g3_ltv_fe.py

#convert categorical columns to numerical
tx_class = pd.get_dummies(tx_cluster)

#calculate and show correlations
corr_matrix = tx_class.corr()
corr_matrix['LTVCluster'].sort_values(ascending=False)

#create X and y, X will be feature set and y is the label - LTV
X = tx_class.drop(['LTVCluster','m6_Revenue'],axis=1)
y = tx_class['LTVCluster']

#split training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.05, random_state=56)