Pandas知识点汇总（2）——布尔索引

数据集地址：https://github.com/PacktPublishing/Pandas-Cookbook

1.计算布尔值统计信息

import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt 

#读取movie,设定行索引是movie_title 
pd.options.display.max_columns = 50 
movie = pd.read_csv("./data/movie.csv",index_col = 'movie_title')

#判断电影时长是否超过两个小时    #Figure1
movie_2_hours = movie['duration'] > 120

#统计时长超过两小时的电影总数
print(movie_2_hours.sum())  #result:1039
#统计时长超过两小时的电影的比例
print(movie_2_hours.mean())
#统计False和True的比例 
print(movie_2_hours.value_counts(normalize = True)) 
#比较同一个DataFrame中的两列
actors = movie[['actor_1_facebook_likes','actor_2_facebook_likes']].dropna()
print((actors['actor_1_facebook_likes'] > actors['actor_2_facebook_likes']).mean()) #Figure2

运行结果：

Figure1

Figure2

2. 构建多个布尔条件

import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt 

#读取movie,设定行索引是movie_title 
pd.options.display.max_columns = 50 
movie = pd.read_csv("./data/movie.csv",index_col = 'movie_title')

#创建多个布尔条件
criteria1 = movie.imdb_score > 8
criteria2 = movie.content_rating == "PG-13"
criteria3 = (movie.title_year < 2000) | (movie.title_year >= 2010)

"""
print(criteria1.head())
print(criteria2.head())
print(criteria3.head())
运行结果：Figure1
"""

#将多个布尔条件合并成一个
criteria_final = criteria1 & criteria2 & criteria3 

print(criteria_final.head())
#运行结果：Figure2

运行结果：

Figure1

Figure2

3.用布尔索引过滤

import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt 

#读取movie,设定行索引是movie_title 
pd.options.display.max_columns = 50 
movie = pd.read_csv("./data/movie.csv",index_col = 'movie_title')
#创建第一个布尔条件
crit_a1 = movie.imdb_score > 8 
crit_a2 = movie.content_rating == 'PG-13'
crit_a3 = (movie.title_year < 2000) | (movie.title_year > 2009)
final_crit_a = crit_a1 & crit_a2 & crit_a3

#创建第二个布尔条件
crit_b1 = movie.imdb_score < 5
crit_b2 = movie.content_rating == 'R'
crit_b3 = (movie.title_year >= 2000) & (movie.title_year <= 2010)
final_crit_b = crit_b1 & crit_b2 & crit_b3

#将两个条件用或运算合并起来
final_crit_all = final_crit_a | final_crit_b
print(final_crit_all.head())  #Figure 1 

#用最终的布尔条件过滤数据
print(movie[final_crit_all].head()) #Figure2

运行结果：

Figure1

Figure2

import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt 

#读取movie,设定行索引是movie_title 
pd.options.display.max_columns = 50 
movie = pd.read_csv("./data/movie.csv",index_col = 'movie_title')
#创建第一个布尔条件
crit_a1 = movie.imdb_score > 8 
crit_a2 = movie.content_rating == 'PG-13'
crit_a3 = (movie.title_year < 2000) | (movie.title_year > 2009)
final_crit_a = crit_a1 & crit_a2 & crit_a3

#创建第二个布尔条件
crit_b1 = movie.imdb_score < 5
crit_b2 = movie.content_rating == 'R'
crit_b3 = (movie.title_year >= 2000) & (movie.title_year <= 2010)
final_crit_b = crit_b1 & crit_b2 & crit_b3

#将两个条件用或运算合并起来
final_crit_all = final_crit_a | final_crit_b

#使用loc,对指定的列做过滤操作，可以清楚地看到过滤是否起作用
cols = ['imdb_score','content_rating','title_year']
movie_filtered = movie.loc[final_crit_all,cols]
print(movie_filtered.head(10))

运行结果：

参考教程：
https://github.com/PacktPublishing/Pandas-Cookbook
https://www.jianshu.com/p/5809f6cf78ca