-
Notifications
You must be signed in to change notification settings - Fork 0
/
final.py
278 lines (230 loc) · 7.23 KB
/
final.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
import csv
from math import *
f_w=open("final_ouput.txt","w")
f_c=open("countries_id_map.txt","r")
f_c_o=open("countries_id_map_orig.txt","r")
f_t=open("target-relations.tsv","r")
f_k=open("selected_indicators","r")
f_s=open("sentences.tsv","r")
f_f=open("kb-facts-train_SI.tsv","r")
country_map=dict()
country_map_from_code=dict()
country_facts=dict()
keyword_list=dict()
targets_list=[]
"""--------------------------------------------------------------------------------------------------------
Classes
--------------------------------------------------------------------------------------------------------"""
#Class Country
class Country:
def __init__(self,c_id) :
self.lists=[[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[],[]]
# self.name=name
self.id=c_id
def __str__(self):
return self.name
#Class Keyword
class Keyword:
def __init__(self,name):
self.name=name
self.lists=[]
def __str__(self):
return self.name
"""--------------------------------------------------------------------------------------------------------
End of Classes
--------------------------------------------------------------------------------------------------------"""
"""--------------------------------------------------------------------------------------------------------
Functions
--------------------------------------------------------------------------------------------------------"""
#Function - convert string to float
def isfloat(value):
try:
float(value)
return True
except ValueError:
return False
#Function - Giving initial confidence to sentences
def initial_confidence(n,N):
if N==0:
return 0
if N-n >0:
d=(N-n)/N
else:
d=(n-N)/N
return 0.65*(2.7**(-1*20*d*d))
#Function - Giving the final confidence to the sentences depending on the matchings found in the sentences and target
def matching(sentence_string,keyword_parameter,init):
count=0
for keywords in keyword_list[keyword_parameter].lists:
if keywords in sentence_string:
count=count+1
final_confidence=1-(1-init)*(2**(-1*count))
if count==0:
final_confidence=final_confidence/2
return round(final_confidence,2)
array_of_unknown_country=[]
def function(sentence_id,sentence_string,sentence_numbers_array,sentence_countries_array):
count=0
f=0
for country in sentence_countries_array:
for number in sentence_numbers_array:
if not isfloat(number):
#print(sentence_id,sentence_string,number)
continue
number=float(number)
if number<0:
number=-1*number
if number==0:
continue
if number >1:
digit = ceil(log10(number))
elif number <=1 and number >= -1:
digit = 0
else :
digit = ceil(log10(-1*number))
#print(country,"d")
#if country=="Israeli":
# continue
#if country not in country_map.keys():
# if country not in array_of_unknown_country:
# array_of_unknown_country.append(country)
# print(country)
#continue
targets={k:[0,0] for k in targets_list}
final_list = country_facts[country_map[country]].lists[digit] + country_facts[country_map[country]].lists[digit+1] + country_facts[country_map[country]].lists[digit-1]
for tuples in final_list:
if ((tuples[0]-number)/number) <= 0.3 and ((tuples[0]-number)/number) >= -0.3:
init=initial_confidence(tuples[0],number)
final_confidence=matching(sentence_string,tuples[1],init)
if targets[tuples[1]][0]<final_confidence:
targets[tuples[1]][0]=final_confidence
targets[tuples[1]][1]=tuples[0]
#string=sentence_id+"\t"+country+"\t"+tuples[1]+"\t"+str(final_confidence)+"\t"+str(number)+"\t"+str(tuples[0])+"\n"
#f_w.write(string)
count=1
for targ,confi in targets.items():
if confi[0]>=0.30:
string=sentence_id+"\t"+country_map_from_code[country_map[country]]+"\t"+targ+"\t"+str(number)+"\t"+str(confi[1])+"\t"+str(confi[0])+"\n"
f_w.write(string)
f=2
# break
# break
# break
if count==0 or f==0:
string=sentence_id+"\t"+"matching to no country"+"\n"
f_w.write(string)
"""--------------------------------------------------------------------------------------------------------
End of Functions
--------------------------------------------------------------------------------------------------------"""
"""--------------------------------------------------------------------------------------------------------
Reading the data and initialising objects
--------------------------------------------------------------------------------------------------------"""
#cc=[]
#Reading the country_id_map.txt and relating countries with country code
reader_c = csv.reader(f_c,dialect="excel-tab")
for row in reader_c:
try:
country_map[row[1]]=row[0]
except:
print(row[1],row[0])
if row[0] not in country_facts:
country_facts[row[0]]=Country(row[0])
#print(row[0])
#else:
# cc.append(row[0])
#print(row[0])
#print("\n")
#print("yes")
f_c.close()
#for i in cc:
# print(i)
#Reading the country_id_map.txt and relating countries with country code
reader_c = csv.reader(f_c_o,dialect="excel-tab")
for row in reader_c:
try:
country_map_from_code[row[0]]=row[1]
except:
print(row[1],row[0])
#if row[0] not in country_facts:
# country_facts[row[0]]=Country(row[0])
#print(row[0])
#else:
# cc.append(row[0])
#print(row[0])
#print("\n")
#print("yes")
f_c.close()
#Reading the kb-facts-train.tsv (facts) and adding the facts in the countries
reader_f = csv.reader(f_f,dialect="excel-tab")
for row in reader_f:
#pr.num=float(row[1])
#pr.Rel=row[2]
tup=(float(row[1]),row[2])
#print(pr.num)
if float(row[1])>1:
if tup not in country_facts[row[0]].lists[ceil(log10(float(row[1])))]:
country_facts[row[0]].lists[ceil(log10(float(row[1])))].append(tup)
elif -1<=float(row[1]) and float(row[1])<=1:
if tup not in country_facts[row[0]].lists[0]:
if float(row[1]) < 0:
tup=(-1*float(row[1]),row[2])
country_facts[row[0]].lists[0].append(tup)
else:
if tup not in country_facts[row[0]].lists[ceil(log10(-1*float(row[1])))]:
if float(row[1]) < 0:
tup=(-1*float(row[1]),row[2])
country_facts[row[0]].lists[ceil(log10(-1*float(row[1])))].append(tup)
"""
for name,country in country_facts.items():
print(name)
i=0
for list1 in country.lists:
print("\t",i)
for tup in list1:
print("\t","\t",tup[0],"\t",tup[1])
i=i+1
print("\n")"""
f_f.close()
reader_t=csv.reader(f_t,dialect="excel-tab")
for row1 in reader_t:
keyword_list[row1[0]]=Keyword(row1[0])
targets_list.append(row1[0])
#print(keyword_list[row1[0]])
reader_k=csv.reader(f_k,dialect="excel-tab")
for row in reader_k:
target=""
for target,sent in keyword_list.items():
if target in row:
break
for col in row:
if col != target:
keyword_list[target].lists.append(col)
#print(target)
#print("\t",keyword_list[target].lists)
reader_s=csv.reader(f_s,dialect="excel-tab")
for row in reader_s:
sid=row[0]
ss=row[1]
sn=row[2]
sc=row[3]
snu=sn.replace(" ","")
scu=sc.replace(" ","")
sna=snu.split(",")
sca=scu.split(",")
snau=[]
scau=[]
for country in sca:
if country not in scau:
scau.append(country)
for num in sna:
if num not in snau:
snau.append(num)
#print(sid,"\t",ss,"\t",sn,"\t",sc)
#print(sna)
#print(sca)
#print(scau)
#print("\n")
function(sid,ss,snau,scau)
f_s.close()
#for ,country in country_map.items():
# print(country)