#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2018/8/11 13:32
# @Author : limingyu
# @Site :
# @File : Test_Matplotlib_fandango2.py
# @Software: PyCharm
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
reviews = pd.read_csv("fandango_score_comparison.csv") #读数据
#各评分媒体集合
cols = ['RT_user_norm','Metacritic_user_nom','IMDB_norm','Fandango_Ratingvalue','Fandango_Stars']
norm_reviews = reviews[cols] #取上述几列内容
print(norm_reviews[0:5]) #打印5行数据
# RT_user_norm ... Fandango_Stars
#0 4.3 ... 5.0
#1 4.0 ... 5.0
#2 4.5 ... 5.0
#3 4.2 ... 5.0
#4 1.4 ... 3.5
#统计所有得分
fandango_score = norm_reviews['Fandango_Ratingvalue'].values
print(fandango_score) #[4.5 4.5 4.5 4.5 3. 4....]
#统计每个得分的总个数
fandango_distribution = norm_reviews['Fandango_Ratingvalue'].value_counts()
print(fandango_distribution)
#4.1 16
#4.2 12
#3.9 12
#4.3 11
#3.7 9...
#对总得分从小到大排序
fandango_distribution = fandango_distribution.sort_index()
print(fandango_distribution)
#2.7 2
#2.8 2
#2.9 5
#3.0 4
imdb_distribution = norm_reviews['IMDB_norm'].value_counts()
imdb_distribution = imdb_distribution.sort_index()
print(imdb_distribution)
#画图
fig,ax = plt.subplots()
#hist()表示带有bins结构，默认bins为10个。
#bins：某个变量过多，坐标轴就化不开，用bins化成范围，减少变量数量。
#ax.hist(norm_reviews['Fandango_Ratingvalue'])
#ax.hist(norm_reviews['Fandango_Ratingvalue'],bins=20) #指定bins为20个
#指定bins和指定横坐标区间[4,5]
ax.hist(norm_reviews['Fandango_Ratingvalue'],range=[4,5],bins=20)
plt.show()
