vgoklani

from pymongo import Connection

import datetime

import time

#connect to mongodb

connection = Connection(‘newitfarmer.com’, 27017)

vgoklani

from pymongo import Connection

import datetime

import time

#connect to mongodb

connection = Connection(‘newitfarmer.com’, 27017)

vgoklani

given a text file containing stopwords, return a python list of its contents.
this list is optimized for twitter/social media and filters out stuff
like RT, nowplaying,  lastfm, 4sq etc.


def get_stopwords(file='stopwords.txt'):
        words = open(file,'r')
        stopwords = [word.strip() for word in words]
	return set(stopwords) 

vgoklani

"""
tiny script to convert a pandas data frame into a JSON object
"""

import ujson as json
import pandas
import numpy as np

df = pandas.DataFrame({
    "time" : [1,2,3,4,5],

vgoklani

# a messy hack written by Edd Dumbill. http://twitter.com/edd

# You may need to rerun this script if you hit a Twitter Error because you
# use up API rate limiting. That's why we pickle the results, so we can resume
# where we left off.

# get the twitter module using 'easy_install twitter'

from twitter.api import Twitter, TwitterError
from twitter.oauth import OAuth

vgoklani

vgoklani

vgoklani

vgoklani

import numpy as np, numpy.linalg as linalg
def fast_svd(M, k):
    p = k+5
    Y = np.dot(M, np.random.normal(size=(M.shape[1],p)))
    Q,r = linalg.qr(Y)
    B = np.dot(Q.T,M)
    Uhat, s, v = linalg.svd(B, full_matrices=False)
    U = np.dot(Q, Uhat)
    return U.T[:k].T, s[:k], v[:k]

vgoklani

"""
(C) Mathieu Blondel - 2010

Implementation of the collapsed Gibbs sampler for
Latent Dirichlet Allocation, as described in

Finding scientifc topics (Griffiths and Steyvers)
"""

import numpy as np