python 之pandas 02统计电影分类情况

统计一组电影的分类情况

str.split()函数
把字符串分割到数组中。str_split(string,length) string：要分割的字符串，length可规定每个数组的长度。

import pandas as pd
import numpy as np
file_path = "./IMDB-Movie-Data.csv"
df = pd.read_csv(file_path)
#提取电影类型这一列，首先将字符串转为数组，再转换为列表
list1 = df["Genre"].str.split(",").tolist()
print(list1)
print("*****")
#获取电影所有类型，转化为集合可去掉重复项
# genre_list =list(set([i for j in list1 for i in j]))
genre_list = []
for j in list1:
    for i in j:
        #append函数没有返回值，不能写genre_list = genre_list.append(i)
        genre_list.append(i)

genre_list=list(set(genre_list))
print(genre_list)
#构造全为0的数组,行数为df数组的行，列数为电影类型的个数
zeros = np.zeros((df.shape[0],len(genre_list)))
#将为0的数组转化为DataFrame格式，列索引为电影类型
zeros_df = pd.DataFrame(zeros,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]):
    #list1[i]为第i个电影的类型组成的列表
    zeros_df.loc[i,list1[i]] = 1
#统计每个分类的数量和
count = zeros_df.sum(axis = 0)
print(count)
#排序
count_new = count.sort_values(ascending = False)
print(count_new)

[['Action', 'Adventure', 'Sci-Fi'], ['Adventure', 'Mystery', 'Sci-Fi'], ['Horror', 'Thriller'], ['Animation', 'Comedy', 'Family'], ['Action', 'Adventure', 'Fantasy'], ['Action', 'Adventure', 'Fantasy'], ['Comedy', 'Drama', 'Music'], ['Comedy'], ['Action', 'Adventure', 'Biography'], ['Adventure', 'Drama', 'Romance'], ['Adventure', 'Family', 'Fantasy'], ['Biography', 'Drama', 'History'], ['Action', 'Adventure', 'Sci-Fi'], ['Animation', 'Adventure', 'Comedy'], ['Action', 'Comedy', 'Drama'], ['Animation', 'Adventure', 'Comedy'], ['Biography', 'Drama', 'History'], ['Action', 'Thriller'], ['Biography', 'Drama'], ['Drama', 'Mystery', 'Sci-Fi'], ['Adventure', 'Drama', 'Thriller'], ['Drama'], ['Crime', 'Drama', 'Horror'], ['Animation', 'Adventure', 'Comedy'], ['Action', 'Adventure', 'Sci-Fi'], ['Comedy'], ['Action', 'Adventure', 'Drama'], ['Horror', 'Thriller'], ['Comedy'], ['Action', 'Adventure', 'Drama'], ['Comedy'], ['Drama', 'Thriller'], ['Action', 'Adventure', 'Sci-Fi'], ['Action', 'Adventure', 'Comedy'], ['Action', 'Horror', 'Sci-Fi'], ['Action', 'Adventure', 'Sci-Fi'], ['Adventure', 'Drama', 'Sci-Fi'], ['Action', 'Adventure', 'Fantasy'], ['Action', 'Adventure', 'Western'], ['Comedy', 'Drama'], ['Animation', 'Adventure', 'Comedy'], ['Drama'], ['Horror'], ['Biography', 'Drama', 'History'], ['Drama'], ['Action', 'Adventure', 'Fantasy'], ['Drama', 'Thriller'], ['Adventure', 'Drama', 'Fantasy'], ['Action', 'Adventure', 'Sci-Fi'], ['Drama'], ['Action', 'Adventure', 'Fantasy'], ['Action', 'Adventure', 'Fantasy'], ['Comedy', 'Drama'], ['Action', 'Crime', 'Thriller'], ['Action', 'Crime', 'Drama'], ['Adventure', 'Drama', 'History'], ['Crime', 'Horror', 'Thriller'], ['Drama', 'Romance'], ['Comedy', 'Drama', 'Romance'], ['Biography', 'Drama'], ['Action', 'Adventure', 'Sci-Fi'], ['Horror', 'Mystery', 'Thriller'], ['Crime', 'Drama', 'Mystery'], ['Drama', 'Romance', 'Thriller'], ['Drama', 'Mystery', 'Sci-Fi'], ['Action', 'Adventure', 'Comedy'], ['Drama', 'History', 'Thriller'], ['Action', 'Adventure', 'Sci-Fi'], ['Drama'], ['Action', 'Drama', 'Thriller'], ['Drama', 'History'], ['Action', 'Drama', 'Romance'], ['Drama', 'Fantasy'], ['Drama', 'Romance'], ['Animation', 'Adventure', 'Comedy'], ['Action', 'Adventure', 'Fantasy'], ['Action', 'Sci-Fi'], ['Adventure', 'Drama', 'War'], ['Action', 'Adventure', 'Fantasy'], ['Action', 'Comedy', 'Fantasy'], ['Action', 'Adventure', 'Sci-Fi'], ['Comedy', 'Drama'], ['Biography', 'Comedy', 'Crime'], ['Crime', 'Drama', 'Mystery'], ['Action', 'Crime', 'Thriller'], ['Action', 'Adventure', 'Sci-Fi'], ['Crime', 'Drama'], ['Action', 'Adventure', 'Fantasy'], ['Crime', 'Drama', 'Mystery'], ['Action', 'Crime', 'Drama'], ['Crime', 'Drama', 'Mystery'], ['Action', 'Adventure', 'Fantasy'], ['Drama'], ['Comedy', 'Crime', 'Drama'], ['Action', 'Adventure', 'Sci-Fi'], ['Action', 'Comedy', 'Crime'], ['Animation', 'Drama', 'Fantasy'], ['Horror', 'Mystery', 'Sci-Fi'], ['Drama', 'Mystery', 'Thriller'], ['Crime', 'Drama', 'Thriller'], ['Biography', 'Crime', 'Drama'], ['Action', 'Adventure', 'Fantasy'], ['Adventure', 'Drama', 'Sci-Fi'], ['Crime', 'Mystery', 'Thriller'], ['Action', 'Adventure', 'Comedy'], ['Crime', 'Drama', 'Thriller'], ['Comedy'], ['Action', 'Adventure', 'Drama'], ['Drama'], ['Drama', 'Mystery', 'Sci-Fi'], ['Action', 'Horror', 'Thriller'], ['Biography', 'Drama', 'History'], ['Romance', 'Sci-Fi'], ['Action', 'Fantasy', 'War'], ['Adventure', 'Drama', 'Fantasy'], ['Comedy'], ['Horror', 'Thriller'], ['Action', 'Biography', 'Drama'], ['Drama', 'Horror', 'Mystery'], ['Animation', 'Adventure', 'Comedy'], ['Adventure', 'Drama', 'Family'], ['Adventure', 'Mystery', 'Sci-Fi'], ['Adventure', 'Comedy', 'Romance'], ['Action'], ['Action', 'Thriller'], ['Adventure', 'Drama', 'Family'], ['Action', 'Adventure', 'Sci-Fi'], ['Adventure', 'Crime', 'Mystery'], ['Comedy', 'Family', 'Musical'], ['Adventure', 'Drama', 'Thriller'], ['Drama'], ['Adventure', 'Comedy', 'Drama'], ['Drama', 'Horror', 'Thriller'], ['Drama', 'Music'], ['Action', 'Crime', 'Thriller'], ['Crime', 'Drama', 'Thriller'], ['Crime', 'Drama', 'Thriller'], ['Drama', 'Romance'], ['Mystery', 'Thriller'], ['Mystery', 'Thriller', 'Western'], ['Action', 'Adventure', 'Sci-Fi'], ['Comedy', 'Family'], ['Biography', 'Comedy', 'Drama'], ['Drama'], ['Drama', 'Western'], ['Drama', 'Mystery', 'Romance'], ['Comedy', 'Drama'], ['Action', 'Drama', 'Mystery'], ['Comedy'], ['Action', 'Adventure', 'Crime'], ['Adventure', 'Family', 'Fantasy'], ['Adventure', 'Sci-Fi', 'Thriller'], ['Drama'], ['Action', 'Crime', 'Drama'], ['Drama', 'Horror', 'Mystery'], ['Action', 'Horror', 'Sci-Fi'], ['Action', 'Adventure', 'Sci-Fi'], ['Comedy', 'Drama', 'Romance'], ['Action', 'Comedy', 'Fantasy'], ['Action', 'Comedy', 'Mystery'], ['Thriller', 'War'], ['Action', 'Comedy', 'Crime'], ['Action', 'Adventure', 'Sci-Fi'], ['Action', 'Adventure', 'Crime'], ['Action', 'Adventure', 'Thriller'], ['Drama', 'Fantasy', 'Romance'], ['Action', 'Adventure', 'Comedy'], ['Biography', 'Drama', 'History'], ['Action', 'Drama', 'History'], ['Action', 'Adventure', 'Thriller'], ['Crime', 'Drama', 'Thriller'], ['Animation', 'Adventure', 'Family'], ['Adventure', 'Horror'], ['Drama', 'Romance', 'Sci-Fi'], ['Animation', 'Adventure', 'Comedy'], ['Action', 'Adventure', 'Family'], ['Action', 'Adventure', 'Drama'], ['Action', 'Comedy'], ['Horror', 'Mystery', 'Thriller'], ['Action', 'Adventure', 'Comedy'], ['Comedy', 'Romance'], ['Horror', 'Mystery'], ['Drama', 'Family