机器学习之设置模型参数和样本集比例

1 需求

1.1 验证曲线：

缺点：只能逐一对超参数进行调参

# 由于无法确定随机森林中的各个参数的最佳值，需要使用验证曲线进行选择
model = se.RandomForestClassifier(max_depth=6, n_estimators=200, random_state=7)

1.2 学习曲线

功能：确定最佳的训练集和测试集

1.3 网格搜索

功能：验证曲线只能每次获取一个最优超参数。如果多个超参数有很多排列组合的话，就可以使用网格搜索寻求最优超参数组合。

2. 所需api

2.1 验证曲线

import sklearn.model_selection as ms  # 交叉验证

train_scores, test_scores = ms.validation_curve(
    model,		# 模型 
    输入集, 输出集, 
    'n_estimators', 		#超参数名
    np.arange(50, 550, 50),	#超参数序列
    cv=5		#折叠数
)

2.2 学习曲线

import sklearn.model_selection as ms  # 交叉验证

_, train_scores, test_scores = ms.learning_curve(
    model,		# 模型 
    输入集, 输出集, 
    [0.9, 0.8, 0.7],	# 训练集大小序列
    cv=5		# 折叠数
)

2.3 网格搜索

import sklearn.model_selection as ms
model = ms.GridSearchCV(模型, 超参数组合列表, cv=折叠数)
model.fit(输入集，输出集)
# 获取网格搜索每个参数组合
model.cv_results_['params']
# 获取网格搜索每个参数组合所对应的平均测试分值
model.cv_results_['mean_test_score']
# 获取最好的参数
model.best_params_
model.best_score_
model.best_estimator_

3. 举例

3.1 验证曲线

import sklearn.model_selection as ms  # 交叉验证

#构建随机森林模型
model = se.RandomForestClassifier(max_depth=9, n_estimators=144, random_state=7)

# 验证曲线选择最优的n_estimators超参数
train_score, test_score = ms.validation_curve(
    model, train_x, train_y, 'n_estimators',
    np.arange(140, 150, 1), cv=5)
print(test_score.mean(axis=1))

#绘制验证曲线结果图
import matplotlib.pyplot as mp
mp.grid(linestyle= ':')
mp.plot(np.arange(140, 150, 1),test_score.mean(axis=1),'o-',
        color = 'dodgerblue',label = 'n_estimators')
mp.legend()
mp.show()

# 验证曲线选择最优的max_depth超参数
train_score, test_score = ms.validation_curve(
    model, train_x, train_y, 'max_depth',
    np.arange(1, 11, 1), cv=5)
print(test_score.mean(axis=1))

#绘制验证曲线结果图
import matplotlib.pyplot as mp
mp.grid(linestyle= ':')
mp.plot(np.arange(1, 11, 1),test_score.mean(axis=1),'o-',
        color = 'dodgerblue',label = 'max_depth')
mp.legend()
mp.show()

3.2学习曲线

import sklearn.model_selection as ms  # 交叉验证

model = se.RandomForestClassifier(max_depth=9, n_estimators=144, random_state=7)

# 学习曲线
train_size = np.arange(0.1, 1.0, 0.1)
_, train_score, test_score = ms.learning_curve(
    model, train_x, train_y,
    train_sizes=train_size, cv=5
)
test_mean = test_score.mean(axis=1)

import matplotlib.pyplot as mp

mp.grid(linestyle=':')
mp.plot(train_size, test_mean, 'o-',
        color='dodgerblue')
mp.legend()
mp.show()

网格搜索

# 基于径向基核函数的支持向量机分类器
params = [{'kernel':['linear'], 'C':[1, 10, 100, 1000]},
    {'kernel':['poly'], 'C':[1], 'degree':[2, 3]}, 
    {'kernel':['rbf'], 'C':[1,10,100,1000], 'gamma':[1, 0.1, 0.01, 0.001]}]
model = ms.GridSearchCV(svm.SVC(probability=True), params, cv=5)
model.fit(train_x, train_y)
for p, s in zip(model.cv_results_['params'],
        model.cv_results_['mean_test_score']):
    print(p, s)
# 获取得分最优的的超参数信息
print(model.best_params_)
# 获取最优得分
print(model.best_score_)
# 获取最优模型的信息
print(model.best_estimator_)