In [1]:

    

import spark_jupyter


    

In [2]:

    

from pyspark import SparkContext, SQLContext
sc = SparkContext("local[*]", "Simple App")
hc = SQLContext(sc)


    

In [3]:

    

df = hc.createDataFrame([['a', 'b', 'c'],['e', 'f', 'g']], schema=['A', 'B', 'C'])
df.show()


    

    
Out[3]:





    
    

        

        

        
            
A
        
            
B
        
            
C
        
        
        
        

        
        

          
            
 a 
          
            
 b 
          
            
 c 
          
        
        
        

          
            
 e 
          
            
 f 
          
            
 g 
          
        
        
        
    
    
    

In [4]:

    

df.printSchema()


    

    
Out[4]:





        

            
Name
            
Type
            
Nullable
        
        
        

            
 A 
            
 string 
            

            
                ✓
            
            
        
        
        

            
 B 
            
 string 
            

            
                ✓
            
            
        
        
        

            
 C 
            
 string 
            

            
                ✓