Created
March 22, 2017 10:58
-
-
Save matthewseddon/2cf87d0690bfc58d2e9d29bc49b373c9 to your computer and use it in GitHub Desktop.
Concatenate two dfs in pyspark
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
"""Concatenate two dataframes in pyspark. | |
run as spark-submit concat_pyspark.py --py-files | |
""" | |
from __future__ import print_function | |
import pyspark | |
from pyspark import SparkContext | |
from pyspark.sql import SQLContext | |
logFile = "README.md" # Should be some file on your system | |
sc = SparkContext("local", "pyspark") | |
sqlContext = SQLContext(sc) | |
logData = sc.textFile(logFile).cache() | |
file_names = ['2017-01-{place}-street.csv'.format(place=p) for p in ('west-yorkshire', 'wiltshire')] | |
data_directory = 'police_data/2017-01/' | |
wy_df = sqlContext.read.format('com.databricks.spark.csv').options(header='true', inferschema='true').load('{}/{}'.format(data_directory, file_names[0])) | |
wi_df = sqlContext.read.format('com.databricks.spark.csv').options(header='true', inferschema='true').load('{}/{}'.format(data_directory, file_names[1])) | |
unified_df = wy_df.unionAll(wi_df) | |
print(unified_df.show()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment