（六）sklearn调整估计器的超参数

1、比较随机搜索RandomizedSearchCV和超参数估计的网格搜索GridSearchCV

随机搜索和网格搜索探索完全相同的参数空间。参数设置的结果非常相似，而随机搜索
的运行时间则大大降低。随机搜索的性能稍差，尽管这很可能是噪声效应，并且不会延
续到保持测试集。
在实践中，只选择那些被认为最重要的参数。

import numpy as np

from time import time
from scipy.stats import randint as sp_randint

from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import RandomizedSearchCV
from sklearn.datasets import load_digits
from sklearn.ensemble import RandomForestClassifier

# 加载数据集，10个类别
digits = load_digits()
X, y = digits.data, digits.target

# 分类器
clf = RandomForestClassifier(n_estimators=20)


# 按照特定格式打印结果
def report(results, n_top=3):
    for i in range(1, n_top + 1):
        candidates = np.flatnonzero(results['rank_test_score'] == i)
        for candidate in candidates:
            print("Model with rank: {0}".format(i))
            print("Mean validation score: {0:.3f} (std: {1:.3f})".format(
                  results['mean_test_score'][candidate],
                  results['std_test_score'][candidate]))
            print("Parameters: {0}".format(results['params'][candidate]))
            print("")


# 参数列表
param_dist = {"max_depth": [3, None],
              "max_features": sp_randint(1, 11),
              "min_samples_split": sp_randint(2, 11),
              "min_samples_leaf": sp_randint(1, 11),
              "bootstrap": [True, False],
              "criterion": ["gini", "entropy"]}

# run randomized search
n_iter_search = 20
random_search = RandomizedSearchCV(clf, param_distributions=param_dist,
                                   n_iter=n_iter_search)

start = time()
random_search.fit(X, y)
print("RandomizedSearchCV took %.2f seconds for %d candidates"
      " parameter settings." % ((time() - start), n_iter_search))
report(random_search.cv_results_)

# use a full grid over all parameters
param_grid = {"max_depth": [3, None],
              "max_features": [1, 3, 10],
              "min_samples_split": [2, 3, 10],
              "min_samples_leaf": [1, 3, 10],
              "bootstrap": [True, False],
              "criterion": ["gini", "entropy"]}

# run grid search
grid_search = GridSearchCV(clf, param_grid=param_grid)
start = time()
grid_search.fit(X, y)

print("GridSearchCV took %.2f seconds for %d candidate parameter settings."
      % (time() - start, len(grid_search.cv_results_['params'])))
report(grid_search.cv_results_)

2、使用SelectFromModel和LassoCV进行特征选择

import matplotlib.pyplot as plt
import numpy as np

from sklearn.datasets import load_boston
from sklearn.feature_selection import SelectFromModel
from sklearn.linear_model import LassoCV

# Load the boston dataset.
boston = load_boston()
X, y = boston['data'], boston['target']

X.shape,y.shape

((506, 13), (506,))

clf = LassoCV()
#用于特征选择的阈值。保留重要性大于或等于的特征，而丢弃其他特征。
sfm = SelectFromModel(clf, threshold=0.25)
sfm.fit(X, y)
n_features = sfm.transform(X).shape[1]

n_features

5

#增加特征的重要性，直到只有2个特征
while n_features > 2:
    sfm.threshold += 0.1
    X_transform = sfm.transform(X)
    n_features = X_transform.shape[1]

#将最重要的两个特征可视化
# Plot the selected two features from X.
plt.title(
    "Features selected from Boston using SelectFromModel with "
    "threshold %0.3f." % sfm.threshold)
feature1 = X_transform[:, 0]
feature2 = X_transform[:, 1]
plt.plot(feature1, feature2, 'r.')
plt.xlabel("Feature number 1")
plt.ylabel("Feature number 2")
plt.ylim([np.min(feature2), np.max(feature2)])
plt.show()