|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "code", |
| 5 | + "execution_count": 1, |
| 6 | + "id": "6d16d334", |
| 7 | + "metadata": {}, |
| 8 | + "outputs": [], |
| 9 | + "source": [ |
| 10 | + "import re" |
| 11 | + ] |
| 12 | + }, |
| 13 | + { |
| 14 | + "cell_type": "code", |
| 15 | + "execution_count": 2, |
| 16 | + "id": "98517c99", |
| 17 | + "metadata": {}, |
| 18 | + "outputs": [ |
| 19 | + { |
| 20 | + "name": "stdout", |
| 21 | + "output_type": "stream", |
| 22 | + "text": [ |
| 23 | + "Exist\n" |
| 24 | + ] |
| 25 | + } |
| 26 | + ], |
| 27 | + "source": [ |
| 28 | + "text = \"This is Rahul Gupta !!! and this is a good day\"\n", |
| 29 | + "if re.search(\"good\",text):\n", |
| 30 | + " print(\"Exist\")\n", |
| 31 | + "else:\n", |
| 32 | + " print(\"not exist\")" |
| 33 | + ] |
| 34 | + }, |
| 35 | + { |
| 36 | + "cell_type": "markdown", |
| 37 | + "id": "e94994da", |
| 38 | + "metadata": {}, |
| 39 | + "source": [ |
| 40 | + "# Tokenization" |
| 41 | + ] |
| 42 | + }, |
| 43 | + { |
| 44 | + "cell_type": "code", |
| 45 | + "execution_count": 3, |
| 46 | + "id": "dcb3a943", |
| 47 | + "metadata": {}, |
| 48 | + "outputs": [ |
| 49 | + { |
| 50 | + "data": { |
| 51 | + "text/plain": [ |
| 52 | + "['',\n", |
| 53 | + " 'one can make a coffee . ',\n", |
| 54 | + " 'one can win the game . ',\n", |
| 55 | + " 'one can make it happen. ']" |
| 56 | + ] |
| 57 | + }, |
| 58 | + "execution_count": 3, |
| 59 | + "metadata": {}, |
| 60 | + "output_type": "execute_result" |
| 61 | + } |
| 62 | + ], |
| 63 | + "source": [ |
| 64 | + "text = \"anyone can make a coffee . anyone can win the game . anyone can make it happen. \"\n", |
| 65 | + "re.split(\"any\",text)" |
| 66 | + ] |
| 67 | + }, |
| 68 | + { |
| 69 | + "cell_type": "code", |
| 70 | + "execution_count": 4, |
| 71 | + "id": "d79f0eec", |
| 72 | + "metadata": {}, |
| 73 | + "outputs": [ |
| 74 | + { |
| 75 | + "data": { |
| 76 | + "text/plain": [ |
| 77 | + "['any', 'any', 'any']" |
| 78 | + ] |
| 79 | + }, |
| 80 | + "execution_count": 4, |
| 81 | + "metadata": {}, |
| 82 | + "output_type": "execute_result" |
| 83 | + } |
| 84 | + ], |
| 85 | + "source": [ |
| 86 | + "re.findall('any',text)" |
| 87 | + ] |
| 88 | + }, |
| 89 | + { |
| 90 | + "cell_type": "code", |
| 91 | + "execution_count": 5, |
| 92 | + "id": "ac9f5620", |
| 93 | + "metadata": {}, |
| 94 | + "outputs": [ |
| 95 | + { |
| 96 | + "data": { |
| 97 | + "text/plain": [ |
| 98 | + "<re.Match object; span=(0, 3), match='any'>" |
| 99 | + ] |
| 100 | + }, |
| 101 | + "execution_count": 5, |
| 102 | + "metadata": {}, |
| 103 | + "output_type": "execute_result" |
| 104 | + } |
| 105 | + ], |
| 106 | + "source": [ |
| 107 | + "re.search('any',text)" |
| 108 | + ] |
| 109 | + }, |
| 110 | + { |
| 111 | + "cell_type": "markdown", |
| 112 | + "id": "251a2da1", |
| 113 | + "metadata": {}, |
| 114 | + "source": [ |
| 115 | + "# Patterns" |
| 116 | + ] |
| 117 | + }, |
| 118 | + { |
| 119 | + "cell_type": "code", |
| 120 | + "execution_count": 23, |
| 121 | + "id": "34b688b0", |
| 122 | + "metadata": {}, |
| 123 | + "outputs": [ |
| 124 | + { |
| 125 | + "data": { |
| 126 | + "text/plain": [ |
| 127 | + "['A', 'A', 'A', 'A', 'A', 'A', 'A', 'A', 'A', 'A']" |
| 128 | + ] |
| 129 | + }, |
| 130 | + "execution_count": 23, |
| 131 | + "metadata": {}, |
| 132 | + "output_type": "execute_result" |
| 133 | + } |
| 134 | + ], |
| 135 | + "source": [ |
| 136 | + "grades = \"ABCAABCCCDAABBBBCCAABCAAABCCCCD\"\n", |
| 137 | + "re.findall('A',grades)" |
| 138 | + ] |
| 139 | + }, |
| 140 | + { |
| 141 | + "cell_type": "code", |
| 142 | + "execution_count": 10, |
| 143 | + "id": "53651790", |
| 144 | + "metadata": {}, |
| 145 | + "outputs": [ |
| 146 | + { |
| 147 | + "data": { |
| 148 | + "text/plain": [ |
| 149 | + "['A',\n", |
| 150 | + " 'B',\n", |
| 151 | + " 'A',\n", |
| 152 | + " 'A',\n", |
| 153 | + " 'B',\n", |
| 154 | + " 'A',\n", |
| 155 | + " 'A',\n", |
| 156 | + " 'B',\n", |
| 157 | + " 'B',\n", |
| 158 | + " 'B',\n", |
| 159 | + " 'B',\n", |
| 160 | + " 'A',\n", |
| 161 | + " 'A',\n", |
| 162 | + " 'B',\n", |
| 163 | + " 'A',\n", |
| 164 | + " 'A',\n", |
| 165 | + " 'B']" |
| 166 | + ] |
| 167 | + }, |
| 168 | + "execution_count": 10, |
| 169 | + "metadata": {}, |
| 170 | + "output_type": "execute_result" |
| 171 | + } |
| 172 | + ], |
| 173 | + "source": [ |
| 174 | + "re.findall('[AB]',grades)" |
| 175 | + ] |
| 176 | + }, |
| 177 | + { |
| 178 | + "cell_type": "code", |
| 179 | + "execution_count": 16, |
| 180 | + "id": "031ea978", |
| 181 | + "metadata": {}, |
| 182 | + "outputs": [ |
| 183 | + { |
| 184 | + "data": { |
| 185 | + "text/plain": [ |
| 186 | + "['AB', 'AB', 'AB', 'AB', 'AB']" |
| 187 | + ] |
| 188 | + }, |
| 189 | + "execution_count": 16, |
| 190 | + "metadata": {}, |
| 191 | + "output_type": "execute_result" |
| 192 | + } |
| 193 | + ], |
| 194 | + "source": [ |
| 195 | + "re.findall('[A][B]',grades)" |
| 196 | + ] |
| 197 | + }, |
| 198 | + { |
| 199 | + "cell_type": "code", |
| 200 | + "execution_count": 19, |
| 201 | + "id": "a425cc1c", |
| 202 | + "metadata": {}, |
| 203 | + "outputs": [ |
| 204 | + { |
| 205 | + "data": { |
| 206 | + "text/plain": [ |
| 207 | + "['AB', 'AB', 'CD', 'AB', 'AB', 'AB', 'CD']" |
| 208 | + ] |
| 209 | + }, |
| 210 | + "execution_count": 19, |
| 211 | + "metadata": {}, |
| 212 | + "output_type": "execute_result" |
| 213 | + } |
| 214 | + ], |
| 215 | + "source": [ |
| 216 | + "re.findall('AB|CD',grades)" |
| 217 | + ] |
| 218 | + }, |
| 219 | + { |
| 220 | + "cell_type": "code", |
| 221 | + "execution_count": 20, |
| 222 | + "id": "18f63cd0", |
| 223 | + "metadata": {}, |
| 224 | + "outputs": [ |
| 225 | + { |
| 226 | + "data": { |
| 227 | + "text/plain": [ |
| 228 | + "['B',\n", |
| 229 | + " 'C',\n", |
| 230 | + " 'B',\n", |
| 231 | + " 'C',\n", |
| 232 | + " 'C',\n", |
| 233 | + " 'C',\n", |
| 234 | + " 'D',\n", |
| 235 | + " 'B',\n", |
| 236 | + " 'B',\n", |
| 237 | + " 'B',\n", |
| 238 | + " 'B',\n", |
| 239 | + " 'C',\n", |
| 240 | + " 'C',\n", |
| 241 | + " 'B',\n", |
| 242 | + " 'C',\n", |
| 243 | + " 'B',\n", |
| 244 | + " 'C',\n", |
| 245 | + " 'C',\n", |
| 246 | + " 'C',\n", |
| 247 | + " 'C',\n", |
| 248 | + " 'D']" |
| 249 | + ] |
| 250 | + }, |
| 251 | + "execution_count": 20, |
| 252 | + "metadata": {}, |
| 253 | + "output_type": "execute_result" |
| 254 | + } |
| 255 | + ], |
| 256 | + "source": [ |
| 257 | + "re.findall('[^A]',grades)" |
| 258 | + ] |
| 259 | + }, |
| 260 | + { |
| 261 | + "cell_type": "markdown", |
| 262 | + "id": "7f7a1e84", |
| 263 | + "metadata": {}, |
| 264 | + "source": [ |
| 265 | + "# Quantifiers" |
| 266 | + ] |
| 267 | + }, |
| 268 | + { |
| 269 | + "cell_type": "code", |
| 270 | + "execution_count": 24, |
| 271 | + "id": "c204afed", |
| 272 | + "metadata": {}, |
| 273 | + "outputs": [ |
| 274 | + { |
| 275 | + "data": { |
| 276 | + "text/plain": [ |
| 277 | + "['AA', 'AA', 'AA', 'AAA']" |
| 278 | + ] |
| 279 | + }, |
| 280 | + "execution_count": 24, |
| 281 | + "metadata": {}, |
| 282 | + "output_type": "execute_result" |
| 283 | + } |
| 284 | + ], |
| 285 | + "source": [ |
| 286 | + "re.findall('A{2,10}',grades)" |
| 287 | + ] |
| 288 | + }, |
| 289 | + { |
| 290 | + "cell_type": "code", |
| 291 | + "execution_count": 31, |
| 292 | + "id": "9c357177", |
| 293 | + "metadata": {}, |
| 294 | + "outputs": [ |
| 295 | + { |
| 296 | + "data": { |
| 297 | + "text/plain": [ |
| 298 | + "['AA', 'AA', 'AA', 'AAA']" |
| 299 | + ] |
| 300 | + }, |
| 301 | + "execution_count": 31, |
| 302 | + "metadata": {}, |
| 303 | + "output_type": "execute_result" |
| 304 | + } |
| 305 | + ], |
| 306 | + "source": [ |
| 307 | + "re.findall('A{2,3}',grades)" |
| 308 | + ] |
| 309 | + }, |
| 310 | + { |
| 311 | + "cell_type": "code", |
| 312 | + "execution_count": 32, |
| 313 | + "id": "e8bcdf93", |
| 314 | + "metadata": {}, |
| 315 | + "outputs": [ |
| 316 | + { |
| 317 | + "data": { |
| 318 | + "text/plain": [ |
| 319 | + "['AABCCCD', 'AAABCCCCD']" |
| 320 | + ] |
| 321 | + }, |
| 322 | + "execution_count": 32, |
| 323 | + "metadata": {}, |
| 324 | + "output_type": "execute_result" |
| 325 | + } |
| 326 | + ], |
| 327 | + "source": [ |
| 328 | + "re.findall('A{1,10}B{1,10}C{1,10}D{1,10}',grades)" |
| 329 | + ] |
| 330 | + }, |
| 331 | + { |
| 332 | + "cell_type": "code", |
| 333 | + "execution_count": 40, |
| 334 | + "id": "5525b766", |
| 335 | + "metadata": {}, |
| 336 | + "outputs": [ |
| 337 | + { |
| 338 | + "name": "stdout", |
| 339 | + "output_type": "stream", |
| 340 | + "text": [ |
| 341 | + "HELLO Rahul !!!\n" |
| 342 | + ] |
| 343 | + } |
| 344 | + ], |
| 345 | + "source": [ |
| 346 | + "text = 'rahul@gmail.com'\n", |
| 347 | + "a = re.split(\"@\",text)\n", |
| 348 | + "name = a[0].capitalize()\n", |
| 349 | + "print(f\"HELLO {name} !!!\")" |
| 350 | + ] |
| 351 | + } |
| 352 | + ], |
| 353 | + "metadata": { |
| 354 | + "kernelspec": { |
| 355 | + "display_name": "Python 3 (ipykernel)", |
| 356 | + "language": "python", |
| 357 | + "name": "python3" |
| 358 | + }, |
| 359 | + "language_info": { |
| 360 | + "codemirror_mode": { |
| 361 | + "name": "ipython", |
| 362 | + "version": 3 |
| 363 | + }, |
| 364 | + "file_extension": ".py", |
| 365 | + "mimetype": "text/x-python", |
| 366 | + "name": "python", |
| 367 | + "nbconvert_exporter": "python", |
| 368 | + "pygments_lexer": "ipython3", |
| 369 | + "version": "3.11.4" |
| 370 | + } |
| 371 | + }, |
| 372 | + "nbformat": 4, |
| 373 | + "nbformat_minor": 5 |
| 374 | +} |
0 commit comments