def plot_cost(x, y):
"""Plot the data and prediction line from three non-empty numpy.ndarray.
Args:
x: has to be an numpy.ndarray, a vector of dimension m * 1.
y: has to be an numpy.ndarray, a vector of dimension m * 1.
theta: has to be an numpy.ndarray, a vector of dimension 2 * 1.
Returns:
Nothing.
Raises:
This function should not raise any Exceptions.
"""
# plt.plot(x, y, 'o')
# x = np.linspace(-15,5,100)
plt.ylim((10, 50))
plt.xlim((-13, -4.5))
ran = 15
upd = ran * 2 / 6
for t0 in np.arange(89 - ran, 89 + ran, upd):
cost_list = []
theta_list = []
for t1 in np.arange(-8 - 100, -8 + 100, 0.1):
lr = MyLR(thetas=[t0, t1], alpha=1e-3, max_iter=50000)
y_ = lr.predict(x)
mse_c = lr.cost_(y, y_) #[0][0]
cost_list.append(mse_c)
theta_list.append(t1)
# print(cost_list[-1])
label = "θ[0]=" + str(int(t0 * 10) / 10)
print(label, "done!")
plt.plot(theta_list, cost_list, label=label)
plt.xlabel("θ[1]")
plt.ylabel("MSE(θ[0], θ[1])")
plt.legend(loc='upper left')
plt.show()
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)))
if (df.shape[1] > 1):
X = np.array(df.iloc[:, 0:-1]).reshape(-1, len(df.columns) - 1)
Y = np.array(df.iloc[:, -1]).reshape(-1,1)
else:
X = np.array(df.iloc[:, :])
print("Dataset without results, if visual asked, an array of zeros will be used")
Y = np.zeros_like(X)
else:
X = ARGS["values"]
Y = np.zeros_like(X)
if ARGS.load:
pkl = DataHandler(ARGS)
PreP_x, PreP_y, theta = pkl.load()
X = PreP_x.re_apply_minmax(X)
Y = PreP_y.re_apply_minmax(Y)
if type(X) == type(None):
sys.exit()
else:
theta = [0] * (X.shape[1] + 1)
print("Theta is: ", theta)
lr = MyLinearRegression(theta, visual=ARGS.visual)
value = lr.predict(X)
print("Predicted value(s):\n", value)
if ARGS.load:
print("\twithout preprocessing:\n", PreP_y.unapply_minmax(value))
if ARGS.visual:
lr.plot_results(X, Y)
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))
adam = tf.keras.optimizers.Adam(learning_rate=1e-4)
scheduler = tf.keras.callbacks.ReduceLROnPlateau()
import pandas as pd
import numpy as np
from sklearn.metrics import mean_squared_error
from my_linear_regression import MyLinearRegression as MyLR
import matplotlib.pyplot as plt
data = pd.read_csv("are_blue_pills_magics.csv")
Xpill = np.array(data["Micrograms"]).reshape(-1, 1)
Yscore = np.array(data["Score"]).reshape(-1, 1)
linear_model1 = MyLR(np.array([[89.0], [-8]]))
linear_model2 = MyLR(np.array([[89.0], [-6]]))
Y_model1 = linear_model1.predict(Xpill)
Y_model2 = linear_model2.predict(Xpill)
# print("Me: ", linear_model1.mse_(Yscore, Y_model1))
# print("Sc: ", mean_squared_error(Yscore, Y_model1))
# print()
#
# print("Me: ", linear_model2.mse_(Yscore, Y_model2))
# print("Sc: ", mean_squared_error(Yscore, Y_model2))
def plot(x, y, theta):
"""Plot the data and prediction line from three non-empty numpy.ndarray.
Args:
x: has to be an numpy.ndarray, a vector of dimension m * 1.
y: has to be an numpy.ndarray, a vector of dimension m * 1.
theta: has to be an numpy.ndarray, a vector of dimension 2 * 1.
Returns:
Nothing.
Raises:
def rmse_cv(*args, **kwargs):
return np.mean(np.sqrt(cross_val_score(*args, scoring=mse)))
# %%baseline
kf = KFold(N_FOLD)
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.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))
# n = 2 expansion
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(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, n=2 expansion, 5fold RMSE ", np.mean(lr_rmse))
import numpy as np
from my_linear_regression import MyLinearRegression as MyLR
if __name__ == "__main__":
X = np.array([[1., 1., 2., 3.], [5., 8., 13., 21.], [34., 55., 89., 144.]])
Y = np.array([[23.], [48.], [218.]])
mylr = MyLR([[1.], [1.], [1.], [1.], [1]])
print("# Example 0:")
print(mylr.predict(X))
print("# Output:")
print("array([[8.], [48.], [323.]])")
print()
print("# Example 1:")
print(mylr.cost_elem_(X,Y))
print("# Output:")
print("array([[37.5], [0.], [1837.5]])")
print()
print("# Example 2:")
print(mylr.cost_(X,Y))
print("# Output:")
print(1875.0)
print()
# sys.lol()
print("# Example 3:")
mylr.fit_(X, Y)
print(mylr.theta)
print("# Output:")
y = dataset.iloc[:, 1].values
# Splitting the dataset into the Training set and Test set
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=1 / 3,
random_state=0)
# Fitting Simple Linear Regression to the Training set
regressor = MyLinearRegression()
regressor.train(X, y)
print(regressor.weight)
print(regressor.bias)
# Predicting the Test set results
y_pred = regressor.predict(X_test)
# Visualising the Training set results
plt.scatter(X_train, y_train, color='red')
plt.plot(X_train, regressor.predict(X_train), color='blue')
plt.title('Salary vs Experience (Training set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()
# Visualising the Test set results
plt.plot(regressor.cost_trend, color='blue')
plt.title('Cost Flow')
plt.xlabel('Iterations')
plt.ylabel('Cost')
plt.show()