ph_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)

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

# Splitting into X (input) and y (output)

Xtrain, ytrain = np.array(train_df[input_columns]), np.array(train_df[output_columns])

Xval, yval = np.array(val_df[input_columns]), np.array(val_df[output_columns])

Xtest, ytest = np.array(test_df[input_columns]), np.array(test_df[output_columns])