|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "metadata": {}, |
| 6 | + "source": [ |
| 7 | + "## 5分钟用Python生成极品家丁全本小说词云\n", |
| 8 | + "\n", |
| 9 | + "使用如下Python库:\n", |
| 10 | + "1. jieba:中文分词库,自然语言处理必备,https://github.com/fxsjy/jieba\n", |
| 11 | + "2. imageio:读取图片,或者写出图片,http://imageio.github.io\n", |
| 12 | + "3. wordcloud:词云生成,可以设定背景图片,https://github.com/amueller/word_cloud" |
| 13 | + ] |
| 14 | + }, |
| 15 | + { |
| 16 | + "cell_type": "code", |
| 17 | + "execution_count": 1, |
| 18 | + "metadata": {}, |
| 19 | + "outputs": [], |
| 20 | + "source": [ |
| 21 | + "import jieba\n", |
| 22 | + "import imageio\n", |
| 23 | + "import wordcloud" |
| 24 | + ] |
| 25 | + }, |
| 26 | + { |
| 27 | + "cell_type": "markdown", |
| 28 | + "metadata": {}, |
| 29 | + "source": [ |
| 30 | + "## 1、将《极品家丁》小说文字分词" |
| 31 | + ] |
| 32 | + }, |
| 33 | + { |
| 34 | + "cell_type": "code", |
| 35 | + "execution_count": 2, |
| 36 | + "metadata": {}, |
| 37 | + "outputs": [], |
| 38 | + "source": [ |
| 39 | + "fin = open('jipinjiading.txt', encoding='utf-8')\n", |
| 40 | + "# 读取txt全部文字\n", |
| 41 | + "txt = fin.read()" |
| 42 | + ] |
| 43 | + }, |
| 44 | + { |
| 45 | + "cell_type": "code", |
| 46 | + "execution_count": 3, |
| 47 | + "metadata": {}, |
| 48 | + "outputs": [ |
| 49 | + { |
| 50 | + "data": { |
| 51 | + "text/plain": [ |
| 52 | + "'\\ufeff《极品家丁》 / 作者:禹岩\\n简介:【本书阅读方法】参考《唐伯虎点秋香》!年轻的销售经理,因为一次意外经历,来到了一个完全不同的世界,成为萧家大宅里一名光荣的——家丁!暮晓春来迟先于百花知岁岁种桃树'" |
| 53 | + ] |
| 54 | + }, |
| 55 | + "execution_count": 3, |
| 56 | + "metadata": {}, |
| 57 | + "output_type": "execute_result" |
| 58 | + } |
| 59 | + ], |
| 60 | + "source": [ |
| 61 | + "txt[:100]" |
| 62 | + ] |
| 63 | + }, |
| 64 | + { |
| 65 | + "cell_type": "code", |
| 66 | + "execution_count": 4, |
| 67 | + "metadata": {}, |
| 68 | + "outputs": [ |
| 69 | + { |
| 70 | + "name": "stderr", |
| 71 | + "output_type": "stream", |
| 72 | + "text": [ |
| 73 | + "Building prefix dict from the default dictionary ...\n", |
| 74 | + "Loading model from cache C:\\Users\\ADMINI~1\\AppData\\Local\\Temp\\jieba.cache\n", |
| 75 | + "Loading model cost 0.703 seconds.\n", |
| 76 | + "Prefix dict has been built succesfully.\n" |
| 77 | + ] |
| 78 | + } |
| 79 | + ], |
| 80 | + "source": [ |
| 81 | + "# 使用jieba分词,精确模式(还有全模式和搜索引擎模式)\n", |
| 82 | + "wordlist = jieba.lcut(txt)" |
| 83 | + ] |
| 84 | + }, |
| 85 | + { |
| 86 | + "cell_type": "code", |
| 87 | + "execution_count": 5, |
| 88 | + "metadata": {}, |
| 89 | + "outputs": [ |
| 90 | + { |
| 91 | + "data": { |
| 92 | + "text/plain": [ |
| 93 | + "list" |
| 94 | + ] |
| 95 | + }, |
| 96 | + "execution_count": 5, |
| 97 | + "metadata": {}, |
| 98 | + "output_type": "execute_result" |
| 99 | + } |
| 100 | + ], |
| 101 | + "source": [ |
| 102 | + "type(wordlist)" |
| 103 | + ] |
| 104 | + }, |
| 105 | + { |
| 106 | + "cell_type": "code", |
| 107 | + "execution_count": 6, |
| 108 | + "metadata": {}, |
| 109 | + "outputs": [ |
| 110 | + { |
| 111 | + "data": { |
| 112 | + "text/plain": [ |
| 113 | + "['\\ufeff', '《', '极品', '家丁', '》', ' ', '/', ' ', '作者', ':']" |
| 114 | + ] |
| 115 | + }, |
| 116 | + "execution_count": 6, |
| 117 | + "metadata": {}, |
| 118 | + "output_type": "execute_result" |
| 119 | + } |
| 120 | + ], |
| 121 | + "source": [ |
| 122 | + "wordlist[:10]" |
| 123 | + ] |
| 124 | + }, |
| 125 | + { |
| 126 | + "cell_type": "code", |
| 127 | + "execution_count": 7, |
| 128 | + "metadata": {}, |
| 129 | + "outputs": [], |
| 130 | + "source": [ |
| 131 | + "string = \" \".join(wordlist)" |
| 132 | + ] |
| 133 | + }, |
| 134 | + { |
| 135 | + "cell_type": "markdown", |
| 136 | + "metadata": {}, |
| 137 | + "source": [ |
| 138 | + "## 2、读取图片-用于词云的背景图" |
| 139 | + ] |
| 140 | + }, |
| 141 | + { |
| 142 | + "cell_type": "code", |
| 143 | + "execution_count": 8, |
| 144 | + "metadata": {}, |
| 145 | + "outputs": [], |
| 146 | + "source": [ |
| 147 | + "image = imageio.imread(\"python-logo.jpg\")" |
| 148 | + ] |
| 149 | + }, |
| 150 | + { |
| 151 | + "cell_type": "code", |
| 152 | + "execution_count": 9, |
| 153 | + "metadata": {}, |
| 154 | + "outputs": [ |
| 155 | + { |
| 156 | + "data": { |
| 157 | + "text/plain": [ |
| 158 | + "(600, 600, 3)" |
| 159 | + ] |
| 160 | + }, |
| 161 | + "execution_count": 9, |
| 162 | + "metadata": {}, |
| 163 | + "output_type": "execute_result" |
| 164 | + } |
| 165 | + ], |
| 166 | + "source": [ |
| 167 | + "# 该图片是600行、600列的尺寸,每个相似点由3个数字组成\n", |
| 168 | + "image.shape" |
| 169 | + ] |
| 170 | + }, |
| 171 | + { |
| 172 | + "cell_type": "markdown", |
| 173 | + "metadata": {}, |
| 174 | + "source": [ |
| 175 | + "<div style=\"text-align:center\">Python-logo图片</div>\n", |
| 176 | + "<img style=\"width:200px;height:200px\" src=\"python-logo.jpg\"/>" |
| 177 | + ] |
| 178 | + }, |
| 179 | + { |
| 180 | + "cell_type": "code", |
| 181 | + "execution_count": 10, |
| 182 | + "metadata": {}, |
| 183 | + "outputs": [ |
| 184 | + { |
| 185 | + "data": { |
| 186 | + "text/plain": [ |
| 187 | + "Array([255, 255, 255], dtype=uint8)" |
| 188 | + ] |
| 189 | + }, |
| 190 | + "execution_count": 10, |
| 191 | + "metadata": {}, |
| 192 | + "output_type": "execute_result" |
| 193 | + } |
| 194 | + ], |
| 195 | + "source": [ |
| 196 | + "# 这三个数字组合起来代表一个颜色\n", |
| 197 | + "# 比如255、255、255是白色的\n", |
| 198 | + "image[0][0]" |
| 199 | + ] |
| 200 | + }, |
| 201 | + { |
| 202 | + "cell_type": "code", |
| 203 | + "execution_count": 11, |
| 204 | + "metadata": {}, |
| 205 | + "outputs": [ |
| 206 | + { |
| 207 | + "data": { |
| 208 | + "text/plain": [ |
| 209 | + "Array([ 55, 113, 163], dtype=uint8)" |
| 210 | + ] |
| 211 | + }, |
| 212 | + "execution_count": 11, |
| 213 | + "metadata": {}, |
| 214 | + "output_type": "execute_result" |
| 215 | + } |
| 216 | + ], |
| 217 | + "source": [ |
| 218 | + "# 图片顶部,中间的位置\n", |
| 219 | + "image[200][300]" |
| 220 | + ] |
| 221 | + }, |
| 222 | + { |
| 223 | + "cell_type": "markdown", |
| 224 | + "metadata": {}, |
| 225 | + "source": [ |
| 226 | + "<div style=\"text-align:center\">像素图片:</div>\n", |
| 227 | + "<div style=\"text-align:center\">在这个网站转换:https://www.sioe.cn/yingyong/yanse-rgb-16/</div>\n", |
| 228 | + "<img src=\"python-logo-pix01.png\"/>" |
| 229 | + ] |
| 230 | + }, |
| 231 | + { |
| 232 | + "cell_type": "code", |
| 233 | + "execution_count": 12, |
| 234 | + "metadata": {}, |
| 235 | + "outputs": [ |
| 236 | + { |
| 237 | + "data": { |
| 238 | + "text/plain": [ |
| 239 | + "Array([255, 213, 69], dtype=uint8)" |
| 240 | + ] |
| 241 | + }, |
| 242 | + "execution_count": 12, |
| 243 | + "metadata": {}, |
| 244 | + "output_type": "execute_result" |
| 245 | + } |
| 246 | + ], |
| 247 | + "source": [ |
| 248 | + "# 图片底部,中间的位置\n", |
| 249 | + "image[500][200]" |
| 250 | + ] |
| 251 | + }, |
| 252 | + { |
| 253 | + "cell_type": "markdown", |
| 254 | + "metadata": {}, |
| 255 | + "source": [ |
| 256 | + "<div style=\"text-align:center\">像素图片:</div>\n", |
| 257 | + "<div style=\"text-align:center\">在这个网站转换:https://www.sioe.cn/yingyong/yanse-rgb-16/</div>\n", |
| 258 | + "<img src=\"python-logo-pix02.png\"/>" |
| 259 | + ] |
| 260 | + }, |
| 261 | + { |
| 262 | + "cell_type": "markdown", |
| 263 | + "metadata": {}, |
| 264 | + "source": [ |
| 265 | + "## 3、生成词云图片" |
| 266 | + ] |
| 267 | + }, |
| 268 | + { |
| 269 | + "cell_type": "code", |
| 270 | + "execution_count": 13, |
| 271 | + "metadata": {}, |
| 272 | + "outputs": [], |
| 273 | + "source": [ |
| 274 | + "wc = wordcloud.WordCloud(width=600,\n", |
| 275 | + " height=600,\n", |
| 276 | + " background_color='white',\n", |
| 277 | + " # 指定字体路径,中文需要指定\n", |
| 278 | + " font_path='msyh.ttc',\n", |
| 279 | + " # mask 指定词云形状图片,默认为矩形\n", |
| 280 | + " mask=image,\n", |
| 281 | + " # 提高清晰度\n", |
| 282 | + " scale=15)" |
| 283 | + ] |
| 284 | + }, |
| 285 | + { |
| 286 | + "cell_type": "code", |
| 287 | + "execution_count": 14, |
| 288 | + "metadata": {}, |
| 289 | + "outputs": [ |
| 290 | + { |
| 291 | + "data": { |
| 292 | + "text/plain": [ |
| 293 | + "<wordcloud.wordcloud.WordCloud at 0x186068755c8>" |
| 294 | + ] |
| 295 | + }, |
| 296 | + "execution_count": 14, |
| 297 | + "metadata": {}, |
| 298 | + "output_type": "execute_result" |
| 299 | + } |
| 300 | + ], |
| 301 | + "source": [ |
| 302 | + "# 将string变量传入wc的generate()方法\n", |
| 303 | + "# 给词云输入文字\n", |
| 304 | + "wc.generate(string)" |
| 305 | + ] |
| 306 | + }, |
| 307 | + { |
| 308 | + "cell_type": "code", |
| 309 | + "execution_count": 15, |
| 310 | + "metadata": {}, |
| 311 | + "outputs": [ |
| 312 | + { |
| 313 | + "data": { |
| 314 | + "text/plain": [ |
| 315 | + "<wordcloud.wordcloud.WordCloud at 0x186068755c8>" |
| 316 | + ] |
| 317 | + }, |
| 318 | + "execution_count": 15, |
| 319 | + "metadata": {}, |
| 320 | + "output_type": "execute_result" |
| 321 | + } |
| 322 | + ], |
| 323 | + "source": [ |
| 324 | + "# 将词云图片导出到当前文件夹\n", |
| 325 | + "wc.to_file('result_wordcloud.png')" |
| 326 | + ] |
| 327 | + }, |
| 328 | + { |
| 329 | + "cell_type": "markdown", |
| 330 | + "metadata": {}, |
| 331 | + "source": [ |
| 332 | + "<img src=\"result_wordcloud.png\" style=\"width:400px;height:400px\">" |
| 333 | + ] |
| 334 | + }, |
| 335 | + { |
| 336 | + "cell_type": "code", |
| 337 | + "execution_count": null, |
| 338 | + "metadata": {}, |
| 339 | + "outputs": [], |
| 340 | + "source": [] |
| 341 | + } |
| 342 | + ], |
| 343 | + "metadata": { |
| 344 | + "kernelspec": { |
| 345 | + "display_name": "Python 3", |
| 346 | + "language": "python", |
| 347 | + "name": "python3" |
| 348 | + }, |
| 349 | + "language_info": { |
| 350 | + "codemirror_mode": { |
| 351 | + "name": "ipython", |
| 352 | + "version": 3 |
| 353 | + }, |
| 354 | + "file_extension": ".py", |
| 355 | + "mimetype": "text/x-python", |
| 356 | + "name": "python", |
| 357 | + "nbconvert_exporter": "python", |
| 358 | + "pygments_lexer": "ipython3", |
| 359 | + "version": "3.7.4" |
| 360 | + } |
| 361 | + }, |
| 362 | + "nbformat": 4, |
| 363 | + "nbformat_minor": 2 |
| 364 | +} |
0 commit comments