Init

.gitignore

+result/

.idea/.gitignore

+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/dataSources.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="DataSourceManagerImpl" format="xml" multifile-model="true">
+    <data-source source="LOCAL" name="MateData" uuid="1ba7e8ea-76b5-4bf8-b2d1-e7c70af6f742">
+      <driver-ref>sqlite.xerial</driver-ref>
+      <synchronize>true</synchronize>
+      <jdbc-driver>org.sqlite.JDBC</jdbc-driver>
+      <jdbc-url>jdbc:sqlite:$PROJECT_DIR$/MateData.db</jdbc-url>
+      <working-dir>$ProjectFileDir$</working-dir>
+    </data-source>
+  </component>
+</project>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (venv)" project-jdk-type="Python SDK">
+    <output url="file://$PROJECT_DIR$/out" />
+  </component>
+</project>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/Buu.iml" filepath="$PROJECT_DIR$/Buu.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

Buu.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager" inherit-compiler-output="true">
+    <exclude-output />
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
\ No newline at end of file

analysis_strategy.py

+from load_data import LoadData
+
+
+def count_in_dict(data_dict, dict_key, step_value=1):
+    if dict_key in data_dict:
+        tmp_count = data_dict[dict_key] + step_value
+    else:
+        tmp_count = step_value
+    data_dict[dict_key] = tmp_count
+
+
+# 分析 0元购、1元抽奖、其他占比
+def analysis_classify(load_data, chart):
+    result_dict = {}
+    for data in load_data.data_list:
+        result_value = str(data['订单名称'])
+        result_value_price = float(data['价格'])
+        if str(result_value).find('0元领') > 0:
+            count_in_dict(result_dict, result_value)
+        elif float(result_value_price) == 1.0:
+            count_in_dict(result_dict, '1元抽奖')
+        else:
+            count_in_dict(result_dict, '其他')
+    chart.draw_pie_chart("0元购、1元抽奖、其他占比", result_dict)
+
+
+# 商品类目聚合
+def analysis_category(load_data, chart):
+    # 商品类目维度 一级类目分类
+    result_dict = {}
+    for data in load_data.real_data_list:
+        result_value = str(data['商品一级类目'])
+        count_in_dict(result_dict, result_value)
+
+    result_tmp = sorted(result_dict.items(), key=lambda kv: (kv[1], kv[0]), reverse=True)
+    result_dict = {}
+    for (key, value) in result_tmp:
+        result_dict[key] = value
+    chart.draw_pie_chart("一级类目占比\n(去除0元领/1元福利等)", result_dict)
+
+    result_dict = {}
+    for data in load_data.real_data_list:
+        result_value = str(data['商品一级类目'] + "_" + data['商品二级类目'])
+        count_in_dict(result_dict, result_value)
+
+    # 商品类目维度 二级类目分类 仅保留前20
+    result_tmp = sorted(result_dict.items(), key=lambda kv: (kv[1], kv[0]), reverse=True)
+    result_dict = {}
+    for index in range(len(result_tmp)):
+        item = result_tmp[index]
+        if index < 20:
+            result_dict[item[0]] = item[1]
+        else:
+            count_in_dict(result_dict, '其他', item[1])
+    chart.draw_pie_chart("二级类目占比\n(去除0元领/1元福利等)", result_dict)
+
+
+# 购买的商品次数
+def analysis_goods(load_data, chart):
+    # 仅第一单是0元领或者1元抽奖，有复购
+    # 仅第一单为正常商品，有复购
+    # 仅第一单是0元领或者1元抽奖，无复购
+    # 仅第一单为正常商品，无复购
+    result_dict = {}
+    for data_user_id in load_data.data_dict:
+        user_buy_list = load_data.data_dict[data_user_id]
+        user_buy_detail = user_buy_list[0]
+        if load_data.is_zero_buy(user_buy_detail):
+            # 仅一单为非常规
+            if len(user_buy_list) == 1:
+                count_in_dict(result_dict, '仅1单(0元领/1元抽奖)\n')
+            else:
+                user_buy_detail_s = user_buy_list[1]
+                if load_data.is_zero_buy(user_buy_detail_s):
+                    count_in_dict(result_dict, '第一单(0元领/1元抽奖)\n第二单(0元领/1元抽奖)\n')
+                else:
+                    count_in_dict(result_dict, '第一单(0元领/1元抽奖)\n第二单(常规订单)\n')
+        else:
+            # 仅一单为常规
+            if len(user_buy_list) == 1:
+                count_in_dict(result_dict, '仅1单(常规订单)\n')
+                print(user_buy_list)
+            else:
+                user_buy_detail_s = user_buy_list[1]
+                if load_data.is_zero_buy(user_buy_detail_s) <= 1.0:
+                    count_in_dict(result_dict, '第一单(常规订单)\n第二单(0元领/1元抽奖)\n')
+                else:
+                    count_in_dict(result_dict, '第一单(常规订单)\n第二单(常规订单)\n')
+
+    chart.draw_pie_chart("复购路径", result_dict)
+
+    result_dict = {}
+    for data in load_data.real_data_list:
+        result_value = str(data['商品类型'])
+        count_in_dict(result_dict, result_value)
+
+    result_tmp = sorted(result_dict.items(), key=lambda kv: (kv[1], kv[0]), reverse=True)
+    result_dict = {}
+    for (key, value) in result_tmp:
+        result_dict[key] = value
+    chart.draw_pie_chart("商品类型占比\n(去除0元领/1元福利等)", result_dict)
+
+
+# 按照价格段进行占比
+def analysis_price(load_data, chart):
+    result_dict = {}
+    for data in load_data.real_data_list:
+        result_price = float(data['价格'])
+        # 价格按10一个step聚合
+        result_price_int = int(result_price / 10)
+        if result_price_int < 1:
+            result_key = '%d-9' % (result_price_int)
+        else:
+            result_key = '%d0-%d9' % (result_price_int, result_price_int)
+
+        count_in_dict(result_dict, result_key)
+
+    result_tmp = sorted(result_dict.items(), key=lambda kv: (kv[1], kv[0]), reverse=True)
+    result_dict = {}
+    for index in range(len(result_tmp)):
+        item = result_tmp[index]
+        if index < 15:
+            result_dict[item[0]] = item[1]
+        else:
+            count_in_dict(result_dict, '其他价格段', item[1])
+    chart.draw_pie_chart("价格段占比\n(去除0元领/1元福利等)", result_dict)
+
+
+# 用户下单时间占比
+def analysis_order(load_data,chart):
+    result_dict = {}
+    for data_key in load_data.real_data_dict:
+        data_value = len(load_data.real_data_dict[data_key])
+        result_key = "%d单" % data_value
+        count_in_dict(result_dict,result_key)
+
+    result_tmp = sorted(result_dict.items(), key=lambda kv: (kv[1], kv[0]), reverse=True)
+    result_dict = {}
+    for (key, value) in result_tmp:
+        result_dict[key] = value
+    chart.draw_pie_chart("订单数占比\n(去除0元领/1元福利等)", result_dict)
+

echart_draw.py

+import pyecharts.options as opts
+from pyecharts.charts import Line, Pie, Page
+
+
+class EChartDraw(object):
+    def __init__(self, result_path):
+        self.page = Page(layout=Page.DraggablePageLayout)
+        self.result_path = result_path
+
+    def draw_pie_chart(self, title_name, data_dict):
+        x_data = sorted(data_dict)
+        y_data = []
+        for key in x_data:
+            y_data.append(data_dict[key])
+        pie = Pie(init_opts=opts.InitOpts(width="1200px", height="600px"))
+        pie.set_global_opts(title_opts=opts.TitleOpts(title=title_name), legend_opts=opts.LegendOpts(pos_top=50),
+                            )
+        pie.add("", [list(z) for z in zip(x_data, y_data)], center=["50%", "60%"])
+        pie.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}({d}%)"))
+        self.page.add(pie)
+
+    def draw_line_chart(self, title_name, data_dict):
+        x_data = sorted(data_dict)
+        y_data = []
+        for key in x_data:
+            y_data.append(data_dict[key])
+        line = Line(init_opts=opts.InitOpts(width="1200px", height="600px"))
+        line.set_global_opts(
+            title_opts=opts.TitleOpts(title=title_name),
+            legend_opts=opts.LegendOpts(pos_top=50),
+            xaxis_opts=opts.AxisOpts(type_="category", axislabel_opts={"rotate": -30}),
+            yaxis_opts=opts.AxisOpts(
+                type_="value",
+                axistick_opts=opts.AxisTickOpts(is_show=True),
+                splitline_opts=opts.SplitLineOpts(is_show=True),
+
+            )
+        )
+        line.add_xaxis(xaxis_data=x_data)
+        line.add_yaxis(
+            series_name="",
+            y_axis=y_data,
+            symbol="emptyCircle",
+            is_symbol_show=True,
+            label_opts=opts.LabelOpts(is_show=True),
+        )
+        self.page.add(line)
+
+    def build(self):
+        self.page.render(self.result_path)

load_data.py

+import xlrd
+
+import csv
+
+
+# 读取数据
+
+class LoadData(object):
+    def __init__(self, file_path):
+        self.file_path = file_path
+        self.title_list = []
+        # 基础数据
+        self.data_list = []
+        # 用户id进行分组
+        self.data_dict = {}
+        # 去除0元领，1元抽奖，服务费
+        self.real_data_list = []
+        # 去除0元领，1元抽奖，服务费
+        self.real_data_dict = []
+
+    def __build_re_buy_data(self):
+        # 需要去除价格为0的
+        for data in self.data_list:
+            if float(data['价格']) == 0.0:
+                print("删除价格为0 ", data)
+                self.data_list.remove(data)
+            if data['itemtype'] == '53':
+                data['商品类型'] = '212商品_一口价'
+            elif data['itemtype'] == '51':
+                data['商品类型'] = '212商品_拍卖'
+
+        self.data_dict = {}
+        self.real_data_list = []
+        self.real_data_dict = {}
+        # 按用户id聚合
+        for data in self.data_list:
+            user_id = str(int(data['用户id']))
+            item_list = []
+            if user_id in self.data_dict:
+                item_list = self.data_dict[user_id]
+            item_list.append(data)
+            sorted(item_list, key=lambda item: item['付费时间'])
+            self.data_dict[user_id] = item_list
+            # 去除价格少于1元的
+            if not self.is_zero_buy(data):
+                self.real_data_list.append(data)
+
+        # 去除0元领后排序
+        for data in self.real_data_list:
+            user_id = str(int(data['用户id']))
+            item_list = []
+            if user_id in self.real_data_dict:
+                item_list = self.real_data_dict[user_id]
+            item_list.append(data)
+            sorted(item_list, key=lambda item: item['付费时间'])
+            self.real_data_dict[user_id] = item_list
+
+    def __load_csv(self):
+        with open(self.file_path) as file:
+            file_csv = csv.reader(file)
+            self.title_list = next(file_csv)
+            for row in file_csv:
+                data = {}
+                for c_index in range(len(self.title_list)):
+                    data[self.title_list[c_index]] = row[c_index]
+                self.data_list.append(data)
+            self.__build_re_buy_data()
+
+    def __load_xlsx(self):
+        workbook = xlrd.open_workbook(self.file_path)
+        sheet = workbook.sheet_by_index(0)
+        print('行数:', sheet.nrows, "列数:", sheet.ncols)
+        # 获取标题
+        for column in range(sheet.ncols):
+            self.title_list.append(sheet.cell(0, column).value)
+
+        print('标题:', self.title_list)
+        for row in range(1, sheet.nrows, 1):
+            data = {}
+            for colum in range(sheet.ncols):
+                data[self.title_list[colum]] = sheet.cell(row, colum).value
+            self.data_list.append(data)
+        self.__build_re_buy_data()
+
+    def load(self):
+        self.title_list = []
+        self.data_list = []
+        if self.file_path.find('.csv') > 0:
+            self.__load_csv()
+            print("读取CSV文件Done>>", self.file_path)
+        elif self.file_path.find('.xlsx') > 0:
+            self.__load_xlsx()
+            print("读取XLSX文件Done>>", self.file_path)
+        else:
+            print("读取失败,不支持该文件类型>>", self.file_path)
+
+    def is_zero_buy(self, data):
+        data_name = data['订单名称']
+        data_price = float(data['价格'])
+        return data_name.find('0元领') != -1 or data_price <= 1.0

main_analysis.py

+import os
+
+from analysis_strategy import analysis_classify, analysis_category, analysis_goods, analysis_price, analysis_order
+from echart_draw import EChartDraw
+from load_data import LoadData
+
+
+def analysis_list(load_data, result_path):
+    chart = EChartDraw('./result/' + result_path)
+    analysis_classify(load_data, chart)
+    analysis_category(load_data, chart)
+    analysis_goods(load_data, chart)
+    analysis_price(load_data, chart)
+    analysis_order(load_data, chart)
+    chart.build()
+
+
+if __name__ == "__main__":
+    # 读取文件
+    for root, dirs, files in os.walk('csv'):
+        for file in files:
+            csv_path = os.path.join(root, file)
+            result_file_name = file.replace('.csv', '_result.html')
+            load_data = LoadData(csv_path)
+            load_data.load()
+            analysis_list(load_data, result_file_name)

requirements.txt

+pyecharts==1.9.1
+xlrd==1.2.0