COMP7404 Machine Learing——Pipelining Transformers & K-Fold Cross-Validation

Pipelining Transformer

pipeline类本身具有fit、predict和score方法，其行为与Scikit-Learn中的其他模型相同

Pipeline是使用 (key，value) 对的list构建的，key是自己为这一step设定的名称，value是对应的处理类, 最后通过list将这些step传入

 

创建pipeline

from sklearn.pipeline import Pipeline
from sklearn.svm import SVC
from sklearn.decomposition import PCA

pipe = Pipeline(steps=[('pca', PCA()), ('svc', SVC())])
#pipe是<class 'sklearn.pipeline.Pipeline'>
print(pipe)

或写作

from sklearn.pipeline import Pipeline
from sklearn.svm import SVC
from sklearn.decomposition import PCA

estimators = [('reduce_dim', PCA()), ('clf', SVC())]
pipe = Pipeline(estimators)

或者用make_pipeline

from sklearn.pipeline import make_pipeline
pipe = make_pipeline(MinMaxScaler(),SVC())

就不用我们指定名称了，函数会自动命名
一般来说，自动命名的步骤名称是类名称的小写版本，如果多个步骤属于同一个类，则会附加一个数字。 

 

pipeline.steps

from sklearn.pipeline import Pipeline
from sklearn.svm import SVC
from sklearn.decomposition import PCA

pipe = Pipeline(steps=[('pca', PCA()), ('svc', SVC())])
#pipe是<class 'sklearn.pipeline.Pipeline'>
print(pipe.steps)

 

通过set_params重新设置每个类里边需传入的参数

设置方法为step的name__parma名=参数值

from sklearn.pipeline import Pipeline
from sklearn.svm import SVC
from sklearn.decomposition import PCA

pipe = Pipeline(steps=[('pca', PCA()), ('svc', SVC())])
#pipe是<class 'sklearn.pipeline.Pipeline'>
pipe.set_params(svc__C=10.0)
print(pipe.steps)

 

 

创建管道并训练

import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline

df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data', header=None)

X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, stratify=y, random_state=1)

pipe_lr = make_pipeline(StandardScaler(), PCA(n_components=2), LogisticRegression(random_state=1, solver='lbfgs'))
pipe_lr.fit(X_train, y_train)

print('Test Accuracy: %.3f' % pipe_lr.score(X_test, y_test))

 

在网格搜索中使用管道

import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline
from sklearn.model_selection import GridSearchCV

df = pd.read_csv('dataset/wdbc.data',header=None)

y = df.loc[:,1].values
X = df.loc[:,2:].values

le = LabelEncoder()
y = le.fit_transform(y)  #因为得到的y是'B'和'E'，字符，需要编码成数字

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2, random_state=1,stratify=y)

pipe = Pipeline([('scaler',StandardScaler()), ('svm',SVC())])

param_grid = {'svm__C':[0.001,0.01,0.1,1,10,100], 'svm__gamma':[0.001,0.01,0.1,1,10,100]}
gs = GridSearchCV(pipe, param_grid=param_grid, cv=5)
gs.fit(X_train, y_train)

print('Accuracy: %.3f' % gs.score(X_test, y_test))

 

 

Stratified K-Fold Cross-Validation

StratifiedKFold()

只是给你划分k份，并不做validation的计算

import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
import numpy as np
from sklearn.model_selection import StratifiedKFold

df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data', header=None)

X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, stratify=y, random_state=1)


pipe_lr = make_pipeline(StandardScaler(), PCA(n_components=2), LogisticRegression(random_state=1, solver='lbfgs'))


kfold = StratifiedKFold(n_splits=10, random_state=1, shuffle=True).split(X_train, y_train)
scores = []
for k, (train, test) in enumerate(kfold):
    pipe_lr.fit(X_train[train], y_train[train])
    score = pipe_lr.score(X_train[test], y_train[test])
    scores.append(score)
    print('Fold: %2d, Class dist.: %s, Acc: %.3f' % (k+1, np.bincount(y_train[train]), score))  
print('\nCV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))

 

cross_val_score

内置k-fold cross-validation scorer ， 写法更简单

import pandas as pd
import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import cross_val_score

df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data', header=None)

X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, stratify=y, random_state=1)

pipe_lr = make_pipeline(StandardScaler(), PCA(n_components=2), LogisticRegression(random_state=1, solver='lbfgs'))

scores = cross_val_score(estimator=pipe_lr, X=X_train, y=y_train, cv=10, n_jobs=1)
print('CV accuracy scores: %s' % scores)
print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))