def train(x, y):
model = PolynomialFeatures(degree=2)
x = model.fit_transform(x)
x_test = model.transform(x)
model = LinearRegression()
model.fit(x, y)
joblib.dump(model, 'f**k.m')
print('多项式回归正确率', model.score(x_test, y))
X_train_no_intercept = X_train
X_train = X_train.reshape(-1, X_train.shape[1])
poly.fit(X_train, y_train)
# The intercept
print('Intercept: \n', poly.intercept_)
# The coefficients
print('Coefficients: \n', poly.coef_)
# The mean square error
print("Residual sum of squares, training data: %.2f"
% np.mean((poly.predict(X_train) - y_train) ** 2))
print("Residual sum of squares, test data: %.2f"
% np.mean((poly.predict(X_test) - y_test) ** 2))
var_to_graph['multReg_poly'] = np.mean((poly.predict(X_test) - y_test) ** 2)
# Explained variance score: 1 is perfect prediction
print('Variance score, training data: %.2f' % poly.score(X_train, y_train))
#vector of prediction error
print('Distribution of prediction error on training data:')
predError = poly.predict(X_train) - y_train
plt.hist(predError)
plt.show()
print('Distribution of prediction error on test data:')
predError = poly.predict(X_test) - y_test
plt.hist(predError)
plt.show()
## RIDGE REGRESSION
# DOC: http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html
# create training and test sets
y_pred = reg2.predict(x_poly)
plt.scatter(x_train[:, 0], y_train, color='red')
plt.plot(np.sort(x_test[:, 0]), np.sort(y_pred), color='blue')
plt.title("railways with poly reg")
plt.show()
#linear regression
reg = LinearRegression()
reg.fit(x_train, y_train)
y_pred = reg.predict(x_test)
plt.scatter(x_train[:, 3], y_train, color='red')
plt.plot(np.sort(x_test[:, 3]), np.sort(y_pred), color='blue')
plt.title("railways with linear reg")
plt.show()
print('The accuracy of the linear reg is {:.2f} out of 1 on training data'.
format(reg.score(x_train, y_train)))
print('The accuracy of the linear reg is {:.2f} out of 1 on test data'.format(
reg.score(x_test, y_test)))
#reg.coef_
#reg.intercept_
from sklearn.metrics import mean_squared_error
rmse = np.sqrt(mean_squared_error(y_test, y_pred))
print(rmse)
#KNN
from sklearn.neighbors import KNeighborsClassifier
reg = KNeighborsClassifier()
reg.fit(x_train, y_train)
y_pred = reg.predict(x_test)
plt.scatter(x_train[:, 0], y_train, color='red')
plt.plot(x_test[:, 0], y_pred, color='blue')
plt.title("railways with KNN reg")
model_rsq_dic['lr'] = (lr.score(lstat_x, y), mean_squared_error(y, y_lr_pred))
plt.scatter(lstat_x, y, s=10)
plt.plot(lstat_x,
y_lr_pred,
color='red',
label='Linear Regression - rsq: 0.544')
poly = PolynomialFeatures(degree=2)
lstat_x_transformed = poly.fit_transform(lstat_x)
poly = LinearRegression()
poly.fit(lstat_x_transformed, y)
print("poly equation", poly.coef_, " intercept ", poly.intercept_)
y_poly_pred = poly.predict(lstat_x_transformed)
print("r^2 of poly", poly.score(lstat_x_transformed, y))
print("mse of poly", mean_squared_error(y, y_poly_pred))
model_rsq_dic['poly'] = (poly.score(lstat_x_transformed,
y), mean_squared_error(y, y_poly_pred))
#REALLY IMPT to sort the values of x before line plot
sort_axis = operator.itemgetter(0)
sorted_zip = sorted(zip(lstat_x, y_poly_pred), key=sort_axis)
x, y_poly_pred = zip(*sorted_zip)
plt.plot(x, y_poly_pred, color='green', label='Poly Regression - rsq: 0.641')
mars = Earth()
mars.fit(
lstat_x,
y,
x_train_fit = poly.fit_transform(x_train_2[["horsepower"]])
x_test_fit = poly.fit_transform((x_test_2[["horsepower"]]))
# Create a linear regression model "poly" and train it
poly = LinearRegression()
poly.fit(x_train_fit, y_train_2)
# Get predicted values of price column
Yhat = poly.predict(x_test_fit)
print("Predicted values from polynomial regression :\n", Yhat[0:5])
# Take the first five predicted values and compare it to the actual targets
print("Actual values :\n", y_test_2[0:5])
# Get R^2 of training and test data
R_sq_train_poly = poly.score(x_train_fit, y_train_2)
R_sq_test_poly = poly.score(x_test_fit, y_test_2)
print("Polynomial Regression R^2 values ", R_sq_train_poly, " and ",
R_sq_test_poly)
# How the R^2 changes on the test data for different order polynomials and plot the results
orders = [1, 2, 3, 4, 5, 6]
R_sq = []
X_train, X_test, Y_train, Y_test = train_test_split(X,
Y,
test_size=0.15,
random_state=1)
for order in orders:
polyF = PolynomialFeatures(degree=order)
X_train_fit = polyF.fit_transform(X_train[["horsepower"]])
X_test_fit = polyF.fit_transform(X_test[["horsepower"]])