# Create variables for max and min dates in our dataset
max_date = df.agg({'OFFMKTDATE': 'max'}).collect()[0][0]
min_date = df.agg({'OFFMKTDATE': 'min'}).collect()[0][0]

# Find how many days our data spans
from pyspark.sql.functions import datediff
range_in_days = datediff(max_date, min_date)

# Find the date to split the dataset on
from pyspark.sql.functions import date_add
split_in_days = round(range_in_days * 0.8)
split_date = date_add(min_date, split_in_days)

# Split the data into 80% train, 20% test
train_df = df.where(df['OFFMKTDATE'] < split_date) 
test_df = df.where(df['OFFMKTDATE'] >= split_date)\
  .where(df['LISTDATE'] >= split_date)