import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
df = pd.read_csv("./IMDB-Movie-Data.csv")
# 获取电影分类数据
genre = df["Genre"]
# 获取不重复的种类列表
temp_list = df["Genre"].str.split(",").tolist()
genre_list = list(set([i for j in temp_list for i in j]))
# 构造全为0的dataframe
zero_np = pd.DataFrame(np.zeros((genre.shape[0], len(genre_list))), columns=genre_list)
# 给为0的dataframe赋值
for i in range(genre.shape[0]):
zero_np.loc[i, temp_list[i]] = 1
# 分类之后求和
genre_count = zero_np.sum(axis=0)
genre_count = genre_count.sort_values()
_x = genre_count.index
_y = genre_count.values
print(type(genre_count))
plt.figure(figsize=(20, 8), dpi=80)
plt.bar(range(len(_x)), _y)
plt.xticks(range(len(_x)), _x)
plt.show()
python 电影种类之简单数据分析
最新推荐文章于 2024-08-13 17:30:00 发布