Dimensionality_Reduction.py

from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

def rfc_test_accuracy(X, y):
    """
    Function which takes the predictor and target variables and returns the test accuracy of the model.
    """
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2) 
    
    RFC = RandomForestClassifier(random_state=123)
    RFC.fit(X_train,y_train)
    
    test_accuracy = accuracy_score(y_test, RFC.predict(X_test))
    
    return test_accuracy
    
def rfc_mean(X,y,trails=20):
    """
    Print the mean value of Random forest classifier for n trails. 
    """
    result = [rfc_test_accuracy(X,y) for i in range(trails)]
    mean = np.array(result).mean() 
    
    return mean
    
    
print("Predictive accuracy of base random forrest classifier ",round(rfc_mean(df.drop('Component', axis=1),df['Component']),3))