notebook.community

Edit and run



In [5]:

    
import pandas as pd
import numpy as np
df = pd.DataFrame(np.random.randn(5, 3), index=['a', 'c', 'e', 'f', 'h'],columns=['one', 'two', 'three'])
df['four'] = 'bar'
df['five'] = df['one'] > 0
df



In [6]:

    
df2 = df.reindex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'])
df2



In [7]:

    
dff = pd.DataFrame(np.random.randn(10,3),columns=list('ABC'))
dff.iloc[3:5,0] = np.nan

dff.iloc[4:6,1] = np.nan

dff.iloc[5:8,2] = np.nan



In [17]:

    
dff.mean()['B':"C"]
pd.Series([1,0],index=list('BC'))









    Out[17]:





B    1
C    0
dtype: int64



In [18]:

    
dff.fillna(pd.Series([1,0],index=list('BC')))



In [20]:

    
d = {'a': list(range(4)), 'b': list('ab..'), 'c': ['a', 'b', np.nan, 'd']}
df = pd.DataFrame(d)
df



In [ ]:

	one	two	three	four	five
a	-0.736298	0.546626	-0.688422	bar	False
c	1.271292	0.054160	-0.320729	bar	True
e	-0.637428	-1.005087	-1.219964	bar	False
f	0.308531	0.196214	-0.312641	bar	True
h	1.066718	0.705849	-0.099920	bar	True

	one	two	three	four	five
a	-0.736298	0.546626	-0.688422	bar	False
b	NaN	NaN	NaN	NaN	NaN
c	1.271292	0.054160	-0.320729	bar	True
d	NaN	NaN	NaN	NaN	NaN
e	-0.637428	-1.005087	-1.219964	bar	False
f	0.308531	0.196214	-0.312641	bar	True
g	NaN	NaN	NaN	NaN	NaN
h	1.066718	0.705849	-0.099920	bar	True

	A	B	C
0	1.055356	0.736670	0.321692
1	-1.464509	-0.453976	-1.348463
2	-0.665578	0.423287	0.429259
3	NaN	-1.037082	0.012615
4	NaN	1.000000	-0.089787
5	-2.764632	1.000000	0.000000
6	-0.613470	-0.392313	0.000000
7	-1.877400	0.364823	0.000000
8	0.191521	-0.406305	-1.861625
9	-1.860177	-0.548034	-0.302685