sklearn.pipeline

pipeline的目的将许多算法模型串联起来，比如将特征提取、归一化、分类组织在一起形成一个典型的机器学习问题工作流。

优点：

1.直接调用fit和predict方法来对pipeline中的所有算法模型进行训练和预测

2.可以结合grid search对参数进行选择。

1.DictVectorizer、DecisionTreeClassifier——>pipeline模型

import pandas as pd

import numpy as np

titanic = pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt')

titanic.head()

titanic.info()

X = titanic[['pclass','age','sex']]

y = titanic['survived']

X['age'].fillna(X['age'].mean(),inplace=True)

X.info()

from sklearn.cross_validation import train_test_split

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25,random_state=33)

X_train = X_train.to_dict(orient='record')

X_test = X_test.to_dict(orient='record')

#将非数值型数据转换为数值型数据

from sklearn.feature_extraction import DictVectorizer

from sklearn.tree import DecisionTreeClassifier

from sklearn.pipeline import Pipeline

'''

vec = DictVectorizer()

vec.fit_transform(data)

clf = DecisionTreeClassifier(random_state=0)

clf.fit(X_train,y_train)

clf.predict(X_test)

'''

clf = Pipeline([('vecd',DictVectorizer(sparse=False)),('dtc',DecisionTreeClassifier())])

vec = DictVectorizer(sparse=False)

clf.fit(X_train,y_train)

y_predict = clf.predict(X_test)

from sklearn.metrics import classification_report

print (clf.score(X_test,y_test))

print(classification_report(y_predict,y_test,target_names=['died','survivied']))

2.结合GridSearch进行参数调优

from sklearn.datasets import fetch_20newsgroups

import numpy as np

news = fetch_20newsgroups(subset='all')

from sklearn.cross_validation import train_test_split

X_train,X_test,y_train,y_test = train_test_split(news.data[:3000],news.target[:3000],test_size=0.25,random_state=33)

from sklearn.feature_extraction.text import TfidfVectorizer

vec = TfidfVectorizer()

X_count_train = vec.fit_transform(X_train)

X_count_test = vec.transform(X_test)

from sklearn.svm import SVC

from sklearn.pipeline import Pipeline

#使用pipeline简化系统搭建流程，将文本抽取与分类器模型串联起来

clf = Pipeline([

    ('vect',TfidfVectorizer(stop_words='english')),('svc',SVC())

])

# 注意，这里经pipeline进行特征处理、SVC模型训练之后，得到的直接就是训练好的分类器clf

parameters = {

    'svc__gamma':np.logspace(-2,1,4),

    'svc__C':np.logspace(-1,1,3),

    'vect__analyzer':['word']

}

#n_jobs=-1代表使用计算机的全部CPU

from sklearn.grid_search import GridSearchCV

gs = GridSearchCV(clf,parameters,verbose=2,refit=True,cv=3,n_jobs=-1)

%time _=gs.fit(X_train,y_train)

print (gs.best_params_,gs.best_score_)

print (gs.score(X_test,y_test))

parameters变量里面的key都有一个前缀，不难发现，这个前缀其实就是在Pipeline中定义的操作名。二者相结合，是我们的代码变得十分简洁。