[机器学习从零到壹sklearn]·0.1.1·线性拟合

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

# 引入包
from sklearn.linear_model.stochastic_gradient import SGDRegressor
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split



class Args:

    seed=1234
    data_file="sample_data.csv"
    num_samples=100
    train_size=0.75
    test_size=0.25
    num_epochs=100

args = Args()

# 设置随机种子来保证结果可复现
np.random.seed(args.seed)

# 生成数据
def generate_data(num_samples):
    X = np.array(range(num_samples))
    random_noise = np.random.uniform(-20,20,size=num_samples)
    y = 3.65*X + 10 + random_noise # add some noise
    return X, y

# 生成随机但是线性的数据
X, y = generate_data(args.num_samples)
data = np.vstack([X, y]).T
df = pd.DataFrame(data, columns=['X', 'y'])
print(df.head())


# 划分数据集
X_train, X_test, y_train, y_test = train_test_split(
    df["X"].values.reshape(-1, 1), df["y"], test_size=args.test_size, 
    random_state=args.seed)
print ("X_train:", X_train.shape)
print ("y_train:", y_train.shape)
print ("X_test:", X_test.shape)
print ("y_test:", y_test.shape)

# 标准化训练集
X_scaler = StandardScaler().fit(X_train)
y_scaler = StandardScaler().fit(y_train.values.reshape(-1,1))

# 分别在训练集和测试集上做标准化
standardized_X_train = X_scaler.transform(X_train)
standardized_y_train = y_scaler.transform(y_train.values.reshape(-1,1)).ravel()
standardized_X_test = X_scaler.transform(X_test)
standardized_y_test = y_scaler.transform(y_test.values.reshape(-1,1)).ravel()

print ("mean:", np.mean(standardized_X_train, axis=0), 
       np.mean(standardized_y_train, axis=0)) # mean should be ~0
print ("std:", np.std(standardized_X_train, axis=0), 
       np.std(standardized_y_train, axis=0))   # std should be 1

lm = SGDRegressor(loss="squared_loss", penalty="none", max_iter=args.num_epochs)
# lm model
print(lm)

lm.fit(X=standardized_X_train, y=standardized_y_train)

pred_train = (lm.predict(standardized_X_train) * np.sqrt(y_scaler.var_)) + y_scaler.mean_
pred_test = (lm.predict(standardized_X_test) * np.sqrt(y_scaler.var_)) + y_scaler.mean_


# 调整图大小
plt.figure(figsize=(16,9))


# 画出训练数据



plt.subplot(1, 2, 1)
plt.title("Train")
plt.scatter(X_train, y_train, label="y_train")
plt.plot(X_train, pred_train, color="red", linewidth=1, linestyle="-", label="lm")
plt.legend(loc='lower right')

# 画出测试数据
plt.subplot(1, 2, 2)
plt.title("Test")
plt.scatter(X_test, y_test, label="y_test")
plt.plot(X_test, pred_test, color="red", linewidth=1, linestyle="-", label="lm")
plt.legend(loc='lower right')

plt.show()

     X          y
0  0.0  -2.339222
1  1.0  18.534351
2  2.0  14.809110
3  3.0  32.364343
4  4.0  35.799032
X_train: (75, 1)
y_train: (75,)
X_test: (25, 1)
y_test: (25,)
mean: [8.22952817e-17] 3.1798637796972193e-16
std: [1.] 1.0000000000000002
SGDRegressor(alpha=0.0001, average=False, early_stopping=False, epsilon=0.1,
       eta0=0.01, fit_intercept=True, l1_ratio=0.15,
       learning_rate='invscaling', loss='squared_loss', max_iter=100,
       n_iter=None, n_iter_no_change=5, penalty='none', power_t=0.25,
       random_state=None, shuffle=True, tol=None, validation_fraction=0.1,
       verbose=0, warm_start=False)