1. # coding=utf-8
    2. import pandas as pd
    3. from matplotlib import pyplot as plt
    4. import numpy as np
    5. file_path = "./IMDB-Movie-Data.csv"
    7. df = pd.read_csv(file_path)
    8. print(df["Genre"].head(3))
    9. #统计分类的列表
    10. temp_list = df["Genre"].str.split(",").tolist()  #[[],[],[]]
    12. genre_list = list(set([i for j in temp_list for i in j]))
    14. #构造全为0的数组
    15. zeros_df = pd.DataFrame(np.zeros((df.shape[0],len(genre_list))),columns=genre_list)
    16. # print(zeros_df)
    18. #给每个电影出现分类的位置赋值1
    19. for i in range(df.shape[0]):
    20.     #zeros_df.loc[0,["Sci-fi","Mucical"]] = 1
    21.     zeros_df.loc[i,temp_list[i]] = 1
    23. # print(zeros_df.head(3))
    25. #统计每个分类的电影的数量和
    26. genre_count = zeros_df.sum(axis=0)
    27. print(genre_count)
    29. #排序
    30. genre_count = genre_count.sort_values()
    31. _x = genre_count.index
    32. _y = genre_count.values
    33. #画图
    34. plt.figure(figsize=(20,8),dpi=80)
    35. plt.bar(range(len(_x)),_y,width=0.4,color="orange")
    36. plt.xticks(range(len(_x)),_x)
    37. plt.show()