import pandas as ps
import matplotlib.pyplot as plt
reviews = pd.read_csv(r"E:\PyCharm\fandango_score_comparison.csv")
cols = ["FILM", "RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingv
norm_reviews = reviews[cols]
fig, ax = plt.subplots()
ax.hist(norm_reviews["Fandango_Ratingvalue") #查看不同区间的个数(蓝)
ax.hist(norm_reviews["Fandango_Ratingvalue", bins=20) #同时分成20个容器
ax.hist(norm_reviews["Fandango_Ratingvalue", range=(4,5) bins=20) #同时选择区间4到5
如下图:
fig = plt.figure(figsize=(10,5))
ax1 = fig.add_subplot(2,2,1)
ax2 = fig.add_sbplot(2,2,4)
ax1.hist(norm_reviews["Fandango_Ratingvalue"], range(0,5), bins=20)
ax2.hist(norm_reviews["Fandango_Ratingvalue"], range(0.5), bins=20)
ax2.set_ylim(10,50) #设置y轴的范围
如图:
盒图如下(4分图):
fig, ax = plt.subplots()
ax.boxplot(norm_reviews["RT_user_norm"]) #设置4分图
ax.set_xticklabels(norm_reviews["RT_user_norm"]) #把x轴名字改为RE_user_norm
ax.set_ylim(0,5) #设置高度范围
plt.show()
如图:
多盒图在同一张图中显示
num_cols = ["RT_user_norm", "Metacritic_user_nom","Fandango_Ratingvalue"]
fig, ax = plt.subplots()
ax.boxplot(norm_reviews[num_cols].values)
ax.set_xticklabels(num_cols, rotation=90)
ax.set_ylim(0,5)
plt.show()
如下图;