comparison ml_visualization_ex.py @ 21:14fa42b095c4 draft

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

20:a5665e1b06b0

import plotly.graph_objs as go
from galaxy_ml.utils import load_model, read_columns, SafeEval
from keras.models import model_from_json
from keras.utils import plot_model
from sklearn.feature_selection.base import SelectorMixin
from sklearn.metrics import auc, average_precision_score, confusion_matrix, precision_recall_curve, roc_curve
from sklearn.pipeline import Pipeline


safe_eval = SafeEval()

# plotly default colors
default_colors = [

    data = []
    for idx in range(df1.shape[1]):
        y_true = df1.iloc[:, idx].values
        y_score = df2.iloc[:, idx].values

        precision, recall, _ = precision_recall_curve(y_true, y_score, pos_label=pos_label)
        ap = average_precision_score(y_true, y_score, pos_label=pos_label or 1)

        trace = go.Scatter(
            x=recall,
            y=precision,

    for idx in range(df1.shape[1]):
        y_true = df1.iloc[:, idx].values
        y_score = df2.iloc[:, idx].values

        precision, recall, _ = precision_recall_curve(y_true, y_score, pos_label=pos_label)
        ap = average_precision_score(y_true, y_score, pos_label=pos_label or 1)

        plt.step(
            recall,
            precision,

    data = []
    for idx in range(df1.shape[1]):
        y_true = df1.iloc[:, idx].values
        y_score = df2.iloc[:, idx].values

        fpr, tpr, _ = roc_curve(y_true, y_score, pos_label=pos_label, drop_intermediate=drop_intermediate)
        roc_auc = auc(fpr, tpr)

        trace = go.Scatter(
            x=fpr,
            y=tpr,

            name="%s (area = %.3f)" % (idx, roc_auc),
        )
        data.append(trace)

    layout = go.Layout(
        xaxis=dict(title="False Positive Rate", linecolor="lightslategray", linewidth=1),
        yaxis=dict(title="True Positive Rate", linecolor="lightslategray", linewidth=1),
        title=dict(
            text=title or "Receiver Operating Characteristic (ROC) Curve",
            x=0.5,
            y=0.92,

    plotly.offline.plot(fig, filename="output.html", auto_open=False)
    # to be discovered by `from_work_dir`
    os.rename("output.html", "output")


def visualize_roc_curve_matplotlib(df1, df2, pos_label, drop_intermediate=True, title=None):
    """visualize roc-curve using matplotlib and output svg image"""
    backend = matplotlib.get_backend()
    if "inline" not in backend:
        matplotlib.use("SVG")
    plt.style.use("seaborn-colorblind")

    for idx in range(df1.shape[1]):
        y_true = df1.iloc[:, idx].values
        y_score = df2.iloc[:, idx].values

        fpr, tpr, _ = roc_curve(y_true, y_score, pos_label=pos_label, drop_intermediate=drop_intermediate)
        roc_auc = auc(fpr, tpr)

        plt.step(
            fpr,
            tpr,

        "all_but_by_header_name",
    ]:
        col = plot_selection[column_name]["col1"]
    else:
        col = None
    _, input_df = read_columns(file_path, c=col,
                               c_option=column_option,
                               return_df=True,
                               sep='\t', header=header,
                               parse_dates=True)
    return input_df


def main(
    inputs,

    if plot_type == "feature_importances":
        with open(infile_estimator, "rb") as estimator_handler:
            estimator = load_model(estimator_handler)

        column_option = params["plotting_selection"]["column_selector_options"]["selected_column_selector_option"]
        if column_option in [
            "by_index_number",
            "all_but_by_index_number",
            "by_header_name",
            "all_but_by_header_name",

        if hasattr(estimator, "coef_"):
            coefs = estimator.coef_
        else:
            coefs = getattr(estimator, "feature_importances_", None)
        if coefs is None:
            raise RuntimeError("The classifier does not expose " '"coef_" or "feature_importances_" ' "attributes")

        threshold = params["plotting_selection"]["threshold"]
        if threshold is not None:
            mask = (coefs > threshold) | (coefs < -threshold)
            coefs = coefs[mask]

            mode="lines",
        )
        layout = go.Layout(
            xaxis=dict(title="Number of features selected"),
            yaxis=dict(title="Cross validation score"),
            title=dict(text=title or None, x=0.5, y=0.92, xanchor="center", yanchor="top"),
            font=dict(family="sans-serif", size=11),
            # control backgroud colors
            plot_bgcolor="rgba(255,255,255,0)",
        )
        """

        return 0

    elif plot_type == "classification_confusion_matrix":
        plot_selection = params["plotting_selection"]
        input_true = get_dataframe(true_labels, plot_selection, "header_true", "column_selector_options_true")
        header_predicted = "infer" if plot_selection["header_predicted"] else None
        input_predicted = pd.read_csv(predicted_labels, sep="\t", parse_dates=True, header=header_predicted)
        true_classes = input_true.iloc[:, -1].copy()
        predicted_classes = input_predicted.iloc[:, -1].copy()
        axis_labels = list(set(true_classes))
        c_matrix = confusion_matrix(true_classes, predicted_classes)
        fig, ax = plt.subplots(figsize=(7, 7))

21:14fa42b095c4

import plotly.graph_objs as go
from galaxy_ml.utils import load_model, read_columns, SafeEval
from keras.models import model_from_json
from keras.utils import plot_model
from sklearn.feature_selection.base import SelectorMixin
from sklearn.metrics import (auc, average_precision_score, confusion_matrix,
                             precision_recall_curve, roc_curve)
from sklearn.pipeline import Pipeline

safe_eval = SafeEval()

# plotly default colors
default_colors = [

    data = []
    for idx in range(df1.shape[1]):
        y_true = df1.iloc[:, idx].values
        y_score = df2.iloc[:, idx].values

        precision, recall, _ = precision_recall_curve(
            y_true, y_score, pos_label=pos_label
        )
        ap = average_precision_score(y_true, y_score, pos_label=pos_label or 1)

        trace = go.Scatter(
            x=recall,
            y=precision,

    for idx in range(df1.shape[1]):
        y_true = df1.iloc[:, idx].values
        y_score = df2.iloc[:, idx].values

        precision, recall, _ = precision_recall_curve(
            y_true, y_score, pos_label=pos_label
        )
        ap = average_precision_score(y_true, y_score, pos_label=pos_label or 1)

        plt.step(
            recall,
            precision,

    data = []
    for idx in range(df1.shape[1]):
        y_true = df1.iloc[:, idx].values
        y_score = df2.iloc[:, idx].values

        fpr, tpr, _ = roc_curve(
            y_true, y_score, pos_label=pos_label, drop_intermediate=drop_intermediate
        )
        roc_auc = auc(fpr, tpr)

        trace = go.Scatter(
            x=fpr,
            y=tpr,

            name="%s (area = %.3f)" % (idx, roc_auc),
        )
        data.append(trace)

    layout = go.Layout(
        xaxis=dict(
            title="False Positive Rate", linecolor="lightslategray", linewidth=1
        ),
        yaxis=dict(title="True Positive Rate", linecolor="lightslategray", linewidth=1),
        title=dict(
            text=title or "Receiver Operating Characteristic (ROC) Curve",
            x=0.5,
            y=0.92,

    plotly.offline.plot(fig, filename="output.html", auto_open=False)
    # to be discovered by `from_work_dir`
    os.rename("output.html", "output")


def visualize_roc_curve_matplotlib(
    df1, df2, pos_label, drop_intermediate=True, title=None
):
    """visualize roc-curve using matplotlib and output svg image"""
    backend = matplotlib.get_backend()
    if "inline" not in backend:
        matplotlib.use("SVG")
    plt.style.use("seaborn-colorblind")

    for idx in range(df1.shape[1]):
        y_true = df1.iloc[:, idx].values
        y_score = df2.iloc[:, idx].values

        fpr, tpr, _ = roc_curve(
            y_true, y_score, pos_label=pos_label, drop_intermediate=drop_intermediate
        )
        roc_auc = auc(fpr, tpr)

        plt.step(
            fpr,
            tpr,

        "all_but_by_header_name",
    ]:
        col = plot_selection[column_name]["col1"]
    else:
        col = None
    _, input_df = read_columns(
        file_path,
        c=col,
        c_option=column_option,
        return_df=True,
        sep="\t",
        header=header,
        parse_dates=True,
    )
    return input_df


def main(
    inputs,

    if plot_type == "feature_importances":
        with open(infile_estimator, "rb") as estimator_handler:
            estimator = load_model(estimator_handler)

        column_option = params["plotting_selection"]["column_selector_options"][
            "selected_column_selector_option"
        ]
        if column_option in [
            "by_index_number",
            "all_but_by_index_number",
            "by_header_name",
            "all_but_by_header_name",

        if hasattr(estimator, "coef_"):
            coefs = estimator.coef_
        else:
            coefs = getattr(estimator, "feature_importances_", None)
        if coefs is None:
            raise RuntimeError(
                "The classifier does not expose "
                '"coef_" or "feature_importances_" '
                "attributes"
            )

        threshold = params["plotting_selection"]["threshold"]
        if threshold is not None:
            mask = (coefs > threshold) | (coefs < -threshold)
            coefs = coefs[mask]

            mode="lines",
        )
        layout = go.Layout(
            xaxis=dict(title="Number of features selected"),
            yaxis=dict(title="Cross validation score"),
            title=dict(
                text=title or None, x=0.5, y=0.92, xanchor="center", yanchor="top"
            ),
            font=dict(family="sans-serif", size=11),
            # control backgroud colors
            plot_bgcolor="rgba(255,255,255,0)",
        )
        """

        return 0

    elif plot_type == "classification_confusion_matrix":
        plot_selection = params["plotting_selection"]
        input_true = get_dataframe(
            true_labels, plot_selection, "header_true", "column_selector_options_true"
        )
        header_predicted = "infer" if plot_selection["header_predicted"] else None
        input_predicted = pd.read_csv(
            predicted_labels, sep="\t", parse_dates=True, header=header_predicted
        )
        true_classes = input_true.iloc[:, -1].copy()
        predicted_classes = input_predicted.iloc[:, -1].copy()
        axis_labels = list(set(true_classes))
        c_matrix = confusion_matrix(true_classes, predicted_classes)
        fig, ax = plt.subplots(figsize=(7, 7))