robert 2.0.0__tar.gz → 2.0.2__tar.gz

{robert-2.0.0 → robert-2.0.2}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.1
 Name: robert
-Version: 2.0.0
+Version: 2.0.2
 Summary: Refiner and Optimizer of a Bunch of Existing Regression Tools
 Home-page: https://github.com/jvalegre/robert
-Download-URL: https://github.com/jvalegre/robert/archive/refs/tags/2.0.0.tar.gz
+Download-URL: https://github.com/jvalegre/robert/archive/refs/tags/2.0.2.tar.gz
 Author: Juan V. Alegre Requena, David Dalmau
 Author-email: jv.alegre@csic.es
 License: MIT
@@ -16,6 +16,8 @@ Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -31,5 +33,9 @@ Requires-Dist: bayesian-optimization==3.0.0b1
 Requires-Dist: numba==0.60.0
 Requires-Dist: shap==0.46.0
 Requires-Dist: weasyprint==63.1
+Requires-Dist: PySide6
+Requires-Dist: PyMuPDF
+Requires-Dist: ansi2html
+Requires-Dist: rdkit==2024.3.3
 
 Documentation in Read The Docs: https://robert.readthedocs.io

{robert-2.0.0 → robert-2.0.2}/README.md

@@ -17,17 +17,20 @@ Don't miss out the latest hands-on tutorials from our [YouTube channel](https://
 ## Recommended installation
 1. (Only once) Create new conda environment: `conda create -n robert python=3.10`  
 2. Activate conda environment: `conda activate robert`  
-3. Install ROBERT using pip: `pip install robert` 
-4. Install libraries for the PDF report `conda install -y -c conda-forge glib gtk3 pango mscorefonts`
-5. (Only for compatible devices) Install Intelex accelerator: `pip install scikit-learn-intelex==2025.0.1`  
+3. Install ROBERT using pip: `pip install robert`
+4. Install RDKit (only if you plan to use easyROB): `pip install rdkit`
+5. Install libraries for the PDF report `conda install -y -c conda-forge glib gtk3 pango mscorefonts`
+6. (Only for compatible devices) Install Intelex accelerator: `pip install scikit-learn-intelex==2025.2.0`  
 * Inexperienced users should visit the *Users with no Python experience* section in [Read the Docs](https://robert.readthedocs.io).
 ## Update the program
-1. Update to the latest version: `pip install robert --upgrade`  
+1. Update to the latest version: `pip install robert --upgrade`
 
 ## Developers and help desk  
 List of main developers and contact emails:  
   - [ ] [Juan V. Alegre-Requena](https://orcid.org/0000-0002-0769-7168). Contact: [jv.alegre@csic.es](mailto:jv.alegre@csic.es)  
-  - [ ] [David Dalmau Ginesta](https://orcid.org/0000-0002-2506-6546). Contact: [ddalmau@unizar.es](mailto:ddalmau@unizar.es)  
+  - [ ] [David Dalmau Ginesta](https://orcid.org/0000-0002-2506-6546). Contact: [ddalmau@unizar.es](mailto:ddalmau@unizar.es)
+  - [ ] [Miguel Martinez Fernandez](https://orcid.org/0009-0002-8538-7250). Contact [miguel.martinez@csic.es](mailto:miguel.martinez@csic.es)
+  - [ ] [Luis Giner Tendero](https://github.com/LlGinerT/). Contact [lginertendero@gmail.com](mailto:lginertendero@gmail.com)
 
 For suggestions and improvements of the code (greatly appreciated!), please reach out through the issues and pull requests options of Github.  
 
@@ -58,6 +61,7 @@ If you use any of the ROBERT modules, please include this citation:
 If you use the AQME module, please include this citation:  
 * Alegre-Requena et al., AQME: Automated Quantum Mechanical Environments for Researchers and Educators. *Wiley Interdiscip. Rev. Comput. Mol. Sci.* **2023**, *13*, e1663.
 
-Additionally, please include the corresponding reference for Scikit-learn and SHAP:  
+Additionally, please include the corresponding reference for Scikit-learn, SHAP and BayesianOptimization:  
 * Pedregosa et al., Scikit-learn: Machine Learning in Python. *J. Mach. Learn. Res.* **2011**, *12*, 2825-2830.  
-* Lundberg et al., From local explanations to global understanding with explainable AI for trees. *Nat. Mach. Intell.* **2020**, *2*, 56–67.  
+* Lundberg et al., From local explanations to global understanding with explainable AI for trees. *Nat. Mach. Intell.* **2020**, *2*, 56–67.
+* Fernando Nogueira, {Bayesian Optimization}: Open source constrained global optimization tool for {Python}, **2014**, https://github.com/bayesian-optimization/BayesianOptimization  

{robert-2.0.0 → robert-2.0.2}/robert/aqme.py

@@ -125,7 +125,7 @@ class aqme:
                     aqme_indv_name = f'AQME_indiv_{smi_suffix}'
 
                 # run AQME-QDESCP to generate descriptors
-                cmd_qdescp = ['python', '-m', 'aqme', '--qdescp', '--input', f'{aqme_indv_name}.csv', '--program', 'xtb', '--csv_name', f'{aqme_indv_name}.csv', '--nprocs', f'{self.args.nprocs}', '--robert']
+                cmd_qdescp = ['python','-u', '-m', 'aqme', '--qdescp', '--input', f'{aqme_indv_name}.csv', '--program', 'xtb', '--csv_name', f'{aqme_indv_name}.csv', '--nprocs', f'{self.args.nprocs}', '--robert']
                 _ = self.run_aqme(cmd_qdescp, self.args.qdescp_keywords)
 
                 if smi_suffix is not None:

{robert-2.0.0 → robert-2.0.2}/robert/curate.py

@@ -8,10 +8,10 @@ Parameters
         Name of the column containing the response variable in the input CSV file (i.e. 'solubility'). 
     discard : list, default=[]
         List containing the columns of the input CSV file that will not be included as descriptors
-        in the curated CSV file (i.e. ['name','SMILES']).
+        in the curated CSV file (i.e. "['name','SMILES']").
     ignore : list, default=[]
         List containing the columns of the input CSV file that will be ignored during the curation process
-        (i.e. ['name','SMILES']). The descriptors will be included in the curated CSV file. The y value
+        (i.e. "['name','SMILES']"). The descriptors will be included in the curated CSV file. The y value
         is automatically ignored.
     names : str, default=''
         Column of the names for each datapoint. Names are used to print outliers.

{robert-2.0.0 → robert-2.0.2}/robert/generate.py

@@ -63,15 +63,23 @@ Parameters
         Number of features to keep after the PFI filter. If pfi_max is 0, all the features that pass the PFI
         filter are used.
     auto_test : bool, default=True
-        Raises % of test points to 10% if test_set is lower than that.
-    test_set : float, default=0.1
-        Amount of datapoints to separate as external test set (0.1 = 10%). These points will not be used during the
+        Raises % of test points to 20% if test_set is lower than that.
+    test_set : float, default=0.2
+        Amount of datapoints to separate as external test set (0.2 = 20%). These points will not be used during the
         hyperoptimization, and PREDICT will use the points as test set during ROBERT workflows. Select
         --test_set 0 to use only training and validation.
     kfold : int, default=5
         Number of random data splits for the cross-validation of the models. 
     repeat_kfolds : int, default=10
         Number of repetitions for the k-fold cross-validation of the models.
+    split : str, default='even'
+        Specifies how the data is split into training and test sets. Options:
+        1. 'even': splits the data evenly into training and test sets.
+        2. 'RND': randomly splits the data.
+        3. 'stratified': splits the data while preserving the distribution of the target variable.
+        4. 'KN': uses a k-means approach to select representative samples.
+        5. 'EXTRA_Q1': selects the 10% lowest values.
+        6. 'EXTRA_Q5': selects the 10% highest values.
         
 """
 #####################################################.

{robert-2.0.0 → robert-2.0.2}/robert/predict_utils.py

@@ -61,14 +61,15 @@ def plot_predictions(self, params_dict, Xy_data, path_n_suffix):
         # Plot CV average ± SD graph of validation or test set
         _ = graph_reg(self,Xy_data,params_dict,set_types,path_n_suffix,graph_style,sd_graph=True)
         if 'y_external' in Xy_data and not Xy_data['y_external'].isnull().values.any() and len(Xy_data['y_external']) > 0:
-            # Plot CV average ± SD graph of validation or test set
-            _ = graph_reg(self,Xy_data,params_dict,set_types,path_n_suffix,graph_style,csv_test=True,sd_graph=True)
+            # Plot CV average ± SD graph of external set
+            set_type = 'external'
+            _ = graph_reg(self,Xy_data,params_dict,set_type,path_n_suffix,graph_style,csv_test=True,sd_graph=True)
 
     elif params_dict['type'].lower() == 'clas':
         for set_type in set_types:
             _ = graph_clas(self,Xy_data,params_dict,set_type,path_n_suffix)
-        if 'y_pred_csv_test' in Xy_data and not Xy_data['y_csv_test'].isnull().values.any() and len(Xy_data['y_csv_test']) > 0:
-            set_type = 'csv_test'
+        if 'y_external' in Xy_data and not Xy_data['y_external'].isnull().values.any() and len(Xy_data['y_external']) > 0:
+            set_type = 'external'
             _ = graph_clas(self,Xy_data,params_dict,set_type,path_n_suffix,csv_test=True)
 
     return graph_style
@@ -182,11 +183,11 @@ def print_predict(self,Xy_data,model_data,suffix_title):
             print_results += f"\n      -  External test : R2 = {Xy_data['r2_external']:.2}, MAE = {Xy_data['mae_external']:.2}, RMSE = {Xy_data['rmse_external']:.2}"
 
     elif model_data['type'].lower() == 'clas':
-        print_results += f"\n      -  {CV_type} : Accuracy = {Xy_data['acc_train']:.2}, F1 score = {Xy_data['f1_train']:.2}, MCC = {Xy_data['mcc_train']:.2}"
+        print_results += f"\n      -  {CV_type} : Accur. = {Xy_data['acc_train']:.2}, F1 score = {Xy_data['f1_train']:.2}, MCC = {Xy_data['mcc_train']:.2}"
         if 'y_pred_test' in Xy_data and not Xy_data['y_test'].isnull().values.any() and len(Xy_data['y_test']) > 0:
-            print_results += f"\n      -  Test : Accuracy = {Xy_data['acc_test']:.2}, F1 score = {Xy_data['f1_test']:.2}, MCC = {Xy_data['mcc_test']:.2}"
-        if 'y_pred_csv_test' in Xy_data and not Xy_data['y_csv_test'].isnull().values.any() and len(Xy_data['y_csv_test']) > 0:
-            print_results += f"\n      -  csv_test : Accur. = {Xy_data['acc_csv_test']:.2}, F1 score = {Xy_data['f1_csv_test']:.2}, MCC = {Xy_data['mcc_csv_test']:.2}"
+            print_results += f"\n      -  Test : Accur. = {Xy_data['acc_test']:.2}, F1 score = {Xy_data['f1_test']:.2}, MCC = {Xy_data['mcc_test']:.2}"
+        if 'y_external' in Xy_data and not Xy_data['y_external'].isnull().values.any() and len(Xy_data['y_external']) > 0:
+            print_results += f"\n      -  External test : Accur. = {Xy_data['acc_external']:.2}, F1 score = {Xy_data['f1_external']:.2}, MCC = {Xy_data['mcc_external']:.2}"
 
     self.args.log.write(print_results)
 

{robert-2.0.0 → robert-2.0.2}/robert/report.py

@@ -342,7 +342,7 @@ class report:
             if data_score[f'cv_sd_score_{suffix}'] == 0:
                 warnings_dict[f'moderate_warnings_{suffix}'].append('Imprecise predictions (Section B.3b)')
         elif pred_type == 'clas':
-            if data_score[f'r2_diff_score_{suffix}'] == 0:
+            if data_score[f'diff_mcc_score_{suffix}'] == 0:
                 warnings_dict[f'moderate_warnings_{suffix}'].append('Imprecise predictions (Section B.3b)')
 
         # y distribution
@@ -528,11 +528,11 @@ class report:
 
                     elif section == 'adv_sorted_cv':
                         # advanced score analysis 3d, descriptor proportion
-                        columns_score.append(adv_sorted_cv(self,suffix,data_score,spacing*2))
+                        columns_score.append(adv_sorted_cv(self,suffix,data_score,spacing*2,pred_type))
 
                     elif section == 'adv_cv_diff' and pred_type == 'clas':
                         # advanced score analysis 3b, difference of MCC in model and CV
-                        columns_score.append(adv_cv_diff(self,suffix,data_score,spacing*2))
+                        columns_score.append(adv_cv_diff(self,suffix,data_score,spacing*2,pred_type))
 
             # Combine both columns
             adv_score_dat += combine_cols(columns_score)
@@ -889,9 +889,9 @@ class report:
         if aqme_workflow:
             if not find_aqme:
                 repro_dat += f"""{reduced_line}{space}- AQME is required, but no version was found:</p>"""
-            repro_dat += f"""{reduced_line}{space}- Install AQME and its dependencies: conda install -y -c conda-forge aqme</p>"""
+                repro_dat += f"""{reduced_line}{space}- Install AQME and its dependencies: pip install aqme==VERSION_USED</p>"""
             if find_aqme:
-                repro_dat += f"""{reduced_line}{space}- Adjust AQME version: pip install aqme=={aqme_version}</p>"""
+                repro_dat += f"""{reduced_line}{space}- Install or adjust AQME version: pip install aqme=={aqme_version}</p>"""
 
             try:
                 path_xtb = Path(f'{os.getcwd()}/AQME/QDESCP')
@@ -1163,15 +1163,7 @@ class report:
             if pred_type.lower() == 'reg':
                 results_images = [str(file_path) for file_path in module_path.rglob(f'{file_name}_*.png')]
             elif pred_type.lower() == 'clas':
-                results_images  = []
-                all_images = [str(file_path) for file_path in module_path.rglob('*.png')]
-                for img in all_images:
-                    if 'test' in set_types:
-                        if file_name in img and '_test.png' in img:
-                            results_images.append(img)
-                    else:
-                        if file_name in img and '_valid.png' in img:
-                            results_images.append(img)
+                results_images = [str(file_path) for file_path in module_path.rglob(f'{file_name}_*.png')]
         # images with no suffixes in the names
         else:
             results_images = [str(file_path) for file_path in module_path.rglob(f'{file_name}_*.png')]