In [76]:
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets, linear_model
from sklearn.metrics import mean_squared_error, r2_score
In [77]:
# Load the boston housing price dataset
boston = datasets.load_boston()
In [78]:
# Inspect dataset
boston
Out[78]:
In [79]:
# Use only one feature for visualisation purposes
boston_X = boston.data[:, 2]
boston_X = boston_X[:, np.newaxis]
In [129]:
# Formate target data
boston_y = boston.target[:, np.newaxis]
In [81]:
# Create linear regression object
regr = linear_model.LinearRegression()
In [82]:
# Train the model using the training data sets
regr.fit(boston_X, boston_y)
Out[82]:
In [83]:
# Predict the target of the training data set
boston_y_pred = regr.predict(boston_X)
In [89]:
# Print the coefficients
print('Coefficients: ', regr.coef_)
# Print mean squared error
print("Mean squared error: %.2f" % mean_squared_error(boston_y, boston_y_pred))
# Print explained variance score: 1 is perfect prediction
print('Variance score: %.2f' % r2_score(boston_y, boston_y_pred))
In [90]:
# Plot outputs
plt.scatter(boston_X, boston_y, color='black')
plt.plot(boston_X, boston_y_pred, color='blue', linewidth=3)
plt.xticks(())
plt.yticks(())
plt.show()
In [110]:
from sklearn.model_selection import train_test_split
In [134]:
# Split the data into training/testing sets
boston_X_train, boston_X_test, boston_y_train, boston_y_test = train_test_split(boston_X, boston_y, test_size=0.2)
In [135]:
# Train the model using the training sets
regr.fit(boston_X_train, boston_y_train)
Out[135]:
In [136]:
# Make predictions using the testing set
boston_y_pred = regr.predict(boston_X_test)
In [137]:
# Print the coefficients
print('Coefficients: ', regr.coef_)
# Print mean squared error
print("Mean squared error: %.2f" % mean_squared_error(boston_y_test, boston_y_pred))
# Print explained variance score: 1 is perfect prediction
print('Variance score: %.2f' % r2_score(boston_y_test, boston_y_pred))
In [138]:
# Plot outputs
plt.scatter(boston_X_test, boston_y_test, color='black')
plt.plot(boston_X_test, boston_y_pred, color='blue', linewidth=3)
plt.xticks(())
plt.yticks(())
plt.show()
In [139]:
boston_X = boston.data
In [165]:
boston_y = boston.target[:, np.newaxis]
In [166]:
boston_X_train, boston_X_test, boston_y_train, boston_y_test = train_test_split(boston_X, boston_y, test_size=0.2)
In [167]:
regr.fit(boston_X_train, boston_y_train)
Out[167]:
In [168]:
boston_y_pred = regr.predict(boston_X_test)
In [169]:
# Print the coefficients
print('Coefficients: ', regr.coef_)
# Print mean squared error
print("Mean squared error: %.2f" % mean_squared_error(boston_y_test, boston_y_pred))
# Print explained variance score: 1 is perfect prediction
print('Variance score: %.2f' % r2_score(boston_y_test, boston_y_pred))
In [69]:
from sklearn.linear_model import Ridge
In [195]:
ridge = Ridge()
In [196]:
ridge.fit(boston_X_train, boston_y_train)
Out[196]:
In [197]:
boston_y_pred = ridge.predict(boston_X_test)
In [198]:
# Print the coefficients
print('Coefficients: ', regr.coef_)
# Print mean squared error
print("Mean squared error: %.2f" % mean_squared_error(boston_y_test, boston_y_pred))
# Print explained variance score: 1 is perfect prediction
print('Variance score: %.2f' % r2_score(boston_y_test, boston_y_pred))