Pipeline: Multiple classifiers?

Question

I read following example on Pipelines and GridSearchCV in Python: http://www.davidsbatista.net/blog/2017/04/01/document_classification/

Logistic Regression:

pipeline = Pipeline([
    ('tfidf', TfidfVectorizer(stop_words=stop_words)),
    ('clf', OneVsRestClassifier(LogisticRegression(solver='sag')),
])
parameters = {
    'tfidf__max_df': (0.25, 0.5, 0.75),
    'tfidf__ngram_range': [(1, 1), (1, 2), (1, 3)],
    "clf__estimator__C": [0.01, 0.1, 1],
    "clf__estimator__class_weight": ['balanced', None],
}

SVM:

pipeline = Pipeline([
    ('tfidf', TfidfVectorizer(stop_words=stop_words)),
    ('clf', OneVsRestClassifier(LinearSVC()),
])
parameters = {
    'tfidf__max_df': (0.25, 0.5, 0.75),
    'tfidf__ngram_range': [(1, 1), (1, 2), (1, 3)],
    "clf__estimator__C": [0.01, 0.1, 1],
    "clf__estimator__class_weight": ['balanced', None],
}

Is there a way that Logistic Regression and SVM could be combined into one Pipeline? Say, I have a TfidfVectorizer and like to test against multiple classifiers that each then output the best model/parameters.

Answer 1

Here is an easy way to optimize over any classifier and for each classifier any settings of parameters.

Create a switcher class that works for any estimator

from sklearn.base import BaseEstimator
class ClfSwitcher(BaseEstimator):

def __init__(
    self, 
    estimator = SGDClassifier(),
):
    """
    A Custom BaseEstimator that can switch between classifiers.
    :param estimator: sklearn object - The classifier
    """ 

    self.estimator = estimator


def fit(self, X, y=None, **kwargs):
    self.estimator.fit(X, y)
    return self


def predict(self, X, y=None):
    return self.estimator.predict(X)


def predict_proba(self, X):
    return self.estimator.predict_proba(X)


def score(self, X, y):
    return self.estimator.score(X, y)

Now you can pass in anything for the estimator parameter. And you can optimize any parameter for any estimator you pass in as follows:

Perform hyper-parameter optimization

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.linear_model import SGDClassifier
from sklearn.pipeline import Pipeline
from sklearn.model_selection import GridSearchCV

pipeline = Pipeline([
    ('tfidf', TfidfVectorizer()),
    ('clf', ClfSwitcher()),
])

parameters = [
    {
        'clf__estimator': [SGDClassifier()], # SVM if hinge loss / logreg if log loss
        'tfidf__max_df': (0.25, 0.5, 0.75, 1.0),
        'tfidf__stop_words': ['english', None],
        'clf__estimator__penalty': ('l2', 'elasticnet', 'l1'),
        'clf__estimator__max_iter': [50, 80],
        'clf__estimator__tol': [1e-4],
        'clf__estimator__loss': ['hinge', 'log', 'modified_huber'],
    },
    {
        'clf__estimator': [MultinomialNB()],
        'tfidf__max_df': (0.25, 0.5, 0.75, 1.0),
        'tfidf__stop_words': [None],
        'clf__estimator__alpha': (1e-2, 1e-3, 1e-1),
    },
]

gscv = GridSearchCV(pipeline, parameters, cv=5, n_jobs=12, return_train_score=False, verbose=3)
gscv.fit(train_data, train_labels)

How to interpret clf__estimator__loss

clf__estimator__loss is interpreted as the loss parameter for whatever estimator is, where estimator = SGDClassifier() in the top most example and is itself a parameter of clf which is a ClfSwitcher object.