python数据分组聚合案例（星巴克数量统计）

知识点

import pandas as pd
import numpy as np
file_path='C:/Users/ming/Desktop/DataAnalysis-master/day05/code/starbucks_store_worldwide.csv'
df=pd.read_csv(file_path)
# 读取前一行
print(df.head(1))
# 读取字段
print(df.info())
# 按国家这个字段进行分组
grope=df.groupby(by='Country')
print(grope)
#DataFrameGroupBy
#可以进行遍历
# for i,j in grouped:
#     print(i)
#     print("-"*100)
#     print(j,type(j))
#     print("*"*100)
# df[df["Country"]="US"]
#调用聚合方法
# print(grope.count())
# print(grope['Brand'].count())
country_count=grope['Brand'].count()
# 美国星巴克数量
print(country_count['US'])
# 中国星巴克数量
print(country_count['CN'])

import pandas as pd
import numpy as np
file_path='C:/Users/ming/Desktop/DataAnalysis-master/day05/code/starbucks_store_worldwide.csv'
df=pd.read_csv(file_path)
# 读取前一行
print(df.head(1))
# 读取字段
print(df.info())
 # 按国家这个字段进行分组
# grope=df.groupby(by='Country')
# print(grope)
#DataFrameGroupBy
#可以进行遍历
# for i,j in grouped:
#     print(i)
#     print("-"*100)
#     print(j,type(j))
#     print("*"*100)
# df[df["Country"]="US"]
#调用聚合方法
# print(grope.count())
# print(grope['Brand'].count())
# country_count=grope['Brand'].count()
# # 美国星巴克数量
# print(country_count['US'])
# # 中国星巴克数量
# print(country_count['CN'])

# 统计中国国家省份的数量
china_data=df[df['Country']=='CN']
groped=china_data.groupby(by='State/Province')['Brand'].count()
print(groped)

import pandas as pd
import numpy as np
file_path='C:/Users/ming/Desktop/DataAnalysis-master/day05/code/starbucks_store_worldwide.csv'
df=pd.read_csv(file_path)
# 读取前一行
print(df.head(1))
# 读取字段
print(df.info())
 # 按国家这个字段进行分组
# grope=df.groupby(by='Country')
# print(grope)
#DataFrameGroupBy
#可以进行遍历
# for i,j in grouped:
#     print(i)
#     print("-"*100)
#     print(j,type(j))
#     print("*"*100)
# df[df["Country"]="US"]
#调用聚合方法
# print(grope.count())
# print(grope['Brand'].count())
# country_count=grope['Brand'].count()
# # 美国星巴克数量
# print(country_count['US'])
# # 中国星巴克数量
# print(country_count['CN'])

# 统计中国国家省份的数量
# china_data=df[df['Country']=='CN']
# groped=china_data.groupby(by='State/Province')['Brand'].count()
# print(groped)

# 数据按照多个条件进行分组
gr=df['Brand'].groupby(by=[df['Country'],df['State/Province']]).count()
print(gr)
print(type(gr))

import pandas as pd
import numpy as np
file_path='C:/Users/ming/Desktop/DataAnalysis-master/day05/code/starbucks_store_worldwide.csv'
df=pd.read_csv(file_path)
# 读取前一行
print(df.head(1))
# 读取字段
print(df.info())
 # 按国家这个字段进行分组
# grope=df.groupby(by='Country')
# print(grope)
#DataFrameGroupBy
#可以进行遍历
# for i,j in grouped:
#     print(i)
#     print("-"*100)
#     print(j,type(j))
#     print("*"*100)
# df[df["Country"]="US"]
#调用聚合方法
# print(grope.count())
# print(grope['Brand'].count())
# country_count=grope['Brand'].count()
# # 美国星巴克数量
# print(country_count['US'])
# # 中国星巴克数量
# print(country_count['CN'])

# 统计中国国家省份的数量
# china_data=df[df['Country']=='CN']
# groped=china_data.groupby(by='State/Province')['Brand'].count()
# print(groped)

# 数据按照多个条件进行分组,类型Series
# gr=df['Brand'].groupby(by=[df['Country'],df['State/Province']]).count()
# print(gr)
# print(type(gr))
# 数据按照多个条件进行分组,返回DataFrame
grouped1 = df[["Brand"]].groupby(by=[df["Country"],df["State/Province"]]).count()
# grouped2= df.groupby(by=[df["Country"],df["State/Province"]])[["Brand"]].count()
# grouped3 = df.groupby(by=[df["Country"],df["State/Province"]]).count()[["Brand"]]