import evaluate import datasets import numpy as np # 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 list of dictionary): relation and its type of prediction references (list of list of dictionary): references for each relation and its type Returns: **output** (`dictionary` of `dictionary`s) with multiple key-value pairs - **entity type** (`dictionary`): score of all of the type - **tp** : true positive count - **fp** : false positive count - **fn** : false negative count - **p** : precision - **r** : recall - **f1** : micro f1 score - **Macro_f1** : macro f1 score - **Macro_p** : macro precision - **Macro_r** : macro recall 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} """ def convert_format(data:list): """ Args: data (list) : list of dictionaries with different entity elements e.g [ {'head': ['phipigments', 'tinadaviespigments'...], 'head_type': ['product', 'brand'...], 'type': ['sell', 'sell'...], 'tail': ['國際認證之色乳', '國際認證之色乳'...], 'tail_type': ['product', 'product'...]}, {'head': ['SABONTAIWAN', 'SNTAIWAN'...], 'head_type': ['brand', 'brand'...], 'type': ['sell', 'sell'...], 'tail': ['大馬士革玫瑰有機光燦系列', '大馬士革玫瑰有機光燦系列'...], 'tail_type': ['product', 'product'...]} ... ] """ predictions = [] for item in data: prediction_group = [] for i in range(len(item['head'])): prediction = { 'head': item['head'][i], 'head_type': item['head_type'][i], 'type': item['type'][i], 'tail': item['tail'][i], 'tail_type': item['tail_type'][i], } prediction_group.append(prediction) predictions.append(prediction_group) return predictions @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION) class relation_extraction(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({ "head": datasets.Value("string"), "head_type": datasets.Value("string"), "type": datasets.Value("string"), "tail": datasets.Value("string"), "tail_type": datasets.Value("string"), }), 'references': datasets.Sequence({ "head": datasets.Value("string"), "head_type": datasets.Value("string"), "type": datasets.Value("string"), "tail": datasets.Value("string"), "tail_type": datasets.Value("string"), }), }), # 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 _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, mode, only_all=True, relation_types=[]): """Returns the scores""" # TODO: Compute the different scores of the module predictions = convert_format(predictions) references = convert_format(references) assert mode in ["strict", "boundaries"] # construct relation_types from ground truth if not given if len(relation_types) == 0: for triplets in references: for triplet in triplets: relation = triplet["type"] if relation not in relation_types: relation_types.append(relation) scores = {rel: {"tp": 0, "fp": 0, "fn": 0} for rel in relation_types + ["ALL"]} # Count GT relations and Predicted relations n_sents = len(references) n_rels = sum([len([rel for rel in sent]) for sent in references]) n_found = sum([len([rel for rel in sent]) for sent in predictions]) # Count TP, FP and FN per type for pred_sent, gt_sent in zip(predictions, references): for rel_type in relation_types: # strict mode takes argument types into account if mode == "strict": pred_rels = {(rel["head"], rel["head_type"], rel["tail"], rel["tail_type"]) for rel in pred_sent if rel["type"] == rel_type} gt_rels = {(rel["head"], rel["head_type"], rel["tail"], rel["tail_type"]) for rel in gt_sent if rel["type"] == rel_type} # boundaries mode only takes argument spans into account elif mode == "boundaries": pred_rels = {(rel["head"], rel["tail"]) for rel in pred_sent if rel["type"] == rel_type} gt_rels = {(rel["head"], rel["tail"]) for rel in gt_sent if rel["type"] == rel_type} scores[rel_type]["tp"] += len(pred_rels & gt_rels) scores[rel_type]["fp"] += len(pred_rels - gt_rels) scores[rel_type]["fn"] += len(gt_rels - pred_rels) # Compute per entity Precision / Recall / F1 for rel_type in scores.keys(): if scores[rel_type]["tp"]: scores[rel_type]["p"] = 100 * scores[rel_type]["tp"] / (scores[rel_type]["fp"] + scores[rel_type]["tp"]) scores[rel_type]["r"] = 100 * scores[rel_type]["tp"] / (scores[rel_type]["fn"] + scores[rel_type]["tp"]) else: scores[rel_type]["p"], scores[rel_type]["r"] = 0, 0 if not scores[rel_type]["p"] + scores[rel_type]["r"] == 0: scores[rel_type]["f1"] = 2 * scores[rel_type]["p"] * scores[rel_type]["r"] / ( scores[rel_type]["p"] + scores[rel_type]["r"]) else: scores[rel_type]["f1"] = 0 # Compute micro F1 Scores tp = sum([scores[rel_type]["tp"] for rel_type in relation_types]) fp = sum([scores[rel_type]["fp"] for rel_type in relation_types]) fn = sum([scores[rel_type]["fn"] for rel_type in relation_types]) if tp: precision = 100 * tp / (tp + fp) recall = 100 * tp / (tp + fn) f1 = 2 * precision * recall / (precision + recall) else: precision, recall, f1 = 0, 0, 0 scores["ALL"]["p"] = precision scores["ALL"]["r"] = recall scores["ALL"]["f1"] = f1 scores["ALL"]["tp"] = tp scores["ALL"]["fp"] = fp scores["ALL"]["fn"] = fn # Compute Macro F1 Scores scores["ALL"]["Macro_f1"] = np.mean([scores[ent_type]["f1"] for ent_type in relation_types]) scores["ALL"]["Macro_p"] = np.mean([scores[ent_type]["p"] for ent_type in relation_types]) scores["ALL"]["Macro_r"] = np.mean([scores[ent_type]["r"] for ent_type in relation_types]) if only_all: return scores["ALL"] return scores