baseline_model.py

def run_model(df, folds, feats, model):
    """
    Takes in a dataframe of 'plays', the # folds,
    features list and model, prints and returns
    the mean score across all the folds
    Parameters
    ---------
    df : a dataframe object
            Contains the plays
    folds : int
            Number of foldsZ
    feats : a list object
            Contains the features' columns
    model : a string object
            The model name

    Returns
    -------
    np.mean(scores) : float
            Contains the average score
    """
    
    scores = []
    for fold in range(folds):

        # get training data using folds
        df_train = df[df.kfold != fold].reset_index(drop=True)

        # get validation data using folds
        df_valid = df[df.kfold == fold].reset_index(drop=True)

        # get training data
        x_train = df_train[feats].values

        # get validation data
        x_valid = df_valid[feats].values

        # initialize Logistic Regression model
        model =  model

        # fit model on training data (ohe)
        model.fit(x_train, df_train.gm_cluster.values)

        # predict on validation data
        valid_preds = model.predict(x_valid)

        # get f1_weighted score
        f1 = f1_score(df_valid.gm_cluster.values, valid_preds, average='weighted')

        # print f1
        print(f"Fold = {fold}, F1 = {f1}")

        # register the score in the score list
        scores.append(f1)

    # print total score
    print(f"Model {model} \n===================\nMean F1 Score = {np.mean(scores)}")
    return np.mean(scores)
  
# initialize Logistic Regression model
logres = LogisticRegression(
    multi_class='multinomial',
    solver='lbfgs',
    n_jobs=-1)