基于pandas进行数据预处理

1 import pandas as pd
2 import numpy as np
3 train_df =pd.read_csv(‘../datas/train.csv‘)  # train set
4 test_df  = pd.read_csv(‘../datas/test.csv‘)   # test  set
5 combine  = [train_df, test_df]

1 #查看前五条数据
2 print train_df.head(5)  
3 #查看每列数据类型以及nan情况
4 print train_df.info()  
5 # 获得所有object属性
6 print train_data.describe().columns 

1 #查看连续数值属性基本统计情况
2 print train_df.describe()  
3 #查看object属性数据统计情况
4 print train_df.describe(include=[‘O‘])  
5 # 统计Title单列各个元素对应的个数
6 print train_df[‘Title‘].value_counts() 
7 # 属性列删除
8 train_df = train_df.drop([‘Name‘, ‘PassengerId‘], axis=0)  

 1 # 直接丢弃缺失数据列的行
 2 print df4.dropna(axis=1,subset=[‘col1‘])  # 丢弃nan的行,subset指定查看哪几列 
 3 print df4.dropna(axis=0)  # 丢弃nan的列
 4 # 采用其他值填充
 5 dataset[‘Cabin‘] = dataset[‘Cabin‘].fillna(‘U‘) 
 6 dataset[‘Title‘] = dataset[‘Title‘].fillna(0) 
 7 # 采用出现最频繁的值填充
 8 freq_port = train_df.Embarked.dropna().mode()[0]
 9 dataset[‘Embarked‘] = dataset[‘Embarked‘].fillna(freq_port)
10 # 采用中位数或者平均数填充
11 test_df[‘Fare‘].fillna(test_df[‘Fare‘].dropna().median(), inplace=True)
12 test_df[‘Fare‘].fillna(test_df[‘Fare‘].dropna().mean(), inplace=True)

1 # 创造一个新列，FareBand，将连续属性Fare切分成四份
2 train_df[‘FareBand‘] = pd.qcut(train_df[‘Fare‘], 4)
3 # 查看切分后的属性与target属性Survive的关系
4 train_df[[‘FareBand‘, ‘Survived‘]].groupby([‘FareBand‘], as_index=False).mean().sort_values(by=‘FareBand‘, ascending=True)
5 # 建立object属性映射字典  
6 title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Royalty":5, "Officer": 6}
7 dataset[‘Title‘] = dataset[‘Title‘].map(title_mapping)

1 print train_df[[‘AgeBand‘, ‘Survived‘]].groupby([‘AgeBand‘], as_index=False).mean().sort_values(by=‘AgeBand‘, ascending=True)

 1 ”’ 
 2 创建df对象 
 3 ””’ 
 4 s1 = pd.Series([1,2,3,np.nan,4,5]) 
 5 s2 = pd.Series([np.nan,1,2,3,4,5]) 
 6 print s1 
 7 dates = pd.date_range(“20130101”,periods=6) 
 8 print dates 
 9 df = pd.DataFrame(np.random.rand(6,4),index=dates,columns=list(“ABCD”)) 
10 # print df 
11 df2 = pd.DataFrame({“A”:1, 
12 ‘B’:pd.Timestamp(‘20130102’), 
13 ‘C’:pd.Series(1,index=list(range(4)),dtype=’float32’), 
14 ‘D’:np.array([3]*4,dtype=np.int32), 
15 ‘E’:pd.Categorical([‘test’,’train’,’test’,’train’]), 
16 ‘F’:’foo’ 
17 }) 
18 # print df2.dtypes
19 
20 df3 = pd.DataFrame({‘col1‘:s1,
21                     ‘col2‘:s2
22 })
23 print df3
24 
25 ‘‘‘
26 2.查看df数据
27 ‘‘‘
28 print df3.head(2) #查看头几条
29 print df3.tail(3) #查看尾几条
30 print df.index  #查看索引
31 print df.info()  #查看非non数据条数
32 print type(df.values)  #返回二元数组
33 # print df3.values
34 print df.describe()   #对每列数据进行初步的统计
35 print df3
36 print df3.sort_values(by=[‘col1‘],axis=0,ascending=True) #按照哪几列排序
37 
38 ‘‘‘
39 3.选择数据
40 ‘‘‘
41 ser_1 = df3[‘col1‘]
42 print type(ser_1) #pandas.core.series.Series
43 print df3[0:2] #前三行
44 print df3.loc[df3.index[0]]  #通过index来访问
45 print df3.loc[df3.index[0],[‘col2‘]]  #通过行index，和列名来唯一确定一个位置
46 print df3.iloc[1] #通过位置来访问
47 print df3.iloc[[1,2],1:2] #通过位置来访问
48 print "==="
49 print df3.loc[:,[‘col1‘,‘col2‘]].as_matrix()   # 返回nunpy二元数组
50 print type(df3.loc[:,[‘col1‘,‘col2‘]].as_matrix())
51 
52 ‘‘‘
53 4.布尔索引，过滤数据
54 ‘‘‘
55 print df3[df3.col1 >2]
56 df4 = df3.copy()
57 df4[‘col3‘]=pd.Series([‘one‘,‘two‘,‘two‘,‘three‘,‘one‘,‘two‘])
58 print df4
59 print df4[df4[‘col3‘].isin([‘one‘,‘two‘])]
60 df4.loc[:,‘col3‘]="five"
61 print df4
62 
63 ‘‘‘
64 5.缺失值处理，pandas将缺失值用nan代替
65 ‘‘‘
66 print pd.isnull(df4)
67 print df4.dropna(axis=0,subset=[‘col1‘])  # 丢弃nan的行,subset指定查看哪几列
68 print df4.dropna(axis=1)  # 丢弃nan的列