Created
March 28, 2022 21:34
-
-
Save PandoraRiot/b920a56a8e4bd646a90c21d23b660c84 to your computer and use it in GitHub Desktop.
03_00_Clasificacion_BW__TF_IDF.ipynb
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"nbformat": 4, | |
"nbformat_minor": 0, | |
"metadata": { | |
"colab": { | |
"name": "03_00_Clasificacion_BW__TF_IDF.ipynb", | |
"provenance": [], | |
"collapsed_sections": [], | |
"include_colab_link": true | |
}, | |
"kernelspec": { | |
"name": "python3", | |
"display_name": "Python 3" | |
} | |
}, | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "view-in-github", | |
"colab_type": "text" | |
}, | |
"source": [ | |
"<a href=\"https://colab.research.google.com/gist/PandoraRiot/b920a56a8e4bd646a90c21d23b660c84/03_00_clasificacion_bw__tf_idf.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "4wCFBly4uu9c" | |
}, | |
"source": [ | |
"import pandas as pd\n", | |
"from sklearn.feature_extraction.text import TfidfVectorizer" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "355mRwx6uyki" | |
}, | |
"source": [ | |
"documentA = 'i love dogs'\n", | |
"documentB = 'i hate dogs and knitting'\n", | |
"documentC ='knitting is my hobby and my passion'" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "GUlaDZXYvC6a" | |
}, | |
"source": [ | |
"bagOfWordsA = documentA.split(' ')\n", | |
"bagOfWordsB = documentB.split(' ')\n", | |
"bagOfWordsC = documentC.split(' ')" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "bTuUh7Hlw84Z" | |
}, | |
"source": [ | |
"#VEAMOSLO COMO BAG OF WORDS\n", | |
"\n", | |
"# Cargar libreria\n", | |
"import numpy as np\n", | |
"from sklearn.feature_extraction.text import CountVectorizer\n", | |
"# Crear vector de textos\n", | |
"text_data = np.array([documentA,documentB,documentC])\n", | |
"\n", | |
"# Crear bolsa de palabas (matriz)\n", | |
"count = CountVectorizer()\n", | |
"bag_of_words = count.fit_transform(text_data)\n", | |
"\n", | |
"# A arreglo\n", | |
"bag_of_words.toarray()\n", | |
"\n", | |
"\n", | |
"# Obtener nombres para las columnas\n", | |
"feature_names = count.get_feature_names()\n", | |
"\n", | |
"# ver nombre de las columnas\n", | |
"feature_names\n", | |
"\n", | |
"# Crear data frame\n", | |
"df_bw=pd.DataFrame(bag_of_words.toarray(), columns=feature_names)" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"" | |
], | |
"metadata": { | |
"id": "WfAmbfvrc5Lq" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"" | |
], | |
"metadata": { | |
"id": "fIIinhRac5Ya" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "ALHqkk54w_FC", | |
"outputId": "995bb76c-545b-4d7f-e91b-70c00f693486", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 141 | |
} | |
}, | |
"source": [ | |
"df_bw" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"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>and</th>\n", | |
" <th>dogs</th>\n", | |
" <th>hate</th>\n", | |
" <th>hobby</th>\n", | |
" <th>is</th>\n", | |
" <th>knitting</th>\n", | |
" <th>love</th>\n", | |
" <th>my</th>\n", | |
" <th>passion</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>1</td>\n", | |
" <td>1</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>1</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>2</td>\n", | |
" <td>1</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" and dogs hate hobby is knitting love my passion\n", | |
"0 0 1 0 0 0 0 1 0 0\n", | |
"1 1 1 1 0 0 1 0 0 0\n", | |
"2 1 0 0 1 1 1 0 2 1" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 5 | |
} | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "7oDH-A3yNFQx" | |
}, | |
"source": [ | |
"Tf-idf (del inglés Term frequency – Inverse document frequency), frecuencia de término – frecuencia inversa de documento (https://es.wikipedia.org/wiki/Tf-idf)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "BIF2ywCMMzSS" | |
}, | |
"source": [ | |
"" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "oZtyR1PzMzXD" | |
}, | |
"source": [ | |
"" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "5dbDF-n_Mzbl" | |
}, | |
"source": [ | |
"" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "6CD2HCqdvGSq" | |
}, | |
"source": [ | |
"uniqueWords = set(bagOfWordsA).union(set(bagOfWordsB))\n", | |
"uniqueWords=uniqueWords.union(bagOfWordsC)" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "YoZVtnH8vMNv", | |
"outputId": "7d187131-6230-42f9-9379-fd27d7dfd490", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 188 | |
} | |
}, | |
"source": [ | |
"uniqueWords\n" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": [ | |
"{'and',\n", | |
" 'dogs',\n", | |
" 'hate',\n", | |
" 'hobby',\n", | |
" 'i',\n", | |
" 'is',\n", | |
" 'knitting',\n", | |
" 'love',\n", | |
" 'my',\n", | |
" 'passion'}" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 7 | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "SzbfGGfYvM8_" | |
}, | |
"source": [ | |
"#diccionario\n", | |
"numOfWordsA = dict.fromkeys(uniqueWords, 0)\n", | |
"\n", | |
"for word in bagOfWordsA:\n", | |
" numOfWordsA[word] += 1\n", | |
" \n", | |
"numOfWordsB = dict.fromkeys(uniqueWords, 0)\n", | |
"\n", | |
"for word in bagOfWordsB:\n", | |
" numOfWordsB[word] += 1\n", | |
"\n", | |
"numOfWordsC = dict.fromkeys(uniqueWords, 0)\n", | |
"\n", | |
"for word in bagOfWordsC:\n", | |
" numOfWordsC[word] += 1 " | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "Mrip3wk6vakQ", | |
"outputId": "c9afbbc7-8165-4ffc-9040-f65282fadee0", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 188 | |
} | |
}, | |
"source": [ | |
"numOfWordsA" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": [ | |
"{'and': 0,\n", | |
" 'dogs': 1,\n", | |
" 'hate': 0,\n", | |
" 'hobby': 0,\n", | |
" 'i': 1,\n", | |
" 'is': 0,\n", | |
" 'knitting': 0,\n", | |
" 'love': 1,\n", | |
" 'my': 0,\n", | |
" 'passion': 0}" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 9 | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "_WJ7qXK0vc2F", | |
"outputId": "33ceb23b-19e3-4b2b-a3ca-d62d43fd2cd2", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 188 | |
} | |
}, | |
"source": [ | |
"numOfWordsB" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": [ | |
"{'and': 1,\n", | |
" 'dogs': 1,\n", | |
" 'hate': 1,\n", | |
" 'hobby': 0,\n", | |
" 'i': 1,\n", | |
" 'is': 0,\n", | |
" 'knitting': 1,\n", | |
" 'love': 0,\n", | |
" 'my': 0,\n", | |
" 'passion': 0}" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 10 | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "jp0rnrh1ve4J", | |
"outputId": "e175570a-37e7-467f-ede2-76d7fea016cf", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 188 | |
} | |
}, | |
"source": [ | |
"numOfWordsC" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": [ | |
"{'and': 1,\n", | |
" 'dogs': 0,\n", | |
" 'hate': 0,\n", | |
" 'hobby': 1,\n", | |
" 'i': 0,\n", | |
" 'is': 1,\n", | |
" 'knitting': 1,\n", | |
" 'love': 0,\n", | |
" 'my': 2,\n", | |
" 'passion': 1}" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 11 | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "yRyW0iQZvg96" | |
}, | |
"source": [ | |
"def computeTF(wordDict, bagOfWords):\n", | |
" tfDict = {}\n", | |
" bagOfWordsCount = len(bagOfWords)\n", | |
" for word, count in wordDict.items():\n", | |
" tfDict[word] = count / float(bagOfWordsCount)\n", | |
" return tfDict" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "OmOXBkS0vmo0" | |
}, | |
"source": [ | |
"#TF de cada documento\n", | |
"tfA = computeTF(numOfWordsA, bagOfWordsA)\n", | |
"tfB = computeTF(numOfWordsB, bagOfWordsB)\n", | |
"tfC = computeTF(numOfWordsC, bagOfWordsC)" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "Y7CVv-FMvsc_", | |
"outputId": "d71eeabd-00c8-499b-8fe8-61568c60b7a7", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 188 | |
} | |
}, | |
"source": [ | |
"tfA" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": [ | |
"{'and': 0.0,\n", | |
" 'dogs': 0.3333333333333333,\n", | |
" 'hate': 0.0,\n", | |
" 'hobby': 0.0,\n", | |
" 'i': 0.3333333333333333,\n", | |
" 'is': 0.0,\n", | |
" 'knitting': 0.0,\n", | |
" 'love': 0.3333333333333333,\n", | |
" 'my': 0.0,\n", | |
" 'passion': 0.0}" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 14 | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "zK6VUFxSv0aG" | |
}, | |
"source": [ | |
"def computeIDF(documents):\n", | |
" import math\n", | |
" N = len(documents) #numero de documentos\n", | |
" \n", | |
" idfDict = dict.fromkeys(documents[0].keys(), 0)\n", | |
" for document in documents:\n", | |
" for word, val in document.items():\n", | |
" if val > 0:\n", | |
" idfDict[word] += 1\n", | |
" \n", | |
" for word, val in idfDict.items():\n", | |
" idfDict[word] = math.log(N / float(val))\n", | |
" return idfDict" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "8tIwR-LTv0sx" | |
}, | |
"source": [ | |
"idfs = computeIDF([numOfWordsA, numOfWordsB,numOfWordsC])" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "k5McMyILv4xw", | |
"outputId": "f5c48cc1-e8d4-468b-b54d-e410472ad93b", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 188 | |
} | |
}, | |
"source": [ | |
"idfs" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"data": { | |
"text/plain": [ | |
"{'and': 0.4054651081081644,\n", | |
" 'dogs': 0.4054651081081644,\n", | |
" 'hate': 1.0986122886681098,\n", | |
" 'hobby': 1.0986122886681098,\n", | |
" 'i': 0.4054651081081644,\n", | |
" 'is': 1.0986122886681098,\n", | |
" 'knitting': 0.4054651081081644,\n", | |
" 'love': 1.0986122886681098,\n", | |
" 'my': 1.0986122886681098,\n", | |
" 'passion': 1.0986122886681098}" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 17 | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "_pORwkSowC8M" | |
}, | |
"source": [ | |
"def computeTFIDF(tfBagOfWords, idfs):\n", | |
" tfidf = {}\n", | |
" for word, val in tfBagOfWords.items():\n", | |
" tfidf[word] = val * idfs[word]\n", | |
" return tfidf" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "0dWBuQqKwPCT" | |
}, | |
"source": [ | |
"tfidfA = computeTFIDF(tfA, idfs)\n", | |
"tfidfB = computeTFIDF(tfB, idfs)\n", | |
"tfidfC = computeTFIDF(tfC, idfs)\n", | |
"\n", | |
"df = pd.DataFrame([tfidfA, tfidfB,tfidfC])" | |
], | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "fKCLpD8cwSgn", | |
"outputId": "0e505d2e-ac3c-42c8-d019-2562ab263e9f", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 141 | |
} | |
}, | |
"source": [ | |
"df" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"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>knitting</th>\n", | |
" <th>passion</th>\n", | |
" <th>hate</th>\n", | |
" <th>hobby</th>\n", | |
" <th>dogs</th>\n", | |
" <th>and</th>\n", | |
" <th>love</th>\n", | |
" <th>my</th>\n", | |
" <th>i</th>\n", | |
" <th>is</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.135155</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.366204</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.135155</td>\n", | |
" <td>0.000000</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>0.081093</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.219722</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.081093</td>\n", | |
" <td>0.081093</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.081093</td>\n", | |
" <td>0.000000</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>0.057924</td>\n", | |
" <td>0.156945</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.156945</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.057924</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.313889</td>\n", | |
" <td>0.000000</td>\n", | |
" <td>0.156945</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" knitting passion hate ... my i is\n", | |
"0 0.000000 0.000000 0.000000 ... 0.000000 0.135155 0.000000\n", | |
"1 0.081093 0.000000 0.219722 ... 0.000000 0.081093 0.000000\n", | |
"2 0.057924 0.156945 0.000000 ... 0.313889 0.000000 0.156945\n", | |
"\n", | |
"[3 rows x 10 columns]" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 22 | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "MtJeY_QuwY32", | |
"outputId": "fd0a5a0e-c39c-439a-d958-d9c965bb60b8", | |
"colab": { | |
"base_uri": "https://localhost:8080/", | |
"height": 141 | |
} | |
}, | |
"source": [ | |
"df_bw" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "execute_result", | |
"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>and</th>\n", | |
" <th>dogs</th>\n", | |
" <th>hate</th>\n", | |
" <th>hobby</th>\n", | |
" <th>is</th>\n", | |
" <th>knitting</th>\n", | |
" <th>love</th>\n", | |
" <th>my</th>\n", | |
" <th>passion</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>1</td>\n", | |
" <td>1</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>0</td>\n", | |
" <td>1</td>\n", | |
" <td>1</td>\n", | |
" <td>1</td>\n", | |
" <td>0</td>\n", | |
" <td>2</td>\n", | |
" <td>1</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" and dogs hate hobby is knitting love my passion\n", | |
"0 0 1 0 0 0 0 1 0 0\n", | |
"1 1 1 1 0 0 1 0 0 0\n", | |
"2 1 0 0 1 1 1 0 2 1" | |
] | |
}, | |
"metadata": { | |
"tags": [] | |
}, | |
"execution_count": 21 | |
} | |
] | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment