Python学习 Day19

# coding=utf-8
import pandas as pd
from matplotlib import pyplot as plt
import numpy as np
file_path = "/Users/kenny/Downloads/python学习/拜师/数据分析资料/day05/code/IMDB-Movie-Data.csv"

df = pd.read_csv(file_path)
print(df["Genre"].head(3))
#统计分类的列表
temp_list = df["Genre"].str.split(",").tolist()  #[[],[],[]]

genre_list = list(set([i for j in temp_list for i in j]))

#构造全为0的数组
zeros_df = pd.DataFrame(np.zeros((df.shape[0],len(genre_list))),columns=genre_list)
# print(zeros_df)

#给每个电影出现分类的位置赋值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))

#统计每个分类的电影的数量和
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
#画图
plt.figure(figsize=(20,8),dpi=80)
plt.bar(range(len(_x)),_y,width=0.4,color="orange")
plt.xticks(range(len(_x)),_x)
plt.show()

# coding=utf-8
import pandas as pd
import numpy as np

file_path = "/Users/kenny/Downloads/python学习/拜师/数据分析资料/day05/code/starbucks_store_worldwide.csv"

df = pd.read_csv(file_path)
print(df.head(1))
print(df.info())
grouped = df.groupby(by="Country")
print(grouped)

#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

# country_count = grouped["Brand"].count()
# print(country_count["US"])
# print(country_count["CN"])

#统计中国每个省店铺的数量
# china_data = df[df["Country"] =="CN"]
#
# grouped = china_data.groupby(by="State/Province").count()["Brand"]
#
# print(grouped)

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

#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"]]

print(grouped1,type(grouped1))
# print("*"*100)
# print(grouped2,type(grouped2))
# print("*"*100)
#
# print(grouped3,type(grouped3))

#索引的方法和属性
print(grouped1.index)