#!/usr/bin/python
# -*- coding: utf-8 -*- #
from wfMySQL import MySQLConnector
from filter import dimension
from wfDatabase import wfdb
import codecs
mysql = MySQLConnector()
# Instance Database List Class
obj_db = wfdb()
# Get category and segment View name list
view_list = obj_db.getViewList()
def generateGexf(list_terms, category, chi_kind):
len_term = len(list_terms)
outfile = codecs.open('gexf/' + chi_kind + '_' + str(category) + '.gexf', 'w', 'utf-8')
outfile.write('<?xml version="1.0" encoding="UTF-8"?>\n')
outfile.write('<gexf xmlns="http://www.gexf.net/1.2draft" version="1.2">\n')
outfile.write('<graph mode="static" defaultedgetype="undirected">\n')
outfile.write('<nodes>\n')
for i in range(len_term):
outfile.write('<node id="%s" label="%s" />\n' % (str(i), list_terms[i]))
outfile.write('</nodes>\n')
x = 0
outfile.write('<edges>\n')
for i in range(5):
print 'Building edge in category-"' + str(category) + '", Dataset: ' + view_list[i]
# Get confidence interval
def mean_confidence_interval(data, confidence=0.95):
a = 1.0 * np.array(data)
n = len(a)
m, se = np.mean(a), sp.sem(a)
h = se * sp.t._ppf((1 + confidence) / 2., n - 1)
return [m, h, m - h, m + h]
# Instance dimension class
obj_dims = dimension()
# Instance Database list class
obj_db = wfdb()
# Instance mysql connector class
mysql = MySQLConnector()
# Get Average CHI Score Dictionary
dict_avg_chi = obj_dims.getAvgCHIList()
# Get Maxiunm CHI Score Dictionary
dict_max_chi = obj_dims.getMaxCHIList()
# Filter CHI Score dictionary by threshold
dict_flted_avgchi = obj_dims.doFilteredList(avg_filter_threshold, dict_avg_chi)
dict_flted_maxchi = obj_dims.doFilteredList(max_filter_threshold, dict_max_chi)
# Get Database View List
tfidf_viewlist = obj_db.getTFIDFViewList()
for source_db in range(5):
# Get most common element in list
def most_common(list_term):
dict_count = {}
for item in list_term:
dict_count.setdefault(item, 0)
dict_count[item] += 1
return max(dict_count.iteritems(), key=itemgetter(1))[0]
# Instance dimension class
obj_dims = dimension()
# Instance Database list class
obj_db = wfdb()
# Instance mysql connector class
mysql = MySQLConnector()
# Get Average CHI Score Dictionary
dict_avg_chi = obj_dims.getAvgCHIList()
# Get Maxiunm CHI Score Dictionary
dict_max_chi = obj_dims.getMaxCHIList()
# Filter CHI Score dictionary by threshold
dict_flted_avgchi = obj_dims.doFilteredList(avg_filter_threshold, dict_avg_chi)
dict_flted_maxchi = obj_dims.doFilteredList(max_filter_threshold, dict_max_chi)
# Rest All value to 0.0 in dictionary
dict_avg_zero = dict.fromkeys(dict_flted_avgchi, 0.0)
dict_max_zero = dict.fromkeys(dict_flted_maxchi, 0.0)
new_category = []
for i in random_list:
new_feature.append(feature_dataset[i])
new_category.append(category_dataset[i])
feature_dataset[:] = []
category_dataset[:] = []
return new_feature, new_category
# Instance dimension class
obj_dims = dimension()
# Instance Database list class
obj_db = wfdb()
# Instance mysql connector class
mysql = MySQLConnector()
# Get Average CHI Score Dictionary list
avg_chi_list = obj_dims.getAvgCHIList()
# Get Max CHI Score dictionary list
max_chi_list = obj_dims.getMaxCHIList()
# Filter list by CHI score
filted_avg_list = obj_dims.doFilteredList(avg_filter_num, avg_chi_list)
filted_max_list = obj_dims.doFilteredList(max_filter_num, max_chi_list)
# Get database View List
tfidf_viewlist = obj_db.getTFIDFViewList()
# Length of vector dimension
#!/usr/bin/python
# -*- coding: utf-8 -*- #
from wfMySQL import MySQLConnector
from wfDatabase import wfdb
import codecs
import re
import enchant
# How many terms were you want to get
limit = 300
mysql = MySQLConnector()
# Instance Database List Class
obj_db = wfdb()
ptn1 = re.compile("^[\w\d]*$")
ptn2 = re.compile("^[\d]*$")
dic = enchant.Dict("en_US")
def verifyEngNum(term):
if ptn1.match(term):
if ptn2.match(term):
return 1
else:
if dic.check(term):
return 2
else:
return 3
#!/usr/bin/python
# -*- coding: utf-8 -*- #
from wfMySQL import MySQLConnector
# Instance Database connector class
mysql = MySQLConnector()
def pairReliablility(user1, user2, coder_clsfi):
len_n = len(coder_clsfi)
M = 0
for key, value in coder_clsfi.items():
if value[user1] == value[user2]:
M += 1
rebilty = (2.0 * M) / (2.0 * len_n)
print "User: "******", " + str(user2)
print "M (Number of totally agreement): " + str(M)
print "N1,N2 (Should agree with number): " + str(len_n)
print "Mutual consent degree = 2M/(N1+N2): " + str(rebilty) + "\n\n"
sql_get = "SELECT `SamplingNo`, `ClsNo1`, `UserId` FROM `CoderCompare` ORDER BY `CoderCompare`.`SamplingNo` ASC"
result = mysql.queryrows(sql_get)
coder_clsfi = {}
for row in result:
sno = int(row[0])
cls = int(row[1])
user = int(row[2])