tapex/run_wikisql_with_tapex.py [426:550]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if is_training:
            model_inputs = tokenizer(
                table=tables,
                query=questions,
                answer=answers,
                max_length=data_args.max_source_length,
                padding=padding,
                truncation=True,
            )
        else:
            model_inputs = tokenizer(
                table=tables, query=questions, max_length=data_args.max_source_length, padding=padding, truncation=True
            )

        labels = tokenizer(
            answer=[", ".join(answer) for answer in answers],
            max_length=max_target_length,
            padding=padding,
            truncation=True,
        )

        # If we are padding here, replace all tokenizer.pad_token_id in the labels by -100 when we want to ignore
        # padding in the loss.
        if padding == "max_length" and data_args.ignore_pad_token_for_loss:
            labels["input_ids"] = [
                [(l if l != tokenizer.pad_token_id else -100) for l in label] for label in labels["input_ids"]
            ]

        model_inputs["labels"] = labels["input_ids"]

        return model_inputs

    # in training, we can use the answer as extra information to truncate large tables
    preprocess_tableqa_function_training = partial(preprocess_tableqa_function, is_training=True)

    if training_args.do_train:
        if "train" not in datasets:
            raise ValueError("--do_train requires a train dataset")
        train_dataset = datasets["train"]
        if data_args.max_train_samples is not None:
            train_dataset = train_dataset.select(range(data_args.max_train_samples))
        train_dataset = train_dataset.map(
            preprocess_tableqa_function_training,
            batched=True,
            num_proc=data_args.preprocessing_num_workers,
            remove_columns=column_names,
            load_from_cache_file=not data_args.overwrite_cache,
        )

    if training_args.do_eval:
        max_target_length = data_args.val_max_target_length
        if "validation" not in datasets:
            raise ValueError("--do_eval requires a validation dataset")
        eval_dataset = datasets["validation"]
        if data_args.max_eval_samples is not None:
            eval_dataset = eval_dataset.select(range(data_args.max_eval_samples))
        eval_dataset = eval_dataset.map(
            preprocess_tableqa_function,
            batched=True,
            num_proc=data_args.preprocessing_num_workers,
            remove_columns=column_names,
            load_from_cache_file=not data_args.overwrite_cache,
        )

    if training_args.do_predict:
        max_target_length = data_args.val_max_target_length
        if "test" not in datasets:
            raise ValueError("--do_predict requires a test dataset")
        predict_dataset = datasets["test"]
        if data_args.max_predict_samples is not None:
            predict_dataset = predict_dataset.select(range(data_args.max_predict_samples))
        predict_dataset = predict_dataset.map(
            preprocess_tableqa_function,
            batched=True,
            num_proc=data_args.preprocessing_num_workers,
            remove_columns=column_names,
            load_from_cache_file=not data_args.overwrite_cache,
        )

    # Data collator
    label_pad_token_id = -100 if data_args.ignore_pad_token_for_loss else tokenizer.pad_token_id
    data_collator = DataCollatorForSeq2Seq(
        tokenizer,
        model=model,
        label_pad_token_id=label_pad_token_id,
        pad_to_multiple_of=8 if training_args.fp16 else None,
    )

    def postprocess_text(preds, labels):
        preds = [pred.strip() for pred in preds]
        labels = [label.strip() for label in labels]

        return preds, labels

    def compute_metrics(eval_preds):
        preds, labels = eval_preds
        if isinstance(preds, tuple):
            preds = preds[0]
        decoded_preds = tokenizer.batch_decode(preds, skip_special_tokens=True)
        if data_args.ignore_pad_token_for_loss:
            # Replace -100 in the labels as we can't decode them.
            labels = np.where(labels != -100, labels, tokenizer.pad_token_id)
        decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)

        # Some simple post-processing
        decoded_preds, decoded_labels = postprocess_text(decoded_preds, decoded_labels)

        delimiter = ", "

        # define example evaluation
        def evaluate_example(predict_str: str, ground_str: str):
            predict_spans = predict_str.split(delimiter)
            ground_spans = ground_str.split(delimiter)
            predict_values = defaultdict(lambda: 0)
            ground_values = defaultdict(lambda: 0)
            for span in predict_spans:
                try:
                    predict_values[float(span)] += 1
                except ValueError:
                    predict_values[span.strip()] += 1
            for span in ground_spans:
                try:
                    ground_values[float(span)] += 1
                except ValueError:
                    ground_values[span.strip()] += 1
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tapex/run_wikitablequestions_with_tapex.py [402:526]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if is_training:
            model_inputs = tokenizer(
                table=tables,
                query=questions,
                answer=answers,
                max_length=data_args.max_source_length,
                padding=padding,
                truncation=True,
            )
        else:
            model_inputs = tokenizer(
                table=tables, query=questions, max_length=data_args.max_source_length, padding=padding, truncation=True
            )

        labels = tokenizer(
            answer=[", ".join(answer) for answer in answers],
            max_length=max_target_length,
            padding=padding,
            truncation=True,
        )

        # If we are padding here, replace all tokenizer.pad_token_id in the labels by -100 when we want to ignore
        # padding in the loss.
        if padding == "max_length" and data_args.ignore_pad_token_for_loss:
            labels["input_ids"] = [
                [(l if l != tokenizer.pad_token_id else -100) for l in label] for label in labels["input_ids"]
            ]

        model_inputs["labels"] = labels["input_ids"]

        return model_inputs

    # in training, we can use the answer as extra information to truncate large tables
    preprocess_tableqa_function_training = partial(preprocess_tableqa_function, is_training=True)

    if training_args.do_train:
        if "train" not in datasets:
            raise ValueError("--do_train requires a train dataset")
        train_dataset = datasets["train"]
        if data_args.max_train_samples is not None:
            train_dataset = train_dataset.select(range(data_args.max_train_samples))
        train_dataset = train_dataset.map(
            preprocess_tableqa_function_training,
            batched=True,
            num_proc=data_args.preprocessing_num_workers,
            remove_columns=column_names,
            load_from_cache_file=not data_args.overwrite_cache,
        )

    if training_args.do_eval:
        max_target_length = data_args.val_max_target_length
        if "validation" not in datasets:
            raise ValueError("--do_eval requires a validation dataset")
        eval_dataset = datasets["validation"]
        if data_args.max_eval_samples is not None:
            eval_dataset = eval_dataset.select(range(data_args.max_eval_samples))
        eval_dataset = eval_dataset.map(
            preprocess_tableqa_function,
            batched=True,
            num_proc=data_args.preprocessing_num_workers,
            remove_columns=column_names,
            load_from_cache_file=not data_args.overwrite_cache,
        )

    if training_args.do_predict:
        max_target_length = data_args.val_max_target_length
        if "test" not in datasets:
            raise ValueError("--do_predict requires a test dataset")
        predict_dataset = datasets["test"]
        if data_args.max_predict_samples is not None:
            predict_dataset = predict_dataset.select(range(data_args.max_predict_samples))
        predict_dataset = predict_dataset.map(
            preprocess_tableqa_function,
            batched=True,
            num_proc=data_args.preprocessing_num_workers,
            remove_columns=column_names,
            load_from_cache_file=not data_args.overwrite_cache,
        )

    # Data collator
    label_pad_token_id = -100 if data_args.ignore_pad_token_for_loss else tokenizer.pad_token_id
    data_collator = DataCollatorForSeq2Seq(
        tokenizer,
        model=model,
        label_pad_token_id=label_pad_token_id,
        pad_to_multiple_of=8 if training_args.fp16 else None,
    )

    def postprocess_text(preds, labels):
        preds = [pred.strip() for pred in preds]
        labels = [label.strip() for label in labels]

        return preds, labels

    def compute_metrics(eval_preds):
        preds, labels = eval_preds
        if isinstance(preds, tuple):
            preds = preds[0]
        decoded_preds = tokenizer.batch_decode(preds, skip_special_tokens=True)
        if data_args.ignore_pad_token_for_loss:
            # Replace -100 in the labels as we can't decode them.
            labels = np.where(labels != -100, labels, tokenizer.pad_token_id)
        decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)

        # Some simple post-processing
        decoded_preds, decoded_labels = postprocess_text(decoded_preds, decoded_labels)

        delimiter = ", "

        # define example evaluation
        def evaluate_example(predict_str: str, ground_str: str):
            predict_spans = predict_str.split(delimiter)
            ground_spans = ground_str.split(delimiter)
            predict_values = defaultdict(lambda: 0)
            ground_values = defaultdict(lambda: 0)
            for span in predict_spans:
                try:
                    predict_values[float(span)] += 1
                except ValueError:
                    predict_values[span.strip()] += 1
            for span in ground_spans:
                try:
                    ground_values[float(span)] += 1
                except ValueError:
                    ground_values[span.strip()] += 1
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -