recsys4.py

# splits ratings dataframe to training and validation dataframes
def get_data(ratings, valid_pct:float = 0.2):
    # shuffle the indexes
    ln = random.sample(range(0, len(ratings)), len(ratings))
    
    # split based on the given validation set percentage 
    part = int(len(ln)*valid_pct)
    
    valid_index = ln[0:part]
    train_index = ln[part:]
    valid = ratings.iloc[valid_index]
    train = ratings.iloc[train_index]
    return [train,valid]