# coding=utf-8
import pandas as pd
from matplotlib import pyplot as plt
import numpy as np
file_path = "./IMDB-Movie-Data.csv"
 
df = pd.read_csv(file_path)
print(df["Genre"].head(3))
#統計分類的列表
temp_list = df["Genre"].str.split(",").tolist()  #[[],[],[]]
 
genre_list = list(set([i for j in temp_list for i in j]))
 
#構造全為0的數組
zeros_df = pd.DataFrame(np.zeros((df.shape[0],len(genre_list))),columns=genre_list)
# print(zeros_df)
 
#給每個電影出現分類的位置賦值1
for i in range(df.shape[0]):
    #zeros_df.loc[0,["Sci-fi","Mucical"]] = 1
    zeros_df.loc[i,temp_list[i]] = 1
 
# print(zeros_df.head(3))
 
#統計每個分類的電影的數量和
genre_count = zeros_df.sum(axis=0)
print(genre_count)
 
#排序
genre_count = genre_count.sort_values()
_x = genre_count.index
_y = genre_count.values
#畫圖
plt.figure(figsize=(20,8),dpi=80)
plt.bar(range(len(_x)),_y,width=0.4,color="blue")
plt.xticks(range(len(_x)),_x)
plt.show()

import pandas as pd
 
file_path = "./starbucks_store_worldwide.csv"
 
df = pd.read_csv(file_path)
grouped = df.groupby(by="Country")#按照分組查詢
# print(grouped)
 
#DataFrameGroupBy
#可以進行遍歷
# for i,j in grouped:
#     print(i)
#     print("-"*100)
#     print(j,type(j))
#     print("*"*100)
# 調用聚合方法
country_count = grouped["Brand"].count()
# print(country_count["US"])
# print(country_count["CN"])
 
#統計中國每個省店鋪的數量
china_data = df[df["Country"] =="CN"]
grouped = china_data.groupby(by="State/Province").count()["Brand"]
# print(grouped)
# 數據按照多個條件進行分組,返回Series
grouped = df["Brand"].groupby(by=[df["Country"],df["State/Province"]]).count()
# print(grouped)
# print(type(grouped))
# 數據按照多個條件進行分組,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"]]
print(grouped1,type(grouped1))
print("*"*100)
print(grouped2,type(grouped2))
print("*"*100)
print(grouped3,type(grouped3))