以下操作我使用的python版本为3.6.5
导包
import pandas as pd
import numpy as np
from pandas import Series,DataFrame
读取csv文件
credits = pd.read_csv('D:/BaiduNetdiskDownload/tmdb-movie-metadata/tmdb_5000_credits.csv')
movies = pd.read_csv('D:/BaiduNetdiskDownload/tmdb-movie-metadata/tmdb_5000_movies.csv')
熟悉表的基础信息
#查看表的基本信息
credits.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 4803 entries, 0 to 4802
Data columns (total 4 columns):
movie_id 4803 non-null int64
title 4803 non-null object
cast 4803 non-null object
crew 4803 non-null object
dtypes: int64(1), object(3)
memory usage: 150.2+ KB
#查看前10行
credits.head(10)
#查看后10行
credits.tail(10)
#查看列名
credits.columns
#查看表的值
credits.values
#查看行名
credits.index
#查看表5-10行,2-5列
credits.ix[5:10, 2:5]
#查看表的维度(多少行多少列)
movies.shape
对数据的筛选
#筛选出movie_id < 20的数据
credits[credits.movie_id < 20]
#movie_id < 20 并且 title = 'Star Wars'
credits[(credits.movie_id < 20) & (credits.title == 'Star Wars')]
#movie_id < 20 或者 title = 'Star Wars'
credits[(credits.movie_id < 20) | (credits.title == 'Star Wars')]
查看表的统计描述
credits.describe()
movie_id
count 4803.000000
mean 57165.484281
std 88694.614033
min 5.000000
25% 9014.500000
50% 14629.000000
75% 58610.500000
max 459488.000000
#对某列进行排序,默认升序
credits.sort_values(by='movie_id')
未完待继续。。。