From e54d92f552f64154be535d8480b1f105228dcb7c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=90=B4=E6=B2=82=E9=92=8A?= <13190667+Yizhao_Wu4926@user.noreply.gitee.com> Date: Sun, 16 Jul 2023 06:37:39 +0000 Subject: [PATCH] =?UTF-8?q?=E5=88=A0=E9=99=A4=E6=96=87=E4=BB=B6=20?= =?UTF-8?q?=E8=B4=AD=E7=89=A9=E8=AF=84=E8=AE=BA=20=E6=83=85=E6=84=9F?= =?UTF-8?q?=E5=88=86=E7=B1=BB/main.ipynb?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- 购物评论 情感分类/main.ipynb | 828 ----------------------------------- 1 file changed, 828 deletions(-) delete mode 100644 购物评论 情感分类/main.ipynb diff --git a/购物评论 情感分类/main.ipynb b/购物评论 情感分类/main.ipynb deleted file mode 100644 index c55d334..0000000 --- a/购物评论 情感分类/main.ipynb +++ /dev/null @@ -1,828 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": 77, - "metadata": {}, - "outputs": [], - "source": [ - "# 导入需要的包\n", - "from collections import defaultdict\n", - "import pandas as pd\n", - "import re\n", - "import jieba\n", - "from sklearn.feature_extraction.text import CountVectorizer\n", - "from sklearn.model_selection import train_test_split\n", - "from sklearn.svm import SVC\n", - "from sklearn.metrics import classification_report\n", - "from gensim.models.word2vec import Word2Vec\n" - ] - }, - { - "cell_type": "code", - "execution_count": 78, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
rawy
0感觉用这个手机下载MP3听很方便，用T-Flash卡装上歌，就可以当一个小MP3用了，很不错...1
1外观美观，速度也不错。上面一排触摸键挺实用。应该对得起这个价格。当然再降点大家肯定也不反对。...1
2我刚拿到书，也没有仔细阅读，就是粗粗的翻了点，觉得还行。里面是蓝黑两种颜色的，有些单词的下面...1
3对于二胡曲的精选，应该出版一个系列套装，可分别出售，单独购买。精品二胡曲是有年代和阶段性的，...1
4用了一年半的 e680 终于送小偷了。刚刚买了一台e850，用了三天，说说我自己的感受。1：...1
\n", - "
" - ], - "text/plain": [ - " raw y\n", - "0 感觉用这个手机下载MP3听很方便，用T-Flash卡装上歌，就可以当一个小MP3用了，很不错... 1\n", - "1 外观美观，速度也不错。上面一排触摸键挺实用。应该对得起这个价格。当然再降点大家肯定也不反对。... 1\n", - "2 我刚拿到书，也没有仔细阅读，就是粗粗的翻了点，觉得还行。里面是蓝黑两种颜色的，有些单词的下面... 1\n", - "3 对于二胡曲的精选，应该出版一个系列套装，可分别出售，单独购买。精品二胡曲是有年代和阶段性的，... 1\n", - "4 用了一年半的 e680 终于送小偷了。刚刚买了一台e850，用了三天，说说我自己的感受。1：... 1" - ] - }, - "execution_count": 78, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# 读入数据\n", - "df_pos = pd.read_excel(r\"data/购物评论.xlsx\", sheet_name=\"正向\", header=None)\n", - "df_pos[\"y\"] = 1\n", - "df_neg = pd.read_excel(r\"data/购物评论.xlsx\", sheet_name=\"负向\", header=None)\n", - "df_neg[\"y\"] = 0\n", - "# 将正样本和负样本拼接在一起\n", - "df = df_pos.append(df_neg, ignore_index=True)\n", - "df.columns = [\"raw\", \"y\"]\n", - "\n", - "df.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 79, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "0 [感觉, 用, 这个, 手机, 下载, MP3, 听, 很, 方便, ，, 用, T, -,...\n", - "1 [外观, 美观, ，, 速度, 也, 不错, 。, 上面, 一排, 触摸, 键, 挺, 实用...\n", - "2 [我刚, 拿到, 书, ，, 也, 没有, 仔细阅读, ，, 就是, 粗粗, 的, 翻, 了...\n", - "3 [对于, 二胡曲, 的, 精选, ，, 应该, 出版, 一个系列, 套装, ，, 可, 分别...\n", - "4 [用, 了, 一年, 半, 的, , e680, , 终于, 送, 小偷, 了, 。, ...\n", - "Name: raw, dtype: object" - ] - }, - "execution_count": 79, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# 数据清洗\n", - "# 由于有些情感词本身也是停用词。因此这里仅去掉换行和空字符，不做其他的清理工作，以保留情感词。\n", - "df_cut = df[\"raw\"].apply(lambda x: re.sub('\\n', '', x))\n", - "# 将清洗后的文本用jieba.lcut转换为list形式\n", - "df_cut = df_cut.apply(jieba.lcut)\n", - "\n", - "df_cut.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 80, - "metadata": {}, - "outputs": [], - "source": [ - "# 基于词典的情感分析\n", - "# 读入并创建情感词典\n", - "sentiment_dict = defaultdict(float) # 方便处理不存在于词典中的关键字\n", - "# 使用with open以节约内存\n", - "with open(r\"data\\BosonNLP_sentiment_score.txt\", \"r\", encoding=\"utf-8\") as sen_file:\n", - " for line in sen_file:\n", - " try:\n", - " key, value = line.split(\" \") # 直接运行会有奇怪的问题出现\n", - " except Exception:\n", - " # 直接跳过有问题的行\n", - " pass\n", - " else:\n", - " sentiment_dict[key] = float(value) # 正常情况" - ] - }, - { - "cell_type": "code", - "execution_count": 81, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "0 21.581138\n", - "1 14.952362\n", - "2 6.245357\n", - "3 30.980969\n", - "4 36.519372\n", - "Name: raw, dtype: float64" - ] - }, - "execution_count": 81, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# 以最简单的直接匹配的方式进行情感打分\n", - "def get_score(words):\n", - " return sum(sentiment_dict[word] for word in words)\n", - "\n", - "\n", - "y = df_cut.apply(get_score)\n", - "\n", - "y.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 82, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "该模型的准确率为： 0.6764648722184433\n" - ] - } - ], - "source": [ - "# 根据分数>0为正向、分数<0为负向判定准确率\n", - "precise = lambda x: (df[\"y\"][x] == 1 and score[x] > 0) or (df[\"y\"][x] == 0 and score[x] <= 0)\n", - "# 准确度评估\n", - "print(\"该模型的准确度为：\", sum(1 for i in range(len(df)) if precise(i)) / len(df))" - ] - }, - { - "cell_type": "code", - "execution_count": 83, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "我谢谢蒙牛！多一层体贴，多一层爱护！双重保护。\n", - "正向\n", - " 蒙牛是店大欺客 至少态度比蒙牛好～～后期赶紧整改！\n", - "正向\n", - "宝贝收到了，孩子爱吃，敏感肌能用，很启发大脑，提升睡眠质量，五星好评。\n", - "正向\n", - "五星好评，分期付清\n", - "正向\n", - "对得起我们吗？rnm，退钱！\n", - "负向\n" - ] - } - ], - "source": [ - "def score_pred(string):\n", - " words = \" \".join(jieba.cut(string))\n", - " # 预测并输出\n", - " result = 1 if get_score(string) > 0 else 0\n", - " if result == 1:\n", - " print(\"正向\")\n", - " else:\n", - " print(\"负向\")\n", - "\n", - "\n", - "# 使用上述模型进行预测\n", - "test_comment = [\n", - " \"我谢谢蒙牛！多一层体贴，多一层爱护！双重保护。\",\n", - " \" 蒙牛是店大欺客 至少态度比蒙牛好～～后期赶紧整改！\",\n", - " \"宝贝收到了，孩子爱吃，敏感肌能用，很启发大脑，提升睡眠质量，五星好评。\",\n", - " \"五星好评，分期付清\",\n", - " \"对得起我们吗？rnm，退钱！\"\n", - "]\n", - "for comment in test_comment:\n", - " print(comment)\n", - " score_pred(comment)" - ] - }, - { - "cell_type": "code", - "execution_count": 84, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "0 感觉 用 这个 手机 下载 MP3 听 很 方便 ， 用 T - Flash 卡装 上 歌 ...\n", - "1 外观 美观 ， 速度 也 不错 。 上面 一排 触摸 键 挺 实用 。 应该 对得起 这个 ...\n", - "2 我刚 拿到 书 ， 也 没有 仔细阅读 ， 就是 粗粗 的 翻 了 点 ， 觉得 还 行 。...\n", - "3 对于 二胡曲 的 精选 ， 应该 出版 一个系列 套装 ， 可 分别 出售 ， 单独 购买 ...\n", - "4 用 了 一年 半 的 e680 终于 送 小偷 了 。 刚刚 买 了 一台 e850...\n", - "Name: raw, dtype: object" - ] - }, - "execution_count": 84, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# 基于词袋模型进行情感分析\n", - "# 将之前用jieba分好的列表转化为空格分隔的字符串，以方便使用词袋\n", - "df_cleantxt = df_cut.apply(lambda x: \" \".join(x))\n", - "\n", - "df_cleantxt.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 85, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "<20582x12014 sparse matrix of type ''\n", - "\twith 513919 stored elements in Compressed Sparse Row format>" - ] - }, - "execution_count": 85, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "countvec = CountVectorizer(min_df = 5) # 特征向量，出现5次以上的才纳入\n", - "# 转化为词频矩阵\n", - "wordmtx = countvec.fit_transform(df_cleantxt)\n", - "\n", - "wordmtx # 一个稀疏矩阵对象，无法直接显示" - ] - }, - { - "cell_type": "code", - "execution_count": 86, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[LibSVM]" - ] - }, - { - "data": { - "text/plain": [ - "SVC(verbose=True)" - ] - }, - "execution_count": 86, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# 按照7：3的比例生成训练集和测试集，并使用SVM进行建模\n", - "x_train, x_test, y_train, y_test = train_test_split(wordmtx, df.y, test_size=0.3, random_state=0) # 指定random_state可以确保每次分割出的训练集和测试集相同\n", - "# 创建分类器，使用径向基核函数作为核函数\n", - "clf = SVC(kernel=\"rbf\", verbose=True)\n", - "# 训练分类器（耗时很长，慎点）\n", - "clf.fit(x_train, y_train)" - ] - }, - { - "cell_type": "code", - "execution_count": 87, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "该分类器的准确度为： 0.9551606857777469\n" - ] - } - ], - "source": [ - "# 准确度评估\n", - "print(\"该分类器的准确度为：\", clf.score(x_train, y_train))" - ] - }, - { - "cell_type": "code", - "execution_count": 88, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - " precision recall f1-score support\n", - "\n", - " 0 0.87 0.89 0.88 3047\n", - " 1 0.89 0.87 0.88 3128\n", - "\n", - " accuracy 0.88 6175\n", - " macro avg 0.88 0.88 0.88 6175\n", - "weighted avg 0.88 0.88 0.88 6175\n", - "\n" - ] - } - ], - "source": [ - "# 支持向量机的评估报告\n", - "# 四个列名分别为：精确率、召回率、F1值、支持数量\n", - "# 三个行名分别为：准确率、宏平均、加权平均\n", - "print(classification_report(y_test, clf.predict(x_test)))" - ] - }, - { - "cell_type": "code", - "execution_count": 89, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "我谢谢蒙牛！多一层体贴，多一层爱护！双重保护。\n", - "正向\n", - " 蒙牛是店大欺客 至少态度比蒙牛好～～后期赶紧整改！\n", - "负向\n", - "宝贝收到了，孩子爱吃，敏感肌能用，很启发大脑，提升睡眠质量，五星好评。\n", - "正向\n", - "五星好评，分期付清\n", - "负向\n", - "对得起我们吗？rnm，退钱！\n", - "负向\n" - ] - } - ], - "source": [ - "def bow_pred(string): \n", - " global clf, countvec\n", - " model = clf\n", - " # 数据转换为词频矩阵\n", - " words = \" \".join(jieba.cut(string))\n", - " words_vecs = countvec.transform([words])\n", - " # 预测并输出\n", - " result = model.predict(words_vecs)\n", - " if result[0] == 1:\n", - " print(\"正向\")\n", - " else:\n", - " print(\"负向\")\n", - "\n", - "\n", - "# 使用上述模型进行预测\n", - "for comment in test_comment:\n", - " print(comment)\n", - " bow_pred(comment)" - ] - }, - { - "cell_type": "code", - "execution_count": 90, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "(6274592, 9394570)" - ] - }, - "execution_count": 90, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# 基于Word2Vec的情感分析\n", - "# 按照7：3的比例生成训练集和测试集\n", - "x_train, x_test, y_train, y_test = train_test_split(df_cut, df.y, test_size=0.3, random_state=0)\n", - "# 初始化word2vec模型和词表\n", - "n_dim = 300 # 指定向量维度\n", - "w2vmodel = Word2Vec(vector_size=n_dim, min_count=10) # 出现10次以上的才纳入\n", - "# 生成词表\n", - "w2vmodel.build_vocab(x_train)\n", - "w2vmodel.train(x_train, total_examples=w2vmodel.corpus_count, epochs = 10) # 训练模型" - ] - }, - { - "cell_type": "code", - "execution_count": 91, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
0123456789...290291292293294295296297298299
00.2878590.211170-0.0026940.015414-0.130773-0.252820-0.1737650.0192470.1395260.084161...-0.1744840.183404-0.012513-0.2072010.4145040.2893060.317440-0.2800710.0931960.119094
10.1255040.2102810.2428410.152100-0.118140-0.1056820.0006010.0911970.1574580.128822...-0.0488290.089328-0.048414-0.1008010.1538240.3202740.117689-0.3062260.321337-0.032039
20.2081490.2002550.0286640.0960520.1579040.190969-0.0035780.351330-0.1821460.020400...-0.0550780.2284870.0662140.011649-0.0278200.206249-0.050040-0.1257920.412140-0.081710
30.3906790.2350060.2791630.1600660.273807-0.093850-0.0122550.1243180.1161290.007561...-0.092300-0.054543-0.191227-0.1233190.1799810.2140380.072776-0.2263280.267805-0.407456
40.2263860.250651-0.100598-0.016630-0.165644-0.165641-0.1083140.0476990.0303860.061525...-0.0938420.1219370.224285-0.0550720.3810970.1089290.1586390.004664-0.072203-0.276887
\n", - "

5 rows × 300 columns

\n", - "
" - ], - "text/plain": [ - " 0 1 2 3 4 5 6 \\\n", - "0 0.287859 0.211170 -0.002694 0.015414 -0.130773 -0.252820 -0.173765 \n", - "1 0.125504 0.210281 0.242841 0.152100 -0.118140 -0.105682 0.000601 \n", - "2 0.208149 0.200255 0.028664 0.096052 0.157904 0.190969 -0.003578 \n", - "3 0.390679 0.235006 0.279163 0.160066 0.273807 -0.093850 -0.012255 \n", - "4 0.226386 0.250651 -0.100598 -0.016630 -0.165644 -0.165641 -0.108314 \n", - "\n", - " 7 8 9 ... 290 291 292 293 \\\n", - "0 0.019247 0.139526 0.084161 ... -0.174484 0.183404 -0.012513 -0.207201 \n", - "1 0.091197 0.157458 0.128822 ... -0.048829 0.089328 -0.048414 -0.100801 \n", - "2 0.351330 -0.182146 0.020400 ... -0.055078 0.228487 0.066214 0.011649 \n", - "3 0.124318 0.116129 0.007561 ... -0.092300 -0.054543 -0.191227 -0.123319 \n", - "4 0.047699 0.030386 0.061525 ... -0.093842 0.121937 0.224285 -0.055072 \n", - "\n", - " 294 295 296 297 298 299 \n", - "0 0.414504 0.289306 0.317440 -0.280071 0.093196 0.119094 \n", - "1 0.153824 0.320274 0.117689 -0.306226 0.321337 -0.032039 \n", - "2 -0.027820 0.206249 -0.050040 -0.125792 0.412140 -0.081710 \n", - "3 0.179981 0.214038 0.072776 -0.226328 0.267805 -0.407456 \n", - "4 0.381097 0.108929 0.158639 0.004664 -0.072203 -0.276887 \n", - "\n", - "[5 rows x 300 columns]" - ] - }, - "execution_count": 91, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "def m_avgvec(words, w2vmodel):\n", - " \"\"\"\n", - " 用各个词向量直接平均的方式生成整句对应的向量\n", - " \"\"\"\n", - " return pd.DataFrame([w2vmodel.wv[w] for w in words if w in w2vmodel.wv]).agg(\"mean\")\n", - "\n", - "\n", - "# 生成建模用矩阵（耗时很长，慎点）\n", - "train_vecs = pd.DataFrame([m_avgvec(s, w2vmodel) for s in x_train])\n", - "\n", - "train_vecs.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 92, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[LibSVM]" - ] - }, - { - "data": { - "text/plain": [ - "SVC(verbose=True)" - ] - }, - "execution_count": 92, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# 用转换后的矩阵拟合SVM模型\n", - "clf2 = SVC(kernel=\"rbf\", verbose=True)\n", - "# 训练分类器（耗时很长，慎点）\n", - "clf2.fit(train_vecs, y_train)\n" - ] - }, - { - "cell_type": "code", - "execution_count": 93, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "该分类器的准确度为： 0.8936628028041924\n" - ] - } - ], - "source": [ - "# 准确度评估\n", - "print(\"该分类器的准确度为：\", clf2.score(train_vecs, y_train))" - ] - }, - { - "cell_type": "code", - "execution_count": 94, - "metadata": {}, - "outputs": [], - "source": [ - "# 生成测试用矩阵（耗时很长，慎点）\n", - "test_vecs = pd.DataFrame([m_avgvec(s, w2vmodel) for s in x_test])" - ] - }, - { - "cell_type": "code", - "execution_count": 95, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - " precision recall f1-score support\n", - "\n", - " 0 0.87 0.87 0.87 3047\n", - " 1 0.87 0.87 0.87 3128\n", - "\n", - " accuracy 0.87 6175\n", - " macro avg 0.87 0.87 0.87 6175\n", - "weighted avg 0.87 0.87 0.87 6175\n", - "\n" - ] - } - ], - "source": [ - "# 支持向量机的评估报告\n", - "print(classification_report(y_test, clf2.predict(test_vecs)))" - ] - }, - { - "cell_type": "code", - "execution_count": 96, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "我谢谢蒙牛！多一层体贴，多一层爱护！双重保护。\n", - "正向\n", - " 蒙牛是店大欺客 至少态度比蒙牛好～～后期赶紧整改！\n", - "负向\n", - "宝贝收到了，孩子爱吃，敏感肌能用，很启发大脑，提升睡眠质量，五星好评。\n", - "正向\n", - "五星好评，分期付清\n", - "正向\n", - "对得起我们吗？rnm，退钱！\n", - "负向\n" - ] - } - ], - "source": [ - "def w2v_pred(string):\n", - " global clf2, w2vmodel\n", - " # 将句子转换为矩阵形式\n", - " vecs = pd.DataFrame([m_avgvec(string, w2vmodel)])\n", - " # 预测并输出\n", - " result = clf2.predict(vecs)\n", - " if result[0] == 1:\n", - " print(\"正向\")\n", - " else:\n", - " print(\"负向\") \n", - "\n", - "\n", - "# 使用上述模型进行预测\n", - "for comment in test_comment:\n", - " print(comment)\n", - " w2v_pred(comment)" - ] - } - ], - "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": "3.7.9" - }, - "orig_nbformat": 4 - }, - "nbformat": 4, - "nbformat_minor": 2 -}