Fitted_DataPoints_vs_ActualPoints

from pylab import rcParams

class Fitted_DataPoints_vs_ActualPoints(Data_Modelling):
    

    def __init__(self,n_estimators,
                    max_depth,
                    min_samples_split,
                    min_samples_leaf,
                    max_leaf_nodes,
                    min_impurity_split,
                    min_impurity_decrease,
                    bootstrap,
                    min_child_weight,
                    learning_rate,
                    Subsample,
                    Alpha,
                    Lamda,
                    random_state,
                    criterion):
        
        Data_Modelling.__init__(self,n_estimators,
                    max_depth,
                    min_samples_split,
                    min_samples_leaf,
                    max_leaf_nodes,
                    min_impurity_split,
                    min_impurity_decrease,
                    bootstrap,
                    min_child_weight,
                    learning_rate,
                    Subsample,
                    Alpha,
                    Lamda,
                    random_state,
                    criterion)
        
        
        print("Data Points object created")
        
        
    def Random_Forest_Model(self,df):

        RF_Regressor = RandomForestRegressor(n_estimators = self.n_estimators,
                            max_depth = self.max_depth,
                            min_samples_split = self.min_samples_split,
                            min_samples_leaf = self.min_samples_leaf,
                            max_leaf_nodes = self.max_leaf_nodes,
                            bootstrap = self.bootstrap,
                            criterion = self.criterion)

        RF_Regressor.fit(x_train,y_train)

        RF_pred=RF_Regressor.predict(x_test)

        np.sqrt(metrics.mean_squared_error(y_test,RF_pred))

        r2_score(y_test,RF_pred)


        rcParams['figure.figsize'] = 10, 10
        fig, ax = plt.subplots()
        ax.scatter(y_test, RF_pred)
        ax.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)
        print('Customer LifeTime Value Prediction   ::  Data Points  vs Fitted Lines')
        ax.set_xlabel('Actual')
        ax.set_ylabel('Predicted')
        plt.show()


DP = Fitted_DataPoints_vs_ActualPoints(500,5,3,3,None,1,0.1,True,3,0.07,0.7,0,1.5,29,'mse')

DP.Random_Forest_Model(df)