Save and reuse TfidfVectorizer in scikit learn
I am using TfidfVectorizer in scikit to create a matrix from text data. Now I need to save this object for reuse later. I tried using pickle but it gave the following error.
loc=open('vectorizer.obj','w')
pickle.dump(self.vectorizer,loc)
*** TypeError: can't pickle instancemethod objects
I tried using joblib in sklearn.externals which again gave a similar error. Is there a way to save this object so I can reuse it later?
Here is my complete object:
class changeToMatrix(object):
def __init__(self,ngram_range=(1,1),tokenizer=StemTokenizer()):
from sklearn.feature_extraction.text import TfidfVectorizer
self.vectorizer = TfidfVectorizer(ngram_range=ngram_range,analyzer='word',lowercase=True,\
token_pattern='[a-zA-Z0-9]+',strip_accents='unicode',tokenizer=tokenizer)
def load_ref_text(self,text_file):
textfile = open(text_file,'r')
lines=textfile.readlines()
textfile.close()
lines = ' '.join(lines)
sent_tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
sentences = [ sent_tokenizer.tokenize(lines.strip()) ]
sentences1 = [item.strip().strip('.') for sublist in sentences for item in sublist]
chk2=pd.DataFrame(self.vectorizer.fit_transform(sentences1).toarray()) #vectorizer is transformed in this step
return sentences1,[chk2]
def get_processed_data(self,data_loc):
ref_sentences,ref_dataframes=self.load_ref_text(data_loc)
loc=open("indexedData/vectorizer.obj","w")
pickle.dump(self.vectorizer,loc) #getting error here
loc.close()
return ref_sentences,ref_dataframes
source to share
First, it's better to leave imports at the top of your code instead of your class:
from sklearn.feature_extraction.text import TfidfVectorizer
class changeToMatrix(object):
def __init__(self,ngram_range=(1,1),tokenizer=StemTokenizer()):
...
The following is StemTokenizer
not a canon class. You may have gotten it from http://sahandsaba.com/visualizing-philosophers-and-scientists-by-the-words-they-used-with-d3js-and-python.html or maybe somewhere else. so we'll assume it returns a list of strings .
class StemTokenizer(object):
def __init__(self):
self.ignore_set = {'footnote', 'nietzsche', 'plato', 'mr.'}
def __call__(self, doc):
words = []
for word in word_tokenize(doc):
word = word.lower()
w = wn.morphy(word)
if w and len(w) > 1 and w not in self.ignore_set:
words.append(w)
return words
Now, to answer your real question, you might need to open the file in byte mode before you dump the pickle, i.e .:
>>> from sklearn.feature_extraction.text import TfidfVectorizer
>>> from nltk import word_tokenize
>>> import cPickle as pickle
>>> vectorizer = TfidfVectorizer(ngram_range=(0,2),analyzer='word',lowercase=True, token_pattern='[a-zA-Z0-9]+',strip_accents='unicode',tokenizer=word_tokenize)
>>> vectorizer
TfidfVectorizer(analyzer='word', binary=False, decode_error=u'strict',
dtype=<type 'numpy.int64'>, encoding=u'utf-8', input=u'content',
lowercase=True, max_df=1.0, max_features=None, min_df=1,
ngram_range=(0, 2), norm=u'l2', preprocessor=None, smooth_idf=True,
stop_words=None, strip_accents='unicode', sublinear_tf=False,
token_pattern='[a-zA-Z0-9]+',
tokenizer=<function word_tokenize at 0x7f5ea68e88c0>, use_idf=True,
vocabulary=None)
>>> with open('vectorizer.pk', 'wb') as fin:
... pickle.dump(vectorizer, fin)
...
>>> exit()
alvas@ubi:~$ ls -lah vectorizer.pk
-rw-rw-r-- 1 alvas alvas 763 Jun 15 14:18 vectorizer.pk
Note . Using idiom with
to access the file i / o will automatically close the file after you exit the scope with
.
Regarding the problem with SnowballStemmer()
, please note what SnowballStemmer('english')
is the object and the function is generating SnowballStemmer('english').stem
.
IMPORTANT
-
TfidfVectorizer
The tokenizer parameter expects to take a string and return a list of strings - But Stockmer Snowball doesn't take a string as input and returns a list of strings.
So, you will need to do this:
>>> from nltk.stem import SnowballStemmer
>>> from nltk import word_tokenize
>>> stemmer = SnowballStemmer('english').stem
>>> def stem_tokenize(text):
... return [stemmer(i) for i in word_tokenize(text)]
...
>>> vectorizer = TfidfVectorizer(ngram_range=(0,2),analyzer='word',lowercase=True, token_pattern='[a-zA-Z0-9]+',strip_accents='unicode',tokenizer=stem_tokenize)
>>> with open('vectorizer.pk', 'wb') as fin:
... pickle.dump(vectorizer, fin)
...
>>> exit()
alvas@ubi:~$ ls -lah vectorizer.pk
-rw-rw-r-- 1 alvas alvas 758 Jun 15 15:55 vectorizer.pk
source to share