vect.py

from __future__ import print_function

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.grid_search import GridSearchCV
from sklearn.pipeline import make_pipeline
from sklearn.dummy import DummyClassifier
from sklearn.cross_validation import LeaveOneOut

docs = ["the cat lives in the hat", "the quick brown fox jumps over a dog",
        "a clockwork orange"]

default_vect = CountVectorizer()
vocab_vect = CountVectorizer(vocabulary=["the", "a"])

print("Vectorizer with default setting: ", default_vect.fit(docs).vocabulary_)
print("Vectorizer with fixed vocab: ", vocab_vect.fit(docs).vocabulary_)

grid = GridSearchCV(make_pipeline(vocab_vect, DummyClassifier()),
                    dict(dummyclassifier__strategy=['uniform']),
                    cv=LeaveOneOut(3))
grid.fit(docs, [1, 0, 1])
print("Vectorizer with fixed vocab after grid search: ",
      grid.best_estimator_.steps[0][1].vocabulary_)