# HG changeset patch
# User goeckslab
# Date 1733893183 0
# Node ID 1f20fe57fdeeae143f730e3f3ca7db3a68e0bb2c
planemo upload for repository https://github.com/goeckslab/Galaxy-Pycaret commit d79b0f722b7d09505a526d1a4332f87e548a3df1
diff -r 000000000000 -r 1f20fe57fdee base_model_trainer.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/base_model_trainer.py Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,359 @@
+import base64
+import logging
+import os
+import tempfile
+
+from feature_importance import FeatureImportanceAnalyzer
+
+import h5py
+
+import joblib
+
+import numpy as np
+
+import pandas as pd
+
+from sklearn.metrics import average_precision_score
+
+from utils import get_html_closing, get_html_template
+
+logging.basicConfig(level=logging.DEBUG)
+LOG = logging.getLogger(__name__)
+
+
+class BaseModelTrainer:
+
+ def __init__(
+ self,
+ input_file,
+ target_col,
+ output_dir,
+ task_type,
+ random_seed,
+ test_file=None,
+ **kwargs
+ ):
+ self.exp = None # This will be set in the subclass
+ self.input_file = input_file
+ self.target_col = target_col
+ self.output_dir = output_dir
+ self.task_type = task_type
+ self.random_seed = random_seed
+ self.data = None
+ self.target = None
+ self.best_model = None
+ self.results = None
+ self.features_name = None
+ self.plots = {}
+ self.expaliner = None
+ self.plots_explainer_html = None
+ self.trees = []
+ for key, value in kwargs.items():
+ setattr(self, key, value)
+ self.setup_params = {}
+ self.test_file = test_file
+ self.test_data = None
+
+ LOG.info(f"Model kwargs: {self.__dict__}")
+
+ def load_data(self):
+ LOG.info(f"Loading data from {self.input_file}")
+ self.data = pd.read_csv(self.input_file, sep=None, engine='python')
+ self.data.columns = self.data.columns.str.replace('.', '_')
+
+ numeric_cols = self.data.select_dtypes(include=['number']).columns
+ non_numeric_cols = self.data.select_dtypes(exclude=['number']).columns
+
+ self.data[numeric_cols] = self.data[numeric_cols].apply(
+ pd.to_numeric, errors='coerce')
+
+ if len(non_numeric_cols) > 0:
+ LOG.info(f"Non-numeric columns found: {non_numeric_cols.tolist()}")
+
+ names = self.data.columns.to_list()
+ target_index = int(self.target_col)-1
+ self.target = names[target_index]
+ self.features_name = [name
+ for i, name in enumerate(names)
+ if i != target_index]
+ if hasattr(self, 'missing_value_strategy'):
+ if self.missing_value_strategy == 'mean':
+ self.data = self.data.fillna(
+ self.data.mean(numeric_only=True))
+ elif self.missing_value_strategy == 'median':
+ self.data = self.data.fillna(
+ self.data.median(numeric_only=True))
+ elif self.missing_value_strategy == 'drop':
+ self.data = self.data.dropna()
+ else:
+ # Default strategy if not specified
+ self.data = self.data.fillna(self.data.median(numeric_only=True))
+
+ if self.test_file:
+ LOG.info(f"Loading test data from {self.test_file}")
+ self.test_data = pd.read_csv(
+ self.test_file, sep=None, engine='python')
+ self.test_data = self.test_data[numeric_cols].apply(
+ pd.to_numeric, errors='coerce')
+ self.test_data.columns = self.test_data.columns.str.replace(
+ '.', '_'
+ )
+
+ def setup_pycaret(self):
+ LOG.info("Initializing PyCaret")
+ self.setup_params = {
+ 'target': self.target,
+ 'session_id': self.random_seed,
+ 'html': True,
+ 'log_experiment': False,
+ 'system_log': False,
+ 'index': False,
+ }
+
+ if self.test_data is not None:
+ self.setup_params['test_data'] = self.test_data
+
+ if hasattr(self, 'train_size') and self.train_size is not None \
+ and self.test_data is None:
+ self.setup_params['train_size'] = self.train_size
+
+ if hasattr(self, 'normalize') and self.normalize is not None:
+ self.setup_params['normalize'] = self.normalize
+
+ if hasattr(self, 'feature_selection') and \
+ self.feature_selection is not None:
+ self.setup_params['feature_selection'] = self.feature_selection
+
+ if hasattr(self, 'cross_validation') and \
+ self.cross_validation is not None \
+ and self.cross_validation is False:
+ self.setup_params['cross_validation'] = self.cross_validation
+
+ if hasattr(self, 'cross_validation') and \
+ self.cross_validation is not None:
+ if hasattr(self, 'cross_validation_folds'):
+ self.setup_params['fold'] = self.cross_validation_folds
+
+ if hasattr(self, 'remove_outliers') and \
+ self.remove_outliers is not None:
+ self.setup_params['remove_outliers'] = self.remove_outliers
+
+ if hasattr(self, 'remove_multicollinearity') and \
+ self.remove_multicollinearity is not None:
+ self.setup_params['remove_multicollinearity'] = \
+ self.remove_multicollinearity
+
+ if hasattr(self, 'polynomial_features') and \
+ self.polynomial_features is not None:
+ self.setup_params['polynomial_features'] = self.polynomial_features
+
+ if hasattr(self, 'fix_imbalance') and \
+ self.fix_imbalance is not None:
+ self.setup_params['fix_imbalance'] = self.fix_imbalance
+
+ LOG.info(self.setup_params)
+ self.exp.setup(self.data, **self.setup_params)
+
+ def train_model(self):
+ LOG.info("Training and selecting the best model")
+ if self.task_type == "classification":
+ average_displayed = "Weighted"
+ self.exp.add_metric(id=f'PR-AUC-{average_displayed}',
+ name=f'PR-AUC-{average_displayed}',
+ target='pred_proba',
+ score_func=average_precision_score,
+ average='weighted'
+ )
+
+ if hasattr(self, 'models') and self.models is not None:
+ self.best_model = self.exp.compare_models(
+ include=self.models)
+ else:
+ self.best_model = self.exp.compare_models()
+ self.results = self.exp.pull()
+ if self.task_type == "classification":
+ self.results.rename(columns={'AUC': 'ROC-AUC'}, inplace=True)
+
+ _ = self.exp.predict_model(self.best_model)
+ self.test_result_df = self.exp.pull()
+ if self.task_type == "classification":
+ self.test_result_df.rename(
+ columns={'AUC': 'ROC-AUC'}, inplace=True)
+
+ def save_model(self):
+ hdf5_model_path = "pycaret_model.h5"
+ with h5py.File(hdf5_model_path, 'w') as f:
+ with tempfile.NamedTemporaryFile(delete=False) as temp_file:
+ joblib.dump(self.best_model, temp_file.name)
+ temp_file.seek(0)
+ model_bytes = temp_file.read()
+ f.create_dataset('model', data=np.void(model_bytes))
+
+ def generate_plots(self):
+ raise NotImplementedError("Subclasses should implement this method")
+
+ def encode_image_to_base64(self, img_path):
+ with open(img_path, 'rb') as img_file:
+ return base64.b64encode(img_file.read()).decode('utf-8')
+
+ def save_html_report(self):
+ LOG.info("Saving HTML report")
+
+ model_name = type(self.best_model).__name__
+ excluded_params = ['html', 'log_experiment', 'system_log', 'test_data']
+ filtered_setup_params = {
+ k: v
+ for k, v in self.setup_params.items() if k not in excluded_params
+ }
+ setup_params_table = pd.DataFrame(
+ list(filtered_setup_params.items()),
+ columns=['Parameter', 'Value'])
+
+ best_model_params = pd.DataFrame(
+ self.best_model.get_params().items(),
+ columns=['Parameter', 'Value'])
+ best_model_params.to_csv(
+ os.path.join(self.output_dir, 'best_model.csv'),
+ index=False)
+ self.results.to_csv(os.path.join(
+ self.output_dir, "comparison_results.csv"))
+ self.test_result_df.to_csv(os.path.join(
+ self.output_dir, "test_results.csv"))
+
+ plots_html = ""
+ length = len(self.plots)
+ for i, (plot_name, plot_path) in enumerate(self.plots.items()):
+ encoded_image = self.encode_image_to_base64(plot_path)
+ plots_html += f"""
+
+
{plot_name.capitalize()}
+
+
"
+
+ tree_plots = ""
+ for i, tree in enumerate(self.trees):
+ if tree:
+ tree_plots += f"""
+
+
Tree {i+1}
+
+
PyCaret Model Training Report
+
+
+ Setup & Best Model
+
+ Best Model Plots
+
+ Feature Importance
+
+ Explainer
+
+
+
Setup Parameters
+
+ | Parameter | Value |
|---|
+ {setup_params_table.to_html(
+ index=False, header=False, classes='table')}
+
+
If you want to know all the experiment setup parameters,
+ please check the PyCaret documentation for
+ the classification/regression exp function.
+
Best Model: {model_name}
+
+ | Parameter | Value |
|---|
+ {best_model_params.to_html(
+ index=False, header=False, classes='table')}
+
+
Comparison Results on the Cross-Validation Set
+
+ {self.results.to_html(index=False, classes='table')}
+
+
Results on the Test Set for the best model
+
+ {self.test_result_df.to_html(index=False, classes='table')}
+
+
+
Best Model Plots on the testing set
+ {plots_html}
+
+
+ {feature_importance_html}
+
+
+ {self.plots_explainer_html}
+ {tree_plots}
+
+ {get_html_closing()}
+ """
+
+ with open(os.path.join(
+ self.output_dir, "comparison_result.html"), "w") as file:
+ file.write(html_content)
+
+ def save_dashboard(self):
+ raise NotImplementedError("Subclasses should implement this method")
+
+ def generate_plots_explainer(self):
+ raise NotImplementedError("Subclasses should implement this method")
+
+ # not working now
+ def generate_tree_plots(self):
+ from sklearn.ensemble import RandomForestClassifier, \
+ RandomForestRegressor
+ from xgboost import XGBClassifier, XGBRegressor
+ from explainerdashboard.explainers import RandomForestExplainer
+
+ LOG.info("Generating tree plots")
+ X_test = self.exp.X_test_transformed.copy()
+ y_test = self.exp.y_test_transformed
+
+ is_rf = isinstance(self.best_model, RandomForestClassifier) or \
+ isinstance(self.best_model, RandomForestRegressor)
+
+ is_xgb = isinstance(self.best_model, XGBClassifier) or \
+ isinstance(self.best_model, XGBRegressor)
+
+ try:
+ if is_rf:
+ num_trees = self.best_model.n_estimators
+ if is_xgb:
+ num_trees = len(self.best_model.get_booster().get_dump())
+ explainer = RandomForestExplainer(self.best_model, X_test, y_test)
+ for i in range(num_trees):
+ fig = explainer.decisiontree_encoded(tree_idx=i, index=0)
+ LOG.info(f"Tree {i+1}")
+ LOG.info(fig)
+ self.trees.append(fig)
+ except Exception as e:
+ LOG.error(f"Error generating tree plots: {e}")
+
+ def run(self):
+ self.load_data()
+ self.setup_pycaret()
+ self.train_model()
+ self.save_model()
+ self.generate_plots()
+ self.generate_plots_explainer()
+ self.generate_tree_plots()
+ self.save_html_report()
+ # self.save_dashboard()
diff -r 000000000000 -r 1f20fe57fdee dashboard.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/dashboard.py Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,159 @@
+import logging
+from typing import Any, Dict, Optional
+
+from pycaret.utils.generic import get_label_encoder
+
+logging.basicConfig(level=logging.DEBUG)
+LOG = logging.getLogger(__name__)
+
+
+def generate_classifier_explainer_dashboard(
+ exp,
+ estimator,
+ display_format: str = "dash",
+ dashboard_kwargs: Optional[Dict[str, Any]] = None,
+ run_kwargs: Optional[Dict[str, Any]] = None,
+ **kwargs,):
+
+ """
+ This function is changed from pycaret.classification.oop.dashboard()
+
+ This function generates the interactive dashboard for a trained model.
+ The dashboard is implemented using
+ ExplainerDashboard (explainerdashboard.readthedocs.io)
+
+
+ estimator: scikit-learn compatible object
+ Trained model object
+
+
+ display_format: str, default = 'dash'
+ Render mode for the dashboard. The default is set to ``dash``
+ which will
+ render a dashboard in browser. There are four possible options:
+
+ - 'dash' - displays the dashboard in browser
+ - 'inline' - displays the dashboard in the jupyter notebook cell.
+ - 'jupyterlab' - displays the dashboard in jupyterlab pane.
+ - 'external' - displays the dashboard in a separate tab.
+ (use in Colab)
+
+
+ dashboard_kwargs: dict, default = {} (empty dict)
+ Dictionary of arguments passed to the ``ExplainerDashboard`` class.
+
+
+ run_kwargs: dict, default = {} (empty dict)
+ Dictionary of arguments passed to the ``run``
+ method of ``ExplainerDashboard``.
+
+
+ **kwargs:
+ Additional keyword arguments to pass to the ``ClassifierExplainer``
+ or ``RegressionExplainer`` class.
+
+
+ Returns:
+ ExplainerDashboard
+ """
+
+ dashboard_kwargs = dashboard_kwargs or {}
+ run_kwargs = run_kwargs or {}
+
+ from explainerdashboard import ClassifierExplainer, ExplainerDashboard
+
+ le = get_label_encoder(exp.pipeline)
+ if le:
+ labels_ = list(le.classes_)
+ else:
+ labels_ = None
+
+ # Replaceing chars which dash doesnt accept for column name `.` , `{`, `}`
+
+ X_test_df = exp.X_test_transformed.copy()
+ LOG.info(X_test_df)
+ X_test_df.columns = [
+ col.replace(".", "__").replace("{", "__").replace("}", "__")
+ for col in X_test_df.columns
+ ]
+
+ explainer = ClassifierExplainer(
+ estimator, X_test_df, exp.y_test_transformed, labels=labels_, **kwargs
+ )
+ return ExplainerDashboard(
+ explainer, mode=display_format,
+ contributions=False, whatif=False,
+ **dashboard_kwargs
+ )
+
+
+def generate_regression_explainer_dashboard(
+ exp,
+ estimator,
+ display_format: str = "dash",
+ dashboard_kwargs: Optional[Dict[str, Any]] = None,
+ run_kwargs: Optional[Dict[str, Any]] = None,
+ **kwargs,):
+
+ """
+ This function is changed from pycaret.regression.oop.dashboard()
+
+ This function generates the interactive dashboard for a trained model.
+ The dashboard is implemented using ExplainerDashboard
+ (explainerdashboard.readthedocs.io)
+
+
+ estimator: scikit-learn compatible object
+ Trained model object
+
+
+ display_format: str, default = 'dash'
+ Render mode for the dashboard. The default is set to ``dash``
+ which will
+ render a dashboard in browser. There are four possible options:
+
+ - 'dash' - displays the dashboard in browser
+ - 'inline' - displays the dashboard in the jupyter notebook cell.
+ - 'jupyterlab' - displays the dashboard in jupyterlab pane.
+ - 'external' - displays the dashboard in a separate tab.
+ (use in Colab)
+
+
+ dashboard_kwargs: dict, default = {} (empty dict)
+ Dictionary of arguments passed to the ``ExplainerDashboard`` class.
+
+
+ run_kwargs: dict, default = {} (empty dict)
+ Dictionary of arguments passed to the ``run`` method
+ of ``ExplainerDashboard``.
+
+
+ **kwargs:
+ Additional keyword arguments to pass to the
+ ``ClassifierExplainer`` or
+ ``RegressionExplainer`` class.
+
+
+ Returns:
+ ExplainerDashboard
+ """
+
+ dashboard_kwargs = dashboard_kwargs or {}
+ run_kwargs = run_kwargs or {}
+
+ from explainerdashboard import ExplainerDashboard, RegressionExplainer
+
+ # Replaceing chars which dash doesnt accept for column name `.` , `{`, `}`
+ X_test_df = exp.X_test_transformed.copy()
+ X_test_df.columns = [
+ col.replace(".", "__").replace("{", "__").replace("}", "__")
+ for col in X_test_df.columns
+ ]
+ explainer = RegressionExplainer(
+ estimator, X_test_df, exp.y_test_transformed, **kwargs
+ )
+ return ExplainerDashboard(
+ explainer, mode=display_format, contributions=False,
+ whatif=False, shap_interaction=False, decision_trees=False,
+ **dashboard_kwargs
+ )
diff -r 000000000000 -r 1f20fe57fdee feature_importance.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/feature_importance.py Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,171 @@
+import base64
+import logging
+import os
+
+import matplotlib.pyplot as plt
+
+import pandas as pd
+
+from pycaret.classification import ClassificationExperiment
+from pycaret.regression import RegressionExperiment
+
+logging.basicConfig(level=logging.DEBUG)
+LOG = logging.getLogger(__name__)
+
+
+class FeatureImportanceAnalyzer:
+ def __init__(
+ self,
+ task_type,
+ output_dir,
+ data_path=None,
+ data=None,
+ target_col=None):
+
+ if data is not None:
+ self.data = data
+ LOG.info("Data loaded from memory")
+ else:
+ self.target_col = target_col
+ self.data = pd.read_csv(data_path, sep=None, engine='python')
+ self.data.columns = self.data.columns.str.replace('.', '_')
+ self.data = self.data.fillna(self.data.median(numeric_only=True))
+ self.task_type = task_type
+ self.target = self.data.columns[int(target_col) - 1]
+ self.exp = ClassificationExperiment() \
+ if task_type == 'classification' \
+ else RegressionExperiment()
+ self.plots = {}
+ self.output_dir = output_dir
+
+ def setup_pycaret(self):
+ LOG.info("Initializing PyCaret")
+ setup_params = {
+ 'target': self.target,
+ 'session_id': 123,
+ 'html': True,
+ 'log_experiment': False,
+ 'system_log': False
+ }
+ LOG.info(self.task_type)
+ LOG.info(self.exp)
+ self.exp.setup(self.data, **setup_params)
+
+ # def save_coefficients(self):
+ # model = self.exp.create_model('lr')
+ # coef_df = pd.DataFrame({
+ # 'Feature': self.data.columns.drop(self.target),
+ # 'Coefficient': model.coef_[0]
+ # })
+ # coef_html = coef_df.to_html(index=False)
+ # return coef_html
+
+ def save_tree_importance(self):
+ model = self.exp.create_model('rf')
+ importances = model.feature_importances_
+ processed_features = self.exp.get_config('X_transformed').columns
+ LOG.debug(f"Feature importances: {importances}")
+ LOG.debug(f"Features: {processed_features}")
+ feature_importances = pd.DataFrame({
+ 'Feature': processed_features,
+ 'Importance': importances
+ }).sort_values(by='Importance', ascending=False)
+ plt.figure(figsize=(10, 6))
+ plt.barh(
+ feature_importances['Feature'],
+ feature_importances['Importance'])
+ plt.xlabel('Importance')
+ plt.title('Feature Importance (Random Forest)')
+ plot_path = os.path.join(
+ self.output_dir,
+ 'tree_importance.png')
+ plt.savefig(plot_path)
+ plt.close()
+ self.plots['tree_importance'] = plot_path
+
+ def save_shap_values(self):
+ model = self.exp.create_model('lightgbm')
+ import shap
+ explainer = shap.Explainer(model)
+ shap_values = explainer.shap_values(
+ self.exp.get_config('X_transformed'))
+ shap.summary_plot(shap_values,
+ self.exp.get_config('X_transformed'), show=False)
+ plt.title('Shap (LightGBM)')
+ plot_path = os.path.join(
+ self.output_dir, 'shap_summary.png')
+ plt.savefig(plot_path)
+ plt.close()
+ self.plots['shap_summary'] = plot_path
+
+ def generate_feature_importance(self):
+ # coef_html = self.save_coefficients()
+ self.save_tree_importance()
+ self.save_shap_values()
+
+ def encode_image_to_base64(self, img_path):
+ with open(img_path, 'rb') as img_file:
+ return base64.b64encode(img_file.read()).decode('utf-8')
+
+ def generate_html_report(self):
+ LOG.info("Generating HTML report")
+
+ # Read and encode plot images
+ plots_html = ""
+ for plot_name, plot_path in self.plots.items():
+ encoded_image = self.encode_image_to_base64(plot_path)
+ plots_html += f"""
+
+
{'Feature importance analysis from a'
+ 'trained Random Forest'
+ if plot_name == 'tree_importance'
+ else 'SHAP Summary from a trained lightgbm'}
+
{'Use gini impurity for'
+ 'calculating feature importance for classification'
+ 'and Variance Reduction for regression'
+ if plot_name == 'tree_importance'
+ else ''}
+
+
PyCaret Feature Importance Report
+ {plots_html}
+ """
+
+ return html_content
+
+ def run(self):
+ LOG.info("Running feature importance analysis")
+ self.setup_pycaret()
+ self.generate_feature_importance()
+ html_content = self.generate_html_report()
+ LOG.info("Feature importance analysis completed")
+ return html_content
+
+
+if __name__ == "__main__":
+ import argparse
+ parser = argparse.ArgumentParser(description="Feature Importance Analysis")
+ parser.add_argument(
+ "--data_path", type=str, help="Path to the dataset")
+ parser.add_argument(
+ "--target_col", type=int,
+ help="Index of the target column (1-based)")
+ parser.add_argument(
+ "--task_type", type=str,
+ choices=["classification", "regression"],
+ help="Task type: classification or regression")
+ parser.add_argument(
+ "--output_dir",
+ type=str,
+ help="Directory to save the outputs")
+ args = parser.parse_args()
+
+ analyzer = FeatureImportanceAnalyzer(
+ args.data_path, args.target_col,
+ args.task_type, args.output_dir)
+ analyzer.run()
diff -r 000000000000 -r 1f20fe57fdee pycaret_classification.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/pycaret_classification.py Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,204 @@
+import logging
+
+from base_model_trainer import BaseModelTrainer
+
+from dashboard import generate_classifier_explainer_dashboard
+
+from pycaret.classification import ClassificationExperiment
+
+from utils import add_hr_to_html, add_plot_to_html
+
+LOG = logging.getLogger(__name__)
+
+
+class ClassificationModelTrainer(BaseModelTrainer):
+ def __init__(
+ self,
+ input_file,
+ target_col,
+ output_dir,
+ task_type,
+ random_seed,
+ test_file=None,
+ **kwargs):
+ super().__init__(
+ input_file,
+ target_col,
+ output_dir,
+ task_type,
+ random_seed,
+ test_file,
+ **kwargs)
+ self.exp = ClassificationExperiment()
+
+ def save_dashboard(self):
+ LOG.info("Saving explainer dashboard")
+ dashboard = generate_classifier_explainer_dashboard(self.exp,
+ self.best_model)
+ dashboard.save_html("dashboard.html")
+
+ def generate_plots(self):
+ LOG.info("Generating and saving plots")
+ plots = ['confusion_matrix', 'auc', 'threshold', 'pr',
+ 'error', 'class_report', 'learning', 'calibration',
+ 'vc', 'dimension', 'manifold', 'rfe', 'feature',
+ 'feature_all']
+ for plot_name in plots:
+ try:
+ if plot_name == 'auc' and not self.exp.is_multiclass:
+ plot_path = self.exp.plot_model(self.best_model,
+ plot=plot_name,
+ save=True,
+ plot_kwargs={
+ 'micro': False,
+ 'macro': False,
+ 'per_class': False,
+ 'binary': True
+ }
+ )
+ self.plots[plot_name] = plot_path
+ continue
+
+ plot_path = self.exp.plot_model(self.best_model,
+ plot=plot_name, save=True)
+ self.plots[plot_name] = plot_path
+ except Exception as e:
+ LOG.error(f"Error generating plot {plot_name}: {e}")
+ continue
+
+ def generate_plots_explainer(self):
+ LOG.info("Generating and saving plots from explainer")
+
+ from explainerdashboard import ClassifierExplainer
+
+ X_test = self.exp.X_test_transformed.copy()
+ y_test = self.exp.y_test_transformed
+
+ explainer = ClassifierExplainer(self.best_model, X_test, y_test)
+ self.expaliner = explainer
+ plots_explainer_html = ""
+
+ try:
+ fig_importance = explainer.plot_importances()
+ plots_explainer_html += add_plot_to_html(fig_importance)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot importance(mean shap): {e}")
+
+ try:
+ fig_importance_perm = explainer.plot_importances(
+ kind="permutation")
+ plots_explainer_html += add_plot_to_html(fig_importance_perm)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot importance(permutation): {e}")
+
+ # try:
+ # fig_shap = explainer.plot_shap_summary()
+ # plots_explainer_html += add_plot_to_html(fig_shap,
+ # include_plotlyjs=False)
+ # except Exception as e:
+ # LOG.error(f"Error generating plot shap: {e}")
+
+ # try:
+ # fig_contributions = explainer.plot_contributions(
+ # index=0)
+ # plots_explainer_html += add_plot_to_html(
+ # fig_contributions, include_plotlyjs=False)
+ # except Exception as e:
+ # LOG.error(f"Error generating plot contributions: {e}")
+
+ # try:
+ # for feature in self.features_name:
+ # fig_dependence = explainer.plot_dependence(col=feature)
+ # plots_explainer_html += add_plot_to_html(fig_dependence)
+ # except Exception as e:
+ # LOG.error(f"Error generating plot dependencies: {e}")
+
+ try:
+ for feature in self.features_name:
+ fig_pdp = explainer.plot_pdp(feature)
+ plots_explainer_html += add_plot_to_html(fig_pdp)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot pdp: {e}")
+
+ try:
+ for feature in self.features_name:
+ fig_interaction = explainer.plot_interaction(
+ col=feature, interact_col=feature)
+ plots_explainer_html += add_plot_to_html(fig_interaction)
+ except Exception as e:
+ LOG.error(f"Error generating plot interactions: {e}")
+
+ try:
+ for feature in self.features_name:
+ fig_interactions_importance = \
+ explainer.plot_interactions_importance(
+ col=feature)
+ plots_explainer_html += add_plot_to_html(
+ fig_interactions_importance)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot interactions importance: {e}")
+
+ # try:
+ # for feature in self.features_name:
+ # fig_interactions_detailed = \
+ # explainer.plot_interactions_detailed(
+ # col=feature)
+ # plots_explainer_html += add_plot_to_html(
+ # fig_interactions_detailed)
+ # except Exception as e:
+ # LOG.error(f"Error generating plot interactions detailed: {e}")
+
+ try:
+ fig_precision = explainer.plot_precision()
+ plots_explainer_html += add_plot_to_html(fig_precision)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot precision: {e}")
+
+ try:
+ fig_cumulative_precision = explainer.plot_cumulative_precision()
+ plots_explainer_html += add_plot_to_html(fig_cumulative_precision)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot cumulative precision: {e}")
+
+ try:
+ fig_classification = explainer.plot_classification()
+ plots_explainer_html += add_plot_to_html(fig_classification)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot classification: {e}")
+
+ try:
+ fig_confusion_matrix = explainer.plot_confusion_matrix()
+ plots_explainer_html += add_plot_to_html(fig_confusion_matrix)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot confusion matrix: {e}")
+
+ try:
+ fig_lift_curve = explainer.plot_lift_curve()
+ plots_explainer_html += add_plot_to_html(fig_lift_curve)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot lift curve: {e}")
+
+ try:
+ fig_roc_auc = explainer.plot_roc_auc()
+ plots_explainer_html += add_plot_to_html(fig_roc_auc)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot roc auc: {e}")
+
+ try:
+ fig_pr_auc = explainer.plot_pr_auc()
+ plots_explainer_html += add_plot_to_html(fig_pr_auc)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot pr auc: {e}")
+
+ self.plots_explainer_html = plots_explainer_html
diff -r 000000000000 -r 1f20fe57fdee pycaret_macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/pycaret_macros.xml Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,25 @@
+
+ 3.3.2
+ 0
+ @PYCARET_VERSION@+@SUFFIX@
+ 21.05
+
+
+ quay.io/goeckslab/galaxy-pycaret:3.3.2
+
+
+
+
+ @Manual{PyCaret,
+ author = {Moez Ali},
+ title = {PyCaret: An open source, low-code machine learning library in Python},
+ year = {2020},
+ month = {April},
+ note = {PyCaret version 1.0.0},
+ url = {https://www.pycaret.org}
+}
+
+
+
+
+
\ No newline at end of file
diff -r 000000000000 -r 1f20fe57fdee pycaret_predict.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/pycaret_predict.py Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,200 @@
+import argparse
+import logging
+import tempfile
+
+import h5py
+
+import joblib
+
+import pandas as pd
+
+from pycaret.classification import ClassificationExperiment
+from pycaret.regression import RegressionExperiment
+
+from sklearn.metrics import average_precision_score
+
+from utils import encode_image_to_base64, get_html_closing, get_html_template
+
+LOG = logging.getLogger(__name__)
+
+
+class PyCaretModelEvaluator:
+ def __init__(self, model_path, task, target):
+ self.model_path = model_path
+ self.task = task.lower()
+ self.model = self.load_h5_model()
+ self.target = target if target != "None" else None
+
+ def load_h5_model(self):
+ """Load a PyCaret model from an HDF5 file."""
+ with h5py.File(self.model_path, 'r') as f:
+ model_bytes = bytes(f['model'][()])
+ with tempfile.NamedTemporaryFile(delete=False) as temp_file:
+ temp_file.write(model_bytes)
+ temp_file.seek(0)
+ loaded_model = joblib.load(temp_file.name)
+ return loaded_model
+
+ def evaluate(self, data_path):
+ """Evaluate the model using the specified data."""
+ raise NotImplementedError("Subclasses must implement this method")
+
+
+class ClassificationEvaluator(PyCaretModelEvaluator):
+ def evaluate(self, data_path):
+ metrics = None
+ plot_paths = {}
+ data = pd.read_csv(data_path, engine='python', sep=None)
+ if self.target:
+ exp = ClassificationExperiment()
+ names = data.columns.to_list()
+ LOG.error(f"Column names: {names}")
+ target_index = int(self.target)-1
+ target_name = names[target_index]
+ exp.setup(data, target=target_name, test_data=data, index=False)
+ exp.add_metric(id='PR-AUC-Weighted',
+ name='PR-AUC-Weighted',
+ target='pred_proba',
+ score_func=average_precision_score,
+ average='weighted')
+ predictions = exp.predict_model(self.model)
+ metrics = exp.pull()
+ plots = ['confusion_matrix', 'auc', 'threshold', 'pr',
+ 'error', 'class_report', 'learning', 'calibration',
+ 'vc', 'dimension', 'manifold', 'rfe', 'feature',
+ 'feature_all']
+ for plot_name in plots:
+ try:
+ if plot_name == 'auc' and not exp.is_multiclass:
+ plot_path = exp.plot_model(self.model,
+ plot=plot_name,
+ save=True,
+ plot_kwargs={
+ 'micro': False,
+ 'macro': False,
+ 'per_class': False,
+ 'binary': True
+ })
+ plot_paths[plot_name] = plot_path
+ continue
+
+ plot_path = exp.plot_model(self.model,
+ plot=plot_name, save=True)
+ plot_paths[plot_name] = plot_path
+ except Exception as e:
+ LOG.error(f"Error generating plot {plot_name}: {e}")
+ continue
+ generate_html_report(plot_paths, metrics)
+
+ else:
+ exp = ClassificationExperiment()
+ exp.setup(data, target=None, test_data=data, index=False)
+ predictions = exp.predict_model(self.model, data=data)
+
+ return predictions, metrics, plot_paths
+
+
+class RegressionEvaluator(PyCaretModelEvaluator):
+ def evaluate(self, data_path):
+ metrics = None
+ plot_paths = {}
+ data = pd.read_csv(data_path, engine='python', sep=None)
+ if self.target:
+ names = data.columns.to_list()
+ target_index = int(self.target)-1
+ target_name = names[target_index]
+ exp = RegressionExperiment()
+ exp.setup(data, target=target_name, test_data=data, index=False)
+ predictions = exp.predict_model(self.model)
+ metrics = exp.pull()
+ plots = ['residuals', 'error', 'cooks',
+ 'learning', 'vc', 'manifold',
+ 'rfe', 'feature', 'feature_all']
+ for plot_name in plots:
+ try:
+ plot_path = exp.plot_model(self.model,
+ plot=plot_name, save=True)
+ plot_paths[plot_name] = plot_path
+ except Exception as e:
+ LOG.error(f"Error generating plot {plot_name}: {e}")
+ continue
+ generate_html_report(plot_paths, metrics)
+ else:
+ exp = RegressionExperiment()
+ exp.setup(data, target=None, test_data=data, index=False)
+ predictions = exp.predict_model(self.model, data=data)
+
+ return predictions, metrics, plot_paths
+
+
+def generate_html_report(plots, metrics):
+ """Generate an HTML evaluation report."""
+ plots_html = ""
+ for plot_name, plot_path in plots.items():
+ encoded_image = encode_image_to_base64(plot_path)
+ plots_html += f"""
+
+
{plot_name.capitalize()}
+
+
+ """
+
+ metrics_html = metrics.to_html(index=False, classes="table")
+
+ html_content = f"""
+ {get_html_template()}
+ Model Evaluation Report
+
+
+
+
Plots
+ {plots_html}
+
+ {get_html_closing()}
+ """
+
+ # Save HTML report
+ with open("evaluation_report.html", "w") as html_file:
+ html_file.write(html_content)
+
+
+if __name__ == "__main__":
+ parser = argparse.ArgumentParser(
+ description="Evaluate a PyCaret model stored in HDF5 format.")
+ parser.add_argument("--model_path",
+ type=str,
+ help="Path to the HDF5 model file.")
+ parser.add_argument("--data_path",
+ type=str,
+ help="Path to the evaluation data CSV file.")
+ parser.add_argument("--task",
+ type=str,
+ choices=["classification", "regression"],
+ help="Specify the task: classification or regression.")
+ parser.add_argument("--target",
+ default=None,
+ help="Column number of the target")
+ args = parser.parse_args()
+
+ if args.task == "classification":
+ evaluator = ClassificationEvaluator(
+ args.model_path, args.task, args.target)
+ elif args.task == "regression":
+ evaluator = RegressionEvaluator(
+ args.model_path, args.task, args.target)
+ else:
+ raise ValueError(
+ "Unsupported task type. Use 'classification' or 'regression'.")
+
+ predictions, metrics, plots = evaluator.evaluate(args.data_path)
+
+ predictions.to_csv("predictions.csv", index=False)
diff -r 000000000000 -r 1f20fe57fdee pycaret_predict.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/pycaret_predict.xml Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,61 @@
+
+ predicts/evaluates your pycaret ML model on a dataset.
+
+ pycaret_macros.xml
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ target_feature
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ This tool uses PyCaret to evaluate a machine learning model or do prediction.
+
+ **Outputs**:
+
+ - **prediction**: The prediction results on the dataset in a csv format.
+
+ - **report**: The evaluation report is generated in HTML format.
+ if you upload a dataset with a target column and select the target column in the target_feature input field.
+
+
+
+
\ No newline at end of file
diff -r 000000000000 -r 1f20fe57fdee pycaret_regression.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/pycaret_regression.py Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,134 @@
+import logging
+
+from base_model_trainer import BaseModelTrainer
+
+from dashboard import generate_regression_explainer_dashboard
+
+from pycaret.regression import RegressionExperiment
+
+from utils import add_hr_to_html, add_plot_to_html
+
+LOG = logging.getLogger(__name__)
+
+
+class RegressionModelTrainer(BaseModelTrainer):
+ def __init__(
+ self,
+ input_file,
+ target_col,
+ output_dir,
+ task_type,
+ random_seed,
+ test_file=None,
+ **kwargs):
+ super().__init__(
+ input_file,
+ target_col,
+ output_dir,
+ task_type,
+ random_seed,
+ test_file,
+ **kwargs)
+ self.exp = RegressionExperiment()
+
+ def save_dashboard(self):
+ LOG.info("Saving explainer dashboard")
+ dashboard = generate_regression_explainer_dashboard(self.exp,
+ self.best_model)
+ dashboard.save_html("dashboard.html")
+
+ def generate_plots(self):
+ LOG.info("Generating and saving plots")
+ plots = ['residuals', 'error', 'cooks',
+ 'learning', 'vc', 'manifold',
+ 'rfe', 'feature', 'feature_all']
+ for plot_name in plots:
+ try:
+ plot_path = self.exp.plot_model(self.best_model,
+ plot=plot_name, save=True)
+ self.plots[plot_name] = plot_path
+ except Exception as e:
+ LOG.error(f"Error generating plot {plot_name}: {e}")
+ continue
+
+ def generate_plots_explainer(self):
+ LOG.info("Generating and saving plots from explainer")
+
+ from explainerdashboard import RegressionExplainer
+
+ X_test = self.exp.X_test_transformed.copy()
+ y_test = self.exp.y_test_transformed
+
+ explainer = RegressionExplainer(self.best_model, X_test, y_test)
+ self.expaliner = explainer
+ plots_explainer_html = ""
+
+ try:
+ fig_importance = explainer.plot_importances()
+ plots_explainer_html += add_plot_to_html(fig_importance)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot importance: {e}")
+
+ try:
+ fig_importance_permutation = \
+ explainer.plot_importances_permutation(
+ kind="permutation")
+ plots_explainer_html += add_plot_to_html(
+ fig_importance_permutation)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot importance permutation: {e}")
+
+ try:
+ for feature in self.features_name:
+ fig_shap = explainer.plot_pdp(feature)
+ plots_explainer_html += add_plot_to_html(fig_shap)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot shap dependence: {e}")
+
+ # try:
+ # for feature in self.features_name:
+ # fig_interaction = explainer.plot_interaction(col=feature)
+ # plots_explainer_html += add_plot_to_html(fig_interaction)
+ # except Exception as e:
+ # LOG.error(f"Error generating plot shap interaction: {e}")
+
+ try:
+ for feature in self.features_name:
+ fig_interactions_importance = \
+ explainer.plot_interactions_importance(
+ col=feature)
+ plots_explainer_html += add_plot_to_html(
+ fig_interactions_importance)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot shap summary: {e}")
+
+ # Regression specific plots
+ try:
+ fig_pred_actual = explainer.plot_predicted_vs_actual()
+ plots_explainer_html += add_plot_to_html(fig_pred_actual)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot prediction vs actual: {e}")
+
+ try:
+ fig_residuals = explainer.plot_residuals()
+ plots_explainer_html += add_plot_to_html(fig_residuals)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot residuals: {e}")
+
+ try:
+ for feature in self.features_name:
+ fig_residuals_vs_feature = \
+ explainer.plot_residuals_vs_feature(feature)
+ plots_explainer_html += add_plot_to_html(
+ fig_residuals_vs_feature)
+ plots_explainer_html += add_hr_to_html()
+ except Exception as e:
+ LOG.error(f"Error generating plot residuals vs feature: {e}")
+
+ self.plots_explainer_html = plots_explainer_html
diff -r 000000000000 -r 1f20fe57fdee pycaret_train.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/pycaret_train.py Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,117 @@
+import argparse
+import logging
+
+from pycaret_classification import ClassificationModelTrainer
+
+from pycaret_regression import RegressionModelTrainer
+
+logging.basicConfig(level=logging.DEBUG)
+LOG = logging.getLogger(__name__)
+
+
+def main():
+ parser = argparse.ArgumentParser()
+ parser.add_argument("--input_file", help="Path to the input file")
+ parser.add_argument("--target_col", help="Column number of the target")
+ parser.add_argument("--output_dir",
+ help="Path to the output directory")
+ parser.add_argument("--model_type",
+ choices=["classification", "regression"],
+ help="Type of the model")
+ parser.add_argument("--train_size", type=float,
+ default=None,
+ help="Train size for PyCaret setup")
+ parser.add_argument("--normalize", action="store_true",
+ default=None,
+ help="Normalize data for PyCaret setup")
+ parser.add_argument("--feature_selection", action="store_true",
+ default=None,
+ help="Perform feature selection for PyCaret setup")
+ parser.add_argument("--cross_validation", action="store_true",
+ default=None,
+ help="Perform cross-validation for PyCaret setup")
+ parser.add_argument("--cross_validation_folds", type=int,
+ default=None,
+ help="Number of cross-validation folds \
+ for PyCaret setup")
+ parser.add_argument("--remove_outliers", action="store_true",
+ default=None,
+ help="Remove outliers for PyCaret setup")
+ parser.add_argument("--remove_multicollinearity", action="store_true",
+ default=None,
+ help="Remove multicollinearity for PyCaret setup")
+ parser.add_argument("--polynomial_features", action="store_true",
+ default=None,
+ help="Generate polynomial features for PyCaret setup")
+ parser.add_argument("--feature_interaction", action="store_true",
+ default=None,
+ help="Generate feature interactions for PyCaret setup")
+ parser.add_argument("--feature_ratio", action="store_true",
+ default=None,
+ help="Generate feature ratios for PyCaret setup")
+ parser.add_argument("--fix_imbalance", action="store_true",
+ default=None,
+ help="Fix class imbalance for PyCaret setup")
+ parser.add_argument("--models", nargs='+',
+ default=None,
+ help="Selected models for training")
+ parser.add_argument("--random_seed", type=int,
+ default=42,
+ help="Random seed for PyCaret setup")
+ parser.add_argument("--test_file", type=str, default=None,
+ help="Path to the test data file")
+
+ args = parser.parse_args()
+
+ model_kwargs = {
+ "train_size": args.train_size,
+ "normalize": args.normalize,
+ "feature_selection": args.feature_selection,
+ "cross_validation": args.cross_validation,
+ "cross_validation_folds": args.cross_validation_folds,
+ "remove_outliers": args.remove_outliers,
+ "remove_multicollinearity": args.remove_multicollinearity,
+ "polynomial_features": args.polynomial_features,
+ "feature_interaction": args.feature_interaction,
+ "feature_ratio": args.feature_ratio,
+ "fix_imbalance": args.fix_imbalance,
+ }
+ LOG.info(f"Model kwargs: {model_kwargs}")
+
+ # Remove None values from model_kwargs
+
+ LOG.info(f"Model kwargs 2: {model_kwargs}")
+ if args.models:
+ model_kwargs["models"] = args.models[0].split(",")
+
+ model_kwargs = {k: v for k, v in model_kwargs.items() if v is not None}
+
+ if args.model_type == "classification":
+ trainer = ClassificationModelTrainer(
+ args.input_file,
+ args.target_col,
+ args.output_dir,
+ args.model_type,
+ args.random_seed,
+ args.test_file,
+ **model_kwargs)
+ elif args.model_type == "regression":
+ if "fix_imbalance" in model_kwargs:
+ del model_kwargs["fix_imbalance"]
+ trainer = RegressionModelTrainer(
+ args.input_file,
+ args.target_col,
+ args.output_dir,
+ args.model_type,
+ args.random_seed,
+ args.test_file,
+ **model_kwargs)
+ else:
+ LOG.error("Invalid model type. Please choose \
+ 'classification' or 'regression'.")
+ return
+ trainer.run()
+
+
+if __name__ == "__main__":
+ main()
diff -r 000000000000 -r 1f20fe57fdee test-data/auto-mpg.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/auto-mpg.tsv Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,399 @@
+MPG Cylinders Displacement Horsepower Weight Acceleration ModelYear Origin
+18.0 8 307.0 130.0 3504. 12.0 70 1
+15.0 8 350.0 165.0 3693. 11.5 70 1
+18.0 8 318.0 150.0 3436. 11.0 70 1
+16.0 8 304.0 150.0 3433. 12.0 70 1
+17.0 8 302.0 140.0 3449. 10.5 70 1
+15.0 8 429.0 198.0 4341. 10.0 70 1
+14.0 8 454.0 220.0 4354. 9.0 70 1
+14.0 8 440.0 215.0 4312. 8.5 70 1
+14.0 8 455.0 225.0 4425. 10.0 70 1
+15.0 8 390.0 190.0 3850. 8.5 70 1
+15.0 8 383.0 170.0 3563. 10.0 70 1
+14.0 8 340.0 160.0 3609. 8.0 70 1
+15.0 8 400.0 150.0 3761. 9.5 70 1
+14.0 8 455.0 225.0 3086. 10.0 70 1
+24.0 4 113.0 95.00 2372. 15.0 70 3
+22.0 6 198.0 95.00 2833. 15.5 70 1
+18.0 6 199.0 97.00 2774. 15.5 70 1
+21.0 6 200.0 85.00 2587. 16.0 70 1
+27.0 4 97.00 88.00 2130. 14.5 70 3
+26.0 4 97.00 46.00 1835. 20.5 70 2
+25.0 4 110.0 87.00 2672. 17.5 70 2
+24.0 4 107.0 90.00 2430. 14.5 70 2
+25.0 4 104.0 95.00 2375. 17.5 70 2
+26.0 4 121.0 113.0 2234. 12.5 70 2
+21.0 6 199.0 90.00 2648. 15.0 70 1
+10.0 8 360.0 215.0 4615. 14.0 70 1
+10.0 8 307.0 200.0 4376. 15.0 70 1
+11.0 8 318.0 210.0 4382. 13.5 70 1
+9.0 8 304.0 193.0 4732. 18.5 70 1
+27.0 4 97.00 88.00 2130. 14.5 71 3
+28.0 4 140.0 90.00 2264. 15.5 71 1
+25.0 4 113.0 95.00 2228. 14.0 71 3
+25.0 4 98.00 ? 2046. 19.0 71 1
+19.0 6 232.0 100.0 2634. 13.0 71 1
+16.0 6 225.0 105.0 3439. 15.5 71 1
+17.0 6 250.0 100.0 3329. 15.5 71 1
+19.0 6 250.0 88.00 3302. 15.5 71 1
+18.0 6 232.0 100.0 3288. 15.5 71 1
+14.0 8 350.0 165.0 4209. 12.0 71 1
+14.0 8 400.0 175.0 4464. 11.5 71 1
+14.0 8 351.0 153.0 4154. 13.5 71 1
+14.0 8 318.0 150.0 4096. 13.0 71 1
+12.0 8 383.0 180.0 4955. 11.5 71 1
+13.0 8 400.0 170.0 4746. 12.0 71 1
+13.0 8 400.0 175.0 5140. 12.0 71 1
+18.0 6 258.0 110.0 2962. 13.5 71 1
+22.0 4 140.0 72.00 2408. 19.0 71 1
+19.0 6 250.0 100.0 3282. 15.0 71 1
+18.0 6 250.0 88.00 3139. 14.5 71 1
+23.0 4 122.0 86.00 2220. 14.0 71 1
+28.0 4 116.0 90.00 2123. 14.0 71 2
+30.0 4 79.00 70.00 2074. 19.5 71 2
+30.0 4 88.00 76.00 2065. 14.5 71 2
+31.0 4 71.00 65.00 1773. 19.0 71 3
+35.0 4 72.00 69.00 1613. 18.0 71 3
+27.0 4 97.00 60.00 1834. 19.0 71 2
+26.0 4 91.00 70.00 1955. 20.5 71 1
+24.0 4 113.0 95.00 2278. 15.5 72 3
+25.0 4 97.50 80.00 2126. 17.0 72 1
+23.0 4 97.00 54.00 2254. 23.5 72 2
+20.0 4 140.0 90.00 2408. 19.5 72 1
+21.0 4 122.0 86.00 2226. 16.5 72 1
+13.0 8 350.0 165.0 4274. 12.0 72 1
+14.0 8 400.0 175.0 4385. 12.0 72 1
+15.0 8 318.0 150.0 4135. 13.5 72 1
+14.0 8 351.0 153.0 4129. 13.0 72 1
+17.0 8 304.0 150.0 3672. 11.5 72 1
+11.0 8 429.0 208.0 4633. 11.0 72 1
+13.0 8 350.0 155.0 4502. 13.5 72 1
+12.0 8 350.0 160.0 4456. 13.5 72 1
+13.0 8 400.0 190.0 4422. 12.5 72 1
+19.0 3 70.00 97.00 2330. 13.5 72 3
+15.0 8 304.0 150.0 3892. 12.5 72 1
+13.0 8 307.0 130.0 4098. 14.0 72 1
+13.0 8 302.0 140.0 4294. 16.0 72 1
+14.0 8 318.0 150.0 4077. 14.0 72 1
+18.0 4 121.0 112.0 2933. 14.5 72 2
+22.0 4 121.0 76.00 2511. 18.0 72 2
+21.0 4 120.0 87.00 2979. 19.5 72 2
+26.0 4 96.00 69.00 2189. 18.0 72 2
+22.0 4 122.0 86.00 2395. 16.0 72 1
+28.0 4 97.00 92.00 2288. 17.0 72 3
+23.0 4 120.0 97.00 2506. 14.5 72 3
+28.0 4 98.00 80.00 2164. 15.0 72 1
+27.0 4 97.00 88.00 2100. 16.5 72 3
+13.0 8 350.0 175.0 4100. 13.0 73 1
+14.0 8 304.0 150.0 3672. 11.5 73 1
+13.0 8 350.0 145.0 3988. 13.0 73 1
+14.0 8 302.0 137.0 4042. 14.5 73 1
+15.0 8 318.0 150.0 3777. 12.5 73 1
+12.0 8 429.0 198.0 4952. 11.5 73 1
+13.0 8 400.0 150.0 4464. 12.0 73 1
+13.0 8 351.0 158.0 4363. 13.0 73 1
+14.0 8 318.0 150.0 4237. 14.5 73 1
+13.0 8 440.0 215.0 4735. 11.0 73 1
+12.0 8 455.0 225.0 4951. 11.0 73 1
+13.0 8 360.0 175.0 3821. 11.0 73 1
+18.0 6 225.0 105.0 3121. 16.5 73 1
+16.0 6 250.0 100.0 3278. 18.0 73 1
+18.0 6 232.0 100.0 2945. 16.0 73 1
+18.0 6 250.0 88.00 3021. 16.5 73 1
+23.0 6 198.0 95.00 2904. 16.0 73 1
+26.0 4 97.00 46.00 1950. 21.0 73 2
+11.0 8 400.0 150.0 4997. 14.0 73 1
+12.0 8 400.0 167.0 4906. 12.5 73 1
+13.0 8 360.0 170.0 4654. 13.0 73 1
+12.0 8 350.0 180.0 4499. 12.5 73 1
+18.0 6 232.0 100.0 2789. 15.0 73 1
+20.0 4 97.00 88.00 2279. 19.0 73 3
+21.0 4 140.0 72.00 2401. 19.5 73 1
+22.0 4 108.0 94.00 2379. 16.5 73 3
+18.0 3 70.00 90.00 2124. 13.5 73 3
+19.0 4 122.0 85.00 2310. 18.5 73 1
+21.0 6 155.0 107.0 2472. 14.0 73 1
+26.0 4 98.00 90.00 2265. 15.5 73 2
+15.0 8 350.0 145.0 4082. 13.0 73 1
+16.0 8 400.0 230.0 4278. 9.50 73 1
+29.0 4 68.00 49.00 1867. 19.5 73 2
+24.0 4 116.0 75.00 2158. 15.5 73 2
+20.0 4 114.0 91.00 2582. 14.0 73 2
+19.0 4 121.0 112.0 2868. 15.5 73 2
+15.0 8 318.0 150.0 3399. 11.0 73 1
+24.0 4 121.0 110.0 2660. 14.0 73 2
+20.0 6 156.0 122.0 2807. 13.5 73 3
+11.0 8 350.0 180.0 3664. 11.0 73 1
+20.0 6 198.0 95.00 3102. 16.5 74 1
+21.0 6 200.0 ? 2875. 17.0 74 1
+19.0 6 232.0 100.0 2901. 16.0 74 1
+15.0 6 250.0 100.0 3336. 17.0 74 1
+31.0 4 79.00 67.00 1950. 19.0 74 3
+26.0 4 122.0 80.00 2451. 16.5 74 1
+32.0 4 71.00 65.00 1836. 21.0 74 3
+25.0 4 140.0 75.00 2542. 17.0 74 1
+16.0 6 250.0 100.0 3781. 17.0 74 1
+16.0 6 258.0 110.0 3632. 18.0 74 1
+18.0 6 225.0 105.0 3613. 16.5 74 1
+16.0 8 302.0 140.0 4141. 14.0 74 1
+13.0 8 350.0 150.0 4699. 14.5 74 1
+14.0 8 318.0 150.0 4457. 13.5 74 1
+14.0 8 302.0 140.0 4638. 16.0 74 1
+14.0 8 304.0 150.0 4257. 15.5 74 1
+29.0 4 98.00 83.00 2219. 16.5 74 2
+26.0 4 79.00 67.00 1963. 15.5 74 2
+26.0 4 97.00 78.00 2300. 14.5 74 2
+31.0 4 76.00 52.00 1649. 16.5 74 3
+32.0 4 83.00 61.00 2003. 19.0 74 3
+28.0 4 90.00 75.00 2125. 14.5 74 1
+24.0 4 90.00 75.00 2108. 15.5 74 2
+26.0 4 116.0 75.00 2246. 14.0 74 2
+24.0 4 120.0 97.00 2489. 15.0 74 3
+26.0 4 108.0 93.00 2391. 15.5 74 3
+31.0 4 79.00 67.00 2000. 16.0 74 2
+19.0 6 225.0 95.00 3264. 16.0 75 1
+18.0 6 250.0 105.0 3459. 16.0 75 1
+15.0 6 250.0 72.00 3432. 21.0 75 1
+15.0 6 250.0 72.00 3158. 19.5 75 1
+16.0 8 400.0 170.0 4668. 11.5 75 1
+15.0 8 350.0 145.0 4440. 14.0 75 1
+16.0 8 318.0 150.0 4498. 14.5 75 1
+14.0 8 351.0 148.0 4657. 13.5 75 1
+17.0 6 231.0 110.0 3907. 21.0 75 1
+16.0 6 250.0 105.0 3897. 18.5 75 1
+15.0 6 258.0 110.0 3730. 19.0 75 1
+18.0 6 225.0 95.00 3785. 19.0 75 1
+21.0 6 231.0 110.0 3039. 15.0 75 1
+20.0 8 262.0 110.0 3221. 13.5 75 1
+13.0 8 302.0 129.0 3169. 12.0 75 1
+29.0 4 97.00 75.00 2171. 16.0 75 3
+23.0 4 140.0 83.00 2639. 17.0 75 1
+20.0 6 232.0 100.0 2914. 16.0 75 1
+23.0 4 140.0 78.00 2592. 18.5 75 1
+24.0 4 134.0 96.00 2702. 13.5 75 3
+25.0 4 90.00 71.00 2223. 16.5 75 2
+24.0 4 119.0 97.00 2545. 17.0 75 3
+18.0 6 171.0 97.00 2984. 14.5 75 1
+29.0 4 90.00 70.00 1937. 14.0 75 2
+19.0 6 232.0 90.00 3211. 17.0 75 1
+23.0 4 115.0 95.00 2694. 15.0 75 2
+23.0 4 120.0 88.00 2957. 17.0 75 2
+22.0 4 121.0 98.00 2945. 14.5 75 2
+25.0 4 121.0 115.0 2671. 13.5 75 2
+33.0 4 91.00 53.00 1795. 17.5 75 3
+28.0 4 107.0 86.00 2464. 15.5 76 2
+25.0 4 116.0 81.00 2220. 16.9 76 2
+25.0 4 140.0 92.00 2572. 14.9 76 1
+26.0 4 98.00 79.00 2255. 17.7 76 1
+27.0 4 101.0 83.00 2202. 15.3 76 2
+17.5 8 305.0 140.0 4215. 13.0 76 1
+16.0 8 318.0 150.0 4190. 13.0 76 1
+15.5 8 304.0 120.0 3962. 13.9 76 1
+14.5 8 351.0 152.0 4215. 12.8 76 1
+22.0 6 225.0 100.0 3233. 15.4 76 1
+22.0 6 250.0 105.0 3353. 14.5 76 1
+24.0 6 200.0 81.00 3012. 17.6 76 1
+22.5 6 232.0 90.00 3085. 17.6 76 1
+29.0 4 85.00 52.00 2035. 22.2 76 1
+24.5 4 98.00 60.00 2164. 22.1 76 1
+29.0 4 90.00 70.00 1937. 14.2 76 2
+33.0 4 91.00 53.00 1795. 17.4 76 3
+20.0 6 225.0 100.0 3651. 17.7 76 1
+18.0 6 250.0 78.00 3574. 21.0 76 1
+18.5 6 250.0 110.0 3645. 16.2 76 1
+17.5 6 258.0 95.00 3193. 17.8 76 1
+29.5 4 97.00 71.00 1825. 12.2 76 2
+32.0 4 85.00 70.00 1990. 17.0 76 3
+28.0 4 97.00 75.00 2155. 16.4 76 3
+26.5 4 140.0 72.00 2565. 13.6 76 1
+20.0 4 130.0 102.0 3150. 15.7 76 2
+13.0 8 318.0 150.0 3940. 13.2 76 1
+19.0 4 120.0 88.00 3270. 21.9 76 2
+19.0 6 156.0 108.0 2930. 15.5 76 3
+16.5 6 168.0 120.0 3820. 16.7 76 2
+16.5 8 350.0 180.0 4380. 12.1 76 1
+13.0 8 350.0 145.0 4055. 12.0 76 1
+13.0 8 302.0 130.0 3870. 15.0 76 1
+13.0 8 318.0 150.0 3755. 14.0 76 1
+31.5 4 98.00 68.00 2045. 18.5 77 3
+30.0 4 111.0 80.00 2155. 14.8 77 1
+36.0 4 79.00 58.00 1825. 18.6 77 2
+25.5 4 122.0 96.00 2300. 15.5 77 1
+33.5 4 85.00 70.00 1945. 16.8 77 3
+17.5 8 305.0 145.0 3880. 12.5 77 1
+17.0 8 260.0 110.0 4060. 19.0 77 1
+15.5 8 318.0 145.0 4140. 13.7 77 1
+15.0 8 302.0 130.0 4295. 14.9 77 1
+17.5 6 250.0 110.0 3520. 16.4 77 1
+20.5 6 231.0 105.0 3425. 16.9 77 1
+19.0 6 225.0 100.0 3630. 17.7 77 1
+18.5 6 250.0 98.00 3525. 19.0 77 1
+16.0 8 400.0 180.0 4220. 11.1 77 1
+15.5 8 350.0 170.0 4165. 11.4 77 1
+15.5 8 400.0 190.0 4325. 12.2 77 1
+16.0 8 351.0 149.0 4335. 14.5 77 1
+29.0 4 97.00 78.00 1940. 14.5 77 2
+24.5 4 151.0 88.00 2740. 16.0 77 1
+26.0 4 97.00 75.00 2265. 18.2 77 3
+25.5 4 140.0 89.00 2755. 15.8 77 1
+30.5 4 98.00 63.00 2051. 17.0 77 1
+33.5 4 98.00 83.00 2075. 15.9 77 1
+30.0 4 97.00 67.00 1985. 16.4 77 3
+30.5 4 97.00 78.00 2190. 14.1 77 2
+22.0 6 146.0 97.00 2815. 14.5 77 3
+21.5 4 121.0 110.0 2600. 12.8 77 2
+21.5 3 80.00 110.0 2720. 13.5 77 3
+43.1 4 90.00 48.00 1985. 21.5 78 2
+36.1 4 98.00 66.00 1800. 14.4 78 1
+32.8 4 78.00 52.00 1985. 19.4 78 3
+39.4 4 85.00 70.00 2070. 18.6 78 3
+36.1 4 91.00 60.00 1800. 16.4 78 3
+19.9 8 260.0 110.0 3365. 15.5 78 1
+19.4 8 318.0 140.0 3735. 13.2 78 1
+20.2 8 302.0 139.0 3570. 12.8 78 1
+19.2 6 231.0 105.0 3535. 19.2 78 1
+20.5 6 200.0 95.00 3155. 18.2 78 1
+20.2 6 200.0 85.00 2965. 15.8 78 1
+25.1 4 140.0 88.00 2720. 15.4 78 1
+20.5 6 225.0 100.0 3430. 17.2 78 1
+19.4 6 232.0 90.00 3210. 17.2 78 1
+20.6 6 231.0 105.0 3380. 15.8 78 1
+20.8 6 200.0 85.00 3070. 16.7 78 1
+18.6 6 225.0 110.0 3620. 18.7 78 1
+18.1 6 258.0 120.0 3410. 15.1 78 1
+19.2 8 305.0 145.0 3425. 13.2 78 1
+17.7 6 231.0 165.0 3445. 13.4 78 1
+18.1 8 302.0 139.0 3205. 11.2 78 1
+17.5 8 318.0 140.0 4080. 13.7 78 1
+30.0 4 98.00 68.00 2155. 16.5 78 1
+27.5 4 134.0 95.00 2560. 14.2 78 3
+27.2 4 119.0 97.00 2300. 14.7 78 3
+30.9 4 105.0 75.00 2230. 14.5 78 1
+21.1 4 134.0 95.00 2515. 14.8 78 3
+23.2 4 156.0 105.0 2745. 16.7 78 1
+23.8 4 151.0 85.00 2855. 17.6 78 1
+23.9 4 119.0 97.00 2405. 14.9 78 3
+20.3 5 131.0 103.0 2830. 15.9 78 2
+17.0 6 163.0 125.0 3140. 13.6 78 2
+21.6 4 121.0 115.0 2795. 15.7 78 2
+16.2 6 163.0 133.0 3410. 15.8 78 2
+31.5 4 89.00 71.00 1990. 14.9 78 2
+29.5 4 98.00 68.00 2135. 16.6 78 3
+21.5 6 231.0 115.0 3245. 15.4 79 1
+19.8 6 200.0 85.00 2990. 18.2 79 1
+22.3 4 140.0 88.00 2890. 17.3 79 1
+20.2 6 232.0 90.00 3265. 18.2 79 1
+20.6 6 225.0 110.0 3360. 16.6 79 1
+17.0 8 305.0 130.0 3840. 15.4 79 1
+17.6 8 302.0 129.0 3725. 13.4 79 1
+16.5 8 351.0 138.0 3955. 13.2 79 1
+18.2 8 318.0 135.0 3830. 15.2 79 1
+16.9 8 350.0 155.0 4360. 14.9 79 1
+15.5 8 351.0 142.0 4054. 14.3 79 1
+19.2 8 267.0 125.0 3605. 15.0 79 1
+18.5 8 360.0 150.0 3940. 13.0 79 1
+31.9 4 89.00 71.00 1925. 14.0 79 2
+34.1 4 86.00 65.00 1975. 15.2 79 3
+35.7 4 98.00 80.00 1915. 14.4 79 1
+27.4 4 121.0 80.00 2670. 15.0 79 1
+25.4 5 183.0 77.00 3530. 20.1 79 2
+23.0 8 350.0 125.0 3900. 17.4 79 1
+27.2 4 141.0 71.00 3190. 24.8 79 2
+23.9 8 260.0 90.00 3420. 22.2 79 1
+34.2 4 105.0 70.00 2200. 13.2 79 1
+34.5 4 105.0 70.00 2150. 14.9 79 1
+31.8 4 85.00 65.00 2020. 19.2 79 3
+37.3 4 91.00 69.00 2130. 14.7 79 2
+28.4 4 151.0 90.00 2670. 16.0 79 1
+28.8 6 173.0 115.0 2595. 11.3 79 1
+26.8 6 173.0 115.0 2700. 12.9 79 1
+33.5 4 151.0 90.00 2556. 13.2 79 1
+41.5 4 98.00 76.00 2144. 14.7 80 2
+38.1 4 89.00 60.00 1968. 18.8 80 3
+32.1 4 98.00 70.00 2120. 15.5 80 1
+37.2 4 86.00 65.00 2019. 16.4 80 3
+28.0 4 151.0 90.00 2678. 16.5 80 1
+26.4 4 140.0 88.00 2870. 18.1 80 1
+24.3 4 151.0 90.00 3003. 20.1 80 1
+19.1 6 225.0 90.00 3381. 18.7 80 1
+34.3 4 97.00 78.00 2188. 15.8 80 2
+29.8 4 134.0 90.00 2711. 15.5 80 3
+31.3 4 120.0 75.00 2542. 17.5 80 3
+37.0 4 119.0 92.00 2434. 15.0 80 3
+32.2 4 108.0 75.00 2265. 15.2 80 3
+46.6 4 86.00 65.00 2110. 17.9 80 3
+27.9 4 156.0 105.0 2800. 14.4 80 1
+40.8 4 85.00 65.00 2110. 19.2 80 3
+44.3 4 90.00 48.00 2085. 21.7 80 2
+43.4 4 90.00 48.00 2335. 23.7 80 2
+36.4 5 121.0 67.00 2950. 19.9 80 2
+30.0 4 146.0 67.00 3250. 21.8 80 2
+44.6 4 91.00 67.00 1850. 13.8 80 3
+40.9 4 85.00 ? 1835. 17.3 80 2
+33.8 4 97.00 67.00 2145. 18.0 80 3
+29.8 4 89.00 62.00 1845. 15.3 80 2
+32.7 6 168.0 132.0 2910. 11.4 80 3
+23.7 3 70.00 100.0 2420. 12.5 80 3
+35.0 4 122.0 88.00 2500. 15.1 80 2
+23.6 4 140.0 ? 2905. 14.3 80 1
+32.4 4 107.0 72.00 2290. 17.0 80 3
+27.2 4 135.0 84.00 2490. 15.7 81 1
+26.6 4 151.0 84.00 2635. 16.4 81 1
+25.8 4 156.0 92.00 2620. 14.4 81 1
+23.5 6 173.0 110.0 2725. 12.6 81 1
+30.0 4 135.0 84.00 2385. 12.9 81 1
+39.1 4 79.00 58.00 1755. 16.9 81 3
+39.0 4 86.00 64.00 1875. 16.4 81 1
+35.1 4 81.00 60.00 1760. 16.1 81 3
+32.3 4 97.00 67.00 2065. 17.8 81 3
+37.0 4 85.00 65.00 1975. 19.4 81 3
+37.7 4 89.00 62.00 2050. 17.3 81 3
+34.1 4 91.00 68.00 1985. 16.0 81 3
+34.7 4 105.0 63.00 2215. 14.9 81 1
+34.4 4 98.00 65.00 2045. 16.2 81 1
+29.9 4 98.00 65.00 2380. 20.7 81 1
+33.0 4 105.0 74.00 2190. 14.2 81 2
+34.5 4 100.0 ? 2320. 15.8 81 2
+33.7 4 107.0 75.00 2210. 14.4 81 3
+32.4 4 108.0 75.00 2350. 16.8 81 3
+32.9 4 119.0 100.0 2615. 14.8 81 3
+31.6 4 120.0 74.00 2635. 18.3 81 3
+28.1 4 141.0 80.00 3230. 20.4 81 2
+30.7 6 145.0 76.00 3160. 19.6 81 2
+25.4 6 168.0 116.0 2900. 12.6 81 3
+24.2 6 146.0 120.0 2930. 13.8 81 3
+22.4 6 231.0 110.0 3415. 15.8 81 1
+26.6 8 350.0 105.0 3725. 19.0 81 1
+20.2 6 200.0 88.00 3060. 17.1 81 1
+17.6 6 225.0 85.00 3465. 16.6 81 1
+28.0 4 112.0 88.00 2605. 19.6 82 1
+27.0 4 112.0 88.00 2640. 18.6 82 1
+34.0 4 112.0 88.00 2395. 18.0 82 1
+31.0 4 112.0 85.00 2575. 16.2 82 1
+29.0 4 135.0 84.00 2525. 16.0 82 1
+27.0 4 151.0 90.00 2735. 18.0 82 1
+24.0 4 140.0 92.00 2865. 16.4 82 1
+23.0 4 151.0 ? 3035. 20.5 82 1
+36.0 4 105.0 74.00 1980. 15.3 82 2
+37.0 4 91.00 68.00 2025. 18.2 82 3
+31.0 4 91.00 68.00 1970. 17.6 82 3
+38.0 4 105.0 63.00 2125. 14.7 82 1
+36.0 4 98.00 70.00 2125. 17.3 82 1
+36.0 4 120.0 88.00 2160. 14.5 82 3
+36.0 4 107.0 75.00 2205. 14.5 82 3
+34.0 4 108.0 70.00 2245 16.9 82 3
+38.0 4 91.00 67.00 1965. 15.0 82 3
+32.0 4 91.00 67.00 1965. 15.7 82 3
+38.0 4 91.00 67.00 1995. 16.2 82 3
+25.0 6 181.0 110.0 2945. 16.4 82 1
+38.0 6 262.0 85.00 3015. 17.0 82 1
+26.0 4 156.0 92.00 2585. 14.5 82 1
+22.0 6 232.0 112.0 2835 14.7 82 1
+32.0 4 144.0 96.00 2665. 13.9 82 3
+36.0 4 135.0 84.00 2370. 13.0 82 1
+27.0 4 151.0 90.00 2950. 17.3 82 1
+27.0 4 140.0 86.00 2790. 15.6 82 1
+44.0 4 97.00 52.00 2130. 24.6 82 2
+32.0 4 135.0 84.00 2295. 11.6 82 1
+28.0 4 120.0 79.00 2625. 18.6 82 1
+31.0 4 119.0 82.00 2720. 19.4 82 1
diff -r 000000000000 -r 1f20fe57fdee test-data/evaluation_report_classification.html
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/evaluation_report_classification.html Wed Dec 11 04:59:43 2024 +0000
@@ -0,0 +1,236 @@
+
+
+
+
+ Model Training Report
+
+
+
+
+
+
Model Evaluation Report
+
+
+
Metrics
+
+
+
+
+ | Model |
+ Accuracy |
+ AUC |
+ Recall |
+ Prec. |
+ F1 |
+ Kappa |
+ MCC |
+ PR-AUC-Weighted |
+
+
+
+
+ | Light Gradient Boosting Machine |
+ 0.7826 |
+ 0.8162 |
+ 0.7419 |
+ 0.7667 |
+ 0.7541 |
+ 0.5594 |
+ 0.5596 |
+ 0.7753 |
+
+
+
+
+
+
+
Plots
+
+
+
Confusion_matrix
+
+
+
+
+
+
Auc
+
+
+
+
+
+
Threshold
+
+
+
+
+
+
Pr
+
+
+
+
+
+
Error
+
+
+
+
+
+
Class_report
+
+
+
+
+
+
Learning
+
+
+
+
+
+
Calibration
+
+
+
+
+
+
Vc
+
+
+
+
+
+
Dimension
+
+
+
+
+
+
Manifold
+
+
+
+
+
+
Rfe
+
+
+
+
+
+
Feature
+
+
+
+
+
+
Feature_all
+
+
+
+
+
+
+
+
+
Model Evaluation Report
+
+
+
Metrics
+
+
+
+
+ | Model |
+ MAE |
+ MSE |
+ RMSE |
+ R2 |
+ RMSLE |
+ MAPE |
+
+
+
+
+ | Gradient Boosting Regressor |
+ 1.6 |
+ 5.6214 |
+ 2.3709 |
+ 0.9077 |
+ 0.0875 |
+ 0.0691 |
+
+
+
+
+
+
+
Plots
+
+
+
Residuals
+
+
+
+
+
+
Error
+
+
+
+
+
+
Cooks
+
+
+
+
+
+
Learning
+
+
+
+
+
+
Vc
+
+
+
+
+
+
Manifold
+
+
+
+
+
+
Rfe
+
+
+
+
+
+
Feature
+
+
+
+
+
+
Feature_all
+
+
+
+
+
+
+
+
+
PyCaret Model Training Report
+
+
+ Setup & Best Model
+
+ Best Model Plots
+
+ Feature Importance
+
+ Explainer
+
+
+
+
Setup Parameters
+
+ | Parameter | Value |
|---|
+
+
+
+ | target |
+ PCR |
+
+
+ | session_id |
+ 42 |
+
+
+ | index |
+ False |
+
+
+
+
+
If you want to know all the experiment setup parameters,
+ please check the PyCaret documentation for
+ the classification/regression exp function.
+
Best Model: LGBMClassifier
+
+ | Parameter | Value |
|---|
+
+
+
+ | boosting_type |
+ gbdt |
+
+
+ | class_weight |
+ None |
+
+
+ | colsample_bytree |
+ 1.0 |
+
+
+ | importance_type |
+ split |
+
+
+ | learning_rate |
+ 0.1 |
+
+
+ | max_depth |
+ -1 |
+
+
+ | min_child_samples |
+ 20 |
+
+
+ | min_child_weight |
+ 0.001 |
+
+
+ | min_split_gain |
+ 0.0 |
+
+
+ | n_estimators |
+ 100 |
+
+
+ | n_jobs |
+ -1 |
+
+
+ | num_leaves |
+ 31 |
+
+
+ | objective |
+ None |
+
+
+ | random_state |
+ 42 |
+
+
+ | reg_alpha |
+ 0.0 |
+
+
+ | reg_lambda |
+ 0.0 |
+
+
+ | subsample |
+ 1.0 |
+
+
+ | subsample_for_bin |
+ 200000 |
+
+
+ | subsample_freq |
+ 0 |
+
+
+
+
+
Comparison Results on the Cross-Validation Set
+
+
+
+
+ | Model |
+ Accuracy |
+ ROC-AUC |
+ Recall |
+ Prec. |
+ F1 |
+ Kappa |
+ MCC |
+ PR-AUC-Weighted |
+ TT (Sec) |
+
+
+
+
+ | Light Gradient Boosting Machine |
+ 0.715 |
+ 0.6000 |
+ 0.6500 |
+ 0.6917 |
+ 0.6357 |
+ 0.4380 |
+ 0.4748 |
+ 0.6822 |
+ 0.228 |
+
+
+ | Logistic Regression |
+ 0.670 |
+ 0.6500 |
+ 0.7500 |
+ 0.6167 |
+ 0.6633 |
+ 0.3478 |
+ 0.3742 |
+ 0.7144 |
+ 0.331 |
+
+
+ | Ridge Classifier |
+ 0.670 |
+ 0.6167 |
+ 0.7500 |
+ 0.6167 |
+ 0.6633 |
+ 0.3478 |
+ 0.3742 |
+ 0.0000 |
+ 0.180 |
+
+
+ | Naive Bayes |
+ 0.650 |
+ 0.6333 |
+ 0.6833 |
+ 0.5917 |
+ 0.6257 |
+ 0.2969 |
+ 0.3112 |
+ 0.6978 |
+ 2.694 |
+
+
+ | Quadratic Discriminant Analysis |
+ 0.610 |
+ 0.6333 |
+ 0.4667 |
+ 0.5333 |
+ 0.4733 |
+ 0.2256 |
+ 0.2488 |
+ 0.7033 |
+ 0.158 |
+
+
+ | Linear Discriminant Analysis |
+ 0.605 |
+ 0.6000 |
+ 0.7000 |
+ 0.5900 |
+ 0.6105 |
+ 0.2372 |
+ 0.2577 |
+ 0.6594 |
+ 0.110 |
+
+
+ | CatBoost Classifier |
+ 0.595 |
+ 0.6167 |
+ 0.6167 |
+ 0.5500 |
+ 0.5600 |
+ 0.2165 |
+ 0.2207 |
+ 0.6861 |
+ 12.075 |
+
+
+ | Extra Trees Classifier |
+ 0.590 |
+ 0.6000 |
+ 0.5833 |
+ 0.5000 |
+ 0.5300 |
+ 0.2103 |
+ 0.2167 |
+ 0.6811 |
+ 0.775 |
+
+
+ | SVM - Linear Kernel |
+ 0.585 |
+ 0.6500 |
+ 0.5333 |
+ 0.4667 |
+ 0.4521 |
+ 0.1429 |
+ 0.1690 |
+ 0.0000 |
+ 0.217 |
+
+
+ | K Neighbors Classifier |
+ 0.565 |
+ 0.6292 |
+ 0.5000 |
+ 0.5750 |
+ 0.5057 |
+ 0.1413 |
+ 0.1469 |
+ 0.6717 |
+ 0.685 |
+
+
+ | Random Forest Classifier |
+ 0.555 |
+ 0.5667 |
+ 0.5833 |
+ 0.5167 |
+ 0.5233 |
+ 0.1524 |
+ 0.1540 |
+ 0.6211 |
+ 0.847 |
+
+
+ | Dummy Classifier |
+ 0.540 |
+ 0.5000 |
+ 0.0000 |
+ 0.0000 |
+ 0.0000 |
+ 0.0000 |
+ 0.0000 |
+ 0.4600 |
+ 0.165 |
+
+
+ | Ada Boost Classifier |
+ 0.510 |
+ 0.4417 |
+ 0.5667 |
+ 0.4650 |
+ 0.4971 |
+ 0.0656 |
+ 0.0275 |
+ 0.5819 |
+ 0.645 |
+
+
+ | Decision Tree Classifier |
+ 0.495 |
+ 0.5000 |
+ 0.4333 |
+ 0.4333 |
+ 0.4133 |
+ 0.0049 |
+ 0.0040 |
+ 0.5483 |
+ 0.329 |
+
+
+ | Gradient Boosting Classifier |
+ 0.475 |
+ 0.4333 |
+ 0.4500 |
+ 0.4000 |
+ 0.4033 |
+ -0.0033 |
+ -0.0239 |
+ 0.5800 |
+ 0.643 |
+
+
+ | Extreme Gradient Boosting |
+ 0.460 |
+ 0.4833 |
+ 0.4333 |
+ 0.3333 |
+ 0.3667 |
+ -0.0489 |
+ -0.0537 |
+ 0.6281 |
+ 0.422 |
+
+
+
+
+
Results on the Test Set for the best model
+
+
+
+
+ | Model |
+ Accuracy |
+ ROC-AUC |
+ Recall |
+ Prec. |
+ F1 |
+ Kappa |
+ MCC |
+ PR-AUC-Weighted |
+
+
+
+
+ | Light Gradient Boosting Machine |
+ 0.8095 |
+ 0.7454 |
+ 0.6667 |
+ 0.8571 |
+ 0.75 |
+ 0.6 |
+ 0.6124 |
+ 0.6799 |
+
+
+
+
+
+
+
Best Model Plots on the testing set
+
+
+
Confusion_matrix
+
+
+
+
+
Auc
+
+
+
+
+
Threshold
+
+
+
+
+
Pr
+
+
+
+
+
Error
+
+
+
+
+
Class_report
+
+
+
+
+
Learning
+
+
+
+
+
Calibration
+
+
+
+
+
Vc
+
+
+
+
+
Dimension
+
+
+
+
+
Manifold
+
+
+
+
+
Rfe
+
+
+
+
+
Feature
+
+
+
+
+
Feature_all
+
+
+
+
+
+
+
PyCaret Feature Importance Report
+
+
+
Feature importance analysis from atrained Random Forest
+
Use gini impurity forcalculating feature importance for classificationand Variance Reduction for regression
+
+
+
+
+
SHAP Summary from a trained lightgbm
+
+
+
+
+
+
+
+
+
+
+
PyCaret Model Training Report
+
+
+ Setup & Best Model
+
+ Best Model Plots
+
+ Feature Importance
+
+ Explainer
+
+
+
+
Setup Parameters
+
+ | Parameter | Value |
|---|
+
+
+
+ | target |
+ PCR |
+
+
+ | session_id |
+ 42 |
+
+
+ | index |
+ False |
+
+
+ | train_size |
+ 0.8 |
+
+
+ | normalize |
+ True |
+
+
+ | feature_selection |
+ True |
+
+
+ | fold |
+ 5 |
+
+
+ | remove_outliers |
+ True |
+
+
+ | remove_multicollinearity |
+ True |
+
+
+
+
+
If you want to know all the experiment setup parameters,
+ please check the PyCaret documentation for
+ the classification/regression exp function.
+
Best Model: LGBMClassifier
+
+ | Parameter | Value |
|---|
+
+
+
+ | boosting_type |
+ gbdt |
+
+
+ | class_weight |
+ None |
+
+
+ | colsample_bytree |
+ 1.0 |
+
+
+ | importance_type |
+ split |
+
+
+ | learning_rate |
+ 0.1 |
+
+
+ | max_depth |
+ -1 |
+
+
+ | min_child_samples |
+ 20 |
+
+
+ | min_child_weight |
+ 0.001 |
+
+
+ | min_split_gain |
+ 0.0 |
+
+
+ | n_estimators |
+ 100 |
+
+
+ | n_jobs |
+ -1 |
+
+
+ | num_leaves |
+ 31 |
+
+
+ | objective |
+ None |
+
+
+ | random_state |
+ 42 |
+
+
+ | reg_alpha |
+ 0.0 |
+
+
+ | reg_lambda |
+ 0.0 |
+
+
+ | subsample |
+ 1.0 |
+
+
+ | subsample_for_bin |
+ 200000 |
+
+
+ | subsample_freq |
+ 0 |
+
+
+
+
+
Comparison Results on the Cross-Validation Set
+
+
+
+
+ | Model |
+ Accuracy |
+ ROC-AUC |
+ Recall |
+ Prec. |
+ F1 |
+ Kappa |
+ MCC |
+ PR-AUC-Weighted |
+ TT (Sec) |
+
+
+
+
+ | Light Gradient Boosting Machine |
+ 0.7091 |
+ 0.6267 |
+ 0.64 |
+ 0.6895 |
+ 0.6467 |
+ 0.4056 |
+ 0.4224 |
+ 0.5918 |
+ 0.322 |
+
+
+ | Naive Bayes |
+ 0.6545 |
+ 0.6800 |
+ 0.72 |
+ 0.6117 |
+ 0.6498 |
+ 0.3163 |
+ 0.3232 |
+ 0.6930 |
+ 1.240 |
+
+
+ | K Neighbors Classifier |
+ 0.6364 |
+ 0.6467 |
+ 0.56 |
+ 0.6067 |
+ 0.5743 |
+ 0.2603 |
+ 0.2660 |
+ 0.6001 |
+ 0.864 |
+
+
+ | Ridge Classifier |
+ 0.6364 |
+ 0.6467 |
+ 0.64 |
+ 0.5962 |
+ 0.6048 |
+ 0.2700 |
+ 0.2835 |
+ 0.0000 |
+ 0.898 |
+
+
+ | Random Forest Classifier |
+ 0.6364 |
+ 0.6300 |
+ 0.60 |
+ 0.6343 |
+ 0.6013 |
+ 0.2688 |
+ 0.2834 |
+ 0.6539 |
+ 0.906 |
+
+
+ | Logistic Regression |
+ 0.6364 |
+ 0.6400 |
+ 0.64 |
+ 0.5962 |
+ 0.6048 |
+ 0.2700 |
+ 0.2835 |
+ 0.6697 |
+ 0.798 |
+
+
+ | Quadratic Discriminant Analysis |
+ 0.6364 |
+ 0.6933 |
+ 0.72 |
+ 0.5851 |
+ 0.6353 |
+ 0.2815 |
+ 0.2899 |
+ 0.7075 |
+ 0.418 |
+
+
+ | Linear Discriminant Analysis |
+ 0.6364 |
+ 0.6467 |
+ 0.64 |
+ 0.5962 |
+ 0.6048 |
+ 0.2700 |
+ 0.2835 |
+ 0.6751 |
+ 0.364 |
+
+
+ | Gradient Boosting Classifier |
+ 0.6182 |
+ 0.6333 |
+ 0.60 |
+ 0.5843 |
+ 0.5846 |
+ 0.2328 |
+ 0.2389 |
+ 0.6403 |
+ 0.522 |
+
+
+ | Ada Boost Classifier |
+ 0.6182 |
+ 0.6567 |
+ 0.60 |
+ 0.5943 |
+ 0.5891 |
+ 0.2340 |
+ 0.2415 |
+ 0.6517 |
+ 0.560 |
+
+
+ | Extra Trees Classifier |
+ 0.6182 |
+ 0.5800 |
+ 0.56 |
+ 0.5876 |
+ 0.5622 |
+ 0.2266 |
+ 0.2347 |
+ 0.6413 |
+ 0.468 |
+
+
+ | Decision Tree Classifier |
+ 0.6000 |
+ 0.5967 |
+ 0.56 |
+ 0.5867 |
+ 0.5533 |
+ 0.1950 |
+ 0.2060 |
+ 0.5215 |
+ 1.532 |
+
+
+ | CatBoost Classifier |
+ 0.5818 |
+ 0.6667 |
+ 0.48 |
+ 0.5133 |
+ 0.4845 |
+ 0.1454 |
+ 0.1414 |
+ 0.6991 |
+ 3.426 |
+
+
+ | SVM - Linear Kernel |
+ 0.5455 |
+ 0.5000 |
+ 0.40 |
+ 0.5033 |
+ 0.4332 |
+ 0.0684 |
+ 0.0685 |
+ 0.0000 |
+ 1.666 |
+
+
+ | Dummy Classifier |
+ 0.5455 |
+ 0.5000 |
+ 0.00 |
+ 0.0000 |
+ 0.0000 |
+ 0.0000 |
+ 0.0000 |
+ 0.4545 |
+ 0.456 |
+
+
+ | Extreme Gradient Boosting |
+ 0.5273 |
+ 0.5600 |
+ 0.52 |
+ 0.4967 |
+ 0.5042 |
+ 0.0550 |
+ 0.0564 |
+ 0.5943 |
+ 0.336 |
+
+
+
+
+
Results on the Test Set for the best model
+
+
+
+
+ | Model |
+ Accuracy |
+ ROC-AUC |
+ Recall |
+ Prec. |
+ F1 |
+ Kappa |
+ MCC |
+ PR-AUC-Weighted |
+
+
+
+
+ | Light Gradient Boosting Machine |
+ 0.7857 |
+ 0.7604 |
+ 0.6667 |
+ 0.8 |
+ 0.7273 |
+ 0.5532 |
+ 0.5594 |
+ 0.7502 |
+
+
+
+
+
+
+
Best Model Plots on the testing set
+
+
+
Confusion_matrix
+
+
+
+
+
Auc
+
+
+
+
+
Threshold
+
+
+
+
+
Pr
+
+
+
+
+
Error
+
+
+
+
+
Class_report
+
+
+
+
+
Learning
+
+
+
+
+
Calibration
+
+
+
+
+
Vc
+
+
+
+
+
Dimension
+
+
+
+
+
Manifold
+
+
+
+
+
Rfe
+
+
+
+
+
Feature
+
+
+
+
+
Feature_all
+
+
+
+
+
+
+
PyCaret Feature Importance Report
+
+
+
Feature importance analysis from atrained Random Forest
+
Use gini impurity forcalculating feature importance for classificationand Variance Reduction for regression
+
+
+
+
+
SHAP Summary from a trained lightgbm
+
+
+
+
+
+
+
+
+
+
+
PyCaret Model Training Report
+
+
+ Setup & Best Model
+
+ Best Model Plots
+
+ Feature Importance
+
+ Explainer
+
+
+
+
Setup Parameters
+
+ | Parameter | Value |
|---|
+
+
+
+ | target |
+ MPG |
+
+
+ | session_id |
+ 42 |
+
+
+ | index |
+ False |
+
+
+
+
+
If you want to know all the experiment setup parameters,
+ please check the PyCaret documentation for
+ the classification/regression exp function.
+
Best Model: GradientBoostingRegressor
+
+ | Parameter | Value |
|---|
+
+
+
+ | alpha |
+ 0.9 |
+
+
+ | ccp_alpha |
+ 0.0 |
+
+
+ | criterion |
+ friedman_mse |
+
+
+ | init |
+ None |
+
+
+ | learning_rate |
+ 0.1 |
+
+
+ | loss |
+ squared_error |
+
+
+ | max_depth |
+ 3 |
+
+
+ | max_features |
+ None |
+
+
+ | max_leaf_nodes |
+ None |
+
+
+ | min_impurity_decrease |
+ 0.0 |
+
+
+ | min_samples_leaf |
+ 1 |
+
+
+ | min_samples_split |
+ 2 |
+
+
+ | min_weight_fraction_leaf |
+ 0.0 |
+
+
+ | n_estimators |
+ 100 |
+
+
+ | n_iter_no_change |
+ None |
+
+
+ | random_state |
+ 42 |
+
+
+ | subsample |
+ 1.0 |
+
+
+ | tol |
+ 0.0001 |
+
+
+ | validation_fraction |
+ 0.1 |
+
+
+ | verbose |
+ 0 |
+
+
+ | warm_start |
+ False |
+
+
+
+
+
Comparison Results on the Cross-Validation Set
+
+
+
+
+ | Model |
+ MAE |
+ MSE |
+ RMSE |
+ R2 |
+ RMSLE |
+ MAPE |
+ TT (Sec) |
+
+
+
+
+ | Gradient Boosting Regressor |
+ 2.2775 |
+ 9.8743 |
+ 3.0921 |
+ 0.8383 |
+ 0.1197 |
+ 0.0980 |
+ 0.681 |
+
+
+ | Extra Trees Regressor |
+ 2.2119 |
+ 10.2477 |
+ 3.1304 |
+ 0.8323 |
+ 0.1220 |
+ 0.0949 |
+ 2.212 |
+
+
+ | Light Gradient Boosting Machine |
+ 2.3218 |
+ 10.4931 |
+ 3.1818 |
+ 0.8282 |
+ 0.1252 |
+ 0.1011 |
+ 0.263 |
+
+
+ | CatBoost Regressor |
+ 2.3204 |
+ 10.5063 |
+ 3.1906 |
+ 0.8270 |
+ 0.1256 |
+ 0.1011 |
+ 8.883 |
+
+
+ | Random Forest Regressor |
+ 2.3161 |
+ 11.0170 |
+ 3.2515 |
+ 0.8210 |
+ 0.1252 |
+ 0.0990 |
+ 1.916 |
+
+
+ | Extreme Gradient Boosting |
+ 2.4277 |
+ 11.9887 |
+ 3.3949 |
+ 0.8045 |
+ 0.1336 |
+ 0.1057 |
+ 0.497 |
+
+
+ | Elastic Net |
+ 2.6119 |
+ 12.1337 |
+ 3.4462 |
+ 0.8029 |
+ 0.1426 |
+ 0.1168 |
+ 0.116 |
+
+
+ | Lasso Regression |
+ 2.6238 |
+ 12.2869 |
+ 3.4649 |
+ 0.8011 |
+ 0.1438 |
+ 0.1172 |
+ 0.134 |
+
+
+ | Lasso Least Angle Regression |
+ 2.6238 |
+ 12.2868 |
+ 3.4649 |
+ 0.8011 |
+ 0.1438 |
+ 0.1172 |
+ 0.157 |
+
+
+ | AdaBoost Regressor |
+ 2.5949 |
+ 12.5846 |
+ 3.4968 |
+ 0.7939 |
+ 0.1378 |
+ 0.1153 |
+ 2.469 |
+
+
+ | Bayesian Ridge |
+ 2.6494 |
+ 12.5149 |
+ 3.5121 |
+ 0.7920 |
+ 0.1433 |
+ 0.1194 |
+ 0.268 |
+
+
+ | Ridge Regression |
+ 2.6852 |
+ 12.7684 |
+ 3.5480 |
+ 0.7872 |
+ 0.1448 |
+ 0.1212 |
+ 0.108 |
+
+
+ | Linear Regression |
+ 2.6893 |
+ 12.7997 |
+ 3.5523 |
+ 0.7866 |
+ 0.1450 |
+ 0.1214 |
+ 0.122 |
+
+
+ | Least Angle Regression |
+ 2.7583 |
+ 13.3766 |
+ 3.6327 |
+ 0.7759 |
+ 0.1489 |
+ 0.1249 |
+ 0.165 |
+
+
+ | Huber Regressor |
+ 2.6780 |
+ 14.2077 |
+ 3.7197 |
+ 0.7699 |
+ 0.1404 |
+ 0.1138 |
+ 1.508 |
+
+
+ | Decision Tree Regressor |
+ 2.6552 |
+ 15.5784 |
+ 3.8636 |
+ 0.7507 |
+ 0.1470 |
+ 0.1108 |
+ 0.253 |
+
+
+ | Orthogonal Matching Pursuit |
+ 3.3731 |
+ 20.2491 |
+ 4.4464 |
+ 0.6709 |
+ 0.1767 |
+ 0.1475 |
+ 0.418 |
+
+
+ | K Neighbors Regressor |
+ 3.4315 |
+ 21.1052 |
+ 4.5405 |
+ 0.6546 |
+ 0.1692 |
+ 0.1448 |
+ 0.858 |
+
+
+ | Dummy Regressor |
+ 6.6547 |
+ 62.8366 |
+ 7.8973 |
+ -0.0391 |
+ 0.3303 |
+ 0.3219 |
+ 0.129 |
+
+
+ | Passive Aggressive Regressor |
+ 7.5227 |
+ 84.7568 |
+ 9.0993 |
+ -0.4762 |
+ 0.4067 |
+ 0.3652 |
+ 0.420 |
+
+
+
+
+
Results on the Test Set for the best model
+
+
+
+
+ | Model |
+ MAE |
+ MSE |
+ RMSE |
+ R2 |
+ RMSLE |
+ MAPE |
+
+
+
+
+ | Gradient Boosting Regressor |
+ 2.2015 |
+ 9.911 |
+ 3.1482 |
+ 0.8273 |
+ 0.1198 |
+ 0.094 |
+
+
+
+
+
+
+
Best Model Plots on the testing set
+
+
+
Residuals
+
+
+
+
+
Error
+
+
+
+
+
Cooks
+
+
+
+
+
Learning
+
+
+
+
+
Vc
+
+
+
+
+
Manifold
+
+
+
+
+
Rfe
+
+
+
+
+
Feature
+
+
+
+
+
Feature_all
+
+
+
+
+
+
+
PyCaret Feature Importance Report
+
+
+
Feature importance analysis from atrained Random Forest
+
Use gini impurity forcalculating feature importance for classificationand Variance Reduction for regression
+
+
+
+
+
SHAP Summary from a trained lightgbm
+
+
+
+
+
+
+
+
+
+ """
+
+
+def get_html_closing():
+ return """
+
+
+
+
+ """
+
+
+def customize_figure_layout(fig, margin_dict=None):
+ """
+ Update the layout of a Plotly figure to reduce margins.
+
+ Parameters:
+ fig (plotly.graph_objects.Figure): The Plotly figure to customize.
+ margin_dict (dict, optional): A dictionary specifying margin sizes.
+ Example: {'l': 10, 'r': 10, 't': 10, 'b': 10}
+
+ Returns:
+ plotly.graph_objects.Figure: The updated Plotly figure.
+ """
+ if margin_dict is None:
+ # Set default smaller margins
+ margin_dict = {'l': 40, 'r': 40, 't': 40, 'b': 40}
+
+ fig.update_layout(margin=margin_dict)
+ return fig
+
+
+def add_plot_to_html(fig, include_plotlyjs=True):
+ custom_margin = {'l': 40, 'r': 40, 't': 60, 'b': 60}
+ fig = customize_figure_layout(fig, margin_dict=custom_margin)
+ return fig.to_html(full_html=False,
+ default_height=350,
+ include_plotlyjs="cdn" if include_plotlyjs else False)
+
+
+def add_hr_to_html():
+ return "
"
+
+
+def encode_image_to_base64(image_path):
+ """Convert an image file to a base64 encoded string."""
+ with open(image_path, "rb") as img_file:
+ return base64.b64encode(img_file.read()).decode("utf-8")