Pandas Data Frames

In [1]:
import pandas
 
frame_data = {'name': ['James', 'Jason', 'Rogers'], 'age': [18, 20, 22], 'job': ['Assistant', 'Manager', 'Clerk']} 
df = pandas.DataFrame(frame_data)
df
Out[1]:
name age job
0 James 18 Assistant
1 Jason 20 Manager
2 Rogers 22 Clerk
In [2]:
import pandas as pd

data = [1,2,3,4,5]
df = pd.DataFrame(data)
df
Out[2]:
0
0 1
1 2
2 3
3 4
4 5
In [3]:
data = [['Alex',10],['Bob',12],['Clarke',13]]
df = pd.DataFrame(data,columns=['Name','Age'])
df
Out[3]:
Name Age
0 Alex 10
1 Bob 12
2 Clarke 13
In [7]:
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)
df.loc['d']
Out[7]:
one    NaN
two    4.0
Name: d, dtype: float64
In [9]:
d = {'Name':pd.Series(['Tom','James','Ricky','Vin','Steve','Smith','Jack']),
   'Age':pd.Series([25,26,25,23,30,29,23]),
   'Rating':pd.Series([4.23,3.24,3.98,2.56,3.20,4.6,3.8])}

#Create a DataFrame
df = pd.DataFrame(d)
print ("Our data series is:")
df

Our data series is:
Out[9]:
Name Age Rating
0 Tom 25 4.23
1 James 26 3.24
2 Ricky 25 3.98
3 Vin 23 2.56
4 Steve 30 3.20
5 Smith 29 4.60
6 Jack 23 3.80
In [11]:
import pandas as pd
import numpy as np

data = np.array([['','Col1','Col2'],['Row1',1,2],['Row2',3,4],['Row2',5,6]])
df = pd.DataFrame(data=data[1:,1:],index=data[1:,0],columns=data[0,1:])
df
Out[11]:
Col1 Col2
Row1 1 2
Row2 3 4
Row2 5 6
In [20]:
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)
df
Out[20]:
one two
a 1.0 1
b 2.0 2
c 3.0 3
d NaN 4
In [21]:
# 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'])
df

Adding a new column by passing as Series:
Out[21]:
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
In [22]:
print ("Adding a new column using the existing columns in DataFrame:")
df['four']=df['one']/df['three']
df

Adding a new column using the existing columns in DataFrame:
Out[22]:
one two three four
a 1.0 1 10.0 0.1
b 2.0 2 20.0 0.1
c 3.0 3 30.0 0.1
d NaN 4 NaN NaN
In [ ]: