import pandas as pd import matplotlib.pyplot as plt import seaborn as sns

读取数据

data = pd.read_csv('movies.csv')

将genres类型中用‘|’符合隔开

data['genres'] = data['genres'].str.split('|')

将年份作为索引，将数据集按照年份分组，得出每个年份各电影类型的数量

data = data.explode('genres') data['count'] = 1 data = pd.pivot_table(data, values='count', index='year', columns='genres', aggfunc='sum', fill_value=0)

取2000-2016电影类型数量

data = data.loc[2000:2016]

绘制热力图

plt.figure(figsize=(12, 6)) sns.heatmap(data, cmap='YlGnBu', annot=True, fmt='d', linewidths=.5) plt.title('Movie Genres Heatmap (2000-2016)', fontsize=14) plt.xlabel('Genres', fontsize=12) plt.ylabel('Year', fontsize=12) plt.show()

绘制电影类型饼状图

genres_count = data.sum() plt.figure(figsize=(8,8)) plt.pie(genres_count, labels=genres_count.index, autopct='%1.1f%%') plt.title('Movie Genres Distribution (2000-2016)', fontsize=14) plt.show(