Multiple regression: Python

import numpy as np

from sklearn import linear_model

import sklearn.metrics as sm

from sklearn.preprocessing import PolynomialFeatures

# Input file containing data

input_file = 'data_multivar_regr.txt'

# Load the data from the input file

data = np.loadtxt(input_file, delimiter=',')

X, y = data[:, :-1], data[:, -1]

# Split data into training and testing

num_training = int(0.8 * len(X))

num_test = len(X) - num_training

# Training data

X_train, y_train = X[:num_training], y[:num_training]

# Test data

X_test, y_test = X[num_training:], y[num_training:]

# Create the linear regressor model

linear_regressor = linear_model.LinearRegression()

# Train the model using the training sets

linear_regressor.fit(X_train, y_train)

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)

# Predict the output

y_test_pred = linear_regressor.predict(X_test)

# Measure performance

print("Linear Regressor performance:")

print("Mean absolute error =", round(sm.mean_absolute_error(y_test,

y_test_pred), 2))

print("Mean squared error =", round(sm.mean_squared_error(y_test,

y_test_pred), 2))

print("Median absolute error =", round(sm.median_absolute_error(y_test,

y_test_pred), 2))

print("Explained variance score =",

round(sm.explained_variance_score(y_test, y_test_pred), 2))

print("R2 score =", round(sm.r2_score(y_test, y_test_pred), 2))

Linear Regressor performance: Mean absolute error = 3.58 Mean squared error = 20.31 Median absolute error = 2.99 Explained variance score = 0.86 R2 score = 0.86

# Polynomial regression

polynomial = PolynomialFeatures(degree=10)

X_train_transformed = polynomial.fit_transform(X_train)

datapoint = [[7.75, 6.35, 5.56]]

poly_datapoint = polynomial.fit_transform(datapoint)

poly_linear_model = linear_model.LinearRegression()

poly_linear_model.fit(X_train_transformed, y_train)

print("\nLinear regression:\n", linear_regressor.predict(datapoint))

print("\nPolynomial regression:\n",poly_linear_model.predict(poly_datapoint))

Linear regression: [36.05286276] Polynomial regression: [41.45709521]