Skip to content

Instantly share code, notes, and snippets.

@balamuru
balamuru / gist:4727614
Last active December 12, 2015 06:18
Gensim Clustering attempt
import logging
from scipy.odr import models
import unittest
import os
import os.path
import tempfile
import numpy
import gensim
import logging
@balamuru
balamuru / gist:4726232
Last active December 12, 2015 05:59
scikit incremental vectorizer - debug
# Author: Peter Prettenhofer <[email protected]>
# Lars Buitinck <[email protected]>
# License: Simplified BSD
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import HashingVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import FeatureHasher
from sklearn.pipeline import Pipeline