flag = 3
if flag & 1:
linear_model.fit_(x, y)
y_hat = linear_model.predict_(x)
plot_regression(x, y, y_hat)
if flag & 2:
plot_cost(x, y)
if __name__ == "__main__":
data = pd.read_csv("../resources/are_blue_pills_magics.csv")
Xpill = np.array(data["Micrograms"]).reshape(-1, 1)
Yscore = np.array(data["Score"]).reshape(-1, 1)
if False:
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("model 1") # 57.603042857142825
print(linear_model1.mse_(Yscore, Y_model1))
print(mean_squared_error(Yscore, Y_model1))
print("\nmodel 2") # 232.16344285714285
print(linear_model2.mse_(Yscore, Y_model2))
print(mean_squared_error(Yscore, Y_model2))
plot2graphs(Xpill, Yscore)
Xpill = np.array(data["Micrograms"]).reshape(-1,1)
Yscore = np.array(data["Score"]).reshape(-1,1)
thetas = np.array([1, 1])
#plt.plot(Xpill, Yscore, 'o')
mlr = MyLR(thetas, alpha=0.05, n_cycle=5000)
#th = mlr.fit_(Xpill, Yscore)
#print(th)
#plt.plot(Xpill, (th[1] * Xpill + th[0]), '-r')
#plt.show()
for j in range(80, 100, 5):
res = []
for i in range(-11, -7, 1):
mlr.thetas = np.array([j, i])
dummy, y_hat = mlr.predict_(Xpill)
res.append(mlr.mse_(Yscore, y_hat))
np.array(res)
plt.plot(np.arange(-11, -7), res)
plt.show()
for j in range(80, 100, 5):
res = []
for i in range(-11, -7, 1):
mlr.thetas = np.array([j, i])
dummy, y_hat = mlr.predict_(Xpill)
res.append(mean_squared_error(Yscore, y_hat))
np.array(res)
plt.plot(np.arange(-11, -7), res, '-r')
plt.show()
#for plotting of polynomial curves - cotinuous data set over range of original data
#then add polynomial features and normalise
continuous_x = np.arange(1, 7.01, 0.01).reshape(-1, 1)
x_ = add_polynomial_features(continuous_x, 10)
for i in range(10):
x_[:, i] = minmax(x_[:, i])
thetas = np.ones(11).reshape(-1, 1)
cost_values = []
thetas_list = []
mlr = MLR(thetas, alpha=0.009, n_cycle=5000)
for degree in range(2, 11):
mlr.thetas = thetas[:degree + 1]
thetas_list.append(mlr.fit_(new_train[:, :degree], y_train))
cost_values.append(
mlr.mse_(y_train,
mlr.predict_(new_train[:, :degree])[1]))
i = 2
for elem in thetas_list:
mlr.thetas = elem
y_hat = mlr.predict_(x_[:, :i])[1]
plt.plot(continuous_x, y_hat, '--')
plt.title(str(degree))
plt.title(('degree = ' + str(i) + ' cost: ' + str(cost_values[i - 2])))
plt.plot(x_train, y_train, 'go')
plt.plot(x_test, y_test, 'ro')
plt.show()
i += 1
def cost_(y_hat, y):
j_elem = cost_elem_(y_hat, y)
return np.sum(j_elem)
if __name__ == "__main__":
data = pd.read_csv("../resources/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(linear_model1.mse_(Xpill, Yscore))
print(mean_squared_error(Yscore, Y_model1))
print(linear_model2.mse_(Xpill, Yscore))
print(mean_squared_error(Yscore, Y_model2))
print(Yscore)
#print(linear_model1.cost_(linear_model1.predict_(Xpill), Yscore))
#linear_model1.fit_(Xpill, Yscore)
print(linear_model1.thetas)
theta1_array = np.array([-14, -12, -10, -8, -6, -4])
cost_array = np.zeros(6, )
for j in range(87, 92):
for i in range(6):
print(theta1_array[i])
pre = predict_(Xpill, np.array([j, theta1_array[i]]))
#print(pre)
y_test = np.array([39, 52, 70, 58, 50, 32, 62]).reshape(-1, 1) plt.plot(x_test, y_test, 'o') new = add_polynomial_features(x, 10) thetas = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] cost_values = [] #for plotting of polynomial curves - cotinuous data set over range of original data continuous_x = np.arange(1, 7.01, 0.01).reshape(-1, 1) x_ = add_polynomial_features(continuous_x, 10) degree = 2 mlr = MLR(np.array(thetas[:degree + 1]), alpha=0.002, n_cycle=1500) mlr.fit_(new[:, :degree], y) cost_values.append(mlr.mse_(y, mlr.predict_(new[:, :degree])[1])) y_hat = mlr.predict_(x_[:, :degree])[1] plt.plot(continuous_x, y_hat, '--') plt.title(str(degree)) plt.show() degree = 3 mlr = MLR(np.array(thetas[:degree + 1]), alpha=0.00005, n_cycle=4000) mlr.fit_(new[:, :degree], y) cost_values.append(mlr.mse_(y, mlr.predict_(new[:, :degree])[1])) y_hat = mlr.predict_(x_[:, :degree])[1] plt.plot(x, y, 'o') plt.plot(continuous_x, y_hat, '--') plt.title(str(degree)) plt.show()
def mse_(self, y, y_hat):
return MLR.mse_(self, y, y_hat)
plt.plot(x_test[:, i:i + 1], y_test, 'ro', markersize=3)
plt.show()
#initialise thetas as array with feature number + 1 zeros
thetas = np.zeros(new_features.shape[1] + 1)
#should be able to use same alpha and cycle number for all, as same data
#carry out linear regression on training data
cost_list = []
mlr = MLR(thetas, alpha=0.1, n_cycle=400)
mlr.fit_(x_train, y_train)
y_hat = mlr.predict_(x_test)[1]
cost_list.append(mlr.mse_(y_test, y_hat))
plot(x_test, y_test, y_hat, features)
#carry out 9 ridge regressions on training data, with lambda from 0.1 to 0.9
mrg = MRG(thetas, alpha=0.1, n_cycle=400)
for i in range(1, 10):
mrg.lambda_ = i / 10
mrg.thetas = thetas
plt.title('lambda = ' + str(i / 10))
mrg.fit_(x_train, y_train)
y_hat = mrg.predict_(x_test)[1]
cost_list.append(mlr.mse_(y_test, y_hat))
#plot(x_test, y_test, y_hat, features)
plt.bar(range(0, 10), cost_list)
data = pd.read_csv("../resources/are_blue_pills_magics.csv")
Xpill = np.array(data["Micrograms"]).reshape(-1, 1)
Yscore = np.array(data["Score"]).reshape(-1, 1)
print(Xpill)
print(Yscore)
linear_model1 = MyLR(np.array([[89.0], [-8]]))
linear_model2 = MyLR(np.array([[89.0], [-6]]))
# linear_model1.plot(Xpill, Yscore)
# linear_model2.plot(Xpill, Yscore)
Y_model1 = linear_model1.predict_(Xpill)
Y_model2 = linear_model2.predict_(Xpill)
print("mine: ", linear_model1.mse_(Yscore, Y_model1)) #MY
# 57.60304285714282
print("not mine: ", mean_squared_error(Yscore, Y_model1))
# 57.603042857142825
print("mine: ", linear_model2.mse_(Yscore, Y_model2)) # MY
# 232.16344285714285
print("not mine: ", mean_squared_error(Yscore, Y_model2))
# 232.16344285714285
# linear_model1.plot(Xpill, Y_model1)
# linear_model2.plot(Xpill, Y_model2)