1. # coding=utf-8
    2. import pandas as pd
    3. from matplotlib import pyplot as plt
    6. file_path = "./books.csv"
    8. df = pd.read_csv(file_path)
    9. # print(df.head(2))
    10. #
    11. # print(df.info())
    13. # data1 = df[pd.notnull(df["original_publication_year"])]
    14. #
    15. # grouped = data1.groupby(by="original_publication_year").count()["title"]
    18. #不同年份书的平均评分情况
    19. #去除original_publication_year列中nan的行
    20. data1 = df[pd.notnull(df["original_publication_year"])]
    22. grouped = data1["average_rating"].groupby(by=data1["original_publication_year"]).mean()
    24. # print(grouped)
    26. _x = grouped.index
    27. _y = grouped.values
    29. #画图
    30. plt.figure(figsize=(20,8),dpi=80)
    31. plt.plot(range(len(_x)),_y)
    32. print(len(_x))
    34. plt.xticks(list(range(len(_x)))[::10],_x[::10].astype(int),rotation=45)
    35. plt.show()