pyecharts官網：?https://pyecharts.org/#/zh-cn/composite_charts?

# https://blog.csdn.net/weixin_45081575 import os import json import requests import pandas as pd import jieba.analyse from pyecharts import options as opts from pyecharts.globals import ThemeType from pyecharts.globals import SymbolType from pyecharts.charts import Pie,Bar,Map,WordCloud,Liquid,Pageurl = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98vv59&productId=100001068301&score=0&sortType=5&page={}&pageSize=10&isShadowSku=0&rid=0&fold=1" # url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=100002148075&score=0&sortType=5&page={}&pageSize=10&isShadowSku=0&rid=0&fold=1"headers = {'Referer': 'https://item.jd.com/100001068301.html',# 'Sec-Fetch-Mode': 'no-cors','User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36' } # 過濾詞 stop_words_txt = "stop_words.txt"def get_comment(file_name):num = 1for i in range(0,50):print(f"處理第{i+1}頁")resp = requests.get(url.format(i), headers=headers)resp_list = json.loads(resp.text[24:-2])# content 評價;productColor 顏色;productSize 尺碼 referenceTime 購買時間 nickname昵稱comment_list = []for comment in resp_list["comments"]:print(comment["nickname"])data = {"num":num,"nickname":comment["nickname"],"bra_size":comment['productSize'],"color":comment['productColor'],"comment":(comment['content']).replace("\n"," "),"date":comment['referenceTime']}comment_list.append(data)num += 1save_to_excel(file_name,comment_list)print("表格保存完畢")def save_to_excel(file_name,comment_list):# 如果存在，則追加數據到表格，第一次執行的時候會創建表格，之后的數據則以追加的形式寫入if os.path.exists(file_name):df = pd.read_excel(file_name)df = df.append(comment_list)else:df = pd.DataFrame(comment_list)writer = pd.ExcelWriter(file_name)df.to_excel(excel_writer=writer,sheet_name="jd_comment",columns=["num","nickname","bra_size","color","comment","date"],index=False,encoding="utf-8")writer.save() # 顏色分布柱狀圖 https://blog.csdn.net/weixin_45081575/article/details/103449805 def color_chart(df):print("準備生成：顏色分布柱狀圖")colors = list(df.color.value_counts().items())colors = colors[:10] # 取前面10個顏色# print(colors)bar = (Bar().add_xaxis(list(data[0] for data in colors)).add_yaxis("顏色購買統計",list(data[1]for data in colors)).set_global_opts(title_opts=opts.TitleOpts(title="顏色分布柱狀圖"),xaxis_opts=opts.AxisOpts(name="顏色"),yaxis_opts=opts.AxisOpts(name="數量"),toolbox_opts=opts.ToolboxOpts() # ToolboxOpts工具箱))bar.render(path="顏色柱狀圖.html")# 購買者分布柱狀圖 def nick_name(df):print("準備生成：購買者分布柱狀圖")nick_names = list(df.nickname.value_counts().items())nick_names = nick_names[:10]bar = (Bar().add_xaxis(list(data[0] for data in nick_names)).add_yaxis("購買者數量",list(data[1] for data in nick_names)).set_global_opts(title_opts=opts.TitleOpts(title="購買者分布柱狀圖"),xaxis_opts=opts.AxisOpts(name="購買者"),yaxis_opts=opts.AxisOpts(name="數量"),toolbox_opts=opts.ToolboxOpts()))bar.render("購買者分布柱狀圖.html") # 尺碼分布圖 def size_chart(df):print("準備生成：尺碼分布柱狀圖")sizes = sorted(list(df.bra_size.value_counts().items()))bar = (Bar().add_xaxis(list(data[0] for data in sizes)).add_yaxis("尺碼購買統計",list(data[1] for data in sizes)).set_global_opts(title_opts=opts.TitleOpts(title="尺碼分布柱狀圖"),xaxis_opts=opts.AxisOpts(name="尺碼"),yaxis_opts=opts.AxisOpts(name="數量"),toolbox_opts=opts.ToolboxOpts()))bar.render("尺碼柱狀圖.html")# 區間餅圖和柱狀圖 def avg_cup(df):print("準備生成：區間餅圖和柱狀圖")size_list = sorted(list(df.bra_size.value_counts().items()))cup_dic = {i:0 for i in "ABCD"}for data in size_list:if "A" in data[0]:cup_dic['A'] += data[1]if "B" in data[0]:cup_dic['B'] += data[1]if "C" in data[0]:cup_dic['C'] += data[1]if "D" in data[0]:cup_dic['D'] += data[1]bar = (Bar().add_xaxis(list(cup_dic.keys())).add_yaxis("尺碼數量",list(cup_dic.values())).set_global_opts(title_opts=opts.TitleOpts(title="尺碼區間柱狀圖"),xaxis_opts=opts.AxisOpts(name="尺碼"),yaxis_opts=opts.AxisOpts(name="數量"),toolbox_opts=opts.ToolboxOpts()))bar.render("區間柱狀圖.html")pie = (Pie().add("數量",list(cup_dic.items())).set_global_opts(title_opts=opts.TitleOpts(title="尺碼區間餅圖")).set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{c}(占比:ozvdkddzhkzd%)")) # b代表名字，c代表數量，d代表百分比)pie.render("區間餅圖.html")return (bar,pie)# 評論詞云 def word_cloud(df):print("準備生成：評論詞云")if os.path.exists(stop_words_txt):jieba.analyse.set_stop_words(stop_words_txt)kw_list = jieba.analyse.textrank(''.join(df.comment),topK=65,withWeight=True)word_cloud = (WordCloud(init_opts=opts.InitOpts(bg_color='#c7edcc'))# '傳入列表，word_size_range為字體大小，shape為詞云的形狀'# 形狀 RECT、ROUND_RECT、TRIANGLE、DIAMOND、ARROW# mask_image = "aizhong-logo.png" # 自定義形狀# .add("",kw_list,word_size_range=[15, 100],mask_image="aizhong-logo.png").add("",kw_list,word_size_range=[15, 100],shape=SymbolType.DIAMOND).set_global_opts(title_opts=opts.TitleOpts(title="評論標題詞云Top65"),toolbox_opts=opts.ToolboxOpts()))word_cloud.render("詞云.html")return word_cloud # 水滴圖 def water():print("準備生成：今日濕度水滴圖")liquid = (Liquid().add("lq", [0.45,0.5,0.6],is_outline_show=False,shape=SymbolType.DIAMOND) # 第一個值為顯示的值百分比，第二個指為水的分量.set_global_opts(title_opts=opts.TitleOpts(title="今日濕度水滴圖"),toolbox_opts=opts.ToolboxOpts()))liquid.render("今日濕度水滴圖.html")return liquidif __name__ == '__main__':file_name = "jd_comment.xlsx"if not os.path.exists(file_name):print("表格不存在")get_comment(file_name)df = pd.read_excel(file_name)color_chart(df)word_cloud = word_cloud(df)nick_name(df)size_chart(df)bar,pie = avg_cup(df)liquid = water()# 接下來生成組合圖表 https://pyecharts.org/#/zh-cn/composite_chartspage = Page(layout=Page.DraggablePageLayout)page.add(liquid,bar,pie,word_cloud)# page.render("all.html")# 這個生成的是按順序存放的圖表# 先生成all.html，然后就不要再重新生成了，直接在這上面調整到合適位置后點擊左上角save config，生成chart_config.json# 讀取all.html，并利用chart_config.json的設置重新生成新的resize_render.htmlPage.save_resize_html("all.html", cfg_file="chart_config.json")

參考：https://blog.csdn.net/weixin_45081575/article/details/103449805

其中過濾詞stop_words.txt，第一行要空出來，從第二行開始寫，一行一個詞，保存成utf-8編碼格式，例如：京東

總結

以上是生活随笔為你收集整理的pandas数据分析京东评论者衣服购买情况pyecharts生成可视化图表的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。