gptc/classifier.py

@@ -33,9 +33,7 @@ class Classifier:
         self.model = model
         model_ngrams = cast(int, model.get("__ngrams__", 1))
         self.max_ngram_length = min(max_ngram_length, model_ngrams)
-        self.has_emoji = (
-            gptc.tokenizer.has_emoji and gptc.model_info.model_has_emoji(model)
-        )
+        self.has_emoji = gptc.tokenizer.has_emoji and gptc.model_info.model_has_emoji(model)
 
     def confidence(self, text: str) -> Dict[str, float]:
         """Classify text with confidence.
@@ -55,9 +53,7 @@ class Classifier:
 
         model = self.model
 
-        tokens = gptc.tokenizer.tokenize(
-            text, self.max_ngram_length, self.has_emoji
-        )
+        tokens = gptc.tokenizer.tokenize(text, self.max_ngram_length)
         numbered_probs: Dict[int, float] = {}
         for word in tokens:
             try:

gptc/compiler.py

@@ -77,6 +77,5 @@ def compile(
     model["__names__"] = names
     model["__ngrams__"] = max_ngram_length
     model["__version__"] = 3
-    model["__emoji__"] = int(tokenizer.has_emoji)
 
     return model

gptc/model_info.py

@@ -5,4 +5,4 @@ from typing import Dict, Union, cast, List
 
 
 def model_has_emoji(model: gptc.compiler.MODEL) -> bool:
-    return cast(int, model.get("__emoji__", 0)) == 1
+    return cast(int, model.get("__emoji__]", 0)) == 1

gptc/tokenizer.py

@@ -10,13 +10,11 @@ except ImportError:
     has_emoji = False
 
 
-def tokenize(
-    text: str, max_ngram_length: int = 1, use_emoji: bool = True
-) -> List[str]:
+def tokenize(text: str, max_ngram_length: int = 1) -> List[str]:
     """Convert a string to a list of lemmas."""
     converted_text: Union[str, List[str]] = text.lower()
 
-    if has_emoji and use_emoji:
+    if has_emoji:
         parts = []
         highest_end = 0
         for emoji_part in emoji.emoji_list(text):

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "gptc"
-version = "2.1.1"
+version = "2.1.0"
 description = "General-purpose text classifier"
 readme = "README.md"
 authors = [{ name = "Samuel Sloniker", email = "sam@kj7rrv.com"}]