Watch Me Code 1: Pandas Basics

Series
DataFrame
Select columns, Select rows with Boolean indexing



In [7]:

    
import pandas as pd



In [8]:

    
fruits = pd.Series(['Apple', 'Banana', 'Cherry', 'Orange'], name = "Fruit")
fruits









    Out[8]:





0     Apple
1    Banana
2    Cherry
3    Orange
Name: Fruit, dtype: object



In [9]:

    
qtys = pd.Series([5,7,2,9])
qtys









    Out[9]:





0    5
1    7
2    2
3    9
dtype: int64



In [11]:

    
# dictionary of Series
inventory = pd.DataFrame({ 'Fruit' : fruits, 'Qty' : qtys, 'Price': [2.99,1.99,3.99,2.99] })
inventory



In [12]:

    
# column selection
inventory['Fruit']









    Out[12]:





0     Apple
1    Banana
2    Cherry
3    Orange
Name: Fruit, dtype: object



In [13]:

    
# as DataFrame
inventory[ ['Fruit'] ]



In [14]:

    
#two columns in the list
inventory[ ['Fruit','Price'] ]



In [15]:

    
# Boolean index
inventory['Qty'] >5









    Out[15]:





0    False
1     True
2    False
3     True
Name: Qty, dtype: bool



In [16]:

    
# applying a boolean index to a dataframe
inventory[ inventory['Qty'] >5 ]



In [20]:

    
#combining columns and filters
fruit_and_price_over5 = inventory[['Fruit','Price']][inventory['Qty'] >5 ] 
fruit_and_price_over5









    Out[20]:






  
    
      
      Fruit
      Price
    
  
  
    
      1
      Banana
      1.99
    
    
      3
      Orange
      2.99



In [19]:

    
# Confused? Too hot to handle??? Use variables!
large_qty = inventory[ inventory['Qty'] >5 ]
fruit_and_price_over5 = large_qty[ ['Fruit', 'Price' ] ]
fruit_and_price_over5









    Out[19]:






  
    
      
      Fruit
      Price
    
  
  
    
      1
      Banana
      1.99
    
    
      3
      Orange
      2.99



In [ ]: