再论sklearn分类器

这几天在看 sklearn 的文档，发现他的分类器有很多，这里做一些简略的记录。

大致可以将这些分类器分成两类： 1）单一分类器，2）集成分类器

一、单一分类器

下面这个例子对一些单一分类器效果做了比较

from sklearn.cross_validation import cross_val_score
from sklearn.datasets import make_blobs

# meta-estimator
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import GradientBoostingClassifier 

from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis


classifiers = {
    'KN': KNeighborsClassifier(3),
    'SVC': SVC(kernel="linear", C=0.025),
    'SVC': SVC(gamma=2, C=1),
    'DT': DecisionTreeClassifier(max_depth=5),
    'RF': RandomForestClassifier(n_estimators=10, max_depth=5, max_features=1),  # clf.feature_importances_
    'ET': ExtraTreesClassifier(n_estimators=10, max_depth=None),  # clf.feature_importances_
    'AB': AdaBoostClassifier(n_estimators=100),
    'GB': GradientBoostingClassifier(n_estimators=100, learning_rate=1.0, max_depth=1, random_state=0), # clf.feature_importances_
    'GNB': GaussianNB(),
    'LD': LinearDiscriminantAnalysis(),
    'QD': QuadraticDiscriminantAnalysis()}

    
    
X, y = make_blobs(n_samples=10000, n_features=10, centers=100, random_state=0)


for name, clf in classifiers.items():
    scores = cross_val_score(clf, X, y)
    print(name,'	--> ',scores.mean())

下图是效果图：

二、集成分类器

集成分类器有四种：Bagging, Voting, GridSearch, PipeLine。最后一个PipeLine其实是管道技术

1.Bagging

from sklearn.ensemble import BaggingClassifier
from sklearn.neighbors import KNeighborsClassifier

meta_clf = KNeighborsClassifier() 
bg_clf = BaggingClassifier(meta_clf, max_samples=0.5, max_features=0.5)

2.Voting

from sklearn import datasets
from sklearn import cross_validation
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import VotingClassifier

iris = datasets.load_iris()
X, y = iris.data[:, 1:3], iris.target

clf1 = LogisticRegression(random_state=1)
clf2 = RandomForestClassifier(random_state=1)
clf3 = GaussianNB()

eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2), ('gnb', clf3)], voting='hard', weights=[2,1,2])

for clf, label in zip([clf1, clf2, clf3, eclf], ['Logistic Regression', 'Random Forest', 'naive Bayes', 'Ensemble']):
    scores = cross_validation.cross_val_score(clf, X, y, cv=5, scoring='accuracy')
    print("Accuracy: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))

3.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_)

# =================================================================
# 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_)

4.PipeLine

第一个例子

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)

第二个例子

import numpy as np

from sklearn import linear_model, decomposition, datasets
from sklearn.pipeline import Pipeline
from sklearn.grid_search import GridSearchCV


digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target

# 定义管道，先降维(pca)，再逻辑回归
pca = decomposition.PCA()
logistic = linear_model.LogisticRegression()
pipe = Pipeline(steps=[('pca', pca), ('logistic', logistic)])

# 把管道再作为grid_search的estimator
n_components = [20, 40, 64]
Cs = np.logspace(-4, 4, 3)
estimator = GridSearchCV(pipe, dict(pca__n_components=n_components, logistic__C=Cs))

estimator.fit(X_digits, y_digits)