def solve_linear_regression(self):
nr_features = len(self.train_inputs[0])
# for problem with 1 or 2 features plot data split
if nr_features == 1:
plot_data_split_simple(self.train_inputs, self.train_outputs,
self.test_inputs, self.test_outputs,
[self.input_features[0], "Happiness"])
elif nr_features == 2:
plot_data_split_multiple(
self.train_inputs, self.train_outputs, self.test_inputs,
self.test_outputs,
[self.input_features[0], self.input_features[1], "Happiness"])
# find model
regression = MyLinearRegression()
regression.fit(self.train_inputs, self.train_outputs)
b = regression.b
f = "f(x) = " + str(regression.intercept)
for i in range(len(b)):
f += " + " + str(b[i]) + "*x" + str(i + 1)
print("model: " + f)
# test model
computed_test_results = regression.predict(self.test_inputs)
print("prediction error: " +
str(self.mean_square_error(computed_test_results)))
# for problem with 1 or 2 features plot model and test results
if nr_features == 1:
plot_model_simple(self.train_inputs, self.train_outputs, b[0],
regression.intercept,
[self.input_features[0], "Happiness"])
plot_test_results_simple(self.test_inputs, self.test_outputs,
computed_test_results,
[self.input_features[0], "Happiness"])
elif nr_features == 2:
plot_model_multiple(
self.train_inputs, self.train_outputs, b[1], b[0],
regression.intercept,
[self.input_features[0], self.input_features[1], "Happiness"])
plot_test_results_multiple(
self.test_inputs, self.test_outputs, computed_test_results,
[self.input_features[0], self.input_features[1], "Happiness"])
# compare with sklearn results
regression_sk = LinearRegression()
regression_sk.fit(self.train_inputs, self.train_outputs)
b = regression_sk.coef_
f = "f(x) = " + str(regression_sk.intercept_)
for i in range(len(b)):
f += " + " + str(b[i]) + "*x" + str(i + 1)
print("model sk: " + f)
computed_test_results_sk = regression_sk.predict(self.test_inputs)
print("prediction error sk: " +
str(self.mean_square_error(computed_test_results_sk)))
train = merged[merged["rating_x"] != -1] # rated movies
y_train = train["rating_x"]
X_train = train.drop(["rating_x", "user_id"], axis=1)
# %%model evaluation
kf = KFold(5)
# lr = MyLinearRegression()
# # lr = Lasso() #sklearn implementation as reference benchmark
lr_rmse = []
for train_index, test_index in kf.split(X_train):
lr_X_train, lr_X_test = X_train.iloc[train_index], X_train.iloc[test_index]
lr_y_train, lr_y_test = y_train.iloc[train_index], y_train.iloc[test_index]
lr = MyLinearRegression()
# lr = MyLinearRegression(poly_degree=2)
lr.fit(lr_X_train, lr_y_train)
lr_rmse.append(np.sqrt(mean_squared_error(
lr.predict(lr_X_test), lr_y_test)))
print("LR, 5fold RMSE ", np.mean(lr_rmse))
# %%mlp
mlp = tf.keras.models.Sequential()
mlp.add(tf.keras.layers.Input([48, ]))
mlp.add(tf.keras.layers.BatchNormalization())
mlp.add(tf.keras.layers.Dense(400, activation="sigmoid"))
mlp.add(tf.keras.layers.BatchNormalization())
mlp.add(tf.keras.layers.Dropout(0.4))
mlp.add(tf.keras.layers.Dense(400, activation="sigmoid"))
mlp.add(tf.keras.layers.Dense(1))
Y = np.array(df.iloc[:, -1]).reshape(-1, 1)
pkl = DataHandler(ARGS)
if ARGS.load:
PreP_x, PreP_y, theta = pkl.load()
if PreP_x.scaler:
X = PreP_x.re_apply_minmax(X)
if PreP_y.scaler:
Y = PreP_y.re_apply_minmax(Y)
if type(X) == type(None) or type(Y) == type(None):
sys.exit()
else:
PreP_x = Preprocessing(X, scaler=ARGS.scaler)
PreP_y = Preprocessing(Y, scaler=ARGS.scaler)
X = PreP_x.data
Y = PreP_y.data
theta = [1] * (X.shape[1] + 1)
lr = MyLinearRegression(theta,
alpha=ARGS.alpha,
n_cycle=ARGS.n_cycle,
visual=ARGS.visual)
err = lr.fit(X, Y)
if type(err) == type(None):
sys.exit()
pkl.save(PreP_x, PreP_y, lr.theta)
if ARGS.visual:
lr.plot_results(X, Y)