Download our e-book of Introduction To Python
Mohit Sharma
2 years ago
# import the pandas library
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 = df.reindex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'])
print(df)
one two three
a 0.077988 0.476149 0.965836
b NaN NaN NaN
c -0.390208 -0.551605 -2.301950
d NaN NaN NaN
e -2.000303 -0.788201 1.510072
f -0.930230 -0.670473 1.146615
g NaN NaN NaN
h 0.085100 0.532791 0.887415
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 = df.reindex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'])
print(df['one'].isnone())
a false
b true
c false
d true
e false
f false
g true
h false
Name: one, dtype: bool
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 = df.reindex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'])
print(df['one'].notnone())
a true
b false
c true
d false
e true
f true
g false
h true
Name: one, dtype: bool
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 = df.reindex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'])
print(df['one'].sum())
2.02357685917
import pandas as pd
import numpy as np
df = pd.DataFrame(index=[0,1,2,3,4,5],columns=['one','two'])
print(df['one'].sum())
nan
import pandas as pd
import numpy as np
df = pd.DataFrame(np.random.randn(3, 3), index=['a', 'c', 'e'],columns=['one',
'two', 'three'])
df = df.reindex(['a', 'b', 'c'])
print(df)
print ("NaN replaced with '0':")
print(df.fillna(0))
one two three
a -0.576991 -0.741695 0.553172
b NaN NaN NaN
c 0.744328 -1.735166 1.749580
NaN replaced with '0':
one two three
a -0.576991 -0.741695 0.553172
b 0.000000 0.000000 0.000000
c 0.744328 -1.735166 1.749580
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 = df.reindex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'])
print(df.fillna(method='pad'))
one two three
a 0.077988 0.476149 0.965836
b 0.077988 0.476149 0.965836
c -0.390208 -0.551605 -2.301950
d -0.390208 -0.551605 -2.301950
e -2.000303 -0.788201 1.510072
f -0.930230 -0.670473 1.146615
g -0.930230 -0.670473 1.146615
h 0.085100 0.532791 0.887415
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 = df.reindex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'])
print(df.fillna(method='backfill'))
one two three
a 0.077988 0.476149 0.965836
b -0.390208 -0.551605 -2.301950
c -0.390208 -0.551605 -2.301950
d -2.000303 -0.788201 1.510072
e -2.000303 -0.788201 1.510072
f -0.930230 -0.670473 1.146615
g 0.085100 0.532791 0.887415
h 0.085100 0.532791 0.887415
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 = df.reindex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'])
print(df.dropna())
one two three
a 0.077988 0.476149 0.965836
c -0.390208 -0.551605 -2.301950
e -2.000303 -0.788201 1.510072
f -0.930230 -0.670473 1.146615
h 0.085100 0.532791 0.887415
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 = df.reindex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h'])
print(df.dropna(axis=1))
Empty DataFrame
Columns: [ ]
Index: [a, b, c, d, e, f, g, h]
import pandas as pd
import numpy as np
df = pd.DataFrame({'one':[10,20,30,40,50,2000], 'two':[1000,0,30,40,50,60]})
print(df.replace({1000:10,2000:60}))
one two
0 10 10
1 20 0
2 30 30
3 40 40
4 50 50
5 60 60
import pandas as pd
import numpy as np
df = pd.DataFrame({'one':[10,20,30,40,50,2000], 'two':[1000,0,30,40,50,60]})
print(df.replace({1000:10,2000:60}))
one two
0 10 10
1 20 0
2 30 30
3 40 40
4 50 50
5 60 60