Title: Simple Example Dataframes In Pandas
Slug: pandas_dataframe_examples
Summary: Simple Example Dataframes In Pandas
Date: 2016-05-01 12:00
Category: Python
Tags: Data Wrangling
Authors: Chris Albon

import modules



In [1]:

    
import pandas as pd

Create dataframe



In [2]:

    
raw_data = {'first_name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'], 
        'last_name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze'], 
        'age': [42, 52, 36, 24, 73], 
        'preTestScore': [4, 24, 31, 2, 3],
        'postTestScore': [25, 94, 57, 62, 70]}
df = pd.DataFrame(raw_data, columns = ['first_name', 'last_name', 'age', 'preTestScore', 'postTestScore'])
df









    Out[2]:






  
    
      
      first_name
      last_name
      age
      preTestScore
      postTestScore
    
  
  
    
      0
      Jason
      Miller
      42
      4
      25
    
    
      1
      Molly
      Jacobson
      52
      24
      94
    
    
      2
      Tina
      Ali
      36
      31
      57
    
    
      3
      Jake
      Milner
      24
      2
      62
    
    
      4
      Amy
      Cooze
      73
      3
      70

Create 2nd dataframe



In [3]:

    
raw_data_2 = {'first_name': ['Sarah', 'Gueniva', 'Know', 'Sara', 'Cat'], 
        'last_name': ['Mornig', 'Jaker', 'Alom', 'Ormon', 'Koozer'], 
        'age': [53, 26, 72, 73, 24], 
        'preTestScore': [13, 52, 72, 26, 26],
        'postTestScore': [82, 52, 56, 234, 254]}
df_2 = pd.DataFrame(raw_data_2, columns = ['first_name', 'last_name', 'age', 'preTestScore', 'postTestScore'])
df_2









    Out[3]:






  
    
      
      first_name
      last_name
      age
      preTestScore
      postTestScore
    
  
  
    
      0
      Sarah
      Mornig
      53
      13
      82
    
    
      1
      Gueniva
      Jaker
      26
      52
      52
    
    
      2
      Know
      Alom
      72
      72
      56
    
    
      3
      Sara
      Ormon
      73
      26
      234
    
    
      4
      Cat
      Koozer
      24
      26
      254

Create 3rd dataframe



In [4]:

    
raw_data_3 = {'first_name': ['Sarah', 'Gueniva', 'Know', 'Sara', 'Cat'], 
        'last_name': ['Mornig', 'Jaker', 'Alom', 'Ormon', 'Koozer'],
         'postTestScore_2': [82, 52, 56, 234, 254]}
df_3 = pd.DataFrame(raw_data_3, columns = ['first_name', 'last_name', 'postTestScore_2'])
df_3









    Out[4]:






  
    
      
      first_name
      last_name
      postTestScore_2
    
  
  
    
      0
      Sarah
      Mornig
      82
    
    
      1
      Gueniva
      Jaker
      52
    
    
      2
      Know
      Alom
      56
    
    
      3
      Sara
      Ormon
      234
    
    
      4
      Cat
      Koozer
      254

	first_name	last_name	age	preTestScore	postTestScore
0	Jason	Miller	42	4	25
1	Molly	Jacobson	52	24	94
2	Tina	Ali	36	31	57
3	Jake	Milner	24	2	62
4	Amy	Cooze	73	3	70

	first_name	last_name	age	preTestScore	postTestScore
0	Sarah	Mornig	53	13	82
1	Gueniva	Jaker	26	52	52
2	Know	Alom	72	72	56
3	Sara	Ormon	73	26	234
4	Cat	Koozer	24	26	254