Upload metric.py with huggingface_hub

metric.py

@@ -1,95 +1,147 @@
-# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-"""TODO: Add a description here."""
+#####
+# imports for hf system:
+#####
+from .artifact import __file__ as _
+from .blocks import __file__ as _
+from .card import __file__ as _
+from .catalog import __file__ as _
+from .collections import __file__ as _
+from .common import __file__ as _
+from .file_utils import __file__ as _
+
+# from .fusion import __file__
+from .generator_utils import __file__ as _
+from .instructions import __file__ as _
+from .loaders import __file__ as _
+from .load import __file__ as _
+from .metrics import __file__ as _
+from .normalizers import __file__ as _
+from .operator import __file__ as _
+from .operators import __file__ as _
+from .processors import __file__ as _
+from .recipe import __file__ as _
+from .register import __file__ as _
+from .splitters import __file__ as _
+from .split_utils import __file__ as _
+from .stream import __file__ as _
+from .task import __file__ as _
+from .templates import __file__ as _
+from .text_utils import __file__ as _
+from .schema import __file__ as _
+
+# from .utilize import __file__ as _
+# from .validate import __file__ as _
+#############
+
+from .stream import MultiStream, Stream
+
+from .operator import SequntialOperator, SequntialOperatorInitilizer, MultiStreamOperator, StreamInitializerOperator
+
+from .operators import (
+    ApplyValueOperatorsField,
+    ApplyStreamOperatorsField,
+    SplitByValue,
+    MergeStreams,
+    FlattenInstances,
+)
 
 import evaluate
 import datasets
 
+from datasets import (
+    Features,
+    Value,
+    Sequence,
+)
+
+from dataclasses import field
+from typing import List, Union, Dict, Optional, Generator, Any, Iterable
+
+
+class MultiStreamScoreMean(MultiStreamOperator):
+    def aggegate_results(self, multi_stream: MultiStream):
+        scores = []
+        for stream in multi_stream.values():
+            instance = stream.peak()
+            scores.append(instance["score"]["global"]["score"])
+
+        from statistics import mean
+
+        return mean(scores)
+
+    def spread_results(self, stream: Stream, score: float):
+        for instance in stream:
+            instance["score"]["global"]["groups_mean_score"] = score
+            yield instance
+
+    def process(self, multi_stream: MultiStream) -> MultiStream:
+        mean_score = self.aggegate_results(multi_stream)
+
+        result = {}
+        for stream_name, stream in multi_stream.items():
+            result[stream_name] = Stream(self.spread_results, gen_kwargs={"stream": stream, "score": mean_score})
+
+        return MultiStream(result)
 
-# TODO: Add BibTeX citation
-_CITATION = """\
-@InProceedings{huggingface:module,
-title = {A great new module},
-authors={huggingface, Inc.},
-year={2020}
-}
-"""
-
-# TODO: Add description of the module here
-_DESCRIPTION = """\
-This new module is designed to solve this great ML task and is crafted with a lot of care.
-"""
-
-
-# TODO: Add description of the arguments of the module here
-_KWARGS_DESCRIPTION = """
-Calculates how good are predictions given some references, using certain scores
-Args:
-    predictions: list of predictions to score. Each predictions
-        should be a string with tokens separated by spaces.
-    references: list of reference for each prediction. Each
-        reference should be a string with tokens separated by spaces.
-Returns:
-    accuracy: description of the first score,
-    another_score: description of the second score,
-Examples:
-    Examples should be written in doctest format, and should illustrate how
-    to use the function.
-
-    >>> my_new_module = evaluate.load("my_new_module")
-    >>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
-    >>> print(results)
-    {'accuracy': 1.0}
-"""
-
-# TODO: Define external resources urls if needed
-BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
-
-
-@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
-class Metric(evaluate.Metric):
-    """TODO: Short description of my evaluation module."""
 
+class FromPredictionsAndOriginalData(StreamInitializerOperator):
+    def zip(self, predictions, references):
+        for prediction, original in zip(predictions, references):
+            yield {**original, "prediction": prediction}
+
+    def process(self, predictions: List[str], references: Iterable, split_name: str = "all") -> MultiStream:
+        return MultiStream(
+            {split_name: Stream(self.zip, gen_kwargs={"predictions": predictions, "references": references})}
+        )
+
+
+from .schema import UNITXT_DATASET_SCHEMA
+
+
+class MetricRecipe(SequntialOperatorInitilizer):
+    def prepare(self):
+        self.steps = [
+            FromPredictionsAndOriginalData(),
+            ApplyValueOperatorsField(
+                value_field="prediction", operators_field="processors", default_operators=["to_string"]
+            ),
+            SplitByValue(["group"]),
+            ApplyStreamOperatorsField(
+                "metrics",
+                reversed=True,
+            ),
+            MultiStreamScoreMean(),
+            MergeStreams(),
+        ]
+
+
+UNITXT_METRIC_SCHEMA = Features({"predictions": Value("string"), "references": dict(UNITXT_DATASET_SCHEMA)})
+
+
+# @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
+class UnitextMetric(evaluate.Metric):
     def _info(self):
-        # TODO: Specifies the evaluate.EvaluationModuleInfo object
         return evaluate.MetricInfo(
-            # This is the description that will appear on the modules page.
-            module_type="metric",
-            description=_DESCRIPTION,
-            citation=_CITATION,
-            inputs_description=_KWARGS_DESCRIPTION,
-            # This defines the format of each prediction and reference
-            features=datasets.Features({
-                'predictions': datasets.Value('int64'),
-                'references': datasets.Value('int64'),
-            }),
-            # Homepage of the module for documentation
-            homepage="http://module.homepage",
-            # Additional links to the codebase or references
-            codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
-            reference_urls=["http://path.to.reference.url/new_module"]
+            description="_DESCRIPTION",
+            citation="_CITATION",
+            # inputs_description=_KWARGS_DESCRIPTION,
+            features=UNITXT_METRIC_SCHEMA,
+            codebase_urls=["https://"],
+            reference_urls=[
+                "https://",
+                "https://",
+            ],
         )
 
-    def _download_and_prepare(self, dl_manager):
-        """Optional: download external resources useful to compute the scores"""
-        # TODO: Download external resources if needed
-        pass
-
-    def _compute(self, predictions, references):
-        """Returns the scores"""
-        # TODO: Compute the different scores of the module
-        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
-        return {
-            "accuracy": accuracy,
-        }
+    def _compute(self, predictions: List[str], references: Iterable, flatten: bool = False, split_name: str = "all"):
+        recipe = MetricRecipe()
+
+        multi_stream = recipe(predictions=predictions, references=references, split_name=split_name)
+
+        if flatten:
+            operator = FlattenInstances()
+            multi_stream = operator(multi_stream)
+
+        stream = multi_stream[split_name]
+
+        return list(stream)