重构ACV分析部分代码，将中间结果输出到excel中

analyze_acv.py

@@ -1,5 +1,7 @@
 import pandas as pd
 from typing import List
+from openpyxl import Workbook
+
 def strip_character(column_name, characters: List[str]):
 
     new_col_name = column_name
@@ -26,28 +28,36 @@ def calc_acv_sum(df, acv_name, group_by_column):
     df_grouped_sum[acv_name] = df_grouped_sum[acv_name].apply(lambda x: '{:,}'.format(x))
     return df_grouped_sum
 
+def save_to_excel(dataframes, sheet_names, output_file):
+    with pd.ExcelWriter(output_file, engine='openpyxl') as writer:
+        for df, sheet_name in zip(dataframes, sheet_names):
+            df.to_excel(writer, sheet_name=sheet_name, index=False)
 
 # 读取赢单Excel文件
 df_win = pd.read_excel('./data_src/pingcap_won.xlsx')
 acv_name = 'ACV'
 
+# 创建一个列表来存储所有的数据帧和对应的sheet名称
+dataframes = []
+sheet_names = []
+
 # ACV by 客户分类
-print("------ACV by 行业------")
 df_win_grouped_by_industry_sum = calc_acv_sum(df_win, acv_name, '客户分类')
-print(refine_content(df_win_grouped_by_industry_sum))
+dataframes.append(refine_content(df_win_grouped_by_industry_sum))
+sheet_names.append("ACV by 行业")
 
 # Group by customer industry and calculate the average ACV for each group
-print("------平均ACV by 行业------")
 df_win_grouped_by_industry_mean = calc_acv_mean(df_win, acv_name, '客户分类')
-print(refine_content(df_win_grouped_by_industry_mean))
+dataframes.append(refine_content(df_win_grouped_by_industry_mean))
+sheet_names.append("平均ACV by 行业")
 
-print("------ACV by 子行业------")
 df_win_grouped_by_sub_industry_sum = calc_acv_sum(df_win, acv_name, '客户行业')
-print(refine_content(df_win_grouped_by_sub_industry_sum))
+dataframes.append(refine_content(df_win_grouped_by_sub_industry_sum))
+sheet_names.append("ACV by 子行业")
 
-print("------平均ACV by 子行业------")
 df_win_grouped_by_sub_industry_mean = calc_acv_mean(df_win, acv_name, '客户行业')
-print(refine_content(df_win_grouped_by_sub_industry_mean))  
+dataframes.append(refine_content(df_win_grouped_by_sub_industry_mean))
+sheet_names.append("平均ACV by 子行业")
 
 # 读取Excel文件
 df = pd.read_excel('./data_src/pingcap_pipeline.xlsx')
@@ -55,22 +65,24 @@ df = pd.read_excel('./data_src/pingcap_pipeline.xlsx')
 # 按照"客户分类"列分组，并计算ACV列的和
 acv_name = '预估 ACV'
 
-print("------预估ACV by 行业------")
 df_pipeline_grouped_by_industry_sum = calc_acv_sum(df, acv_name, '负责人所属行业')
-print(refine_content(df_pipeline_grouped_by_industry_sum))
+dataframes.append(refine_content(df_pipeline_grouped_by_industry_sum))
+sheet_names.append("预估ACV by 行业")
 
-
-print("------平均预估ACV by 行业------")
 df_pipeline_grouped_by_industry_mean = calc_acv_mean(df, acv_name, '负责人所属行业')
-print(refine_content(df_pipeline_grouped_by_industry_mean))
+dataframes.append(refine_content(df_pipeline_grouped_by_industry_mean))
+sheet_names.append("平均预估ACV by 行业")
 
-
-print("------预估ACV by 子行业------")
 df_pipeline_grouped_by_sub_industry_sum = calc_acv_sum(df, acv_name, '客户行业')
-print(refine_content(df_pipeline_grouped_by_sub_industry_sum))
+dataframes.append(refine_content(df_pipeline_grouped_by_sub_industry_sum))
+sheet_names.append("预估ACV by 子行业")
 
-
-
-print("------平均预估ACV by 子行业------")
 df_pipeline_grouped_by_sub_industry_mean = calc_acv_mean(df, acv_name, '客户行业')
-print(refine_content(df_pipeline_grouped_by_sub_industry_mean))
+dataframes.append(refine_content(df_pipeline_grouped_by_sub_industry_mean))
+sheet_names.append("平均预估ACV by 子行业")
+
+# 保存所有数据帧到一个Excel文件中
+output_file = './output/acv_analysis.xlsx'
+save_to_excel(dataframes, sheet_names, output_file)
+
+print(f"Analysis results have been saved to {output_file}")

analyze_acv_dist.py

@@ -1,5 +1,6 @@
 import pandas as pd
 from typing import List
+from openpyxl import Workbook
 
 def strip_character(column_name, characters: List[str]):
 
@@ -25,27 +26,25 @@ def get_acv_distribution(df, acv_name, industry_col_name):
     industry_acv_distribution.loc['Total'] = industry_acv_distribution.sum()
     return industry_acv_distribution
 
-# Define the bins for ACV intervals
+# 新增函数：将结果保存到Excel
+def save_to_excel(dfs, sheet_names, output_file):
+    with pd.ExcelWriter(output_file, engine='openpyxl') as writer:
+        for df, sheet_name in zip(dfs, sheet_names):
+            df.to_excel(writer, sheet_name=sheet_name)
+
+# 读取数据
 df = pd.read_excel('./data_src/pingcap_won.xlsx')
-
-
-print('---------成单:ACV Distribution by industry--------')
-
-print(get_acv_distribution(df, 'ACV', '客户分类'))
-
-
-print('---------成单:ACV Distribution by sub-industry--------')
-
-print(get_acv_distribution(df, 'ACV', '客户行业'))
-
-
 df_pipeline = pd.read_excel('./data_src/pingcap_pipeline.xlsx')
 
-print('---------Pipeline:ACV Distribution by industry--------')
+# 获取各种分布
+won_industry_dist = get_acv_distribution(df, 'ACV', '客户分类')
+won_sub_industry_dist = get_acv_distribution(df, 'ACV', '客户行业')
+pipeline_industry_dist = get_acv_distribution(df_pipeline, '预估 ACV', '负责人所属行业')
+pipeline_sub_industry_dist = get_acv_distribution(df_pipeline, '预估 ACV', '客户行业')
 
-print(get_acv_distribution(df_pipeline, '预估 ACV', '负责人所属行业'))
+# 保存结果到Excel
+dfs = [won_industry_dist, won_sub_industry_dist, pipeline_industry_dist, pipeline_sub_industry_dist]
+sheet_names = ['成单-行业分布', '成单-子行业分布', 'Pipeline-行业分布', 'Pipeline-子行业分布']
+save_to_excel(dfs, sheet_names, './output/acv_distribution.xlsx')
 
-
-print('---------Pipeline:ACV Distribution by sub-industry--------')
-
-print(get_acv_distribution(df_pipeline, '预估 ACV', '客户行业'))
+print("ACV distribution analysis completed. Results saved in './output/acv_distribution.xlsx'")