rain_train_val_test_split.py

# Splitting into train, val and test set -- 80-10-10 split

# First, an 80-20 split
train_df, val_test_df = train_test_split(df, test_size = 0.2, random_state = 113)

# Then split the 20% into half
val_df, test_df = train_test_split(val_test_df, test_size = 0.5, random_state = 113)

# Defining the input and output columns
ic = df.columns.tolist()
ic.remove('RainTomorrow')

oc = ['RainTomorrow']

# Split into X and y
ytrain = train_df[oc]
Xtrain = train_df.drop(columns = oc)

yval = val_df[oc]
Xval = val_df.drop(columns = oc)

ytest = test_df[oc]
Xtest = test_df.drop(columns = oc)