       " 660: 0.20100756305184242,\n",
       " 683: 0.20100756305184242,\n",
       " 686: 0.20100756305184242,\n",
       " 698: 0.20100756305184242,\n",
       " 705: 0.20100756305184242,\n",
       " 710: 0.20100756305184242,\n",
       " 760: 0.20100756305184242,\n",
       " 772: 0.20100756305184242,\n",
       " 778: 0.20100756305184242,\n",
       " 783: 0.20100756305184242,\n",
       " 785: 0.20100756305184242,\n",
       " 793: 0.20100756305184242,\n",
       " 800: 0.20100756305184242,\n",
       " 803: 0.20100756305184242,\n",
       " 806: 0.20100756305184242,\n",
       " 859: 0.20100756305184242,\n",
       " 374: 0.1982726388386439,\n",
       " 37: 0.19069251784911848,\n",
       " 55: 0.19069251784911848,\n",
       " 61: 0.19069251784911848,\n",
       " 66: 0.19069251784911848,\n",
       " 117: 0.19069251784911848,\n",
       " 128: 0.19069251784911848,\n",
       " 134: 0.19069251784911848,\n",
       " 156: 0.19069251784911848,\n",
       " 159: 0.19069251784911848,\n",
       " 166: 0.19069251784911848,\n",
       " 181: 0.19069251784911848,\n",
       " 236: 0.19069251784911848,\n",
       " 246: 0.19069251784911848,\n",
       " 299: 0.19069251784911848,\n",
       " 356: 0.19069251784911848,\n",
       " 378: 0.19069251784911848,\n",
       " 395: 0.19069251784911848,\n",
       " 398: 0.19069251784911848,\n",
       " 405: 0.19069251784911848,\n",
       " 409: 0.19069251784911848,\n",
       " 426: 0.19069251784911848,\n",
       " 452: 0.19069251784911848,\n",
       " 457: 0.19069251784911848,\n",
       " 463: 0.19069251784911848,\n",
       " 476: 0.19069251784911848,\n",
       " 478: 0.19069251784911848,\n",
       " 481: 0.19069251784911848,\n",
       " 493: 0.19069251784911848,\n",
       " 497: 0.19069251784911848,\n",
       " 498: 0.19069251784911848,\n",
       " 525: 0.19069251784911848,\n",
       " 539: 0.19069251784911848,\n",
       " 561: 0.19069251784911848,\n",
       " 577: 0.19069251784911848,\n",
       " 655: 0.19069251784911848,\n",
       " 664: 0.19069251784911848,\n",
       " 712: 0.19069251784911848,\n",
       " 717: 0.19069251784911848,\n",
       " 728: 0.19069251784911848,\n",
       " 732: 0.19069251784911848,\n",
       " 741: 0.19069251784911848,\n",
       " 749: 0.19069251784911848,\n",
       " 781: 0.19069251784911848,\n",
       " 798: 0.19069251784911848,\n",
       " 814: 0.19069251784911848,\n",
       " 373: 0.18835264373920443,\n",
       " 9: 0.18181818181818182,\n",
       " 56: 0.18181818181818182,\n",
       " 60: 0.18181818181818182,\n",
       " 70: 0.18181818181818182,\n",
       " 85: 0.18181818181818182,\n",
       " 140: 0.18181818181818182,\n",
       " 180: 0.18181818181818182,\n",
       " 182: 0.18181818181818182,\n",
       " 184: 0.18181818181818182,\n",
       " 185: 0.18181818181818182,\n",
       " 192: 0.18181818181818182,\n",
       " 200: 0.18181818181818182,\n",
       " 212: 0.18181818181818182,\n",
       " 218: 0.18181818181818182,\n",
       " 219: 0.18181818181818182,\n",
       " 221: 0.18181818181818182,\n",
       " 262: 0.18181818181818182,\n",
       " 277: 0.18181818181818182,\n",
       " 296: 0.18181818181818182,\n",
       " 303: 0.18181818181818182,\n",
       " 337: 0.18181818181818182,\n",
       " 353: 0.18181818181818182,\n",
       " 358: 0.18181818181818182,\n",
       " 376: 0.18181818181818182,\n",
       " 377: 0.18181818181818182,\n",
       " 387: 0.18181818181818182,\n",
       " 417: 0.18181818181818182,\n",
       " 456: 0.18181818181818182,\n",
       " 458: 0.18181818181818182,\n",
       " 460: 0.18181818181818182,\n",
       " 475: 0.18181818181818182,\n",
       " 495: 0.18181818181818182,\n",
       " 496: 0.18181818181818182,\n",
       " 516: 0.18181818181818182,\n",
       " 519: 0.18181818181818182,\n",
       " 528: 0.18181818181818182,\n",
       " 532: 0.18181818181818182,\n",
       " 538: 0.18181818181818182,\n",
       " 572: 0.18181818181818182,\n",
       " 573: 0.18181818181818182,\n",
       " 585: 0.18181818181818182,\n",
       " 607: 0.18181818181818182,\n",
       " 643: 0.18181818181818182,\n",
       " 653: 0.18181818181818182,\n",
       " 654: 0.18181818181818182,\n",
       " 656: 0.18181818181818182,\n",
       " 661: 0.18181818181818182,\n",
       " 692: 0.18181818181818182,\n",
       " 744: 0.18181818181818182,\n",
       " 752: 0.18181818181818182,\n",
       " 769: 0.18181818181818182,\n",
       " 774: 0.18181818181818182,\n",
       " 775: 0.18181818181818182,\n",
       " 779: 0.18181818181818182,\n",
       " 815: 0.18181818181818182,\n",
       " 50: 0.17407765595569785,\n",
       " 92: 0.17407765595569785,\n",
       " 94: 0.17407765595569785,\n",
       " 99: 0.17407765595569785,\n",
       " 116: 0.17407765595569785,\n",
       " 132: 0.17407765595569785,\n",
       " 136: 0.17407765595569785,\n",
       " 152: 0.17407765595569785,\n",
       " 247: 0.17407765595569785,\n",
       " 250: 0.17407765595569785,\n",
       " 253: 0.17407765595569785,\n",
       " 270: 0.17407765595569785,\n",
       " 275: 0.17407765595569785,\n",
       " 280: 0.17407765595569785,\n",
       " 288: 0.17407765595569785,\n",
       " 314: 0.17407765595569785,\n",
       " 441: 0.17407765595569785,\n",
       " 617: 0.17407765595569785,\n",
       " 634: 0.17407765595569785,\n",
       " 666: 0.17407765595569785,\n",
       " 726: 0.17407765595569785,\n",
       " 731: 0.17407765595569785,\n",
       " 746: 0.17407765595569785,\n",
       " 804: 0.17407765595569785,\n",
       " 100: 0.16724840200141816,\n",
       " 106: 0.16724840200141816,\n",
       " 197: 0.16724840200141816,\n",
       " 226: 0.16724840200141816,\n",
       " 239: 0.16724840200141816,\n",
       " 273: 0.16724840200141816,\n",
       " 286: 0.16724840200141816,\n",
       " 291: 0.16724840200141816,\n",
       " 292: 0.16724840200141816,\n",
       " 300: 0.16724840200141816,\n",
       " 352: 0.16724840200141816,\n",
       " 366: 0.16724840200141816,\n",
       " 372: 0.16724840200141816,\n",
       " 434: 0.16724840200141816,\n",
       " 461: 0.16724840200141816,\n",
       " 465: 0.16724840200141816,\n",
       " 515: 0.16724840200141816,\n",
       " 558: 0.16724840200141816,\n",
       " 576: 0.16724840200141816,\n",
       " 608: 0.16724840200141816,\n",
       " 618: 0.16724840200141816,\n",
       " 624: 0.16724840200141816,\n",
       " 641: 0.16724840200141816,\n",
       " 642: 0.16724840200141816,\n",
       " 675: 0.16724840200141816,\n",
       " 676: 0.16724840200141816,\n",
       " 693: 0.16724840200141816,\n",
       " 713: 0.16724840200141816,\n",
       " 827: 0.16724840200141816,\n",
       " 828: 0.16724840200141816,\n",
       " 841: 0.16724840200141816,\n",
       " 848: 0.16724840200141816,\n",
       " 855: 0.16724840200141816,\n",
       " 62: 0.16116459280507606,\n",
       " 73: 0.16116459280507606,\n",
       " 113: 0.16116459280507606,\n",
       " 158: 0.16116459280507606,\n",
       " 196: 0.16116459280507606,\n",
       " 298: 0.16116459280507606,\n",
       " 311: 0.16116459280507606,\n",
       " 322: 0.16116459280507606,\n",
       " 510: 0.16116459280507606,\n",
       " 514: 0.16116459280507606,\n",
       " 605: 0.16116459280507606,\n",
       " 625: 0.16116459280507606,\n",
       " 650: 0.16116459280507606,\n",
       " 652: 0.16116459280507606,\n",
       " 755: 0.16116459280507606,\n",
       " 768: 0.16116459280507606,\n",
       " 782: 0.16116459280507606,\n",
       " 839: 0.16116459280507606,\n",
       " 33: 0.1574591643244434,\n",
       " 52: 0.1556997888323046,\n",
       " 93: 0.1556997888323046,\n",
       " 135: 0.1556997888323046,\n",
       " 147: 0.1556997888323046,\n",
       " 149: 0.1556997888323046,\n",
       " 175: 0.1556997888323046,\n",
       " 363: 0.1556997888323046,\n",
       " 421: 0.1556997888323046,\n",
       " 511: 0.1556997888323046,\n",
       " 524: 0.1556997888323046,\n",
       " 368: 0.15289415743128767,\n",
       " 148: 0.15075567228888181,\n",
       " 150: 0.15075567228888181,\n",
       " 169: 0.15075567228888181,\n",
       " 225: 0.15075567228888181,\n",
       " 234: 0.15075567228888181,\n",
       " 444: 0.15075567228888181,\n",
       " 453: 0.15075567228888181,\n",
       " 543: 0.15075567228888181,\n",
       " 658: 0.15075567228888181,\n",
       " 754: 0.15075567228888181,\n",
       " 773: 0.15075567228888181,\n",
       " 805: 0.15075567228888181,\n",
       " 833: 0.15075567228888181,\n",
       " 264: 0.14625448482542613,\n",
       " 620: 0.14625448482542613,\n",
       " 766: 0.14625448482542613,\n",
       " 830: 0.14625448482542613,\n",
       " 77: 0.1421338109037403,\n",
       " 462: 0.1421338109037403,\n",
       " 513: 0.1421338109037403,\n",
       " 521: 0.1421338109037403,\n",
       " 581: 0.1421338109037403,\n",
       " 609: 0.1421338109037403,\n",
       " 682: 0.1421338109037403,\n",
       " 799: 0.1421338109037403,\n",
       " 819: 0.1421338109037403,\n",
       " 29: 0.13834289277321493,\n",
       " 567: 0.13834289277321493,\n",
       " 670: 0.13834289277321493,\n",
       " 748: 0.13834289277321493,\n",
       " 527: 0.13636363636363635,\n",
       " 665: 0.13636363636363635,\n",
       " 312: 0.13483997249264842,\n",
       " 560: 0.13483997249264842,\n",
       " 621: 0.13483997249264842,\n",
       " 674: 0.13483997249264842,\n",
       " 767: 0.13483997249264842,\n",
       " 825: 0.13483997249264842,\n",
       " 847: 0.13483997249264842,\n",
       " 852: 0.13483997249264842,\n",
       " 422: 0.1315903389919538,\n",
       " 592: 0.1315903389919538,\n",
       " 644: 0.1315903389919538,\n",
       " 399: 0.12856486930664499,\n",
       " 424: 0.12856486930664499,\n",
       " 724: 0.12856486930664499,\n",
       " 451: 0.12573892269238632,\n",
       " 523: 0.12573892269238632,\n",
       " 669: 0.12309149097933275,\n",
       " 672: 0.12309149097933275,\n",
       " 645: 0.12060453783110546,\n",
       " 756: 0.12060453783110546,\n",
       " 54: 0.11826247919781652,\n",
       " 213: 0.11826247919781652,\n",
       " 256: 0.11826247919781652,\n",
       " 284: 0.11826247919781652,\n",
       " 443: 0.11826247919781652,\n",
       " 802: 0.11826247919781652,\n",
       " 861: 0.11826247919781652,\n",
       " 261: 0.11605177063713189,\n",
       " 171: 0.11396057645963795,\n",
       " 786: 0.11396057645963795,\n",
       " 838: 0.11396057645963795,\n",
       " 628: 0.11197850219117086,\n",
       " 432: 0.11009637651263607,\n",
       " 556: 0.11009637651263607,\n",
       " 41: 0.10660035817780521,\n",
       " 191: 0.10660035817780521,\n",
       " 315: 0.10660035817780521,\n",
       " 540: 0.10660035817780521,\n",
       " 287: 0.10050378152592121,\n",
       " 554: 0.10050378152592121,\n",
       " 1: 0.0,\n",
       " 17: 0.0,\n",
       " 23: 0.0,\n",
       " 38: 0.0,\n",
       " 39: 0.0,\n",
       " 42: 0.0,\n",
       " 51: 0.0,\n",
       " 53: 0.0,\n",
       " 57: 0.0,\n",
       " 58: 0.0,\n",
       " 64: 0.0,\n",
       " 78: 0.0,\n",
       " 79: 0.0,\n",
       " 80: 0.0,\n",
       " 81: 0.0,\n",
       " 83: 0.0,\n",
       " 84: 0.0,\n",
       " 86: 0.0,\n",
       " 88: 0.0,\n",
       " 89: 0.0,\n",
       " 91: 0.0,\n",
       " 96: 0.0,\n",
       " 104: 0.0,\n",
       " 111: 0.0,\n",
       " 112: 0.0,\n",
       " 115: 0.0,\n",
       " 119: 0.0,\n",
       " 120: 0.0,\n",
       " 121: 0.0,\n",
       " 122: 0.0,\n",
       " 123: 0.0,\n",
       " 133: 0.0,\n",
       " 142: 0.0,\n",
       " 153: 0.0,\n",
       " 164: 0.0,\n",
       " 168: 0.0,\n",
       " 173: 0.0,\n",
       " 193: 0.0,\n",
       " 207: 0.0,\n",
       " 210: 0.0,\n",
       " 211: 0.0,\n",
       " 215: 0.0,\n",
       " 238: 0.0,\n",
       " 251: 0.0,\n",
       " 254: 0.0,\n",
       " 258: 0.0,\n",
       " 266: 0.0,\n",
       " 269: 0.0,\n",
       " 271: 0.0,\n",
       " 289: 0.0,\n",
       " 304: 0.0,\n",
       " 309: 0.0,\n",
       " 310: 0.0,\n",
       " 316: 0.0,\n",
       " 327: 0.0,\n",
       " 330: 0.0,\n",
       " 334: 0.0,\n",
       " 338: 0.0,\n",
       " 343: 0.0,\n",
       " 346: 0.0,\n",
       " 348: 0.0,\n",
       " 349: 0.0,\n",
       " 350: 0.0,\n",
       " 364: 0.0,\n",
       " 369: 0.0,\n",
       " 371: 0.0,\n",
       " 379: 0.0,\n",
       " 383: 0.0,\n",
       " 385: 0.0,\n",
       " 386: 0.0,\n",
       " 391: 0.0,\n",
       " 392: 0.0,\n",
       " 403: 0.0,\n",
       " 406: 0.0,\n",
       " 427: 0.0,\n",
       " 447: 0.0,\n",
       " 471: 0.0,\n",
       " 473: 0.0,\n",
       " 482: 0.0,\n",
       " 484: 0.0,\n",
       " 486: 0.0,\n",
       " 490: 0.0,\n",
       " 491: 0.0,\n",
       " 494: 0.0,\n",
       " 501: 0.0,\n",
       " 512: 0.0,\n",
       " 517: 0.0,\n",
       " 529: 0.0,\n",
       " 530: 0.0,\n",
       " 559: 0.0,\n",
       " 562: 0.0,\n",
       " 568: 0.0,\n",
       " 580: 0.0,\n",
       " 582: 0.0,\n",
       " 594: 0.0,\n",
       " 599: 0.0,\n",
       " 600: 0.0,\n",
       " 613: 0.0,\n",
       " 623: 0.0,\n",
       " 629: 0.0,\n",
       " 633: 0.0,\n",
       " 647: 0.0,\n",
       " 649: 0.0,\n",
       " 659: 0.0,\n",
       " 673: 0.0,\n",
       " 680: 0.0,\n",
       " 684: 0.0,\n",
       " 685: 0.0,\n",
       " 687: 0.0,\n",
       " 688: 0.0,\n",
       " 694: 0.0,\n",
       " 695: 0.0,\n",
       " 699: 0.0,\n",
       " 700: 0.0,\n",
       " 711: 0.0,\n",
       " 733: 0.0,\n",
       " 736: 0.0,\n",
       " 743: 0.0,\n",
       " 747: 0.0,\n",
       " 759: 0.0,\n",
       " 763: 0.0,\n",
       " 765: 0.0,\n",
       " 770: 0.0,\n",
       " 780: 0.0,\n",
       " 795: 0.0,\n",
       " 801: 0.0,\n",
       " 807: 0.0,\n",
       " 812: 0.0,\n",
       " 832: 0.0,\n",
       " 836: 0.0,\n",
       " 842: 0.0,\n",
       " 843: 0.0,\n",
       " 844: 0.0,\n",
       " 846: 0.0,\n",
       " 850: 0.0,\n",
       " 858: 0.0}"
      ]
     },
     "execution_count": 192,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cos_similarity = np.multiply(dot_pdt, L2_product)\n",
    "cos_similarity = cos_similarity.tolist()\n",
    "cos_similarity = enumerate(cos_similarity)\n",
    "cos_similarity = dict(cos_similarity)\n",
    "cos_similarity = dict(sorted(cos_similarity.items(), key = lambda x : x[1], reverse= True))\n",
    "cos_similarity"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "990e33e5d257f203d6dbbe97b600957464dfb55a0c2006ef419f51d1275108a4"
  },
  "kernelspec": {
   "display_name": "Python 3.8.5 ('mynewenv')",
   "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": "3.6.13"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}