README.md

@@ -18,19 +18,18 @@ This will prompt for a string and classify it, then print (in JSON) a dict of
 the format `{category: probability, category:probability, ...}` to stdout. (For
 information about `-n <max_ngram_length>`, see section "Ngrams.")
 
-### Checking individual words or ngrams
+Alternatively, if you only need the most likely category, you can use this:
 
-    gptc check <compiled model file> <token or ngram>
+    gptc classify [-n <max_ngram_length>] <-c|--category> <compiled model file>
 
-This is very similar to `gptc classify`, except it takes the input as an
-argument, and it treats the input as a single token or ngram.
+This will prompt for a string and classify it, outputting the category on
+stdout (or "None" if it cannot determine anything).
 
 ### Compiling models
 
-    gptc compile [-n <max_ngram_length>] [-c <min_count>] <raw model file> <compiled model file>
+    gptc compile [-n <max_ngram_length>] [-c <min_count>] <raw model file>
 
-This will write the compiled model encoded in binary format to `<compiled model
-file>`.
+This will print the compiled model encoded in binary format to stdout.
 
 If `-c` is specified, words and ngrams used less than `min_count` times will be
 excluded from the compiled model.
@@ -44,15 +43,14 @@ example of the format. Any exceptions will be printed to stderr.
 
 ## Library
 
-### `Model.serialize(file)`
+### `gptc.Classifier(model, max_ngram_length=1)`
 
-Write binary data representing the model to `file`.
+Create a `Classifier` object using the given compiled model (as a `gptc.Model`
+object, not as a serialized byte string).
 
-### `Model.deserialize(encoded_model)`
+For information about `max_ngram_length`, see section "Ngrams."
 
-Deserialize a `Model` from a file containing data from `Model.serialize()`.
-
-### `Model.confidence(text, max_ngram_length)`
+#### `Classifier.confidence(text)`
 
 Classify `text`. Returns a dict of the format `{category: probability,
 category:probability, ...}`
@@ -62,15 +60,16 @@ common words between the input and the training data (likely, for example, with
 input in a different language from the training data), an empty dict will be
 returned.
 
-For information about `max_ngram_length`, see section "Ngrams."
+#### `Classifier.classify(text)`
 
-### `Model.get(token)`
+Classify `text`. Returns the category into which the text is placed (as a
+string), or `None` when it cannot classify the text.
 
-Return a confidence dict for the given token or ngram. This function is very
-similar to `Model.confidence()`, except it treats the input as a single token
-or ngram.
+#### `Classifier.model`
 
-### `Model.compile(raw_model, max_ngram_length=1, min_count=1, hash_algorithm="sha256")`
+The classifier's model.
+
+### `gptc.compile(raw_model, max_ngram_length=1, min_count=1)`
 
 Compile a raw model (as a list, not JSON) and return the compiled model (as a
 `gptc.Model` object).
@@ -80,27 +79,15 @@ For information about `max_ngram_length`, see section "Ngrams."
 Words or ngrams used less than `min_count` times throughout the input text are
 excluded from the model.
 
-The hash algorithm should be left as the default, which may change with a minor
-version update, but it can be changed by the application if needed. It is
-stored in the model, so changing the algorithm does not affect compatibility.
-The following algorithms are supported:
+### `gptc.Model.serialize()`
 
-* `md5`
-* `sha1`
-* `sha224`
-* `sha256`
-* `sha384`
-* `sha512`
-* `sha3_224`
-* `sha3_384`
-* `sha3_256`
-* `sha3_512`
-* `shake_128`
-* `shake_256`
-* `blake2b`
-* `blake2s`
+Returns a `bytes` representing the model.
 
-### `gptc.pack(directory, print_exceptions=False)`
+### `gptc.deserialize(encoded_model)`
+
+Deserialize a `Model` from a `bytes` returned by `Model.serialize()`.
+
+### `gptc.pack(directory, print_exceptions=False)
 
 Pack the model in `directory` and return a tuple of the format:
 
@@ -112,13 +99,6 @@ 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 5.0.0. 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
@@ -138,8 +118,7 @@ reduced to the one used when compiling the model.
 
 ## Model format
 
-This section explains the raw model format, which is how models are created and
-edited.
+This section explains the raw model format, which is how models are created and edited.
 
 Raw models are formatted as a list of dicts. See below for the format:
 
@@ -150,10 +129,9 @@ Raw models are formatted as a list of dicts. See below for the format:
         }
     ]
 
-GPTC handles raw models as `list`s of `dict`s of `str`s (`List[Dict[str,
-str]]`), and they can be stored in any way these Python objects can be.
-However, it is recommended to store them in JSON format for compatibility with
-the command-line tool.
+GPTC handles raw models as `list`s of `dict`s of `str`s (`List[Dict[str, str]]`), and they can be stored
+in any way these Python objects can be. However, it is recommended to store
+them in JSON format for compatibility with the command-line tool.
 
 ## Emoji
 

benchmark.py

@@ -25,7 +25,7 @@ print(
     round(
         1000000
         * timeit.timeit(
-            "gptc.Model.compile(raw_model, max_ngram_length)",
+            "gptc.compile(raw_model, max_ngram_length)",
             number=compile_iterations,
             globals=globals(),
         )

gptc/__init__.py

@@ -2,11 +2,13 @@
 
 """General-Purpose Text Classifier"""
 
-from gptc.pack import pack
-from gptc.model import Model
-from gptc.tokenizer import normalize
+from gptc.compiler import compile as compile
+from gptc.classifier import Classifier as Classifier
+from gptc.pack import pack as pack
+from gptc.tokenizer import has_emoji as has_emoji
+from gptc.model import Model as Model, deserialize as deserialize
 from gptc.exceptions import (
-    GPTCError,
-    ModelError,
-    InvalidModelError,
+    GPTCError as GPTCError,
+    ModelError as ModelError,
+    InvalidModelError as InvalidModelError,
 )

gptc/__main__.py

@@ -17,9 +17,6 @@ def main() -> None:
         "compile", help="compile a raw model"
     )
     compile_parser.add_argument("model", help="raw model to compile")
-    compile_parser.add_argument(
-        "out", help="name of file to write compiled model to"
-    )
     compile_parser.add_argument(
         "--max-ngram-length",
         "-n",
@@ -44,12 +41,19 @@ def main() -> None:
         type=int,
         default=1,
     )
-
-    check_parser = subparsers.add_parser(
-        "check", help="check one word or ngram in model"
+    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.add_argument("model", help="compiled model to use")
-    check_parser.add_argument("token", help="token or ngram to check")
 
     pack_parser = subparsers.add_parser(
         "pack", help="pack a model from a directory"
@@ -59,27 +63,29 @@ def main() -> None:
     args = parser.parse_args()
 
     if args.subparser_name == "compile":
-        with open(args.model, "r", encoding="utf-8") as input_file:
-            model = json.load(input_file)
+        with open(args.model, "r") as f:
+            model = json.load(f)
 
-        with open(args.out, "wb+") as output_file:
-            gptc.Model.compile(
+        sys.stdout.buffer.write(
+            gptc.compile(
                 model, args.max_ngram_length, args.min_count
-            ).serialize(output_file)
+            ).serialize()
+        )
     elif args.subparser_name == "classify":
-        with open(args.model, "rb") as model_file:
-            model = gptc.Model.deserialize(model_file)
+        with open(args.model, "rb") as f:
+            model = gptc.deserialize(f.read())
+
+        classifier = gptc.Classifier(model, args.max_ngram_length)
 
         if sys.stdin.isatty():
             text = input("Text to analyse: ")
         else:
             text = sys.stdin.read()
 
-        print(json.dumps(model.confidence(text, args.max_ngram_length)))
-    elif args.subparser_name == "check":
-        with open(args.model, "rb") as model_file:
-            model = gptc.Model.deserialize(model_file)
-        print(json.dumps(model.get(args.token)))
+        if args.category:
+            print(classifier.classify(text))
+        else:
+            print(json.dumps(classifier.confidence(text)))
     else:
         print(json.dumps(gptc.pack(args.model, True)[0]))
 

gptc/classifier.py

@@ -0,0 +1,94 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+import gptc.tokenizer, gptc.compiler, gptc.exceptions, gptc.weighting
+import warnings
+from typing import Dict, Union, cast, List
+
+
+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)
+        self.has_emoji = gptc.tokenizer.has_emoji and model.has_emoji
+
+    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
+
+        """
+
+        model = self.model.weights
+
+        tokens = gptc.tokenizer.tokenize(
+            text, self.max_ngram_length, self.has_emoji
+        )
+        numbered_probs: Dict[int, float] = {}
+        for word in tokens:
+            try:
+                weighted_numbers = gptc.weighting.weight(
+                    [i / 65535 for i in cast(List[float], model[word])]
+                )
+                for category, value in enumerate(weighted_numbers):
+                    try:
+                        numbered_probs[category] += value
+                    except KeyError:
+                        numbered_probs[category] = value
+            except KeyError:
+                pass
+        total = sum(numbered_probs.values())
+        probs: Dict[str, float] = {
+            self.model.names[category]: value / total
+            for category, value in numbered_probs.items()
+        }
+        return probs
+
+    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

gptc/compiler.py

@@ -0,0 +1,86 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+import gptc.tokenizer
+import gptc.model
+from typing import Iterable, Mapping, List, Dict, Union
+
+
+def compile(
+    raw_model: Iterable[Mapping[str, str]],
+    max_ngram_length: int = 1,
+    min_count: int = 1,
+) -> gptc.model.Model:
+    """Compile a raw model.
+
+    Parameters
+    ----------
+    raw_model : list of dict
+        A raw GPTC model.
+
+    max_ngram_length : int
+        Maximum ngram lenght to compile with.
+
+    Returns
+    -------
+    dict
+        A compiled GPTC model.
+
+    """
+
+    categories: Dict[str, List[int]] = {}
+
+    for portion in raw_model:
+        text = gptc.tokenizer.tokenize(portion["text"], max_ngram_length)
+        category = portion["category"]
+        try:
+            categories[category] += text
+        except KeyError:
+            categories[category] = text
+
+    word_counts: Dict[int, Dict[str, int]] = {}
+
+    names = []
+
+    for category, text in categories.items():
+        if not category in names:
+            names.append(category)
+
+        for word in text:
+            try:
+                counts_for_word = word_counts[word]
+            except KeyError:
+                counts_for_word = {}
+                word_counts[word] = counts_for_word
+
+            try:
+                word_counts[word][category] += 1
+            except KeyError:
+                word_counts[word][category] = 1
+
+    word_counts = {
+        word: counts
+        for word, counts in word_counts.items()
+        if sum(counts.values()) >= min_count
+    }
+
+    word_weights: Dict[int, Dict[str, float]] = {}
+    for word, values in word_counts.items():
+        for category, value in values.items():
+            try:
+                word_weights[word][category] = value / len(categories[category])
+            except KeyError:
+                word_weights[word] = {
+                    category: value / len(categories[category])
+                }
+
+    model: Dict[int, List[int]] = {}
+    for word, weights in word_weights.items():
+        total = sum(weights.values())
+        new_weights: List[int] = []
+        for category in names:
+            new_weights.append(
+                round((weights.get(category, 0) / total) * 65535)
+            )
+        model[word] = new_weights
+
+    return gptc.model.Model(model, names, max_ngram_length)

gptc/model.py

@@ -1,120 +1,9 @@
 # SPDX-License-Identifier: GPL-3.0-or-later
 
-from typing import (
-        Iterable,
-        Mapping,
-    List,
-    Dict,
-    cast,
-    BinaryIO,
-    Tuple,
-    TypedDict,
-)
-import json
 import gptc.tokenizer
 from gptc.exceptions import InvalidModelError
-import gptc.weighting
-
-def _count_words(
-    raw_model: Iterable[Mapping[str, str]],
-    max_ngram_length: int,
-    hash_algorithm: str,
-) -> Tuple[Dict[int, Dict[str, int]], Dict[str, int], List[str]]:
-    word_counts: Dict[int, Dict[str, int]] = {}
-    category_lengths: Dict[str, int] = {}
-    names: List[str] = []
-
-    for portion in raw_model:
-        text = gptc.tokenizer.hash_list(
-            gptc.tokenizer.tokenize(portion["text"], max_ngram_length),
-            hash_algorithm,
-        )
-        category = portion["category"]
-
-        if not category in names:
-            names.append(category)
-
-        category_lengths[category] = category_lengths.get(category, 0) + len(
-            text
-        )
-
-        for word in text:
-            if word in word_counts:
-                try:
-                    word_counts[word][category] += 1
-                except KeyError:
-                    word_counts[word][category] = 1
-            else:
-                word_counts[word] = {category: 1}
-
-    return word_counts, category_lengths, names
-
-
-def _get_weights(
-    min_count: int,
-    word_counts: Dict[int, Dict[str, int]],
-    category_lengths: Dict[str, int],
-    names: List[str],
-) -> Dict[int, List[int]]:
-    model: Dict[int, List[int]] = {}
-    for word, counts in word_counts.items():
-        if sum(counts.values()) >= min_count:
-            weights = {
-                category: value / category_lengths[category]
-                for category, value in counts.items()
-            }
-            total = sum(weights.values())
-            new_weights: List[int] = []
-            for category in names:
-                new_weights.append(
-                    round((weights.get(category, 0) / total) * 65535)
-                )
-            model[word] = new_weights
-    return model
-
-class ExplanationEntry(TypedDict):
-    weight: float
-    probabilities: Dict[str, float]
-    count: int
-
-
-Explanation = Dict[
-    str,
-    ExplanationEntry,
-]
-
-Log = List[Tuple[str, float, List[float]]]
-
-
-class Confidences(dict[str, float]):
-    def __init__(self, probs: Dict[str, float]):
-        dict.__init__(self, probs)
-
-
-class TransparentConfidences(Confidences):
-    def __init__(
-        self,
-        probs: Dict[str, float],
-        explanation: Explanation,
-    ):
-        self.explanation = explanation
-        Confidences.__init__(self, probs)
-
-
-def convert_log(log: Log, names: List[str]) -> Explanation:
-    explanation: Explanation = {}
-    for word2, weight, word_probs in log:
-        if word2 in explanation:
-            explanation[word2]["count"] += 1
-        else:
-            explanation[word2] = {
-                "weight": weight,
-                "probabilities": {
-                    name: word_probs[index] for index, name in enumerate(names)
-                },
-                "count": 1,
-            }
-    return explanation
+from typing import Iterable, Mapping, List, Dict, Union
+import json
 
 
 class Model:
@@ -123,200 +12,78 @@ class Model:
         weights: Dict[int, List[int]],
         names: List[str],
         max_ngram_length: int,
-        hash_algorithm: str,
+        has_emoji: Union[None, bool] = None,
     ):
         self.weights = weights
         self.names = names
         self.max_ngram_length = max_ngram_length
-        self.hash_algorithm = hash_algorithm
-
-    def confidence(
-        self, text: str, max_ngram_length: int, transparent: bool = False
-    ) -> Confidences:
-        """Classify text with confidence.
-
-        Parameters
-        ----------
-        text : str
-            The text to classify
-
-        max_ngram_length : int
-            The maximum ngram length to use in classifying
-
-        Returns
-        -------
-        dict
-            {category:probability, category:probability...} or {} if no words
-            matching any categories in the model were found
-
-        """
-
-        model = self.weights
-        max_ngram_length = min(self.max_ngram_length, max_ngram_length)
-
-        raw_tokens = gptc.tokenizer.tokenize(
-            text, min(max_ngram_length, self.max_ngram_length)
+        self.has_emoji = (
+            gptc.tokenizer.has_emoji if has_emoji is None else has_emoji
         )
 
-        tokens = gptc.tokenizer.hash_list(
-            raw_tokens,
-            self.hash_algorithm,
-        )
-
-        if transparent:
-            token_map = {tokens[i]: raw_tokens[i] for i in range(len(tokens))}
-            log: Log = []
-
-        numbered_probs: Dict[int, float] = {}
-
-        for word in tokens:
-            try:
-                unweighted_numbers = [
-                    i / 65535 for i in cast(List[float], model[word])
-                ]
-
-                weight, weighted_numbers = gptc.weighting.weight(
-                    unweighted_numbers
-                )
-
-                if transparent:
-                    log.append(
-                        (
-                            token_map[word],
-                            weight,
-                            unweighted_numbers,
-                        )
-                    )
-
-                for category, value in enumerate(weighted_numbers):
-                    try:
-                        numbered_probs[category] += value
-                    except KeyError:
-                        numbered_probs[category] = value
-            except KeyError:
-                pass
-
-        total = sum(numbered_probs.values())
-        probs: Dict[str, float] = {
-            self.names[category]: value / total
-            for category, value in numbered_probs.items()
-        }
-
-        if transparent:
-            explanation = convert_log(log, self.names)
-            return TransparentConfidences(probs, explanation)
-
-        return Confidences(probs)
-
-    def get(self, token: str) -> Dict[str, float]:
-        try:
-            weights = self.weights[
-                gptc.tokenizer.hash_single(
-                    gptc.tokenizer.normalize(token), self.hash_algorithm
-                )
-            ]
-        except KeyError:
-            return {}
-        return {
-            category: weights[index] / 65535
-            for index, category in enumerate(self.names)
-        }
-
-    def serialize(self, file: BinaryIO) -> None:
-        file.write(b"GPTC model v6\n")
-        file.write(
+    def serialize(self) -> bytes:
+        out = b"GPTC model v4\n"
+        out += (
             json.dumps(
                 {
                     "names": self.names,
                     "max_ngram_length": self.max_ngram_length,
-                    "hash_algorithm": self.hash_algorithm,
+                    "has_emoji": self.has_emoji,
                 }
             ).encode("utf-8")
             + b"\n"
         )
         for word, weights in self.weights.items():
-            file.write(
-                word.to_bytes(6, "big")
-                + b"".join([weight.to_bytes(2, "big") for weight in weights])
+            out += word.to_bytes(6, "big") + b"".join(
+                [weight.to_bytes(2, "big") for weight in weights]
             )
+        return out
 
-    @staticmethod
-    def compile(
-        raw_model: Iterable[Mapping[str, str]],
-        max_ngram_length: int = 1,
-        min_count: int = 1,
-        hash_algorithm: str = "sha256",
-        ) -> 'Model':
-        """Compile a raw model.
 
-        Parameters
-        ----------
-        raw_model : list of dict
-            A raw GPTC model.
-
-        max_ngram_length : int
-            Maximum ngram lenght to compile with.
-
-        Returns
-        -------
-        dict
-            A compiled GPTC model.
-
-        """
-        word_counts, category_lengths, names = _count_words(
-            raw_model, max_ngram_length, hash_algorithm
-        )
-        model = _get_weights(min_count, word_counts, category_lengths, names)
-        return Model(model, names, max_ngram_length, hash_algorithm)
-
-    @staticmethod
-    def deserialize(encoded_model: BinaryIO) -> "Model":
-        prefix = encoded_model.read(14)
-        if prefix != b"GPTC model v6\n":
+def deserialize(encoded_model: bytes) -> Model:
+    try:
+        prefix, config_json, encoded_weights = encoded_model.split(b"\n", 2)
+    except ValueError:
         raise InvalidModelError()
 
-        config_json = b""
-        while True:
-            byte = encoded_model.read(1)
-            if byte == b"\n":
-                break
-
-            if byte == b"":
+    if prefix != b"GPTC model v4":
         raise InvalidModelError()
 
-            config_json += byte
-
     try:
         config = json.loads(config_json.decode("utf-8"))
-        except (UnicodeDecodeError, json.JSONDecodeError) as exc:
-            raise InvalidModelError() from exc
+    except (UnicodeDecodeError, json.JSONDecodeError):
+        raise InvalidModelError()
 
     try:
         names = config["names"]
         max_ngram_length = config["max_ngram_length"]
-            hash_algorithm = config["hash_algorithm"]
-        except KeyError as exc:
-            raise InvalidModelError() from exc
+        has_emoji = config["has_emoji"]
+    except KeyError:
+        raise InvalidModelError()
 
     if not (
-            isinstance(names, list) and isinstance(max_ngram_length, int)
-        ) or not all(isinstance(name, str) for name in names):
+        isinstance(names, list)
+        and isinstance(max_ngram_length, int)
+        and isinstance(has_emoji, bool)
+    ) or not all([isinstance(name, str) for name in names]):
         raise InvalidModelError()
 
     weight_code_length = 6 + 2 * len(names)
 
-        weights: Dict[int, List[int]] = {}
-
-        while True:
-            code = encoded_model.read(weight_code_length)
-            if not code:
-                break
-            if len(code) != weight_code_length:
+    if len(encoded_weights) % weight_code_length != 0:
         raise InvalidModelError()
 
-            weights[int.from_bytes(code[:6], "big")] = [
+    weight_codes = [
+        encoded_weights[x : x + weight_code_length]
+        for x in range(0, len(encoded_weights), weight_code_length)
+    ]
+
+    weights = {
+        int.from_bytes(code[:6], "big"): [
             int.from_bytes(value, "big")
             for value in [code[x : x + 2] for x in range(6, len(code), 2)]
         ]
+        for code in weight_codes
+    }
 
-        return Model(weights, names, max_ngram_length, hash_algorithm)
+    return Model(weights, names, max_ngram_length, has_emoji)

gptc/pack.py

@@ -7,7 +7,7 @@ from typing import List, Dict, Tuple
 
 def pack(
     directory: str, print_exceptions: bool = False
-) -> Tuple[List[Dict[str, str]], List[Tuple[OSError]]]:
+) -> Tuple[List[Dict[str, str]], List[Tuple[Exception]]]:
     paths = os.listdir(directory)
     texts: Dict[str, List[str]] = {}
     exceptions = []
@@ -17,18 +17,16 @@ def pack(
         try:
             for file in os.listdir(os.path.join(directory, path)):
                 try:
-                    with open(
-                        os.path.join(directory, path, file), encoding="utf-8"
-                    ) as input_file:
-                        texts[path].append(input_file.read())
-                except OSError as error:
-                    exceptions.append((error,))
+                    with open(os.path.join(directory, path, file)) as f:
+                        texts[path].append(f.read())
+                except Exception as e:
+                    exceptions.append((e,))
                     if print_exceptions:
-                        print(error, file=sys.stderr)
-        except OSError as error:
-            exceptions.append((error,))
+                        print(e, file=sys.stderr)
+        except Exception as e:
+            exceptions.append((e,))
             if print_exceptions:
-                print(error, file=sys.stderr)
+                print(e, file=sys.stderr)
 
     raw_model = []
 

gptc/tokenizer.py

@@ -1,13 +1,25 @@
 # SPDX-License-Identifier: GPL-3.0-or-later
 
-import unicodedata
-from typing import List, cast
+from typing import List, Union
 import hashlib
+import base64
+
+try:
     import emoji
 
+    has_emoji = True
+except ImportError:
+    has_emoji = False
 
-def tokenize(text: str, max_ngram_length: int = 1) -> List[str]:
-    text = unicodedata.normalize("NFKD", text).casefold()
+
+def tokenize(
+    text: str, max_ngram_length: int = 1, use_emoji: bool = True
+) -> List[int]:
+    """Convert a string to a list of lemmas."""
+    converted_text: Union[str, List[str]] = text.lower()
+
+    if has_emoji and use_emoji:
+        text = text.lower()
         parts = []
         highest_end = 0
         for emoji_part in emoji.emoji_list(text):
@@ -20,14 +32,9 @@ def tokenize(text: str, max_ngram_length: int = 1) -> List[str]:
     tokens = [""]
 
     for char in converted_text:
-        if (
-            char.isalpha()
-            or char.isnumeric()
-            or char == "'"
-            or (char in ",." and (" " + tokens[-1])[-1].isnumeric())
-        ):
+        if char.isalpha() or char == "'":
             tokens[-1] += char
-        elif emoji.is_emoji(char):
+        elif has_emoji and emoji.is_emoji(char):
             tokens.append(char)
             tokens.append("")
         elif tokens[-1] != "":
@@ -36,51 +43,16 @@ def tokenize(text: str, max_ngram_length: int = 1) -> List[str]:
     tokens = [string for string in tokens if string]
 
     if max_ngram_length == 1:
-        return tokens
-
+        ngrams = tokens
+    else:
         ngrams = []
         for ngram_length in range(1, max_ngram_length + 1):
             for index in range(len(tokens) + 1 - ngram_length):
                 ngrams.append(" ".join(tokens[index : index + ngram_length]))
-    return ngrams
 
-
-def _hash_single(token: str, hash_function: type) -> int:
-    return int.from_bytes(
-        hash_function(token.encode("utf-8")).digest()[:6], "big"
+    return [
+        int.from_bytes(
+            hashlib.sha256(token.encode("utf-8")).digest()[:6], "big"
         )
-
-
-def _get_hash_function(hash_algorithm: str) -> type:
-    if hash_algorithm in {
-        "sha224",
-        "md5",
-        "sha512",
-        "sha3_256",
-        "blake2s",
-        "sha3_224",
-        "sha1",
-        "sha256",
-        "sha384",
-        "shake_256",
-        "blake2b",
-        "sha3_512",
-        "shake_128",
-        "sha3_384",
-    }:
-        return cast(type, getattr(hashlib, hash_algorithm))
-
-    raise ValueError("not a valid hash function: " + hash_algorithm)
-
-
-def hash_single(token: str, hash_algorithm: str) -> int:
-    return _hash_single(token, _get_hash_function(hash_algorithm))
-
-
-def hash_list(tokens: List[str], hash_algorithm: str) -> List[int]:
-    hash_function = _get_hash_function(hash_algorithm)
-    return [_hash_single(token, hash_function) for token in tokens]
-
-
-def normalize(text: str) -> str:
-    return " ".join(tokenize(text, 1))
+        for token in ngrams
+    ]

gptc/weighting.py

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-3.0-or-later
 
 import math
-from typing import Sequence, Tuple, List
+from typing import Sequence, Union, Tuple, List
 
 
 def _mean(numbers: Sequence[float]) -> float:
@@ -39,8 +39,8 @@ def _standard_deviation(numbers: Sequence[float]) -> float:
     return math.sqrt(_mean(squared_deviations))
 
 
-def weight(numbers: Sequence[float]) -> Tuple[float, List[float]]:
+def weight(numbers: Sequence[float]) -> List[float]:
     standard_deviation = _standard_deviation(numbers)
-    weight_assigned = standard_deviation * 2
-    weighted_numbers = [i * weight_assigned for i in numbers]
-    return weight_assigned, weighted_numbers
+    weight = standard_deviation * 2
+    weighted_numbers = [i * weight for i in numbers]
+    return weighted_numbers

profiler.py

@@ -1,16 +0,0 @@
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-import cProfile
-import gptc
-import json
-import sys
-
-max_ngram_length = 10
-
-with open("models/raw.json") as f:
-    raw_model = json.load(f)
-
-with open("models/benchmark_text.txt") as f:
-    text = f.read()
-
-cProfile.run("gptc.Model.compile(raw_model, max_ngram_length)")

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "gptc"
-version = "4.0.1"
+version = "3.0.0"
 description = "General-purpose text classifier"
 readme = "README.md"
 authors = [{ name = "Samuel Sloniker", email = "sam@kj7rrv.com"}]