{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "### 情感分析" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [], "source": [ "# 依赖导入\n", "import pandas as pd\n", "from snownlp import SnowNLP\n", "import jieba.posseg as psg\n", "import jieba.analyse\n", "import matplotlib.pyplot as plt\n", "import numpy as np" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# 依赖导入\n", "import pandas as pd\n", "from snownlp import SnowNLP\n", "import jieba.posseg as psg\n", "import jieba.analyse\n", "import matplotlib.pyplot as plt\n", "import numpy as np\n", "\n", "file_path = r'Data\\rawdata_reprocessed.csv'\n", "data = pd.read_csv(file_path).astype(str)\n", "\n", "comments = data['weibo_content']\n", "sentimentlist = []\n", "for comment in comments:\n", " s = SnowNLP(comment)\n", " sentimentlist.append(s.sentiments)\n", "\n", "#可视化结果\n", "plt.hist(sentimentlist, bins=np.arange(0,1,0.01),facecolor='b')\n", "plt.xlabel('Probability')\n", "plt.ylabel('Quantity')\n", "plt.title('Sentiment Analysis')\n", "plt.savefig('sentiment_analysis.png')\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### 数据导入" ] }, { "cell_type": "code", "execution_count": 27, "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", "
weibo_usernameweibo_verificationweibo_contentweibo_content_preprocessedsubmit_timeforward_countscomments_countspoints_times
0辣子鸡谁做的好吃nan好像可以在自己幻想的元宇宙里过一辈子好像已经过完了一辈子双鱼座的脑子要不得好像 幻想 元宇宙 里 一辈子 好像 完 一辈子 双鱼座 脑子 要不得01月10日 23:59000
1远古的刀nan反正闭关锁宇宙我们将会面临下一次的闭关锁国融入不了全球经济王峻涛跟你们讲我相信这个元宇宙真的...反正 闭关 锁 宇宙 将会 面临 闭关锁国 融入 全球 经济 王峻涛 讲 元宇宙 真的 一下...01月10日 23:583230
2暮景烟_深浅nan周深先生之夜元宇宙周深拥有了生米就像拥有了梦的翅膀卡布叻周深放心飞吧生米永相随时尚先生元宇宙...周深 之夜 元宇宙 周深 拥有 生米 拥有 梦 翅膀 卡布 叻 周深 放心 飞 生米 永 相...01月10日 23:58000
3东辉毅恒传媒nan王峻涛其实吧你有空可以再看看这个视频跟你们讲我相信这个元宇宙真的会来虽然不是一下子就到来还需...王峻涛 有空 视频 讲 元宇宙 真的 一下子 到来 技术 突破 社会 讲 玩 后果 人会 分...01月10日 23:57000
4在寒蝉鸣泣中等待夏日重现nan敬元宇宙让基尔希斯坦的女朋友的微博视频敬 元宇宙 基尔 希斯 坦 女朋友 微博 视频01月10日 23:57005
5北北红牛一号微博个人认证我们在玩股票的时候首先要明白当前的市场环境大势第一顺势而为整个市场的高度从龙精药业的板并且给...玩 股票 明白 市场 环境 大势 第一 顺势 市场 高度 从龙精 药业 板 给出 一线 逃命...01月10日 23:56002
6-玫瑰骑士夢微博个人认证朝元気芋泥萄萄宇宙小居民黄仁俊元气活泼跑起来会扬起耳朵的小帕恰签售时挑战的可爱笨笨金色卷卷珍...元 気 芋 泥 萄 萄 宇宙 居民 黄仁俊 元气 活泼 跑 扬起 耳朵 小帕恰 签售 时 挑...01月10日 23:56000
7成都仁寿商会nan元宇宙成苹果禁区将发布首款头显月日消息苹果公司预计将于今年发布其首款混合现实头戴设备彭博社记...元宇宙 成 苹果 禁区 发布 首款 头显 月 日 消息 苹果公司 预计 发布 首款 混合 现...01月10日 23:56000
8是个吃货叻nan帅帅帅冲浪的紅豆鯊啊啊啊太帅了卡布叻周深周深星星瞭望塔周深时尚先生周深先生之夜元宇宙勇敢突破...帅帅帅 冲浪 紅豆 鯊 啊啊啊 太帅 卡布 叻 周深 周深 星星 瞭望 塔周 深 时尚 周深...01月10日 23:55001026193
9是个吃货叻nan周深啊啊啊啊冲浪的紅豆鯊啊啊啊太帅了卡布叻周深周深星星瞭望塔周深时尚先生周深先生之夜元宇宙勇...周深 啊啊啊 冲浪 紅豆 鯊 啊啊啊 太帅 卡布 叻 周深 周深 星星 瞭望 塔周 深 时尚...01月10日 23:55001026193
\n", "
" ], "text/plain": [ " weibo_username weibo_verification \\\n", "0 辣子鸡谁做的好吃 nan \n", "1 远古的刀 nan \n", "2 暮景烟_深浅 nan \n", "3 东辉毅恒传媒 nan \n", "4 在寒蝉鸣泣中等待夏日重现 nan \n", "5 北北红牛一号 微博个人认证 \n", "6 -玫瑰骑士夢 微博个人认证 \n", "7 成都仁寿商会 nan \n", "8 是个吃货叻 nan \n", "9 是个吃货叻 nan \n", "\n", " weibo_content \\\n", "0 好像可以在自己幻想的元宇宙里过一辈子好像已经过完了一辈子双鱼座的脑子要不得 \n", "1 反正闭关锁宇宙我们将会面临下一次的闭关锁国融入不了全球经济王峻涛跟你们讲我相信这个元宇宙真的... \n", "2 周深先生之夜元宇宙周深拥有了生米就像拥有了梦的翅膀卡布叻周深放心飞吧生米永相随时尚先生元宇宙... \n", "3 王峻涛其实吧你有空可以再看看这个视频跟你们讲我相信这个元宇宙真的会来虽然不是一下子就到来还需... \n", "4 敬元宇宙让基尔希斯坦的女朋友的微博视频 \n", "5 我们在玩股票的时候首先要明白当前的市场环境大势第一顺势而为整个市场的高度从龙精药业的板并且给... \n", "6 朝元気芋泥萄萄宇宙小居民黄仁俊元气活泼跑起来会扬起耳朵的小帕恰签售时挑战的可爱笨笨金色卷卷珍... \n", "7 元宇宙成苹果禁区将发布首款头显月日消息苹果公司预计将于今年发布其首款混合现实头戴设备彭博社记... \n", "8 帅帅帅冲浪的紅豆鯊啊啊啊太帅了卡布叻周深周深星星瞭望塔周深时尚先生周深先生之夜元宇宙勇敢突破... \n", "9 周深啊啊啊啊冲浪的紅豆鯊啊啊啊太帅了卡布叻周深周深星星瞭望塔周深时尚先生周深先生之夜元宇宙勇... \n", "\n", " weibo_content_preprocessed submit_time \\\n", "0 好像 幻想 元宇宙 里 一辈子 好像 完 一辈子 双鱼座 脑子 要不得 01月10日 23:59 \n", "1 反正 闭关 锁 宇宙 将会 面临 闭关锁国 融入 全球 经济 王峻涛 讲 元宇宙 真的 一下... 01月10日 23:58 \n", "2 周深 之夜 元宇宙 周深 拥有 生米 拥有 梦 翅膀 卡布 叻 周深 放心 飞 生米 永 相... 01月10日 23:58 \n", "3 王峻涛 有空 视频 讲 元宇宙 真的 一下子 到来 技术 突破 社会 讲 玩 后果 人会 分... 01月10日 23:57 \n", "4 敬 元宇宙 基尔 希斯 坦 女朋友 微博 视频 01月10日 23:57 \n", "5 玩 股票 明白 市场 环境 大势 第一 顺势 市场 高度 从龙精 药业 板 给出 一线 逃命... 01月10日 23:56 \n", "6 元 気 芋 泥 萄 萄 宇宙 居民 黄仁俊 元气 活泼 跑 扬起 耳朵 小帕恰 签售 时 挑... 01月10日 23:56 \n", "7 元宇宙 成 苹果 禁区 发布 首款 头显 月 日 消息 苹果公司 预计 发布 首款 混合 现... 01月10日 23:56 \n", "8 帅帅帅 冲浪 紅豆 鯊 啊啊啊 太帅 卡布 叻 周深 周深 星星 瞭望 塔周 深 时尚 周深... 01月10日 23:55 \n", "9 周深 啊啊啊 冲浪 紅豆 鯊 啊啊啊 太帅 卡布 叻 周深 周深 星星 瞭望 塔周 深 时尚... 01月10日 23:55 \n", "\n", " forward_counts comments_counts points_times \n", "0 0 0 0 \n", "1 32 3 0 \n", "2 0 0 0 \n", "3 0 0 0 \n", "4 0 0 5 \n", "5 0 0 2 \n", "6 0 0 0 \n", "7 0 0 0 \n", "8 0 0 1026193 \n", "9 0 0 1026193 " ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "output_path = r'Output'\n", "file_path = r'Data\\rawdata_reprocessed.csv'\n", "data = pd.read_csv(file_path).astype(str)\n", "jieba.load_userdict(r'Data\\userdic.txt')\n", "data.head(10)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### 词性标注" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "好像/v 可以/c 在/p 自己/r 幻想/n 的/uj 元宇宙/x 里/f 过/ug 一辈子/m 好像/v 已经/d 过完/v 了/ul 一辈子/m 双鱼座/nz 的/uj 脑子/n 要不得/v \n", "反正/d 闭关/v 锁/v 宇宙/n 我们/r 将/d 会/v 面临/v 下/f 一次/m 的/uj 闭关锁国/l 融入/v 不了/v 全球/n 经济/n 王峻涛/nr 跟/p 你们/r 讲/v 我/r 相信/v 这个/r 元宇宙/x 真的/d 会/v 来/v 虽然/c 不是/c 一下子/m 就/d 到来/d 还/d 需要/v 很多/m 技术/n 突破/vn 和/c 社会/n 适应/v 再/d 跟/p 你们/r 讲/v 这次/r 再/d 不/d 跟/p 大家/n 一起/m 玩/v 以后/f 的/uj 后果/n 更/d 严重/a 人会/n 分成/v 有/v 元宇宙/x 的/uj 和/c 只有/c 传统/n 宇宙/n 的/uj 二端/m 互相/d 连/nr 沟通/v 的/uj 机会/n 都/d 没有/v \n", "周/nr 深/a 先生/n 之/u 夜/tg 元宇宙/x 周/nr 深/a 拥有/v 了生/v 米/q 就/d 像/v 拥有/v 了/ul 梦/n 的/uj 翅膀/n 卡布/nr 叻/g 周/nr 深/a 放心/v 飞/v 吧/y 生/v 米永/nr 相随/v 时尚/n 先生/n 元宇宙/x 梅涩甜/nr 的/uj 微博/a 视频/n \n", "王峻涛/nr 其实/d 吧/y 你/r 有空/vn 可以/c 再/d 看看/v 这个/r 视频/n 跟/p 你们/r 讲/v 我/r 相信/v 这个/r 元宇宙/x 真的/d 会/v 来/v 虽然/c 不是/c 一下子/m 就/d 到来/d 还/d 需要/v 很多/m 技术/n 突破/vn 和/c 社会/n 适应/v 再/d 跟/p 你们/r 讲/v 这次/r 再/d 不/d 跟/p 大家/n 一起/m 玩/v 以后/f 的/uj 后果/n 更/d 严重/a 人会/n 分成/v 有/v 元宇宙/x 的/uj 和/c 只有/c 传统/n 宇宙/n 的/uj 二端/m 互相/d 连/nr 沟通/v 的/uj 机会/n 都/d 没有/v \n" ] } ], "source": [ "wb = data[0:4]['weibo_content']\n", "for s in wb:\n", " wordLists = psg.cut(s)\n", " for w in wordLists:\n", " print(w,end=' ')\n", " print()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 情感分析" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "comments = data['weibo_content']\n", "sentimentlist = []\n", "for comment in comments:\n", " s = SnowNLP(comment)\n", " sentimentlist.append(s.sentiments)\n", "# print(s.sentiments)\n", "\n", "#可视化结果\n", "plt.hist(sentimentlist, bins=np.arange(0,1,0.01),facecolor='b')\n", "plt.xlabel('Probability')\n", "plt.ylabel('Quantity')\n", "plt.title('Sentiment Analysis')\n", "plt.show()\n", "\n" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "15\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "\n", "df = data.copy()\n", "attributeList = ['l', 'uj', 'p', 'r', 'vn', 'm', 'k', 'q', 'd', 'ns', 't', 'nz', 'a', 'v', 'n']\n", "wordLists = []\n", "for attribute in attributeList:\n", " sentence = df['weibo_content']\n", " \n", " wordList = []\n", " for line in sentence:\n", " kw_TF_IDF = jieba.analyse.extract_tags(str(line), topK=30, withWeight=True, allowPOS=(attribute))\n", " words = ''\n", " for kw in kw_TF_IDF:\n", " words += kw[0]\n", " if len(words)>0:\n", " wordList.append(words)\n", " wordLists.append(wordList)\n", "k = 0\n", "print(len(wordLists))\n", "for wl in wordLists:\n", " \n", " sentimentlist = []\n", " for ad_v in wl:\n", " s = SnowNLP(ad_v)\n", " sentimentlist.append(s.sentiments)\n", " plt.clf()\n", " plt.hist(sentimentlist, bins=np.arange(0,1,0.01),facecolor='g')\n", " plt.xlabel('Probability')\n", " plt.ylabel('Quantity')\n", " plt.title('Sentiment '+attributeList[k]+' Analysis')\n", " plt.savefig(output_path+'sentiment_'+attributeList[k]+'.png')\n", " k += 1\n" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████| 31670/31670 [30:59<00:00, 17.03it/s] \n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "import pandas as pd\n", "from snownlp import SnowNLP\n", "import jieba.posseg as psg\n", "import jieba.analyse\n", "import matplotlib.pyplot as plt\n", "import numpy as np\n", "from tqdm import tqdm\n", "\n", "file_path = r'Data\\topic_5.csv'\n", "data = pd.read_csv(file_path).astype(str)\n", "\n", "comments = data['weibo_content']\n", "sentimentlist = []\n", "for comment in tqdm(comments):\n", " s = SnowNLP(comment)\n", " sentimentlist.append(s.sentiments)\n", "\n", "#可视化结果\n", "plt.hist(sentimentlist, bins=np.arange(0,1,0.01),facecolor='b')\n", "plt.xlabel('Probability')\n", "plt.ylabel('Quantity')\n", "plt.title('Sentiment Analysis')\n", "plt.savefig('sentiment_analysis.png')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.hist(sentimentlist, bins=np.arange(0,1,0.01),facecolor='b')\n", "plt.xlabel('Probability')\n", "plt.ylabel('Quantity')\n", "plt.title('Sentiment Analysis Topic #5')\n", "plt.savefig('sentiment_analysis.png')" ] } ], "metadata": { "interpreter": { "hash": "8ad04bb091a50ccdbc721be5657843c2a9a7fbc3dc3147e11dd611d30683dae8" }, "kernelspec": { "display_name": "Python 3.8.3 ('base')", "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": "3.8.3" }, "orig_nbformat": 4 }, "nbformat": 4, "nbformat_minor": 2 }