pandas之统计方法2

print("*"*25+"数据分类统计"+"*"*25)

*************************数据分类*************************

import pandas as pd
from matplotlib import pyplot as plt
file_path="./IMDB-Movie-Data.csv"
df = pd.read_csv(file_path)
print(df["Genre"].head(3))

0     Action,Adventure,Sci-Fi
1    Adventure,Mystery,Sci-Fi
2             Horror,Thriller
Name: Genre, dtype: object

temp_list = df["Genre"].str.split(",").tolist() #[[],[],[]]
genre_list = list(set([i for j in temp_list for i in j]))#统计各分类做为列
import numpy as np
zeros_df=pd.DataFrame(np.zeros((df.shape[0],len(genre_list))),columns=genre_list)#构造全0的数组
#给每个电影出现的分类的位置赋值1
for i in range(df.shape[0]):
    zeros_df.loc[i,temp_list[i]] = 1
#     print(temp_list[i])#['Action', 'Adventure', 'Sci-Fi']
#     break
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)
#排序
genre_count=genre_count.sort_values()

#画图
_x=genre_count.index
_y=genre_count.values
plt.figure(figsize=(20,8),dpi=80)
plt.bar(range(len(_x)),_y,width=0.3,color="orange")
plt.xticks(range(len(_x)),_x)
plt.show()

   Music  War  Sport  Mystery  Musical  Action  Comedy  Adventure  Thriller  \
0    0.0  0.0    0.0      0.0      0.0     1.0     0.0        1.0       0.0   
1    0.0  0.0    0.0      1.0      0.0     0.0     0.0        1.0       0.0   
2    0.0  0.0    0.0      0.0      0.0     0.0     0.0        0.0       1.0   

   Drama  Romance  Family  History  Crime  Animation  Biography  Fantasy  \
0    0.0      0.0     0.0      0.0    0.0        0.0        0.0      0.0   
1    0.0      0.0     0.0      0.0    0.0        0.0        0.0      0.0   
2    0.0      0.0     0.0      0.0    0.0        0.0        0.0      0.0   

   Sci-Fi  Western  Horror  
0     1.0      0.0     0.0  
1     1.0      0.0     0.0  
2     0.0      0.0     1.0