From 56550ca4575424ffba82e9800ae28cc49b6baec9 Mon Sep 17 00:00:00 2001
From: Samuel Sloniker <sam@kj7rrv.com>
Date: Sun, 16 Apr 2023 14:27:07 -0700
Subject: [PATCH] Remove Classifier objects

Closes #16
---
 README.md          |  7 -----
 gptc/__init__.py   |  1 -
 gptc/__main__.py   | 20 +-------------
 gptc/classifier.py | 68 ----------------------------------------------
 4 files changed, 1 insertion(+), 95 deletions(-)
 delete mode 100755 gptc/classifier.py

diff --git a/README.md b/README.md
index 33f2531..6eace01 100644
--- a/README.md
+++ b/README.md
@@ -112,13 +112,6 @@ GPTC.
 
 See `models/unpacked/` for an example of the format.
 
-### `gptc.Classifier(model, max_ngram_length=1)`
-
-`Classifier` objects are deprecated starting with GPTC 3.1.0, and will be
-removed in 4.0.0. See [the README from
-3.0.2](https://git.kj7rrv.com/kj7rrv/gptc/src/tag/v3.0.1/README.md) if you need
-documentation.
-
 ## Ngrams
 
 GPTC optionally supports using ngrams to improve classification accuracy. They
diff --git a/gptc/__init__.py b/gptc/__init__.py
index fd24dce..05f5dc5 100644
--- a/gptc/__init__.py
+++ b/gptc/__init__.py
@@ -3,7 +3,6 @@
 """General-Purpose Text Classifier"""
 
 from gptc.compiler import compile as compile
-from gptc.classifier import Classifier as Classifier
 from gptc.pack import pack as pack
 from gptc.model import Model as Model, deserialize as deserialize
 from gptc.tokenizer import normalize as normalize
diff --git a/gptc/__main__.py b/gptc/__main__.py
index 9586299..9c87536 100644
--- a/gptc/__main__.py
+++ b/gptc/__main__.py
@@ -44,19 +44,6 @@ def main() -> None:
         type=int,
         default=1,
     )
-    group = classify_parser.add_mutually_exclusive_group()
-    group.add_argument(
-        "-j",
-        "--json",
-        help="output confidence dict as JSON (default)",
-        action="store_true",
-    )
-    group.add_argument(
-        "-c",
-        "--category",
-        help="output most likely category or `None`",
-        action="store_true",
-    )
 
     check_parser = subparsers.add_parser(
         "check", help="check one word or ngram in model"
@@ -88,12 +75,7 @@ def main() -> None:
         else:
             text = sys.stdin.read()
 
-        if args.category:
-            classifier = gptc.Classifier(model, args.max_ngram_length)
-            print(classifier.classify(text))
-        else:
-            probabilities = model.confidence(text, args.max_ngram_length)
-            print(json.dumps(probabilities))
+        print(json.dumps(model.confidence(text, args.max_ngram_length)))
     elif args.subparser_name == "check":
         with open(args.model, "rb") as f:
             model = gptc.deserialize(f)
diff --git a/gptc/classifier.py b/gptc/classifier.py
deleted file mode 100755
index f2e2bf4..0000000
--- a/gptc/classifier.py
+++ /dev/null
@@ -1,68 +0,0 @@
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-import gptc.model
-from typing import Dict, Union
-
-
-class Classifier:
-    """A text classifier.
-
-    Parameters
-    ----------
-    model : dict
-        A compiled GPTC model.
-
-    max_ngram_length : int
-        The maximum ngram length to use when tokenizing input. If this is
-        greater than the value used when the model was compiled, it will be
-        silently lowered to that value.
-
-    Attributes
-    ----------
-    model : dict
-        The model used.
-
-    """
-
-    def __init__(self, model: gptc.model.Model, max_ngram_length: int = 1):
-        self.model = model
-        model_ngrams = model.max_ngram_length
-        self.max_ngram_length = min(max_ngram_length, model_ngrams)
-
-    def confidence(self, text: str) -> Dict[str, float]:
-        """Classify text with confidence.
-
-        Parameters
-        ----------
-        text : str
-            The text to classify
-
-        Returns
-        -------
-        dict
-            {category:probability, category:probability...} or {} if no words
-            matching any categories in the model were found
-
-        """
-        return self.model.confidence(text, self.max_ngram_length)
-
-    def classify(self, text: str) -> Union[str, None]:
-        """Classify text.
-
-        Parameters
-        ----------
-        text : str
-            The text to classify
-
-        Returns
-        -------
-        str or None
-            The most likely category, or None if no words matching any
-            category in the model were found.
-
-        """
-        probs: Dict[str, float] = self.confidence(text)
-        try:
-            return sorted(probs.items(), key=lambda x: x[1])[-1][0]
-        except IndexError:
-            return None