103 lines
4.1 KiB
Python
103 lines
4.1 KiB
Python
import copy
|
|
import logging
|
|
|
|
from .session.org_mode import global_session as session
|
|
|
|
from .atoms import Atom
|
|
from . import layered_model
|
|
from . import knowledge_evaluation
|
|
from .modifiable_property import is_modifiable_property
|
|
import random
|
|
|
|
def diff_knowledge(before, after):
|
|
import jsondiff
|
|
return jsondiff.diff(before, after)
|
|
|
|
|
|
|
|
class KnowledgeBase(object):
|
|
def __init__(self, knowledge={}, examples=[], trained=[]):
|
|
self.knowledge = copy.copy(knowledge)
|
|
self.originals = []
|
|
self.examples = copy.copy(examples)
|
|
self.trained = copy.copy(trained)
|
|
self.layers = layered_model.BaseModel(self)
|
|
|
|
## Parsing
|
|
def train(self, examples):
|
|
knowledge_before = copy.deepcopy(self.knowledge)
|
|
with session().log('Train'):
|
|
# Parse everything
|
|
for example in examples:
|
|
# If there's parsed data, leverage it ASAP
|
|
if 'parsed' in example and isinstance(example['parsed'], tuple):
|
|
with session().log('parsed information integration'):
|
|
result = knowledge_evaluation.integrate_information(self.knowledge, {
|
|
"parsed": example['parsed'],
|
|
})
|
|
self.act_upon(result)
|
|
|
|
with session().log("language integration"):
|
|
for tokens, decomposition, inferred_tree in self.layers.integrate(self, example):
|
|
session().annotate("Tokens: {}".format(tokens))
|
|
session().annotate("Inferred tree: {}".format(inferred_tree))
|
|
|
|
with session().log("full information integration"):
|
|
tokens = self.layers.tokenization.tokenize(example['text'], return_one=True)
|
|
result = knowledge_evaluation.integrate_information(self.knowledge, {
|
|
"elements": tokens,
|
|
"decomposition": decomposition,
|
|
"parsed": inferred_tree,
|
|
})
|
|
|
|
session().annotate("Result: {}".format(self.get_value(result)))
|
|
self.act_upon(result)
|
|
session().annotate("Set: {}".format(self.get_value(result)))
|
|
self.examples.append((decomposition, inferred_tree))
|
|
self.originals.append(example['text'])
|
|
|
|
# Reduce values
|
|
with session().log("reprocessing"):
|
|
res = self.layers.reprocess(self.examples)
|
|
self.trained = res
|
|
|
|
knowledge_after = copy.deepcopy(self.knowledge)
|
|
knowledge_diff_getter = lambda: diff_knowledge(knowledge_before,
|
|
knowledge_after)
|
|
|
|
return knowledge_diff_getter
|
|
|
|
def process(self, row):
|
|
knowledge_before = copy.deepcopy(self.knowledge)
|
|
with session().log("Process: {}".format(row)):
|
|
fit = list(self.layers.process(self, row))
|
|
if len(fit) == 0:
|
|
return None
|
|
|
|
tokens, inferred_tree = fit[0]
|
|
result = knowledge_evaluation.integrate_information(self.knowledge,
|
|
{
|
|
"elements": tokens,
|
|
"parsed": inferred_tree,
|
|
})
|
|
self.act_upon(result)
|
|
session().annotate("Result: {}".format(result))
|
|
|
|
knowledge_after = copy.deepcopy(self.knowledge)
|
|
knowledge_diff_getter = lambda: diff_knowledge(knowledge_before,
|
|
knowledge_after)
|
|
|
|
return result, inferred_tree, knowledge_diff_getter
|
|
|
|
def get_value(self, result):
|
|
if is_modifiable_property(result):
|
|
return result.getter()
|
|
else:
|
|
return result
|
|
|
|
def act_upon(self, result):
|
|
if is_modifiable_property(result):
|
|
result.setter()
|
|
else:
|
|
logging.warning("Cannot act upon: {}".format(result))
|