qZhang88

import string
import re
from nltk.corpus import stopwords
from nltk.tokenize import TweetTokenizer


cache_english_stopwords=stopwords.words('english')


def tweet_clean(tweet):

qZhang88

# 利用python的正则去解决
import re

def remove_url(txt):
    regex =re.compile(r'https://[a-zA-Z0-9.?/&=:]*',re.S)
    return regex.sub("",txt)

qZhang88

#!/usr/bin/env python

import sys
#from numpy import array, diag, zeros, ones_like, identity, amax, maximum, amin, minimum, loadtxt, kron, ones, reshape
import numpy as np
from numpy.random import rand

#from matplotlib.pyplot import *

from optparse import OptionParser

qZhang88

import re
import json
import math
import random
import fileinput
import collections

class LDASampler(object):
    def __init__(self, docs=None, num_topics=None, alpha=0.1, beta=0.1, state=None):
        if state:

qZhang88

"""Information Retrieval metrics

Useful Resources:
http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt
http://www.nii.ac.jp/TechReports/05-014E.pdf
http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf
http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf
Learning to Rank for Information Retrieval (Tie-Yan Liu)
"""
import numpy as np

qZhang88

# (C) Mathieu Blondel, November 2013
# License: BSD 3 clause

import numpy as np


def ranking_precision_score(y_true, y_score, k=10):
    """Precision at rank k

    Parameters