hw3_p3.py

hw3_p3.py

# CSCI E-63 HW3 - Problem 3
# Author: Walter Yu
# Description: PySpark script to connect to MySQL database, register table and display row count.

# Create context and connect to MySQL:
sqlContext= SQLContext(sc)
dfm = sqlc.read.format("jdbc").option("url","jdbc:mysql://localhost/retail_db").option("driver","com.mysql.jdbc.Driver").option("dbtable","departments").option("user","xxxxx").option("password","xxxxx").load()

# Verify schema, create view and display row count:
dfm.printSchema()
dfm.registerTempTable("departments")
dfm
dfm.count()
dfm.collect()