08. Vectorization.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Count Vectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "CountVectorizer(analyzer='word', binary=False, decode_error='strict',\n",
       "                dtype=<class 'numpy.int64'>, encoding='utf-8', input='content',\n",
       "                lowercase=True, max_df=1.0, max_features=None, min_df=1,\n",
       "                ngram_range=(1, 1), preprocessor=None, stop_words=None,\n",
       "                strip_accents=None, token_pattern='(?u)\\\\b\\\\w\\\\w+\\\\b',\n",
       "                tokenizer=None, vocabulary=None)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text = [\"The quick brown fox jumped over the lazy dog.\"]\n",
    "vectorizer = CountVectorizer()\n",
    "vectorizer.fit(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'the': 7, 'quick': 6, 'brown': 0, 'fox': 2, 'jumped': 3, 'over': 5, 'lazy': 4, 'dog': 1}\n",
      "(1, 8)\n",
      "<class 'scipy.sparse.csr.csr_matrix'>\n",
      "[[1 1 1 1 1 1 1 2]]\n"
     ]
    }
   ],
   "source": [
    "print(vectorizer.vocabulary_)\n",
    "vector = vectorizer.transform(text)\n",
    "print(vector.shape)\n",
    "print(type(vector))\n",
    "print(vector.toarray())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0 0 0 0 0 0 0 1]]\n"
     ]
    }
   ],
   "source": [
    "text2 = [\"the puppy\"]\n",
    "vector = vectorizer.transform(text2)\n",
    "print(vector.toarray())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Tf-idf Vectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import TfidfVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "text = [\"The quick brown fox jumped over the lazy dog.\", \"The dog.\", \"The fox\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'the': 7, 'quick': 6, 'brown': 0, 'fox': 2, 'jumped': 3, 'over': 5, 'lazy': 4, 'dog': 1}\n",
      "[1.69314718 1.28768207 1.28768207 1.69314718 1.69314718 1.69314718\n",
      " 1.69314718 1.        ]\n"
     ]
    }
   ],
   "source": [
    "vectorizer = TfidfVectorizer()\n",
    "vectorizer.fit(text)\n",
    "print(vectorizer.vocabulary_)\n",
    "print(vectorizer.idf_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1, 8)\n",
      "[[0.36388646 0.27674503 0.27674503 0.36388646 0.36388646 0.36388646\n",
      "  0.36388646 0.42983441]]\n"
     ]
    }
   ],
   "source": [
    "vector = vectorizer.transform([text[0]])\n",
    "print(vector.shape)\n",
    "print(vector.toarray())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hashing Vectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import HashingVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1, 20)\n",
      "[[ 0.          0.          0.          0.          0.          0.30151134\n",
      "   0.         -0.30151134  0.30151134  0.         -0.30151134  0.30151134\n",
      "   0.         -0.30151134  0.         -0.30151134  0.          0.\n",
      "  -0.60302269  0.        ]]\n"
     ]
    }
   ],
   "source": [
    "text = [\"The quick brown fox jumprd over the lazy dog.\"]\n",
    "vectorizer = HashingVectorizer(n_features=20)\n",
    "vector = vectorizer.transform(text)\n",
    "print(vector.shape)\n",
    "print(vector.toarray())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}