用sklearn进行手写数字的识别训练，获取学习率和惩罚系数，机器学习入门推荐案例（1）
理论总是让人感觉乏味和枯燥，对于学习率和惩罚系数是如何确定的呢？我们可以用列举法来评价每个参数的得分，进而获取最优的模型参数。
一、 获取手写数据集合
from sklearn.datesets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt
def load_data():
data = load_digits()
x, y = data.data, data.target
#切割测试集和训练集
train_x, test_x, train_y, test_y = train_test_split(test_size= 0.3, random_state=10)
#标准化数据
ss = StandardScaler()
ss.fit(train_x)
train_x = ss.transform(train_x)
test_x = ss.transform(test_x)
return train_x, test_x, train_y, test_y;
处理完数据后，可以展示一下数据的样式，让我们看看图片张啥样
def show_img(X):
images = X.reshape(-1, 8, 8 ) # 格式为（-1， 64,）图片格式为8 * 8
# 构建绘图
fig, axi = plt.subslots(3, 5)
for i, ax in enumerate(axi.flat):
img = images[i]
ax.imshow(img, cmap='gray')
ax.set(xticks=[], yticks=[])
plt.tight_layout()
plt.show()
开始寻找最优的学习率和惩罚系数
def model_fit(X,y, k=5):
learning_rates = [0.001, 0.003, 0.01, 0.03, 0.1, 0.3, 1, 3]
penalties = [0, 0.03, 0.01, 0.1, 0.3, 1, 3] #惩罚系数
all_models = []
for learning_rate in learning_rates:
for penalty in penalties:
print('正训练模型:下降参数为%s，正则化为%s'%(learning_rate, penalty))
#建立逻辑回归模型
model_score = []
#运用交叉验证法取样
kf = KFold(n_split= k, shuffle= True, random_state = 20)
model = SGDclassifier(loss = 'log', learning_rate = "constant", penalty = "l2", eta0 = learning_rate, alpha = penalty)
for train_idx, dev_idx in kf.split(X):
x_train, x_dev = X[train_idx], x[dev_idx]
y_train, y_dev = y[train_idx], y[dev_idx]
model.fit(x_train, x_dev)
s = model.score(y_train, y_dev)
model_score.append(s)
all_models.append([np.mean(model_score), learning_rate, penalty])
print("模型最优解：", sorted(all_models, reverse= True)[0]
测试运行
if __name__ == "__main__":
train_x, test_x, train_y, test_y = load_data()
print(train_x.shape)
print(train_y.shape)
# model_fit(train_x, train_y)
model = SGDClassifier(loss='log', penalty='l2',learning_rate="constant", alpha=0.01, eta0=0.01)
model.fit(train_x, train_y)
y_pred = model.predict(test_x)
print(test_y)
print(y_pred)
完整源码：
# -*- coding: utf-8 -*-
"模型的正则化和超参数的获取"
#1 引入需要的包
import numpy as np
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split, KFold
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import SGDClassifier
#2 划分数据为训练和测试
def load_data():
data = load_digits()
x, y = data.data, data.target
train_x, test_x, train_y, test_y = train_test_split(x, y , test_size = 0.3, random_state = 20)
#3 标准化数据
ss = StandardScaler()
ss.fit(train_x)
train_x = ss.transform(train_x)
test_x = ss.transform(test_x)
return train_x, test_x, train_y, test_y
#4 进行模型的验证取最佳的超参数和正则化参数
def model_fit(x, y, k = 5):
learning_rates = [0.001, 0.003, 0.01, 0.03, 0.1, 0.3, 1, 3]
penalties = [0, 0.03, 0.01, 0.1, 0.3, 1, 3]
all_models = []
for learning_rate in learning_rates:
for penalty in penalties:
print('正训练模型:下降参数为%s，正则化为%s'%(learning_rate, penalty))
#建立逻辑回归模型
model_score = []
model = SGDClassifier(loss='log', penalty='l2', learning_rate='constant', eta0=learning_rate, alpha=penalty)
kf = KFold(n_splits=k, shuffle=True, random_state=10)
for train_idx, dev_idx in kf.split(x):
x_train, x_dev = x[train_idx], x[dev_idx]
y_train, y_dev = y[train_idx], y[dev_idx]
model.fit(x_train, y_train)
s = model.score(x_dev, y_dev)
model_score.append(s)
all_models.append([np.mean(model_score), learning_rate, penalty])
print('最优模型：', sorted(all_models, reverse= True)[0])
if __name__ == "__main__":
train_x, test_x, train_y, test_y = load_data()
print(train_x.shape)
print(train_y.shape)
# model_fit(train_x, train_y)
model = SGDClassifier(loss='log', penalty='l2',learning_rate="constant", alpha=0.01, eta0=0.01)
model.fit(train_x, train_y)
y_pred = model.predict(test_x)
print(test_y)
print(y_pred)