diff ml_visualization_ex.py @ 16:a536d2736c2d draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 3c1e6c72303cfd8a5fd014734f18402b97f8ecb5
author bgruening
date Fri, 22 Sep 2023 16:40:38 +0000
parents 9c19cf3c4ea0
children
line wrap: on
line diff
--- a/ml_visualization_ex.py	Wed Aug 09 13:48:55 2023 +0000
+++ b/ml_visualization_ex.py	Fri Sep 22 16:40:38 2023 +0000
@@ -15,6 +15,7 @@
 from sklearn.metrics import (
     auc,
     average_precision_score,
+    confusion_matrix,
     precision_recall_curve,
     roc_curve,
 )
@@ -258,6 +259,30 @@
     os.rename(os.path.join(folder, "output.svg"), os.path.join(folder, "output"))
 
 
+def get_dataframe(file_path, plot_selection, header_name, column_name):
+    header = "infer" if plot_selection[header_name] else None
+    column_option = plot_selection[column_name]["selected_column_selector_option"]
+    if column_option in [
+        "by_index_number",
+        "all_but_by_index_number",
+        "by_header_name",
+        "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,
     infile_estimator=None,
@@ -271,6 +296,10 @@
     targets=None,
     fasta_path=None,
     model_config=None,
+    true_labels=None,
+    predicted_labels=None,
+    plot_color=None,
+    title=None,
 ):
     """
     Parameter
@@ -311,6 +340,18 @@
 
     model_config : str, default is None
         File path to dataset containing JSON config for neural networks
+
+    true_labels : str, default is None
+        File path to dataset containing true labels
+
+    predicted_labels : str, default is None
+        File path to dataset containing true predicted labels
+
+    plot_color : str, default is None
+        Color of the confusion matrix heatmap
+
+    title : str, default is None
+        Title of the confusion matrix heatmap
     """
     warnings.simplefilter("ignore")
 
@@ -534,6 +575,36 @@
 
         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))
+        im = plt.imshow(c_matrix, cmap=plot_color)
+        for i in range(len(c_matrix)):
+            for j in range(len(c_matrix)):
+                ax.text(j, i, c_matrix[i, j], ha="center", va="center", color="k")
+        ax.set_ylabel("True class labels")
+        ax.set_xlabel("Predicted class labels")
+        ax.set_title(title)
+        ax.set_xticks(axis_labels)
+        ax.set_yticks(axis_labels)
+        fig.colorbar(im, ax=ax)
+        fig.tight_layout()
+        plt.savefig("output.png", dpi=125)
+        os.rename("output.png", "output")
+
+        return 0
+
     # save pdf file to disk
     # fig.write_image("image.pdf", format='pdf')
     # fig.write_image("image.pdf", format='pdf', width=340*2, height=226*2)
@@ -553,6 +624,10 @@
     aparser.add_argument("-t", "--targets", dest="targets")
     aparser.add_argument("-f", "--fasta_path", dest="fasta_path")
     aparser.add_argument("-c", "--model_config", dest="model_config")
+    aparser.add_argument("-tl", "--true_labels", dest="true_labels")
+    aparser.add_argument("-pl", "--predicted_labels", dest="predicted_labels")
+    aparser.add_argument("-pc", "--plot_color", dest="plot_color")
+    aparser.add_argument("-pt", "--title", dest="title")
     args = aparser.parse_args()
 
     main(
@@ -568,4 +643,8 @@
         targets=args.targets,
         fasta_path=args.fasta_path,
         model_config=args.model_config,
+        true_labels=args.true_labels,
+        predicted_labels=args.predicted_labels,
+        plot_color=args.plot_color,
+        title=args.title,
     )