import numpy as np
import matplotlib.pyplot as plt
x = np.random.uniform(-3, 3, size=100)
x = x.reshape(-1, 1)
y = 0.5 * x**2 + x + 2 + np.random.normal(0, 1, 100)
plt.scatter(x, y)
plt.show()
from sklearn.linear_model import linearregression
lin_reg = linearregression()
lin_reg.fit(x, y)
y_predict = lin_reg.predict(x)
plt.scatter(x, y)
plt.plot(x, y_predict, color='r')
plt.show()
x2 = np.hstack([x, x**2])
>>> x2.shape
(100, 2)
lin_reg2 = linearregression()
lin_reg2.fit(x2, y)
y_predict2 = lin_reg2.predict(x2)
plt.scatter(x, y)
plt.plot(np.sort(x), y_predict2[np.argsort(x)], color='r')
plt.show()
from sklearn.preprocessing import polynomialfeatures
poly = polynomialfeatures(degree=2) //為原本資料集新增最多2次冪的特徵
poly.fit(x)
x2 = poly.transform(x)
>>> x2.shape
(100, 3) //第一列全是1，代表x的0次方。第二列和第三列分別代表x的1，2次方
from sklearn.linear_model import linearregression
lin_reg2 = linearregression()
lin_reg2.fit(x2, y)
y_predict2 = lin_reg2.predict(x2)
plt.scatter(x, y)
plt.plot(np.sort(x), y_predict2[np.argsort(x)], color='r')
plt.show()
lin_reg2.coef_ //係數
>>> array([ 0. , 0.9460157 , 0.50420543])
>>> lin_reg2.intercept_
2.1536054095953823 //截距
x = np.random.uniform(-3, 3, size=100)
x = x.reshape(-1, 1)
y = 0.5 * x**2 + x + 2 + np.random.normal(0, 1, 100)
from sklearn.pipeline import pipeline
from sklearn.preprocessing import standardscaler
//構造pipeline時傳入列表，列表中傳入"管道"中每乙個步驟對應的類，每個類時元組的形式。
//送給pipeline的資料沿著"管道"的格式進行
poly_reg = pipeline([
("poly", polynomialfeatures(degree=2)),//第一步：多項式的特徵
("std_scaler", standardscaler()), //第二步：資料歸一化
("lin_reg", linearregression()) //第三部：線性回歸
])poly_reg.fit(x, y)
y_predict = poly_reg.predict(x)
plt.scatter(x, y)
plt.plot(np.sort(x), y_predict[np.argsort(x)], color='r')
plt.show()
from sklearn.metrics import mean_squared_error
y_predict = lin_reg.predict(x)
mean_squared_error(y, y_predict)
np.random.seed(666)
x = np.random.uniform(-3.0, 3.0, size=100)
x = x.reshape(-1, 1)
y = 0.5 * x**2 + x + 2 + np.random.normal(0, 1, size=100)
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=10)
from sklearn.linear_model import linearregression
from sklearn.metrics import mean_squared_error
train_score =
test_score =
for i in range(1, 76):
lin_reg = linearregression()
lin_reg.fit(x_train[:i], y_train[:i])
y_train_predict = lin_reg.predict(x_train[:i])
y_test_predict = lin_reg.predict(x_test)
plt.plot([i for i in range(1, 76)], np.sqrt(train_score), label="train")
plt.plot([i for i in range(1, 76)], np.sqrt(test_score), label="test")
plt.legend()
plt.show()
def
plot_learning_curve
(algo, x_train, x_test, y_train, y_test): //algo:演算法
train_score =
test_score =
for i in range(1, len(x_train)+1):
algo.fit(x_train[:i], y_train[:i])
y_train_predict = algo.predict(x_train[:i])
y_test_predict = algo.predict(x_test)
plt.plot([i for i in range(1, len(x_train)+1)],
np.sqrt(train_score), label="train")
plt.plot([i for i in range(1, len(x_train)+1)],
np.sqrt(test_score), label="test")
plt.legend()
plt.axis([0, len(x_train)+1, 0, 4])
plt.show()
plot_learning_curve(linearregression(), x_train, x_test, y_train, y_test)
多項式回歸
多項式回歸 import torch import numpy defmake features x 獲取 x,x 2,x 3 的矩陣 x x.unsqueeze 1 將一維資料變為 n，1 二維矩陣形式 return torch.cat x i for i in range 1 4 1 按列拼接 ...
多項式回歸
線性回歸適用於資料成線性分布的回歸問題，如果樣本是非線性分布，線性回歸就不再使用，轉而可以採用非線性模型進行回歸，比如多項式回歸 多項式回歸模型定義 與線性模型，多項式模型引入了高次項 y w 0 w1 x w2 x2 w 3x3 wnxn y w 0 w 1x w 2x 2 w 3x 3 w nx...
多項式回歸
多項式回歸 import torch import numpy defmake features x 獲取 x,x 2,x 3 的矩陣 x x.unsqueeze 1 將一維資料變為 n，1 二維矩陣形式 return torch.cat x i for i in range 1 4 1 按列拼接 ...