50 dealing with missing data in Numpy

In [1]:

import numpy as np
import pandas as pd

In [2]:

dist1={'A':[1,2,np.nan],'B':[5,np.nan,np.nan],'C':[1,2,3]}

In [3]:

dist1

Out[3]:

{'A': [1, 2, nan], 'B': [5, nan, nan], 'C': [1, 2, 3]}

In [4]:

df = pd.DataFrame(dist1)

In [5]:

df

Out[5]:

	A	B	C
0	1.0	5.0	1
1	2.0	NaN	2
2	NaN	NaN	3

In [7]:

df.dropna(axis=1)

Out[7]:

	C
0	1
1	2
2	3

In [12]:

df.dropna(thresh=2,axis=1)

Out[12]:

	A	C
0	1.0	1
1	2.0	2
2	NaN	3

In [14]:

df.fillna(value=8)

Out[14]:

	A	B	C
0	1.0	5.0	1
1	2.0	8.0	2
2	8.0	8.0	3

In [15]:

df

Out[15]:

	A	B	C
0	1.0	5.0	1
1	2.0	NaN	2
2	NaN	NaN	3

In [16]:

df['A']

Out[16]:

0    1.0
1    2.0
2    NaN
Name: A, dtype: float64

In [17]:

df['A'].fillna(value=df['A'].mean())

Out[17]:

0    1.0
1    2.0
2    1.5
Name: A, dtype: float64