rohitdholakia

from sklearn import linear_model
from FeatureUtils import *
import numpy as np
(features,output) = getXy(sys.argv[1])

clf = linear_model.LogisticRegression(penalty='l1')
clf.fit(features,output)

print clf.coef_

rohitdholakia

37313  14	68	7	0	0	5	4	162	35	11	0	0
478335	9	14	2	0	0	2	5	70	1	24	0	0
8945	5	94	10	0	1	3	3	3395	239	524	67	0
8741	6	78	2	0	0	4	3	4784	938	564	17	0
8976	3	156	6	0	4	5	4	3778	757	1781	269	0
391411	6	90	1	0	0	2	1	686	32	150	1	0
762005	5	511	0	0	4	2	5	10	0	0	0	0
749982	5	169	0	0	0	1	4	1	0	0	0	0
316016	6	81	1	0	0	3	2	134	29	27	0	0
855171	6	567	1	0	0	1	2	87	0	19	0	0

rohitdholakia

import types
import sys
import marshal
import Utils
from lxml import etree
import csv
class User:
    #this is for user features
    def __init__(self, userId, d):
        self.reputation = d['reputation']

rohitdholakia

import sys
import os
import marshal
import Utils
from lxml import etree
if(len(sys.argv)<2):
    print 'python name.py posts.xml acceptedIdsList users.xml userDictOutput'
    sys.exit()
userdict = {}

rohitdholakia

#Find out the tags that are most often used with questions tagged famous
import sys
import os
import marshal
from lxml import etree
from collections import *
import operator
from Utils import *
if(len(sys.argv)<2):
    print 'python name.py posts.xml tagDistributionDict'

rohitdholakia

def getCreationDate(elem):
    return elem.get("CreationDate")

def getParent(elem):
    return elem.get("ParentId")

def getPostTypeId(elem):
    return elem.get("PostTypeId")

def getOwner(elem):

rohitdholakia

#num     non-hashes    hashes 

1 37.5968768597  38.9962208271
4  39.5982711315  42.2955231667
20 40.4657788277  43.3965361118
50  120.064239025 128.437549829
100  288.91673708 299.555378914
200  584.331137896 609.95442009

rohitdholakia

all:
  python Lookup.py recap.input Outputs mapping.map 1 > Measurements/1.txt
  python Lookup.py recap.input Outputs mapping.map 4 > Measurements/4.txt
  python Lookup.py recap.input Outputs mapping.map 20 > Measurements/20.txt
  python Lookup.py recap.input Outputs mapping.map 50 > Measurements/50.txt
  python Lookup.py recap.input Outputs mapping.map 100 > Measurements/100.txt
  python Lookup.py recap.input Outputs mapping.map 200 > Measurements/200.txt

rohitdholakia

import sys
import os
import multiprocessing
from collections import defaultdict
from TrueCasing import *
import time
import redis
import gzip

class Project:

rohitdholakia

import sys
import os
import multiprocessing
from collections import defaultdict
from TrueCasing import *
import time
import redis
import gzip

class Project: