handy_loading.py

import findspark
from pyspark.sql import SparkSession
from handyspark import *
from matplotlib import pyplot as plt
%matplotlib inline

findspark.init()

spark = SparkSession.builder.getOrCreate()

# DOWNLOAD THE DATASET HERE
# https://raw.githubusercontent.com/dvgodoy/handyspark/master/tests/rawdata/train.csv

# Loads training data for Titanic dataset
sdf = spark.read.csv('train.csv', header=True, inferSchema=True)
# Makes Spark dataframe Handy :-)
hdf = sdf.toHandy()