Add Encode Feature

Author: KrakenAI

main.py

@@ -332,6 +332,29 @@ def summary(model_path):
     print("[Model Config]")
     pprint(model.get_config())
 
+
+def encode(content, word_delimiter="|", tag_delimiter="/", num_step=60):
+    # Create corpus instance
+    corpus = Corpus(word_delimiter=word_delimiter, tag_delimiter=tag_delimiter)
+
+    # Add text to corpus
+    corpus.add_text(content)
+
+    # Create index for character and tag
+    char_index = index_builder(constant.CHARACTER_LIST,
+                               constant.CHAR_START_INDEX)
+    tag_index = index_builder(constant.TAG_LIST, constant.TAG_START_INDEX)
+
+    # Generate input
+    inb = InputBuilder(corpus, char_index, tag_index, num_step, y_one_hot=False)
+
+    # Display encoded content
+    np.set_printoptions(threshold=np.inf)
+    print("[Input]")
+    print(inb.x)
+    print("[Label]")
+    print(inb.y)
+
 def show(var):
     """Show variable"""
 
@@ -367,6 +390,7 @@ def show(var):
         "test": test,
         "reevaluate": reevaluate,
         "summary": summary,
+        "encode": encode,
         "show": show
     })
 

utils.py

@@ -23,15 +23,16 @@ def __init__(self, path, filename, content):
 class Corpus(object):
     """Corpus Manager"""
 
-    def __init__(self, corpus_directory, word_delimiter=None, tag_delimiter=None):
+    def __init__(self, corpus_directory=None, word_delimiter=None, tag_delimiter=None):
         # Global variable
         self.corpus_directory = corpus_directory
         self.word_delimiter = word_delimiter
         self.tag_delimiter = tag_delimiter
         self.__corpus = list()
 
         # Load corpus to memory
-        self._load()
+        if corpus_directory is not None:
+            self._load()
 
     def _preprocessing(self, content):
         """Text preprocessing"""
@@ -92,6 +93,16 @@ def _load(self):
                 # Add text to corpus
                 self.__corpus.append(text)
 
+    def add_text(self, content):
+        # Preprocessing
+        content = self._preprocessing(content)
+
+        # Create text instance
+        text = Text(str(), str(), content)
+
+        # Add text to corpus
+        self.__corpus.append(text)
+
     @property
     def count(self):
         return len(self.__corpus)