In [ ]:
'''
series:
isnull
dropna
dataframes:
isnull
dropna
dropna(how='all')
dropna(axis=1)
dropna(thresh=2)
fillna(1)
fillna(0, inplace=True)
'''
In [1]:
import numpy as np
import pandas as pd
from pandas import Series,DataFrame
In [2]:
data = Series(['one','two',np.nan,'four'])
In [3]:
data
Out[3]:
In [4]:
# finding missing values
data.isnull()
Out[4]:
In [5]:
# drop null values
data.dropna()
Out[5]:
In [6]:
df = DataFrame([[1,2,3],[np.nan,5,6],[7,np.nan,9],[np.nan,np.nan,np.nan]])
In [7]:
df
Out[7]:
In [10]:
# by default drop all rows from dataframe with missing values
clean_df = df.dropna()
clean_df
Out[10]:
In [11]:
# specify dropping rows that all values are missing only
df.dropna(how='all')
Out[11]:
In [12]:
# drop columns
df.dropna(axis=1)
Out[12]:
In [13]:
npn = np.nan
df2 = DataFrame([[1,2,3,npn],[2,npn,5,6],[npn,7,npn,9],[1,npn,npn,npn]])
df2
Out[13]:
In [16]:
# keep rows that has at least 2 datapoints
df2.dropna(thresh=2)
Out[16]:
In [17]:
df2.dropna(thresh=3)
Out[17]:
In [18]:
df2
Out[18]:
In [20]:
# fill null values
df2.fillna(1)
Out[20]:
In [23]:
# fill different values for each column
df2.fillna({0:0,1:1,2:2,3:3})
Out[23]:
In [24]:
# modify existing object
# df2 = df2.fillna()
# or
df2.fillna(0, inplace=True)
In [27]:
df2
Out[27]: