-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathDataGeneration.py
More file actions
328 lines (257 loc) · 8.27 KB
/
DataGeneration.py
File metadata and controls
328 lines (257 loc) · 8.27 KB
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
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
'''
Computational Cognitive Modeling - Prof. Brenden Lake and Prof. Todd Gureckis
Final Project - "Sequence Prediction using Bayesian Concept Learning"
'''
'''
Data Generation:
Guassian Noise: Mean = 0 | Variance = 0.66
Files To Be Generated:-
1. Stationary_Noise_80_19_1
2. Stationary_Noise_40_40_20
3. Stationary_Noise_34_33_33
4. Progessive_Noise_80_19_1
5. Progessive_Noise_40_40_10
6. Progessive_Noise_34_33_33
'''
import numpy as np
import random
import math
def GenSequencesProgressive(hypothesis, mean, variance, sequence_count):
sequence_list = []
count = 0
while True:
flag = True
if count == sequence_count:
break
if (hypothesis == "+"):
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
start = random.randint(1, 41) + val
temp = start
sequence = [temp]
factor = [ random.choice([i for i in range(1,11)]) ]
for i in range(5):
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
if i >= 3:
temp = temp + factor[0]
else:
temp = temp + factor[0] + val
sequence.append(temp)
elif (hypothesis == 'x'):
factor = [random.choice([2,3])]
if (factor[0] == 2):
start = random.randint(1,10)
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
start = start + val
if start <= 0:
continue
if (factor[0] == 3):
start = random.randint(1,4)
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
start = start + val
if start <= 0:
continue
temp = start
sequence = [temp]
for i in range(5):
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
if i >=3:
temp = temp * factor[0]
else:
temp = temp * factor[0] + val
if temp <= 0 :#or temp > 500:
flag = False
break
sequence.append(temp)
elif (hypothesis == "x+"):
factor = [random.choice([2,3]), 0]
if factor[0] == 2:
factor[1] = random.choice([i for i in range(1,11)])
if factor[0] == 3:
factor[1] = random.choice([i for i in range(1,6)])
if (factor[0] == 2):
start = random.randint(1,7)
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
start = start + val
if start <= 0:
continue
if (factor[0] == 3):
start = random.randint(1,2)
if start <= 0:
continue
temp = start
sequence = [temp]
for i in range(5):
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
if (factor[0]==3):
if i >=3 or i==0:
temp = temp * factor[0] + factor[1]
else:
temp = temp * factor[0] + factor[1] + val
else:
if i >=3 or i==0:
temp = temp * factor[0] + factor[1]
else:
temp = temp * factor[0] + factor[1] + val
if temp <= 0 :#or temp > 500:
flag = False
break
sequence.append(temp)
if (not (sequence in sequence_list) and flag):
sequence_list.append(sequence)
count += 1
return sequence_list
def GenSequencesStationary(hypothesis, mean, variance, sequence_count):
sequence_list = []
count = 0
while True:
flag = True
if count == sequence_count:
break
if (hypothesis == "+"):
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
start = random.randint(1, 41)
temp_actual = start
temp = start + val
sequence = [temp]
factor = [ random.choice([i for i in range(1,11)]) ]
for i in range(5):
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
if i>=3:
temp = temp_actual + factor[0]
else:
temp = temp_actual + factor[0] + val
temp_actual = temp_actual + factor[0]
sequence.append(temp)
elif (hypothesis == 'x'):
factor = [random.choice([2,3])]
if (factor[0] == 2):
start = random.randint(1,10)
temp_actual = start
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
start = start + val
if start <= 0:
continue
if (factor[0] == 3):
start = random.randint(1,4)
temp_actual = start
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
start = start + val
if start <= 0:
continue
temp = start
sequence = [temp]
for i in range(5):
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
if i>=3:
temp = temp_actual * factor[0]
else:
temp = temp_actual * factor[0] + val
temp_actual = temp_actual * factor[0]
if temp <= 0 :#or temp > 500:
flag = False
break
sequence.append(temp)
elif (hypothesis == "x+"):
factor = [random.choice([2,3]),0]
if factor[0] == 2:
factor[1] = random.choice([i for i in range(1,11)])
if factor[0] == 3:
factor[1] = random.choice([i for i in range(1,6)])
if (factor[0] == 2):
start = random.randint(1,7)
temp_actual = start
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
start = start + val
if start <= 0:
continue
if (factor[0] == 3):
start = random.randint(1,2)
temp_actual = start
if start <= 0:
continue
temp = start
sequence = [temp]
for i in range(5):
val = np.random.normal(mean, variance)
val = int(np.sign(val) * math.floor(abs(val)))
if i >=3:
temp = temp_actual * factor[0] + factor[1]
else:
temp = temp_actual * factor[0] + factor[1] + val
temp_actual = temp_actual * factor[0] + factor[1]
if temp <= 0 :#or temp > 500:
flag = False
break
sequence.append(temp)
if (not (sequence in sequence_list) and flag):
sequence_list.append(sequence)
count += 1
return sequence_list
def GenNoiseStationary(mean, variance, hypothesis, sequence_count):
if (hypothesis == "+"):
return GenSequencesStationary(hypothesis, mean, variance, sequence_count)
if (hypothesis == "x"):
return GenSequencesStationary(hypothesis, mean, variance, sequence_count)
if (hypothesis == "x+"):
return GenSequencesStationary(hypothesis, mean, variance, sequence_count)
def GenNoiseProgressive(mean, variance, hypothesis, sequence_count):
if (hypothesis == "+"):
return GenSequencesProgressive(hypothesis, mean, variance, sequence_count)
if (hypothesis == "x"):
return GenSequencesProgressive(hypothesis, mean, variance, sequence_count)
if (hypothesis == "x+"):
return GenSequencesProgressive(hypothesis, mean, variance, sequence_count)
def PrintSequences(L):
for l in L:
print(l)
def WriteFile(filename, L):
with open(filename, "w") as f:
for s in L:
f.write(str(s) +"\n")
def main():
mean = 0
variance = 0.66
x = 600
y = 300
z = 200
Addition_Hypotheses_Stationary = GenNoiseStationary(0,0.66,"+",x)
Multiplication_Hypotheses_Stationary = GenNoiseStationary(0,0.66,"x",z)
Addition_Hypotheses_Progressive = GenNoiseProgressive(0,0.66,"+",x)
Multiplication_Hypotheses_Progressive = GenNoiseProgressive(0,0.66,"x",y)
Comb_Hypotheses_Stationary = GenNoiseStationary(0,0.66,"x+",z)
Comb_Hypotheses_Progressive = GenNoiseProgressive(0,0.66,"x+",y)
WriteFile("Addition_Hypotheses_Stationary.txt", Addition_Hypotheses_Stationary)
WriteFile("Addition_Hypotheses_Progressive.txt", Addition_Hypotheses_Progressive)
WriteFile("Multiplication_Hypotheses_Stationary.txt", Multiplication_Hypotheses_Stationary)
WriteFile("Multiplication_Hypotheses_Progressive.txt", Multiplication_Hypotheses_Progressive)
WriteFile("Comb_Hypotheses_Stationary.txt", Comb_Hypotheses_Stationary)
WriteFile("Comb_Hypotheses_Progressive.txt", Comb_Hypotheses_Progressive)
'''print("Addition_Hypotheses_Stationary")
PrintSequences(Addition_Hypotheses_Stationary)
print("Multiplication_Hypotheses_Stationary")
PrintSequences(Multiplication_Hypotheses_Stationary)
#print("Addition_Hypotheses_Progressive")
PrintSequences(Addition_Hypotheses_Progressive)
print("Multiplication_Hypotheses_Progressive")
PrintSequences(Multiplication_Hypotheses_Progressive)
print("Comb_Hypotheses_Stationary")
PrintSequences(Comb_Hypotheses_Stationary)
#print("Comb_Hypotheses_Progressive")
#PrintSequences(Comb_Hypotheses_Progressive)
print(len(Comb_Hypotheses_Stationary))
print(len(Comb_Hypotheses_Progressive))'''
if __name__== "__main__":
main()