Download our e-book of Introduction To Python
Neha Kumawat
2 years ago
pandas.DataFrame( data, index, columns, dtype, copy)
Sr. No. | Parameter and Descritption |
1 | data - data takes various forms like ndarray, series, map, lists, dict, constants, and also another DataFrame. |
2 | if index - For the row labels, the index to be used for the resulting frame is Optional Default np.arrange(n) if no index is passed. |
3 | columns - For column labels, the optional default syntax is - np.arrange(n). This is only true if no index is passed. |
4 | dtype - Data type of each column. |
5 | copy - This command (or whatever it is) is used for copying of data, if the default is False. |
#import the pandas library and aliasing as pd
import pandas as pd
df = pd.DataFrame()
print df
Empty DataFrame
Columns: []
Index: []
import pandas as pd
data = [1,2,3,4,5]
df = pd.DataFrame(data)
print df
0
0 1
1 2
2 3
3 4
4 5
import pandas as pd
data = [['Alex',10],['Bob',12],['Clarke',13]]
df = pd.DataFrame(data,columns=['Name','Age'])
print df
Name Age
0 Alex 10
1 Bob 12
2 Clarke 13
import pandas as pd
data = [['Alex',10],['Bob',12],['Clarke',13]]
df = pd.DataFrame(data,columns=['Name','Age'],dtype=float)
print df
Name Age
0 Alex 10.0
1 Bob 12.0
2 Clarke 13.0
import pandas as pd
data = {'Name':['Tom', 'Jack', 'Steve', 'Ricky'],'Age':[28,34,29,42]}
df = pd.DataFrame(data)
print df
Age Name
0 28 Tom
1 34 Jack
2 29 Steve
3 42 Ricky
import pandas as pd
data = {'Name':['Tom', 'Jack', 'Steve', 'Ricky'],'Age':[28,34,29,42]}
df = pd.DataFrame(data, index=['rank1','rank2','rank3','rank4'])
print df
Age Name
rank1 28 Tom
rank2 34 Jack
rank3 29 Steve
rank4 42 Ricky
import pandas as pd
data = [{'a': 1, 'b': 2},{'a': 5, 'b': 10, 'c': 20}]
df = pd.DataFrame(data)
print df
a b c
0 1 2 NaN
1 5 10 20.0
import pandas as pd
data = [{'a': 1, 'b': 2},{'a': 5, 'b': 10, 'c': 20}]
df = pd.DataFrame(data, index=['first', 'second'])
print df
a b c
first 1 2 NaN
second 5 10 20.0
import pandas as pd
data = [{'a': 1, 'b': 2},{'a': 5, 'b': 10, 'c': 20}]
#With two column indices, values same as dictionary keys
df1 = pd.DataFrame(data, index=['first', 'second'], columns=['a', 'b'])
#With two column indices with one index with other name
df2 = pd.DataFrame(data, index=['first', 'second'], columns=['a', 'b1'])
print df1
print df2
#df1 output
a b
first 1 2
second 5 10
#df2 output
a b1
first 1 NaN
second 5 NaN
import pandas as pd
d = {'one' : pd.Series([1, 2, 3], index=['a', 'b', 'c']),
'two' : pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])}
df = pd.DataFrame(d)
print df
one two
a 1.0 1
b 2.0 2
c 3.0 3
d NaN 4
import pandas as pd
d = {'one' : pd.Series([1, 2, 3], index=['a', 'b', 'c']),
'two' : pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])}
df = pd.DataFrame(d)
print df ['one']
a 1.0
b 2.0
c 3.0
d NaN
Name: one, dtype: float64
import pandas as pd
d = {'one' : pd.Series([1, 2, 3], index=['a', 'b', 'c']),
'two' : pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])}
df = pd.DataFrame(d)
# Adding a new column to an existing DataFrame object with column label by passing new series
print ("Adding a new column by passing as Series:")
df['three']=pd.Series([10,20,30],index=['a','b','c'])
print df
print ("Adding a new column using the existing columns in DataFrame:")
df['four']=df['one']+df['three']
print df
Adding a new column by passing as Series:
one two three
a 1.0 1 10.0
b 2.0 2 20.0
c 3.0 3 30.0
d NaN 4 NaN
Adding a new column using the existing columns in DataFrame:
one two three four
a 1.0 1 10.0 11.0
b 2.0 2 20.0 22.0
c 3.0 3 30.0 33.0
d NaN 4 NaN NaN
# Using the previous DataFrame, we will delete a column
# using del function
import pandas as pd
d = {'one' : pd.Series([1, 2, 3], index=['a', 'b', 'c']),
'two' : pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd']),
'three' : pd.Series([10,20,30], index=['a','b','c'])}
df = pd.DataFrame(d)
print ("Our dataframe is:")
print df
# using del function
print ("Deleting the first column using DEL function:")
del df['one']
print df
# using pop function
print ("Deleting another column using POP function:")
df.pop('two')
print df
Our dataframe is:
one three two
a 1.0 10.0 1
b 2.0 20.0 2
c 3.0 30.0 3
d NaN NaN 4
Deleting the first column using DEL function:
three two
a 10.0 1
b 20.0 2
c 30.0 3
d NaN 4
Deleting another column using POP function:
three
a 10.0
b 20.0
c 30.0
d NaN
import pandas as pd
d = {'one' : pd.Series([1, 2, 3], index=['a', 'b', 'c']),
'two' : pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])}
df = pd.DataFrame(d)
print df.loc['b']
one 2.0
two 2.0
Name: b, dtype: float64
import pandas as pd
d = {'one' : pd.Series([1, 2, 3], index=['a', 'b', 'c']),
'two' : pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])}
df = pd.DataFrame(d)
print df.iloc[2]
one 3.0
two 3.0
Name: c, dtype: float64
import pandas as pd
d = {'one' : pd.Series([1, 2, 3], index=['a', 'b', 'c']),
'two' : pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])}
df = pd.DataFrame(d)
print df[2:4]
one two
c 3.0 3
d NaN 4
import pandas as pd
df = pd.DataFrame([[1, 2], [3, 4]], columns = ['a','b'])
df2 = pd.DataFrame([[5, 6], [7, 8]], columns = ['a','b'])
df = df.append(df2)
print df
a b
0 1 2
1 3 4
0 5 6
1 7 8
import pandas as pd
df = pd.DataFrame([[1, 2], [3, 4]], columns = ['a','b'])
df2 = pd.DataFrame([[5, 6], [7, 8]], columns = ['a','b'])
df = df.append(df2)
# Drop rows with label 0
df = df.drop(0)
print df
a b
1 3 4
1 7 8