{ "nbformat": 4, "nbformat_minor": 2, "metadata": { "language_info": { "name": "python", "codemirror_mode": { "name": "ipython", "version": 3 }, "version": "3.6.0-final" }, "orig_nbformat": 2, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "npconvert_exporter": "python", "pygments_lexer": "ipython3", "version": 3, "kernelspec": { "name": "python36064bitrootconda12dcd85ef9c147fdbdf4c10492696076", "display_name": "Python 3.6.0 64-bit ('root': conda)" } }, "cells": [ { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "import re,os,sys\n", "" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "\n", "df =pd.read_excel(\"data/李子柒螺蛳粉评论.xlsx\")\n", "df.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 去除重复值\n", "df.drop_duplicates(inplace=True)\n", "df.info() " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 时间-热度分析\n" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 时间走势图\n", "df['comment_time'] = pd.to_datetime(df['comment_time'])\n", "df['comment_date'] = df['comment_time'].dt.date\n", "comment_num = df['comment_date'].value_counts().sort_index()\n", "\n", "from pyecharts.charts import Line\n", "from pyecharts import options as opts \n", "\n", "# 折线图\n", "line1 = Line(init_opts=opts.InitOpts(width='1350px', height='750px'))\n", "line1.add_xaxis(comment_num.index.tolist())\n", "line1.add_yaxis('热度', comment_num.values.tolist(),\n", " areastyle_opts=opts.AreaStyleOpts(opacity=0.5),\n", " label_opts=opts.LabelOpts(is_show=False))\n", "line1.set_global_opts(title_opts=opts.TitleOpts(title='商品评价数量走势图'), \n", " xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate='30')),\n", " toolbox_opts=opts.ToolboxOpts(),\n", " visualmap_opts=opts.VisualMapOpts(max_=400))\n", "line1.set_series_opts(linestyle_opts=opts.LineStyleOpts(width=3))\n", "line1.render() \n", "" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "def judge_comment(df, result):\n", "\n", " # 创建一个空数据框\n", " judges = pd.DataFrame(np.zeros(13 * len(df)).reshape(len(df),13),\n", " columns = ['品牌','物流正面','物流负面','包装正面','包装负面','原料正面',\n", " '原料负面','口感正面','口感负面','日期正面','日期负面',\n", " '性价比正面','性价比负面'])\n", "\n", " for i in range(len(result)):\n", " word = result[i]\n", " #李子柒的产品具有强IP属性，基本都是正面评价，这里不统计情绪，只统计提及次数\n", " if '李子柒' in word or '子柒' in word or '小柒' in word or '李子七' in word or '小七' in word:\n", " judges.iloc[i]['品牌'] = 1\n", "\n", " #先判断是不是物流相关的\n", " if '物流' in word or '快递' in word or '配送' in word or '取货' in word:\n", " #再判断是正面还是负面情感\n", " if '好' in word or '不错' in word or '棒' in word or '满意' in word or '迅速' in word:\n", " judges.iloc[i]['物流正面'] = 1\n", " elif '慢' in word or '龟速' in word or '暴力' in word or '差' in word:\n", " judges.iloc[i]['物流负面'] = 1\n", "\n", " #判断是否包装相关\n", " if '包装' in word or '盒子' in word or '袋子' in word or '外观' in word:\n", " if '高端' in word or '大气' in word or '还行' in word or '完整' in word or '好' in word or\\\n", " '严实' in word or '紧' in word or '精致' in word:\n", " judges.iloc[i]['包装正面'] = 1\n", " elif '破' in word or '破损' in word or '瘪' in word or '简陋' in word:\n", " judges.iloc[i]['包装负面'] = 1\n", "\n", " #产品\n", " #产品原料是牛肉为主，且评价大多会提到牛肉，因此我们把这个单独拎出来分析\n", " if '米粉' in word or '汤' in word or '配料' in word or '腐竹' in word or '花生' in word:\n", " if '劲道' in word or '多' in word or '足' in word or '香' in word or '才' in word or\\\n", " '脆' in word or 'nice' in word:\n", " judges.iloc[i]['原料正面'] = 1\n", " elif '小' in word or '少' in word or '没' in word:\n", " judges.iloc[i]['原料负面'] = 1\n", "\n", " #口感的情绪\n", " if '口味' in word or '味道' in word or '口感' in word or '吃起来' in word:\n", " if '不错' in word or '浓鲜' in word or '十足' in word or '鲜' in word or\\\n", " '可以' in word or '喜欢' in word or '符合' in word:\n", " judges.iloc[i]['口感正面'] = 1\n", " elif '不好' in word or '不行' in word or '不鲜' in word or\\\n", " '太烂' in word:\n", " judges.iloc[i]['口感负面'] = 1\n", "\n", " #口感方面，有些是不需要出现前置词，消费者直接评价好吃难吃的，例如：\n", " if '难吃' in word or '不好吃' in word:\n", " judges.iloc[i]['口感负面'] = 1\n", " elif '好吃' in word or '香' in word:\n", " judges.iloc[i]['口感正面'] = 1\n", "\n", " #日期是不是新鲜\n", " if '日期' in word or '时间' in word or '保质期' in word:\n", " if '新鲜' in word:\n", " judges.iloc[i]['日期正面'] = 1\n", " elif '久' in word or '长' in word:\n", " judges.iloc[i]['日期负面'] = 1\n", " elif '过期' in word:\n", " judges.iloc[i]['日期负面'] = 1\n", "\n", " #性价比\n", " if '划算' in word or '便宜' in word or '赚了' in word or '囤货' in word or '超值' in word or \\\n", " '太值' in word or '物美价廉' in word or '实惠' in word or '性价比高' in word or '不贵' in word: \n", " judges.iloc[i]['性价比正面'] = 1\n", " elif '贵' in word or '不值' in word or '亏了' in word or '不划算' in word or '不便宜' in word:\n", " judges.iloc[i]['性价比负面'] = 1\n", "\n", " final_result = pd.concat([df,judges],axis = 1)\n", "\n", " return final_result\n", "" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 得到数据框\n", "judge = judge_comment(df, result=df.content)\n", "judge.head() \n", "" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 结果汇总\n", "rank = judge.iloc[:, 5:].sum().reset_index().sort_values(0, ascending=False) \n", "rank.columns = ['分类', '提及次数']\n", "rank['占比'] = rank['提及次数'] / rank['提及次数'].sum()\n", "rank['高级分类'] = rank['分类'].str[:-2]\n", "rank" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "rank.loc[0, '高级分类'] = '品牌'\n", "rank \n", "" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "df.shape" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "rank_num = rank.groupby('高级分类')['提及次数'].sum().sort_values(ascending=False)\n", "rank_num\n", "" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "\n", "data_pair = [list(z) for z in zip(rank_num.index, rank_num.values)]\n", "data_pair" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from pyecharts.charts import Pie\n", "\n", "pie1 = Pie(init_opts=opts.InitOpts(width='1350px', height='750px'))\n", "pie1.add( \n", " series_name=\"num\",\n", " radius=[\"35%\", \"55%\"],\n", " data_pair=data_pair,\n", " label_opts=opts.LabelOpts(\n", " position=\"outside\",\n", " formatter=\"{a|{a}}{abg|}\\n{hr|}\\n {b|{b}: }{c} {per|{d}%} \",\n", " background_color=\"#eee\",\n", " border_color=\"#aaa\",\n", " border_width=1,\n", " border_radius=4,\n", " rich={\n", " \"a\": {\"color\": \"#999\", \"lineHeight\": 22, \"align\": \"center\"},\n", " \"abg\": {\n", " \"backgroundColor\": \"#e3e3e3\",\n", " \"width\": \"100%\",\n", " \"align\": \"right\",\n", " \"height\": 22,\n", " \"borderRadius\": [4, 4, 0, 0],\n", " },\n", " \"hr\": {\n", " \"borderColor\": \"#aaa\",\n", " \"width\": \"100%\",\n", " \"borderWidth\": 0.5,\n", " \"height\": 0,\n", " },\n", " \"b\": {\"fontSize\": 16, \"lineHeight\": 33},\n", " \"per\": {\n", " \"color\": \"#eee\",\n", " \"backgroundColor\": \"#334455\",\n", " \"padding\": [2, 4],\n", " \"borderRadius\": 2,\n", " },\n", " },\n", " ),\n", ")\n", "pie1.set_global_opts(legend_opts=opts.LegendOpts(pos_left=\"left\", pos_top='30%', orient=\"vertical\"), \n", " toolbox_opts=opts.ToolboxOpts(),\n", " title_opts=opts.TitleOpts(title='消费者关注占比分布'))\n", "pie1.set_series_opts(\n", " tooltip_opts=opts.TooltipOpts(trigger=\"item\", formatter=\"{a}
{b}: {c} ({d}%)\")\n", " )\n", "pie1.render()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from pyecharts import options as opts\n", "from pyecharts.charts import Bar\n", "from pyecharts.commons.utils import JsCode\n", "from pyecharts.globals import ThemeType\n", "\n", "list2 = [\n", " {\"value\": 1484.0, \"percent\": 1484.0 / (1484.0 + 27.0)},\n", " {\"value\": 692.0, \"percent\": 692.0 / (692.0 + 3.0)},\n", " {\"value\": 539.0, \"percent\": 539.0 / (539.0 + 63.0)},\n", " {\"value\": 422.0, \"percent\": 422.0 / (422.0 + 0)},\n", " {\"value\": 142.0, \"percent\": 142.0 / (142.0 + 66.0)},\n", " {\"value\": 124.0, \"percent\": 124.0 / (124.0 + 22.0)},\n", " {\"value\": 58.0, \"percent\": 58.0 / (58.0 + 3.0)},\n", "]\n", "\n", "list3 = [\n", " {\"value\": 27.0, \"percent\": 27.0 / (27.0 + 1484.0)},\n", " {\"value\": 3.0, \"percent\": 3.0 / (3.0 + 692.0)},\n", " {\"value\": 63.0, \"percent\": 63.0 / (63.0 + 539.0)},\n", " {\"value\": 0, \"percent\": 0 / (0 + 422.0)},\n", " {\"value\": 66.0, \"percent\": 66.0 / (66.0 + 142.0)},\n", " {\"value\": 22.0, \"percent\": 22.0 / (22.0 + 124.0)},\n", " {\"value\": 3.0, \"percent\": 3.0 / (3.0 + 58.0)},\n", "]\n", "\n", "\n", "bar1 = Bar(init_opts=opts.InitOpts(width='1350px', height='750px', theme=ThemeType.LIGHT))\n", "bar1.add_xaxis(['口感', '包装', '原料', '品牌', '日期', '性价比', '物流'])\n", "bar1.add_yaxis(\"正面评论\", list2, stack=\"stack1\", category_gap=\"50%\")\n", "bar1.add_yaxis(\"负面评论\", list3, stack=\"stack1\", category_gap=\"50%\")\n", "bar1.set_global_opts(title_opts=opts.TitleOpts(title='关注点细分占比分布')) \n", "bar1.set_series_opts(\n", " label_opts=opts.LabelOpts(\n", " position=\"right\",\n", " formatter=JsCode(\n", " \"function(x){return Number(x.data.percent * 100).toFixed() + '%';}\"\n", " ),\n", " )\n", " )\n", "bar1.render()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import jieba \n", "import jieba.analyse\n", "\n", "txt = df['content'].str.cat(sep='。')\n", "\n", "# 添加关键词\n", "jieba.add_word('李子柒') \n", "\n", "# 读入停用词表\n", "stop_words = []\n", "with open('stop_words.txt', 'r', encoding='utf-8') as f:\n", " lines = f.readlines()\n", " for line in lines:\n", " stop_words.append(line.strip())\n", "\n", "# 添加停用词\n", "stop_words.extend(['40', 'hellip', '一袋', '一包', '一个月', \n", " '一点', '一个多月', '第一次', '哈哈哈', \n", " '螺狮粉', '螺蛳']) \n", "\n", "# 评论字段分词处理\n", "word_num = jieba.analyse.extract_tags(txt,\n", " topK=100,\n", " withWeight=True,\n", " allowPOS=())\n", "\n", "# 去停用词\n", "word_num_selected = []\n", "\n", "for i in word_num:\n", " if i[0] not in stop_words:\n", " word_num_selected.append(i)\n", "\n", "key_words = pd.DataFrame(word_num_selected, columns=['words','num'])\n", "key_words.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from pyecharts.charts import WordCloud\n", "from pyecharts.globals import SymbolType\n", "\n", "# 词云图\n", "word1 = WordCloud(init_opts=opts.InitOpts(width='1350px', height='750px'))\n", "word1.add(\"\", [*zip(key_words.words, key_words.num)],\n", " word_size_range=[20, 200],\n", " shape=SymbolType.DIAMOND)\n", "word1.set_global_opts(title_opts=opts.TitleOpts('评论分布词云图'),\n", " toolbox_opts=opts.ToolboxOpts())\n", "word1.render()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from pyecharts.charts import Page\n", "\n", "page = Page() \n", "page.add(pie1, bar1, word1)\n", "page.render('评论分析.html') \n", "" ] } ] }