Jones Wan joneswan

## Spark Dataframe Cheat Sheet.py
# A simple cheat sheet of Spark Dataframe syntax
# Current for Spark 1.6.1

# import statements
from pyspark.sql import SQLContext
from pyspark.sql.types import *
from pyspark.sql.functions import *

#creating dataframes
df = sqlContext.createDataFrame([(1, 4), (2, 5), (3, 6)], ["A", "B"]) # from manual data

## Dockerfile
## Edited on 21 June, Alice Wang
## To build the docker image
## $ cd .
## $ docker build -t fc .

FROM debian:8.3

RUN DEBIAN_FRONTEND=noninteractive apt-get update --fix-missing
RUN DEBIAN_FRONTEND=noninteractive apt-get install -y python2.7 python2.7-dev pkg-config
RUN DEBIAN_FRONTEND=noninteractive apt-get install -y libxml2-dev libxslt-dev python-lxml

## Bokeh Plot Interacts with the Jupyter Notebook-checkpoint.ipynb

      
        
          
            
              
              1 file
            
          
          
            
              
              0 forks
            
          
            
              
                
                0 comments
              
            
          
            
              
              0 stars
            
          
        
        
          
              
          
          
            
                joneswan
                / Bokeh Plot Interacts with the Jupyter Notebook-checkpoint.ipynb
            
            
              Created
              April 26, 2017 14:03
                — forked from ICBacon/Bokeh Plot Interacts with the Jupyter Notebook-checkpoint.ipynb
            
              
                Bokeh Plots in a Jupyter Notebook Using Iris Flower Data from Tony
              
          
        
      
        
  
    
    

          
    
      
      Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
	# A simple cheat sheet of Spark Dataframe syntax
	# Current for Spark 1.6.1

	# import statements
	from pyspark.sql import SQLContext
	from pyspark.sql.types import *
	from pyspark.sql.functions import *

	#creating dataframes
	df = sqlContext.createDataFrame([(1, 4), (2, 5), (3, 6)], ["A", "B"]) # from manual data
	## Edited on 21 June, Alice Wang
	## To build the docker image
	## $ cd .
	## $ docker build -t fc .

	FROM debian:8.3

	RUN DEBIAN_FRONTEND=noninteractive apt-get update --fix-missing
	RUN DEBIAN_FRONTEND=noninteractive apt-get install -y python2.7 python2.7-dev pkg-config
	RUN DEBIAN_FRONTEND=noninteractive apt-get install -y libxml2-dev libxslt-dev python-lxml