# 讀取Excel文檔并且指定工作表的名稱
file_name = 'Bike_Sales_Playground.xlsx'
df = pd.read_excel(file_name,sheet_name='bike_buyers')

# 新建一張工作表
with pd.ExcelWriter(file_name,#文檔的名稱
                  engine='openpyxl',#調(diào)用模塊的名稱
                  mode='a',#添加的模式
                 if_sheet_exists="replace" #如果已經(jīng)存在，就替換掉
                 ) as writer:
df.to_excel(writer, sheet_name='Working_Sheet',index = False)# 設(shè)置Index為False

# 從新的工作表當(dāng)中來(lái)讀取數(shù)據(jù)
df = pd.read_excel(file_name,sheet_name='Working_Sheet')

# 去掉重復(fù)值
df.drop_duplicates(keep='first', inplace=True, ignore_index=False)
    
# 針對(duì)婚姻狀況這一列，“已婚”替換成“M”，“單身”替換成“S”
df['Marital Status'] = df['Marital Status'].replace('M','Married').replace('S','Single')
    
# 針對(duì)性別這一列，“男性”替換成“F”，而“女性”替換成“M”
df['Gender'] = df['Gender'].replace('F','Female').replace('M','Male')

# 查看表格的前5行
df.head()

# 年齡數(shù)值的處理
df['Age brackets'] = df['Age'].apply(lambda x: 'Less than 30' if x<=30 else('Greater than 55' if x>55 else '31 to 55'))

# 通勤距離的數(shù)值的替換
df['Commute Distance'] = df['Commute Distance'].replace('10+ Miles','More than 10 Miles')

# 透視表1
# 制作數(shù)據(jù)透視表
avg_gender_income_df = np.round(pd.pivot_table(bike_df,
               values = 'Income',
               index = ['Gender'],
               columns = ['Purchased Bike'],
               aggfunc = np.mean
              ),2)

# 將數(shù)據(jù)透視表放入Excel表格中，并且指定工作表
with pd.ExcelWriter(file_name,#工作表的名稱
                    engine='openpyxl',#引擎的名稱
                    mode='a',#Append模式
                   if_sheet_exists="replace" #如果已經(jīng)存在，就替換掉
                   ) as writer:  
    
    avg_gender_income_df.to_excel(writer, sheet_name='Average_Gender_Income')

# 加載文檔，并且指定工作表
wb = load_workbook(file_name)
sheet = wb['Average_Gender_Income']

# 創(chuàng)建柱狀圖
chart1 = BarChart()
chart1.type = "col"
chart1.style = 10
chart1.title = "基于性別與消費(fèi)數(shù)據(jù)之下的平均收入"
chart1.y_axis.title = '性別'
chart1.x_axis.title = '收入'

# 將繪制出來(lái)的柱狀圖放在單元格中去
data1 = Reference(sheet, min_col=2, min_row=1, max_row=3, max_col=3)#Including Headers
cats1 = Reference(sheet, min_col=1, min_row=2, max_row=3)#Not including headers
chart1.add_data(data1, titles_from_data=True)
chart1.dataLabels = DataLabelList() 
chart1.dataLabels.showVal = True
chart1.set_categories(cats1)
chart1.shape = 4
sheet.add_chart(chart1, "A10")
wb.save(file_name)

# 創(chuàng)建一個(gè)空的DataFrame表格
title_df = pd.DataFrame()

# 將結(jié)果放入至Excel文件當(dāng)中去
with pd.ExcelWriter(file_name,#工作表的名稱
                    engine='openpyxl',#引擎的名稱
                    mode='a',#Append模式
                   if_sheet_exists="replace" #如果已經(jīng)存在，就替換掉
                   ) as writer:  
    
    title_df.to_excel(writer, sheet_name='Dashboard')

# 加載文檔，指定工作表是哪個(gè)
wb = load_workbook(file_name)
sheet = wb['Dashboard']
for x in range(1,22):
    sheet.merge_cells('A1:R4')
    
cell = sheet.cell(row=1, column=1)  
cell.value = 'Bike Sales Dashboard'  
cell.alignment = Alignment(horizontal='center', vertical='center')   
cell.font  = Font(b=True, color="F8F8F8",size = 46)
cell.fill = PatternFill("solid", fgColor="2591DB")

# 將繪制出來(lái)的圖表放置到Excel文檔中
sheet.add_chart(chart1,'A5')
sheet.add_chart(chart2,'J5')
chart3.width = 31
sheet.add_chart(chart3,'A20')
wb.save(file_name)

import Bikes_Sales_Report_Automation as auto

# 填入文件的名稱
auto.automate_excel_dashboard('Bike_Sales_Playground.xlsx')