Matplotlib直方图和四方图

import pandas as pdimport matplotlib.pyplot as pltreviews = pd.read_csv("D:\\test\\fandango_scores.csv")clos = ["Fandango_Ratingvalue","RT_norm","IMDB_norm","RT_norm_round","Metacritic_norm_round"]reviews_num = reviews[clos]

dis_imdb = reviews_num["Fandango_Ratingvalue"].value_counts() #对值进行统计dis_index = dis_imdb.sort_index()  #按索引排序print(dis_imdb) print(dis_index)

4.1    163.9    124.2    124.3    113.4     94.5     93.5     93.7     93.6     84.0     74.4     73.2     52.9     53.8     53.3     43.0     44.6     43.1     34.8     32.8     22.7     2Name: Fandango_Ratingvalue, dtype: int642.7     22.8     22.9     53.0     43.1     33.2     53.3     43.4     93.5     93.6     83.7     93.8     53.9    124.0     74.1    164.2    124.3    114.4     74.5     94.6     44.8     3Name: Fandango_Ratingvalue, dtype: int64

fig,ax = plt.subplots()#ax.hist(reviews_num["Fandango_Ratingvalue"]) #直方图#ax.hist(reviews_num["Fandango_Ratingvalue"],bins=20) #指定的划分区间有多少个#ax.hist(reviews_num["Fandango_Ratingvalue"],range=(0,3)) #只统计x轴上0到3的ax.hist(reviews_num["Fandango_Ratingvalue"],bins=20,range=(4,5)) #将4到5之间划分成20个区间plt.show()

fig = plt.figure(figsize=(5,20))ax1= fig.add_subplot(4,1,1)ax2= fig.add_subplot(4,1,2)ax1.hist(reviews_num["Fandango_Ratingvalue"],bins=20,range=(0,5))ax1.set_title("Distribution Rating")ax1.set_ylim(0,50) #设置y轴区间ax2.hist(reviews_num["RT_norm"],bins=20,range=(0,5))ax2.set_title("Distribution Rating")ax2.set_ylim(0,50)plt.show()

fig,ax = plt.subplots()ax.boxplot(reviews_num["RT_norm"])ax.set_xticklabels(["RT_norm"])ax.set_ylim(0,5)plt.show()

fig,ax = plt.subplots()ax.boxplot(reviews_num[clos].values)ax.set_xticklabels(clos,rotation=90)ax.set_ylim(0,5)plt.show()