horizonmetrics.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.
"""TODO: Add a description here."""

import evaluate
import datasets
import numpy as np

from seametrics.horizon.utils import *

# 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 horizonmetrics(evaluate.Metric):
    """TODO: Short description of my evaluation module."""

    def __init__(self,
                 roll_threshold=0.5,
                 pitch_threshold=0.1,
                 vertical_fov_degrees=25.6,
                 **kwargs):
        super().__init__(**kwargs)

        self.slope_threshold = roll_to_slope(roll_threshold)
        self.midpoint_threshold = pitch_to_midpoint(pitch_threshold,
                                                    vertical_fov_degrees)
        self.predictions = None
        self.ground_truth_det = None
        self.slope_error_list = None
        self.midpoint_error_list = None

    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"])

    def add(self, *, predictions, references, **kwargs):
        """
        Update the predictions and ground truth detections.

        Parameters
        ----------
        predictions : list
            List of predicted horizons.
        ground_truth_det : list
            List of ground truth horizons.

        """

        # does not impact the metric, but is required for the interface x_x
        super(evaluate.Metric, self).add(prediction=0, references=0, **kwargs)

        self.predictions = predictions
        self.ground_truth_det = references
        self.slope_error_list = []
        self.midpoint_error_list = []

        for annotated_horizon, proposed_horizon in zip(self.ground_truth_det,
                                                       self.predictions):
            slope_error, midpoint_error = calculate_horizon_error(
                annotated_horizon, proposed_horizon)
            self.slope_error_list.append(slope_error)
            self.midpoint_error_list.append(midpoint_error)

    def _compute(self, *, predictions, references, **kwargs):
        """
        Compute the horizon error across the sequence.

        Returns
        -------
        float
            The computed horizon error.

        """
        return calculate_horizon_error_across_sequence(
            self.slope_error_list, self.midpoint_error_list,
            self.slope_threshold, self.midpoint_threshold)

    def _download_and_prepare(self, dl_manager):
        """Optional: download external resources useful to compute the scores"""
        # TODO: Download external resources if needed
        pass