zensol
/
market_assistant
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

计算ACV分布

This commit is contained in:
Tiger Ren 2024-08-23 19:50:35 +08:00
parent a2f8c0b3a0
commit 085f0dc880
1 changed files with 29 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

77
analyze_acv_dist.py
View File

@ -1,5 +1,6 @@
import pandas as pd
from typing import List
def strip_character(column_name, characters: List[str]):
new_col_name = column_name
@ -14,57 +15,37 @@ def refine_content(df):
df[col] = df[col].apply(lambda x: "其他" if strip_character(x, strip_character_list) == "" else strip_character(x, strip_character_list))
return df
# 读取赢单Excel文件
df_win = pd.read_excel('./data_src/pingcap_won.xlsx')
acv_name = 'ACV'
def get_acv_distribution(df, acv_name, industry_col_name):
# Define the bins for ACV intervals
bins = [0, 1e6, 5e6, float('inf')]
labels = ['<100万', '100万-500万', '>500万']
# Create a new column 'ACV Interval' based on the bins
df['ACV Interval'] = pd.cut(df[acv_name], bins=bins, labels=labels, right=False)
industry_acv_distribution = df.groupby([industry_col_name, 'ACV Interval']).size().unstack(fill_value=0)
industry_acv_distribution.loc['Total'] = industry_acv_distribution.sum()
return industry_acv_distribution
# ACV by 客户分类
df_win_grouped_by_industry = df_win.groupby('客户分类')[acv_name].sum().astype(int).reset_index()
df_win_grouped_by_industry[acv_name] = df_win_grouped_by_industry[acv_name].apply(lambda x: '{:,}'.format(x))
print("------ACV by 行业------")
print(refine_content(df_win_grouped_by_industry))
# Group by customer industry and calculate the average ACV for each group
won_average_acv_by_industry = df_win.groupby('客户分类')[acv_name].mean().astype(int).reset_index()
won_average_acv_by_industry[acv_name] = won_average_acv_by_industry[acv_name].apply(lambda x: '{:,}'.format(x))
print("------平均ACV by 行业------")
print(refine_content(won_average_acv_by_industry))
# Define the bins for ACV intervals
df = pd.read_excel('./data_src/pingcap_won.xlsx')
print('---------成单:ACV Distribution by industry--------')
df_win_grouped_by_sub_industry = df_win.groupby('客户行业')[acv_name].sum().astype(int).reset_index()
df_win_grouped_by_sub_industry[acv_name] = df_win_grouped_by_sub_industry[acv_name].apply(lambda x: '{:,}'.format(x))
print("------ACV by 子行业------")
print(refine_content(df_win_grouped_by_sub_industry))
won_average_acv_by_sub_industry = df_win.groupby('客户行业')[acv_name].mean().astype(int).reset_index()
won_average_acv_by_sub_industry[acv_name] = won_average_acv_by_sub_industry[acv_name].apply(lambda x: '{:,}'.format(x))
print("------平均ACV by 子行业------")
print(refine_content(won_average_acv_by_sub_industry))
# 读取Excel文件
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'
df_pipeline_grouped_by_industry = df.groupby('负责人所属行业')[acv_name].sum().astype(int).reset_index()
df_pipeline_grouped_by_industry = df_pipeline_grouped_by_industry.sort_values(by=acv_name, ascending=False)
df_pipeline_grouped_by_industry[acv_name] = df_pipeline_grouped_by_industry[acv_name].apply(lambda x: '{:,}'.format(x))
print("------预估ACV by 行业------")
print(refine_content(df_pipeline_grouped_by_industry))
pipeline_average_acv_by_industry = df.groupby('负责人所属行业')[acv_name].mean().astype(int).reset_index()
pipeline_average_acv_by_industry[acv_name] = pipeline_average_acv_by_industry[acv_name].apply(lambda x: '{:,}'.format(x))
print("------平均预估ACV by 行业------")
print(refine_content(pipeline_average_acv_by_industry))
df_pipeline_grouped_by_sub_industry = df.groupby('客户行业')[acv_name].sum().astype(int).reset_index()
df_pipeline_grouped_by_sub_industry[acv_name] = df_pipeline_grouped_by_sub_industry[acv_name].apply(lambda x: '{:,}'.format(x))
print("------预估ACV by 子行业------")
print(refine_content(df_pipeline_grouped_by_sub_industry))
print(get_acv_distribution(df, 'ACV', '客户分类'))
pipeline_average_acv_by_sub_industry = df.groupby('客户行业')[acv_name].mean().fillna(0).astype(int).reset_index()
pipeline_average_acv_by_sub_industry[acv_name] = pipeline_average_acv_by_sub_industry[acv_name].apply(lambda x: '{:,}'.format(x))
print("------平均预估ACV by 子行业------")
print(refine_content(pipeline_average_acv_by_sub_industry))
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--------')
print(get_acv_distribution(df_pipeline, '预估 ACV', '负责人所属行业'))
print('---------Pipeline:ACV Distribution by sub-industry--------')
print(get_acv_distribution(df_pipeline, '预估 ACV', '客户行业'))