comparison flexynesis_plot.py @ 5:466b593fd87e draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/flexynesis commit 1afbaf45449e25238935e222f983da62392c067a

4:1a5f8cedda43

def generate_dimred_plots(embeddings, matched_labels, args, output_dir, output_name_base):
    """Generate dimensionality reduction plots"""

    # Parse target variables
    target_vars = [var.strip() for var in args.target_variables.split(',')]

    print(f"Generating {args.method.upper()} plots for {len(target_vars)} target variable(s): {', '.join(target_vars)}")

    # Check variables
    available_vars = matched_labels['variable'].unique()
    missing_vars = [var for var in target_vars if var not in available_vars]

    if missing_vars:
        print(f"Warning: The following target variables were not found in the data: {', '.join(missing_vars)}")
        print(f"Available variables: {', '.join(available_vars)}")

    # Filter to only process available variables
    valid_vars = [var for var in target_vars if var in available_vars]

    if not valid_vars:
        raise ValueError(f"None of the specified target variables were found in the data. Available: {', '.join(available_vars)}")

    # Generate plots for each valid target variable

    # Arguments for dimensionality reduction
    parser.add_argument("--embeddings", type=str,
                        help="Path to input data embeddings file (CSV or tabular format). Required for dimred plots.")
    parser.add_argument("--method", type=str, default='pca', choices=['pca', 'umap'],
                        help="Transformation method ('pca' or 'umap'). Default is 'pca'. Used for dimred plots.")
    parser.add_argument("--target_variables", type=str, required=False,
                        help="Comma-separated list of target variables to plot.")

    # Arguments for Kaplan-Meier
    parser.add_argument("--survival_data", type=str,
                        help="Path to survival data file with columns: duration and event. Required for kaplan_meier plots.")
    parser.add_argument("--surv_time_var", type=str, required=False,

    parser.add_argument("--n_splits", type=int, default=5,
                        help="Number of folds for cross-validation. Default is 5")
    parser.add_argument("--random_state", type=int, default=42,
                        help="Random seed for reproducibility. Default is 42")

    # Arguments for scatter plot, heatmap, PR curves, ROC curves, and box plots
    parser.add_argument("--target_value", type=str, default=None,
                        help="Target value for scatter plot.")

    # Common arguments
    parser.add_argument("--output_dir", type=str, default='output',

                raise FileNotFoundError(f"embeddings file not found: {args.embeddings}")
            if not args.labels:
                raise ValueError("--labels is required for dimensionality reduction plots")
            if not args.method:
                raise ValueError("--method is required for dimensionality reduction plots")
            if not args.target_variables:
                raise ValueError("--target_variables is required for dimensionality reduction plots")

        if args.plot_type in ['kaplan_meier']:
            if not args.survival_data:
                raise ValueError("--survival_data is required when plot_type is 'kaplan_meier'")
            if not os.path.isfile(args.survival_data):

5:466b593fd87e

def generate_dimred_plots(embeddings, matched_labels, args, output_dir, output_name_base):
    """Generate dimensionality reduction plots"""

    # Parse target values from comma-separated string
    if args.target_value:
        target_values = [val.strip() for val in args.target_value.split(',')]
    else:
        # If no target values specified, use all unique variables
        target_values = matched_labels['variable'].unique().tolist()

    print(f"Generating {args.method.upper()} plots for {len(target_values)} target variable(s): {', '.join(target_values)}")

    # Check variables
    available_vars = matched_labels['variable'].unique()
    missing_vars = [var for var in target_values if var not in available_vars]

    if missing_vars:
        print(f"Warning: The following target variables were not found in the data: {', '.join(missing_vars)}")
        print(f"Available variables: {', '.join(available_vars)}")

    # Filter to only process available variables
    valid_vars = [var for var in target_values if var in available_vars]

    if not valid_vars:
        raise ValueError(f"None of the specified target variables were found in the data. Available: {', '.join(available_vars)}")

    # Generate plots for each valid target variable

    # Arguments for dimensionality reduction
    parser.add_argument("--embeddings", type=str,
                        help="Path to input data embeddings file (CSV or tabular format). Required for dimred plots.")
    parser.add_argument("--method", type=str, default='pca', choices=['pca', 'umap'],
                        help="Transformation method ('pca' or 'umap'). Default is 'pca'. Used for dimred plots.")

    # Arguments for Kaplan-Meier
    parser.add_argument("--survival_data", type=str,
                        help="Path to survival data file with columns: duration and event. Required for kaplan_meier plots.")
    parser.add_argument("--surv_time_var", type=str, required=False,

    parser.add_argument("--n_splits", type=int, default=5,
                        help="Number of folds for cross-validation. Default is 5")
    parser.add_argument("--random_state", type=int, default=42,
                        help="Random seed for reproducibility. Default is 42")

    # Arguments for dimred, scatter plot, heatmap, PR curves, ROC curves, and box plots
    parser.add_argument("--target_value", type=str, default=None,
                        help="Target value for scatter plot.")

    # Common arguments
    parser.add_argument("--output_dir", type=str, default='output',

                raise FileNotFoundError(f"embeddings file not found: {args.embeddings}")
            if not args.labels:
                raise ValueError("--labels is required for dimensionality reduction plots")
            if not args.method:
                raise ValueError("--method is required for dimensionality reduction plots")

        if args.plot_type in ['kaplan_meier']:
            if not args.survival_data:
                raise ValueError("--survival_data is required when plot_type is 'kaplan_meier'")
            if not os.path.isfile(args.survival_data):