From 28db5fbd85a92d962d5dcd048594fa988a8466a8 Mon Sep 17 00:00:00 2001 From: joaquintb Date: Mon, 8 Jul 2024 12:18:06 +0200 Subject: [PATCH] Completed comments --- model_selection/cv_metric_distr.py | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/model_selection/cv_metric_distr.py b/model_selection/cv_metric_distr.py index 845eb0f..0dfe30d 100644 --- a/model_selection/cv_metric_distr.py +++ b/model_selection/cv_metric_distr.py @@ -1,24 +1,26 @@ +# CV Metrics Distribution +# Author: Joaquín Torres Bravo """ - Plotting the distribution of the metrics obtained from cv via boxplots. + Plotting the distribution of the metrics obtained from CV via boxplots. """ # Libraries # -------------------------------------------------------------------------------------------------------- import pandas as pd -import matplotlib.pyplot as plt # Corrected import +import matplotlib.pyplot as plt # -------------------------------------------------------------------------------------------------------- if __name__ == "__main__": metric_names = ['F1', 'PREC', 'REC', 'ACC', 'NREC', 'TN', 'FN', 'FP', 'TP', 'AUROC', 'AUPRC'] model_names_simple = ['DT', 'RF', 'Bagging', 'AB', 'XGB', 'LR', 'SVM', 'MLP'] - model_names_cs = ['DT', 'RF', 'Bagging', 'AB', 'LR', 'SVM'] + model_names_cs = ['DT', 'RF', 'Bagging', 'AB', 'LR', 'SVM'] # Cost-sensitive learning # Distribution of cv metrics # -------------------------------------------------------------------------------------------------------- for group in ['pre', 'post']: for method in ['_ORIG', '_ORIG_CW', '_OVER', '_UNDER']: - # Read current sheet as df + # Read CV metrics sheet for current group and method df = pd.read_excel('./output_cv_metrics/metrics.xlsx', sheet_name=group+method) # Model names based on cost-senstive training or not if method == '_ORIG_CW': @@ -27,6 +29,7 @@ if __name__ == "__main__": model_names = model_names_simple # Create figure for current sheet, one row per metric fig, axes = plt.subplots(len(metric_names), 1, figsize=(10, 10 * len(metric_names))) + # For each metric for metric_id, metric_name in enumerate(metric_names): # Get the axis for the current metric ax = axes[metric_id] @@ -45,7 +48,7 @@ if __name__ == "__main__": ax.set_ylim(0, 1) plt.tight_layout() fig.savefig(f'./output/cv_metrics/distributions/{group}{method}.svg', format='svg', dpi=600) - plt.close(fig) # Close the figure to free up memory + plt.close(fig) print("Succesful distribution plots generation") # -------------------------------------------------------------------------------------------------------- \ No newline at end of file -- 2.24.1