Skip to content
Navigation Menu
{{ message }}
forked from aimacode/aima-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathknowledge.py
More file actions
409 lines (310 loc) · 12.4 KB
/
Copy pathknowledge.py
File metadata and controls
409 lines (310 loc) · 12.4 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
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
"""Knowledge in learning, Chapter 19"""
from random import shuffle
from math import log
from utils import powerset
from collections import defaultdict
from itertools import combinations, product
from logic import (FolKB, constant_symbols, predicate_symbols, standardize_variables,
variables, is_definite_clause, subst, expr, Expr)
# ______________________________________________________________________________
def current_best_learning(examples, h, examples_so_far=[]):
""" [Figure 19.2]
The hypothesis is a list of dictionaries, with each dictionary representing
a disjunction."""
if not examples:
return h
e = examples[0]
if is_consistent(e, h):
return current_best_learning(examples[1:], h, examples_so_far + [e])
elif false_positive(e, h):
for h2 in specializations(examples_so_far + [e], h):
h3 = current_best_learning(examples[1:], h2, examples_so_far + [e])
if h3 != 'FAIL':
return h3
elif false_negative(e, h):
for h2 in generalizations(examples_so_far + [e], h):
h3 = current_best_learning(examples[1:], h2, examples_so_far + [e])
if h3 != 'FAIL':
return h3
return 'FAIL'
def specializations(examples_so_far, h):
"""Specialize the hypothesis by adding AND operations to the disjunctions"""
hypotheses = []
for i, disj in enumerate(h):
for e in examples_so_far:
for k, v in e.items():
if k in disj or k == 'GOAL':
continue
h2 = h[i].copy()
h2[k] = '!' + v
h3 = h.copy()
h3[i] = h2
if check_all_consistency(examples_so_far, h3):
hypotheses.append(h3)
shuffle(hypotheses)
return hypotheses
def generalizations(examples_so_far, h):
"""Generalize the hypothesis. First delete operations
(including disjunctions) from the hypothesis. Then, add OR operations."""
hypotheses = []
# Delete disjunctions
disj_powerset = powerset(range(len(h)))
for disjs in disj_powerset:
h2 = h.copy()
for d in reversed(list(disjs)):
del h2[d]
if check_all_consistency(examples_so_far, h2):
hypotheses += h2
# Delete AND operations in disjunctions
for i, disj in enumerate(h):
a_powerset = powerset(disj.keys())
for attrs in a_powerset:
h2 = h[i].copy()
for a in attrs:
del h2[a]
if check_all_consistency(examples_so_far, [h2]):
h3 = h.copy()
h3[i] = h2.copy()
hypotheses += h3
# Add OR operations
if hypotheses == [] or hypotheses == [{}]:
hypotheses = add_or(examples_so_far, h)
else:
hypotheses.extend(add_or(examples_so_far, h))
shuffle(hypotheses)
return hypotheses
def add_or(examples_so_far, h):
"""Adds an OR operation to the hypothesis. The AND operations in the disjunction
are generated by the last example (which is the problematic one)."""
ors = []
e = examples_so_far[-1]
attrs = {k: v for k, v in e.items() if k != 'GOAL'}
a_powerset = powerset(attrs.keys())
for c in a_powerset:
h2 = {}
for k in c:
h2[k] = attrs[k]
if check_negative_consistency(examples_so_far, h2):
h3 = h.copy()
h3.append(h2)
ors.append(h3)
return ors
# ______________________________________________________________________________
def version_space_learning(examples):
""" [Figure 19.3]
The version space is a list of hypotheses, which in turn are a list
of dictionaries/disjunctions."""
V = all_hypotheses(examples)
for e in examples:
if V:
V = version_space_update(V, e)
return V
def version_space_update(V, e):
return [h for h in V if is_consistent(e, h)]
def all_hypotheses(examples):
"""Builds a list of all the possible hypotheses"""
values = values_table(examples)
h_powerset = powerset(values.keys())
hypotheses = []
for s in h_powerset:
hypotheses.extend(build_attr_combinations(s, values))
hypotheses.extend(build_h_combinations(hypotheses))
return hypotheses
def values_table(examples):
"""Builds a table with all the possible values for each attribute.
Returns a dictionary with keys the attribute names and values a list
with the possible values for the corresponding attribute."""
values = defaultdict(lambda: [])
for e in examples:
for k, v in e.items():
if k == 'GOAL':
continue
mod = '!'
if e['GOAL']:
mod = ''
if mod + v not in values[k]:
values[k].append(mod + v)
values = dict(values)
return values
def build_attr_combinations(s, values):
"""Given a set of attributes, builds all the combinations of values.
If the set holds more than one attribute, recursively builds the
combinations."""
if len(s) == 1:
# s holds just one attribute, return its list of values
k = values[s[0]]
h = [[{s[0]: v}] for v in values[s[0]]]
return h
h = []
for i, a in enumerate(s):
rest = build_attr_combinations(s[i+1:], values)
for v in values[a]:
o = {a: v}
for r in rest:
t = o.copy()
for d in r:
t.update(d)
h.append([t])
return h
def build_h_combinations(hypotheses):
"""Given a set of hypotheses, builds and returns all the combinations of the
hypotheses."""
h = []
h_powerset = powerset(range(len(hypotheses)))
for s in h_powerset:
t = []
for i in s:
t.extend(hypotheses[i])
h.append(t)
return h
# ______________________________________________________________________________
def minimal_consistent_det(E, A):
"""Returns a minimal set of attributes which give consistent determination"""
n = len(A)
for i in range(n + 1):
for A_i in combinations(A, i):
if consistent_det(A_i, E):
return set(A_i)
def consistent_det(A, E):
"""Checks if the attributes(A) is consistent with the examples(E)"""
H = {}
for e in E:
attr_values = tuple(e[attr] for attr in A)
if attr_values in H and H[attr_values] != e['GOAL']:
return False
H[attr_values] = e['GOAL']
return True
# ______________________________________________________________________________
class FOIL_container(FolKB):
"""Holds the kb and other necessary elements required by FOIL"""
def __init__(self, clauses=[]):
self.const_syms = set()
self.pred_syms = set()
FolKB.__init__(self, clauses)
def tell(self, sentence):
if is_definite_clause(sentence):
self.clauses.append(sentence)
self.const_syms.update(constant_symbols(sentence))
self.pred_syms.update(predicate_symbols(sentence))
else:
raise Exception("Not a definite clause: {}".format(sentence))
def foil(self, examples, target):
"""Learns a list of first-order horn clauses
'examples' is a tuple: (positive_examples, negative_examples).
positive_examples and negative_examples are both lists which contain substitutions."""
clauses = []
pos_examples = examples[0]
neg_examples = examples[1]
while pos_examples:
clause, extended_pos_examples = self.new_clause((pos_examples, neg_examples), target)
# remove positive examples covered by clause
pos_examples = self.update_examples(target, pos_examples, extended_pos_examples)
clauses.append(clause)
return clauses
def new_clause(self, examples, target):
"""Finds a horn clause which satisfies part of the positive
examples but none of the negative examples.
The horn clause is specified as [consequent, list of antecedents]
Return value is the tuple (horn_clause, extended_positive_examples)"""
clause = [target, []]
# [positive_examples, negative_examples]
extended_examples = examples
while extended_examples[1]:
l = self.choose_literal(self.new_literals(clause), extended_examples)
clause[1].append(l)
extended_examples = [sum([list(self.extend_example(example, l)) for example in
extended_examples[i]], []) for i in range(2)]
return (clause, extended_examples[0])
def extend_example(self, example, literal):
"""Generates extended examples which satisfy the literal"""
# find all substitutions that satisfy literal
for s in self.ask_generator(subst(example, literal)):
s.update(example)
yield s
def new_literals(self, clause):
"""Generates new literals based on known predicate symbols.
Generated literal must share atleast one variable with clause"""
share_vars = variables(clause[0])
for l in clause[1]:
share_vars.update(variables(l))
for pred, arity in self.pred_syms:
new_vars = {standardize_variables(expr('x')) for _ in range(arity - 1)}
for args in product(share_vars.union(new_vars), repeat=arity):
if any(var in share_vars for var in args):
yield Expr(pred, *[var for var in args])
def choose_literal(self, literals, examples):
"""Chooses the best literal based on the information gain"""
def gain(l):
pre_pos = len(examples[0])
pre_neg = len(examples[1])
extended_examples = [sum([list(self.extend_example(example, l)) for example in
examples[i]], []) for i in range(2)]
post_pos = len(extended_examples[0])
post_neg = len(extended_examples[1])
if pre_pos + pre_neg == 0 or post_pos + post_neg == 0:
return -1
# number of positive example that are represented in extended_examples
T = 0
for example in examples[0]:
def represents(d):
return all(d[x] == example[x] for x in example)
if any(represents(l_) for l_ in extended_examples[0]):
T += 1
return T * log((post_pos*(pre_pos + pre_neg) + 1e-4) / ((post_pos + post_neg)*pre_pos))
return max(literals, key=gain)
def update_examples(self, target, examples, extended_examples):
"""Adds to the kb those examples what are represented in extended_examples
List of omitted examples is returned"""
uncovered = []
for example in examples:
def represents(d):
return all(d[x] == example[x] for x in example)
if any(represents(l) for l in extended_examples):
self.tell(subst(example, target))
else:
uncovered.append(example)
return uncovered
# ______________________________________________________________________________
def check_all_consistency(examples, h):
"""Check for the consistency of all examples under h"""
for e in examples:
if not is_consistent(e, h):
return False
return True
def check_negative_consistency(examples, h):
"""Check if the negative examples are consistent under h"""
for e in examples:
if e['GOAL']:
continue
if not is_consistent(e, [h]):
return False
return True
def disjunction_value(e, d):
"""The value of example e under disjunction d"""
for k, v in d.items():
if v[0] == '!':
# v is a NOT expression
# e[k], thus, should not be equal to v
if e[k] == v[1:]:
return False
elif e[k] != v:
return False
return True
def guess_value(e, h):
"""Guess value of example e under hypothesis h"""
for d in h:
if disjunction_value(e, d):
return True
return False
def is_consistent(e, h):
return e["GOAL"] == guess_value(e, h)
def false_positive(e, h):
if e["GOAL"] == False:
if guess_value(e, h):
return True
return False
def false_negative(e, h):
if e["GOAL"] == True:
if not guess_value(e, h):
return True
return False
You can’t perform that action at this time.