comparison model_prediction.py @ 40:b92b5fe51845 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit ea12f973df4b97a2691d9e4ce6bf6fae59d57717"

39:4ee54a853377

    if isinstance(estimator, Pipeline):
        main_est = estimator.steps[-1][-1]
    if hasattr(main_est, "config") and hasattr(main_est, "load_weights"):
        if not infile_weights or infile_weights == "None":
            raise ValueError(
                "The selected model skeleton asks for weights, " "but dataset for weights wan not selected!"
            )
        main_est.load_weights(infile_weights)

    # handle data input
    input_type = params["input_options"]["selected_input"]
    # tabular input
    if input_type == "tabular":
        header = "infer" if params["input_options"]["header1"] else None
        column_option = params["input_options"]["column_selector_options_1"]["selected_column_selector_option"]
        if column_option in [
            "by_index_number",
            "all_but_by_index_number",
            "by_header_name",
            "all_but_by_header_name",

        klass = try_get_attr("galaxy_ml.preprocessors", seq_type)

        pred_data_generator = klass(fasta_path, seq_length=seq_length)

        if params["method"] == "predict":
            preds = estimator.predict(X, data_generator=pred_data_generator, steps=steps)
        else:
            preds = estimator.predict_proba(X, data_generator=pred_data_generator, steps=steps)

    # vcf input
    elif input_type == "variant_effect":
        klass = try_get_attr("galaxy_ml.preprocessors", "GenomicVariantBatchGenerator")

        options = params["input_options"]
        options.pop("selected_input")
        if options["blacklist_regions"] == "none":
            options["blacklist_regions"] = None

        pred_data_generator = klass(ref_genome_path=ref_seq, vcf_path=vcf_path, **options)

        pred_data_generator.set_processing_attrs()

        variants = pred_data_generator.variants

40:b92b5fe51845

    if isinstance(estimator, Pipeline):
        main_est = estimator.steps[-1][-1]
    if hasattr(main_est, "config") and hasattr(main_est, "load_weights"):
        if not infile_weights or infile_weights == "None":
            raise ValueError(
                "The selected model skeleton asks for weights, "
                "but dataset for weights wan not selected!"
            )
        main_est.load_weights(infile_weights)

    # handle data input
    input_type = params["input_options"]["selected_input"]
    # tabular input
    if input_type == "tabular":
        header = "infer" if params["input_options"]["header1"] else None
        column_option = params["input_options"]["column_selector_options_1"][
            "selected_column_selector_option"
        ]
        if column_option in [
            "by_index_number",
            "all_but_by_index_number",
            "by_header_name",
            "all_but_by_header_name",

        klass = try_get_attr("galaxy_ml.preprocessors", seq_type)

        pred_data_generator = klass(fasta_path, seq_length=seq_length)

        if params["method"] == "predict":
            preds = estimator.predict(
                X, data_generator=pred_data_generator, steps=steps
            )
        else:
            preds = estimator.predict_proba(
                X, data_generator=pred_data_generator, steps=steps
            )

    # vcf input
    elif input_type == "variant_effect":
        klass = try_get_attr("galaxy_ml.preprocessors", "GenomicVariantBatchGenerator")

        options = params["input_options"]
        options.pop("selected_input")
        if options["blacklist_regions"] == "none":
            options["blacklist_regions"] = None

        pred_data_generator = klass(
            ref_genome_path=ref_seq, vcf_path=vcf_path, **options
        )

        pred_data_generator.set_processing_attrs()

        variants = pred_data_generator.variants