Pass test using layer structure.

naive-nlu/tree_nlu/knowledge_base.py

@@ -58,7 +58,8 @@ class KnowledgeBase(object):
 
                 # Reduce values
                 with session().log("reprocessing"):
-                    self.layers.reprocess(self.examples)
+                    res = self.layers.reprocess(self.examples)
+                    self.trained = res
 
             knowledge_after = copy.deepcopy(self.knowledge)
             knowledge_diff_getter = lambda: diff_knowledge(knowledge_before,
@@ -69,9 +70,7 @@ class KnowledgeBase(object):
     def process(self, row):
         knowledge_before = copy.deepcopy(self.knowledge)
         with session().log("Process: {}".format(row)):
-            tokens = self.tokenize(row)
+            fit = self.layers.process(self, row)
-
-            fit = parsing.get_fit(self, tokens)
             if fit is None:
                 return None
 

naive-nlu/tree_nlu/layered_model.py

@@ -1,16 +1,18 @@
 from .layers import tokenization_layer
 from .layers import parsing_layer
+from .layers import parsing
+from .session.org_mode import global_session as session
 
 
-def make_yield_pipe(layers, knowledge_base, example):
+def make_yield_pipe(layers, knowledge_base, example, func):
     if len(layers) < 1:
         yield example
         return
 
-    input_generator = make_yield_pipe(layers[:-1], knowledge_base, example)
+    input_generator = make_yield_pipe(layers[:-1], knowledge_base, example, func)
     for input in input_generator:
-        print("-->", input)
+        session().annotate("[{}] --> {}".format(len(layers), input))
-        for d in list(layers[-1].integrate(knowledge_base, input)):
+        for d in list(func(layers[-1], input)):
             yield d
 
 
@@ -25,15 +27,10 @@ class BaseModel:
         ]
 
     def reprocess(self, examples):
-        for example in examples:
-            self._reprocess_single(example)
-
-    def _reprocess_single(self, example):
-        return 
         pattern_examples = []
         for i, sample in enumerate(examples):
             other = examples[:i] + examples[i + 1:]
-            match = get_matching(sample, other)
+            match = parsing.get_matching(sample, other)
             if len(match) > 0:
                 sample = (match, sample[1],)
             pattern_examples.append(sample)
@@ -41,7 +38,12 @@ class BaseModel:
         return pattern_examples
 
     def integrate(self, knowledge_base, example):
-        yield from make_yield_pipe(self.layers, knowledge_base, example)    
+        yield from make_yield_pipe(self.layers, knowledge_base,
+         example, lambda l, i: l.integrate(knowledge_base, i))
+
+    def process(self, knowledge_base, example):
+        yield from make_yield_pipe(self.layers, knowledge_base,
+            example, lambda l, i: l.process(knowledge_base, i))
 
     def tokenize(self, row, return_one=True):
         return self.tokenization.to_tokens(row)

naive-nlu/tree_nlu/layers/parsing.py

@@ -9,6 +9,7 @@ from typing import List, Dict
 from ..modifiable_property import ModifiableProperty
 from .. import parameters
 from ..atoms import Atom, a, is_atom
+from .. import knowledge_evaluation
 
 def make_template(knowledge_base, tokens, parsed):
     matcher = list(tokens)
@@ -97,8 +98,9 @@ def integrate_language(knowledge_base, example):
                     result = build_remix_matrix(knowledge_base, tokens, atom, similar)
                     if result is not None:
                         break
+                else:
+                    raise Exception('Similar not found')
 
-                return
                 remix, (start_bounds, end_bounds) = result
 
                 after_remix = apply_remix(tokens[len(start_bounds):-len(end_bounds)], remix)

naive-nlu/tree_nlu/layers/parsing_layer.py

@@ -8,4 +8,7 @@ class ParsingLayer:
         yield from parsing.integrate_language(knowledge_base, example)
 
     def train(self, knowledge_base, example):
-        assert False
+        assert False
+
+    def process(self, knowledge_base, input):
+        yield from parsing.get_fit(knowledge_base, input)

naive-nlu/tree_nlu/layers/tokenization_layer.py

@@ -29,14 +29,20 @@ class TokenizationLayer:
     def integrate(self, knowledge_base, data):
         assert knowledge_base is self.knowledge_base
 
-        print(data)
         assert 'text' in data
-        with session().log("Tokenize: {}".format(data['text'])):
+        tokens = self.tokenize(data['text'])
-            for tokens in tokenization.to_tokens(self, data['text']):
+        data_with_row = copy.copy(data)
-                data_with_row = copy.copy(data)
+        data_with_row['tokens'] = tokens
-                data_with_row['tokens'] = tokens
+        yield data_with_row
-                print(data_with_row)
+
-                yield data_with_row
+        # with session().log("Tokenize: {}".format(data['text'])):
+        #     for tokens in tokenization.to_tokens(self, data['text']):
+        #         data_with_row = copy.copy(data)
+        #         data_with_row['tokens'] = tokens
+        #         yield data_with_row
+        
+    def process(self, knowledge_base, row):
+        yield self.tokenize(row)
 
 
     def tokenize(self, row, return_one=True):