import numpy as np
X = 2 * np.random.rand(100,1)
y = 4 + 3 * X + np.random.rand(100,1)
import matplotlib.pyplot as plt
plt.plot(X, y, "b.")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.axis([0,2,0,15])
plt.show()
import numpy as np
X = 2 * np.random.rand(100,1)
y = 4 + 3 * X + np.random.rand(100,1)
import matplotlib.pyplot as plt
plt.plot(X, y, "b.")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.axis([0,2,0,15])
plt.show()
X_b=np.c_[np.ones((100,1)), X]
theta_best = np.linalg.inv(X_b.T.dot(X_b)).dot(X_b.T).dot(y)
theta_best
X_new = np.array([[0], [2]])
X_new_b = np.c_[np.ones((2,1)), X_new]
y_predict = X_new_b.dot(theta_best)
y_predict
plt.plot(X_new, y_predict, "r-", linewidth=2, label="Predictions")
plt.plot(X,y,"b.")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.legend(loc="upper left", fontsize=14)
plt.axis([0,2,0,15])
plt.show()
from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(X, y)
lin_reg.intercept_, lin_reg.coef_
X_new = np.array([[0], [2]])
lin_reg.predict(X_new)
~확률적
eta = 0.1
n_iterations = 1000
m = 100
theta = np.random.randn(2,1)
for iteration in range(n_iterations):
gradients = 2/m * X_b.T.dot(X_b.dot(theta)-y)
theta = theta - eta * gradients
theta
theta_path_bgd = []
def plot_gradient_descent(theta, eta, theta_path=None):
m=len(X_b)
plt.plot(X, y, "b.")
n_iterations = 1000
for iteration in range(n_iterations):
if iteration < 10:
y_predict = X_new_b.dot(theta)
style = "b-" if iteration > 0 else "r--"
plt.plot(X_new, y_predict, style)
gradients = 1/m * X_b.T.dot(X_b.dot(theta)-y)
theta = theta - eta * gradients
if theta_path is not None:
theta_path.append(theta)
plt.xlabel("$x_1$", fontsize=18)
plt.axis([0,2,0,15])
plt.title(r"$\eta = {}$".format(eta), fontsize=16)
np.random.seed(42)
theta = np.random.randn(2,1)
plt.figure(figsize=(10,4))
plt.subplot(131); plot_gradient_descent(theta, eta=0.02)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.subplot(132); plot_gradient_descent(theta, eta=0.1, theta_path=theta_path_bgd)
plt.subplot(133); plot_gradient_descent(theta, eta=0.5)
plt.show()
theta_path_sgd = []
m = len(X_b)
np.random.seed(42)
n_epochs = 50
t0,t1 = 5, 50
def learning_schedule(t):
return t0 / (t + t1)
theta = np.random.randn(2,1)
for epoch in range(n_epochs):
for i in range(m):
if epoch ==0 and i < 20:
y_predict = X_new_b.dot(theta)
style = "b-" if i > 0 else "r--"
plt.plot(X_new, y_predict, style)
random_index = np.random.randint(m)
xi = X_b[random_index:random_index+1]
yi = y[random_index:random_index+1]
gradients = 2 * xi.T.dot(xi.dot(theta)-yi)
eta = learning_schedule(epoch * m + i)
theta = theta - eta * gradients
theta_path_sgd.append(theta)
plt.plot(X, y, "b.")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation = 0, fontsize=18)
plt.axis([0,2,0,15])
plt.show()
theta
~미니배치
theta_path_mgd = []
n_iterations = 50
minibatch_size = 20
np.random.seed(42)
theta = np.random.randn(2,1)
t0,t1 = 200, 100
def learning_schedule(t):
return t0 / (t + t1)
t = 0
for epoch in range(n_iterations):
shuffled_indices = np.random.permutation(m)
X_b_shuffled = X_b[shuffled_indices]
y_shuffled = y[shuffled_indices]
for i in range(0,m,minibatch_size):
t +=1
xi = X_b_shuffled[i:i+minibatch_size]
yi = y_shuffled[i:i+minibatch_size]
gradients = 2/minibatch_size * xi.T.dot(xi.dot(theta)-yi)
eta = learning_schedule(t)
theta = theta - eta * gradients
theta_path_mgd.append(theta)
theta
theta_path_bgd = np.array(theta_path_bgd)
theta_path_sgd = np.array(theta_path_sgd)
theta_path_mgd = np.array(theta_path_mgd)
plt.figure(figsize=(7,4))
plt.plot(theta_path_sgd[:, 0], theta_path_sgd[:, 1], "r-s", linewidth=1, label="Stochastic")
plt.plot(theta_path_mgd[:, 0], theta_path_mgd[:, 1], "g-+", linewidth=2, label="Mini-batch")
plt.plot(theta_path_bgd[:, 0], theta_path_bgd[:, 1], "b-o", linewidth=3, label="Batch")
plt.legend(loc="upper left", fontsize=16)
plt.xlabel(r"$\theta_0$", fontsize=20)
plt.ylabel(r"$Wtheta_1$", fontsize=20, rotation=0)
plt.axis([2.5, 4.5, 2.3, 3.9])
plt.show()
다항회귀
from sklearn.preprocessing import PolynomialFeatures
poly_features=PolynomialFeatures(degree=2, include_bias=False)
X_poly=poly_features.fit_transform(X)
X[0]
X_poly[0]
lin_reg = LinearRegression()
lin_reg.fit(X_poly, y)
lin_reg.intercept_, lin_reg.coef_
X_new=np.linspace(-3,3,100).reshape(100,1)
X_new_poly = poly_features.transform(X_new)
y_new = lin_reg.predict(X_new_poly)
plt.plot(X, y, "b.")
plt.plot(X_new, y_new, "r-", linewidth=2, label="Predictions")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.legend(loc="upper left", fontsize=14)
plt.axis([-3, 3, 0, 10])
plt.show()
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
for style, width, degree in (("g-", 1, 300), ("b--", 2, 2), ("r-+", 2, 1)):
polybig_features = PolynomialFeatures(degree=degree, include_bias=False)
std_scaler = StandardScaler()
lin_reg = LinearRegression()
polynomial_regression = Pipeline([
("poly_features", polybig_features),
("std_scaler", std_scaler),
("lin_reg", lin_reg)
])
polynomial_regression.fit(X,y)
y_newbig = polynomial_regression.predict(X_new)
plt.plot(X_new, y_newbig, style, label=str(degree), linewidth=width)
plt.plot(X, y, "b.", linewidth=3)
plt.legend(loc="upper left")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.axis([-3, 3, 0, 10])
plt.show()