ref-metrics.py

# 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.


import random
import datetime
import os

import datasets
import evaluate
from seametrics.user_friendly.utils import calculate_from_payload

import wandb

_CITATION = """\
@InProceedings{huggingface:module,
title = {A great new module},
authors={huggingface, Inc.},
year={2020}
}\
@article{milan2016mot16,
  title={MOT16: A benchmark for multi-object tracking},
  author={Milan, Anton and Leal-Taix{\'e}, Laura and Reid, Ian and Roth, Stefan and Schindler, Konrad},
  journal={arXiv preprint arXiv:1603.00831},
  year={2016}
}
"""

_DESCRIPTION = """\
The MOT Metrics module is designed to evaluate multi-object tracking (MOT) 
algorithms by computing various metrics based on predicted and ground truth bounding 
boxes. It serves as a crucial tool in assessing the performance of MOT systems, 
aiding in the iterative improvement of tracking algorithms."""


_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.
    max_iou (`float`, *optional*):
        If specified, this is the minimum Intersection over Union (IoU) threshold to consider a detection as a true positive.
        Default is 0.5.
"""


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class UserFriendlyMetrics(evaluate.Metric):
    """TODO: Short description of my evaluation module."""

    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.Sequence(
                        datasets.Sequence(datasets.Value("float"))
                    ),
                    "references": datasets.Sequence(
                        datasets.Sequence(datasets.Value("float"))
                    ),
                }
            ),
            # 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"],
        )

    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_from_payload(
        self,
        payload,
        area_ranges_tuples=None,  # Optional parameter
    ):
        """
        Compute the metric from the payload.

        Args:
            payload (Payload): The payload to compute the metric from.
            **kwargs: Additional keyword arguments.

        Returns:
            dict: The computed metric results with the following format:
            {
              "model_name": {
                "overall": {
                  "all": {"tp": ..., "fp": ..., "fn": ..., "f1": ...},
                  ...  # more area ranges
                },
                "per_sequence": {
                  "sequence_name": {
                    "all": {...},
                    ...  # more area ranges
                  },
                  ...  # more sequences
                }
              },
              ...  # more models
            }
        
        Note:
        - If the metric does not support area ranges, the metric should store the results under the `all` key.
        - If a range area is provided it will be displayed in the output. if area_ranges_tuples is None, then all the area ranges will be displayed
        """
        return self.dummy_values(area_ranges_tuples)

    def dummy_values(self, area_ranges_tuples=None):
        """Dummy randome values in the expected format that all new metrics need to return"""

                # Use default ranges if none are provided
        if area_ranges_tuples is None:
            area_names = ["all", "small", "medium", "large"]
        else:
            area_names = {
                key
                for key, value in area_ranges_tuples.items()
                if value["range"] is not None
            }

        # Generate random dummy values
        def generate_random_values():
            return {
                "tp": random.randint(0, 100),  # Random integer between 0 and 100
                "fp": random.randint(0, 50),  # Random integer between 0 and 50
                "fn": random.randint(0, 50),  # Random integer between 0 and 50
                "precision": round(
                    random.uniform(0.5, 1.0), 2
                ),  # Random float between 0.5 and 1.0
                "recall": round(
                    random.uniform(0.5, 1.0), 2
                ),  # Random float between 0.5 and 1.0
                "f1": round(
                    random.uniform(0.5, 1.0), 2
                ),  # Random float between 0.5 and 1.0
            }

        # Initialize output structure
        dummy_output = {"model_1": {"overall": {}, "per_sequence": {"sequence_1": {}}}}

        # Populate only the ranges specified in area_ranges_tuples with random values
        for area_name in area_names:
            dummy_output["model_1"]["overall"][area_name] = generate_random_values()
            dummy_output["model_1"]["per_sequence"]["sequence_1"][
                area_name
            ] = generate_random_values()

        return dummy_output