|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "metadata": {}, |
| 6 | + "source": [ |
| 7 | + "<h3>Stemming in NLTK</h3>" |
| 8 | + ] |
| 9 | + }, |
| 10 | + { |
| 11 | + "cell_type": "code", |
| 12 | + "execution_count": 4, |
| 13 | + "metadata": {}, |
| 14 | + "outputs": [], |
| 15 | + "source": [ |
| 16 | + "from nltk.stem import PorterStemmer\n", |
| 17 | + "stemmer = PorterStemmer()" |
| 18 | + ] |
| 19 | + }, |
| 20 | + { |
| 21 | + "cell_type": "code", |
| 22 | + "execution_count": 10, |
| 23 | + "metadata": {}, |
| 24 | + "outputs": [ |
| 25 | + { |
| 26 | + "name": "stdout", |
| 27 | + "output_type": "stream", |
| 28 | + "text": [ |
| 29 | + "eating | eat\n", |
| 30 | + "eats | eat\n", |
| 31 | + "eat | eat\n", |
| 32 | + "ate | ate\n", |
| 33 | + "adjustable | adjust\n", |
| 34 | + "rafting | raft\n", |
| 35 | + "ability | abil\n", |
| 36 | + "meeting | meet\n" |
| 37 | + ] |
| 38 | + } |
| 39 | + ], |
| 40 | + "source": [ |
| 41 | + "words = [\"eating\", \"eats\", \"eat\", \"ate\", \"adjustable\", \"rafting\", \"ability\", \"meeting\"]\n", |
| 42 | + "\n", |
| 43 | + "for word in words:\n", |
| 44 | + " print(word, \"|\", stemmer.stem(word))" |
| 45 | + ] |
| 46 | + }, |
| 47 | + { |
| 48 | + "cell_type": "markdown", |
| 49 | + "metadata": {}, |
| 50 | + "source": [ |
| 51 | + "<h3>Lemmatization in Spacy</h3>" |
| 52 | + ] |
| 53 | + }, |
| 54 | + { |
| 55 | + "cell_type": "code", |
| 56 | + "execution_count": 24, |
| 57 | + "metadata": {}, |
| 58 | + "outputs": [], |
| 59 | + "source": [ |
| 60 | + "import spacy" |
| 61 | + ] |
| 62 | + }, |
| 63 | + { |
| 64 | + "cell_type": "code", |
| 65 | + "execution_count": 25, |
| 66 | + "metadata": {}, |
| 67 | + "outputs": [ |
| 68 | + { |
| 69 | + "name": "stdout", |
| 70 | + "output_type": "stream", |
| 71 | + "text": [ |
| 72 | + "eating | eat\n", |
| 73 | + "eats | eat\n", |
| 74 | + "eat | eat\n", |
| 75 | + "ate | eat\n", |
| 76 | + "adjustable | adjustable\n", |
| 77 | + "rafting | rafting\n", |
| 78 | + "ability | ability\n", |
| 79 | + "meeting | meeting\n", |
| 80 | + "better | well\n" |
| 81 | + ] |
| 82 | + } |
| 83 | + ], |
| 84 | + "source": [ |
| 85 | + "nlp = spacy.load(\"en_core_web_sm\")\n", |
| 86 | + "\n", |
| 87 | + "doc = nlp(\"Mando talked for 3 hours although talking isn't his thing\")\n", |
| 88 | + "doc = nlp(\"eating eats eat ate adjustable rafting ability meeting better\")\n", |
| 89 | + "for token in doc:\n", |
| 90 | + " print(token, \" | \", token.lemma_)" |
| 91 | + ] |
| 92 | + }, |
| 93 | + { |
| 94 | + "cell_type": "markdown", |
| 95 | + "metadata": {}, |
| 96 | + "source": [ |
| 97 | + "<h3>Customizing lemmatizer</h3>" |
| 98 | + ] |
| 99 | + }, |
| 100 | + { |
| 101 | + "cell_type": "code", |
| 102 | + "execution_count": 26, |
| 103 | + "metadata": {}, |
| 104 | + "outputs": [ |
| 105 | + { |
| 106 | + "data": { |
| 107 | + "text/plain": [ |
| 108 | + "['tok2vec', 'tagger', 'parser', 'attribute_ruler', 'lemmatizer', 'ner']" |
| 109 | + ] |
| 110 | + }, |
| 111 | + "execution_count": 26, |
| 112 | + "metadata": {}, |
| 113 | + "output_type": "execute_result" |
| 114 | + } |
| 115 | + ], |
| 116 | + "source": [ |
| 117 | + "nlp.pipe_names" |
| 118 | + ] |
| 119 | + }, |
| 120 | + { |
| 121 | + "cell_type": "code", |
| 122 | + "execution_count": 29, |
| 123 | + "metadata": { |
| 124 | + "scrolled": true |
| 125 | + }, |
| 126 | + "outputs": [ |
| 127 | + { |
| 128 | + "name": "stdout", |
| 129 | + "output_type": "stream", |
| 130 | + "text": [ |
| 131 | + "Bro | Brother\n", |
| 132 | + ", | ,\n", |
| 133 | + "you | you\n", |
| 134 | + "wanna | wanna\n", |
| 135 | + "go | go\n", |
| 136 | + "? | ?\n", |
| 137 | + "Brah | Brother\n", |
| 138 | + ", | ,\n", |
| 139 | + "do | do\n", |
| 140 | + "n't | not\n", |
| 141 | + "say | say\n", |
| 142 | + "no | no\n", |
| 143 | + "! | !\n", |
| 144 | + "I | I\n", |
| 145 | + "am | be\n", |
| 146 | + "exhausted | exhaust\n" |
| 147 | + ] |
| 148 | + } |
| 149 | + ], |
| 150 | + "source": [ |
| 151 | + "ar = nlp.get_pipe('attribute_ruler')\n", |
| 152 | + "\n", |
| 153 | + "ar.add([[{\"TEXT\":\"Bro\"}],[{\"TEXT\":\"Brah\"}]],{\"LEMMA\":\"Brother\"})\n", |
| 154 | + "\n", |
| 155 | + "doc = nlp(\"Bro, you wanna go? Brah, don't say no! I am exhausted\")\n", |
| 156 | + "for token in doc:\n", |
| 157 | + " print(token.text, \"|\", token.lemma_)" |
| 158 | + ] |
| 159 | + }, |
| 160 | + { |
| 161 | + "cell_type": "code", |
| 162 | + "execution_count": 35, |
| 163 | + "metadata": {}, |
| 164 | + "outputs": [ |
| 165 | + { |
| 166 | + "data": { |
| 167 | + "text/plain": [ |
| 168 | + "Brah" |
| 169 | + ] |
| 170 | + }, |
| 171 | + "execution_count": 35, |
| 172 | + "metadata": {}, |
| 173 | + "output_type": "execute_result" |
| 174 | + } |
| 175 | + ], |
| 176 | + "source": [ |
| 177 | + "doc[6]" |
| 178 | + ] |
| 179 | + }, |
| 180 | + { |
| 181 | + "cell_type": "code", |
| 182 | + "execution_count": 36, |
| 183 | + "metadata": {}, |
| 184 | + "outputs": [ |
| 185 | + { |
| 186 | + "data": { |
| 187 | + "text/plain": [ |
| 188 | + "'Brother'" |
| 189 | + ] |
| 190 | + }, |
| 191 | + "execution_count": 36, |
| 192 | + "metadata": {}, |
| 193 | + "output_type": "execute_result" |
| 194 | + } |
| 195 | + ], |
| 196 | + "source": [ |
| 197 | + "doc[6].lemma_" |
| 198 | + ] |
| 199 | + } |
| 200 | + ], |
| 201 | + "metadata": { |
| 202 | + "kernelspec": { |
| 203 | + "display_name": "Python 3", |
| 204 | + "language": "python", |
| 205 | + "name": "python3" |
| 206 | + }, |
| 207 | + "language_info": { |
| 208 | + "codemirror_mode": { |
| 209 | + "name": "ipython", |
| 210 | + "version": 3 |
| 211 | + }, |
| 212 | + "file_extension": ".py", |
| 213 | + "mimetype": "text/x-python", |
| 214 | + "name": "python", |
| 215 | + "nbconvert_exporter": "python", |
| 216 | + "pygments_lexer": "ipython3", |
| 217 | + "version": "3.8.5" |
| 218 | + } |
| 219 | + }, |
| 220 | + "nbformat": 4, |
| 221 | + "nbformat_minor": 4 |
| 222 | +} |
0 commit comments