sklearn Model-selection + Pipeline

1 GridSearch

import numpy as np

from sklearn.datasets import load_digits

from sklearn.ensemble import RandomForestClassifier
from sklearn.grid_search import GridSearchCV
from sklearn.grid_search import RandomizedSearchCV

# 生成数据
digits = load_digits()
X, y = digits.data, digits.target

# 元分类器
meta_clf = RandomForestClassifier(n_estimators=20)

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

# 运行随机搜索 RandomizedSearch
n_iter_search = 20
rs_clf = RandomizedSearchCV(meta_clf, param_distributions=param_dist,
                                   n_iter=n_iter_search)

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

2search

# =================================================================
# 设置参数
param_grid = {"max_depth": [3, None],
              "max_features": [1, 3, 10],
              "min_samples_split": [1, 3, 10],
              "min_samples_leaf": [1, 3, 10],
              "bootstrap": [True, False],
              "criterion": ["gini", "entropy"]}

# 运行网格搜索 GridSearch
gs_clf = GridSearchCV(meta_clf, param_grid=param_grid)
start = time()
gs_clf.fit(X, y)

print("GridSearchCV took %.2f seconds for %d candidate parameter settings."
      % (time() - start, len(gs_clf.grid_scores_)))
print(gs_clf.grid_scores_)

3

 from sklearn import svm
 from sklearn.datasets import samples_generator
 from sklearn.feature_selection import SelectKBest
 from sklearn.feature_selection import f_regression
 from sklearn.pipeline import Pipeline

 # 生成数据
 X, y = samples_generator.make_classification(n_informative=5, n_redundant=0, random_state=42)

 # 定义Pipeline，先方差分析，再SVM
 anova_filter = SelectKBest(f_regression, k=5)
 clf = svm.SVC(kernel='linear')
 pipe = Pipeline([('anova', anova_filter), ('svc', clf)])

 # 设置anova的参数k=10，svc的参数C=0.1（用双下划线"__"连接！）
 pipe.set_params(anova__k=10, svc__C=.1)
 pipe.fit(X, y)

 prediction = pipe.predict(X)

 pipe.score(X, y)                        

 # 得到 anova_filter 选出来的特征
 s = pipe.named_steps['anova'].get_support()
 print(s)