1. # coding=utf-8
    2. import pandas as pd
    3. import numpy as np
    5. file_path = "./starbucks_store_worldwide.csv"
    7. df = pd.read_csv(file_path)
    8. # print(df.head(1))
    9. # print(df.info())
    10. # grouped = df.groupby(by="Country")
    11. # print(grouped)
    13. #DataFrameGroupBy
    14. #可以进行遍历
    15. # for i,j in grouped:
    16. #     print(i)
    17. #     print("-"*100)
    18. #     print(j,type(j))
    19. #     print("*"*100)
    20. # df[df["Country"]="US"]
    21. #调用聚合方法
    24. # country_count = grouped["Brand"].count()
    25. # print(country_count["US"])
    26. # print(country_count["CN"])
    28. #统计中国每个省店铺的数量
    29. # china_data = df[df["Country"] =="CN"]
    30. #
    31. # grouped = china_data.groupby(by="State/Province").count()["Brand"]
    32. #
    33. # print(grouped)
    35. #数据按照多个条件进行分组,返回Series
    36. # grouped = df["Brand"].groupby(by=[df["Country"],df["State/Province"]]).count()
    37. # print(grouped)
    38. # print(type(grouped))
    40. #数据按照多个条件进行分组,返回DataFrame
    41. grouped1 = df[["Brand"]].groupby(by=[df["Country"],df["State/Province"]]).count()
    42. # grouped2= df.groupby(by=[df["Country"],df["State/Province"]])[["Brand"]].count()
    43. # grouped3 = df.groupby(by=[df["Country"],df["State/Province"]]).count()[["Brand"]]
    45. print(grouped1,type(grouped1))
    46. # print("*"*100)
    47. # print(grouped2,type(grouped2))
    48. # print("*"*100)
    49. #
    50. # print(grouped3,type(grouped3))
    52. #索引的方法和属性
    53. print(grouped1.index)