robert 2.0.1__tar.gz → 2.0.2__tar.gz

{robert-2.0.1 → robert-2.0.2}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.1
 Name: robert
-Version: 2.0.1
+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/2.0.1.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
@@ -34,5 +36,6 @@ 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-2.0.1 → 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-2.0.1 → 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-2.0.1 → robert-2.0.2}/robert/utils.py

@@ -58,7 +58,7 @@ import warnings # this avoids warnings from sklearn
 warnings.filterwarnings("ignore")
 
 
-robert_version = "2.0.1"
+robert_version = "2.0.2"
 time_run = time.strftime("%Y/%m/%d %H:%M:%S", time.localtime())
 robert_ref = "Dalmau, D.; Alegre Requena, J. V. WIREs Comput Mol Sci. 2024, 14, e1733."
 
@@ -2597,7 +2597,7 @@ def prepare_sets(self,csv_df,csv_X,csv_y,test_points,column_names,csv_external_d
                 self.args.log.write(f'\nx  WARNING! The test_set option was set to {self.args.test_set}, this value will be raised to 0.2 to include a meaningful amount of points in the test set. You can bypass this option and include less test points with "--auto_test False".')
 
         if self.args.test_set > 0:
-            self.args.log.write(f'\no  Before hyproptimization, {int(self.args.test_set*100)}% of the data (or 4 points at least) was separated as test set, using an even distribution of data points across the range of y values.')
+            self.args.log.write(f'\no  Before hyperoptimization, {int(self.args.test_set*100)}% of the data (or 4 points at least) was separated as test set, using an even distribution of data points across the range of y values.')
             try:
                 test_points = test_select(self,X_scaled_df,csv_y)
             except TypeError:
@@ -2624,6 +2624,7 @@ def load_dfs(self,folder_model,module,sanity_check=False,print_info=True):
         path_db = f"{Path(os.getcwd()).joinpath(folder_model)}"
     if os.path.exists(path_db):
         csv_files = glob.glob(f'{Path(path_db).joinpath("*.csv")}')
+        csv_files.sort(key=lambda f: f.endswith('_db.csv')) # sort the database file to be the last one, depending on the OS was taking first the dabatase and then the parameters
         for csv_file in csv_files:
             if csv_file.endswith('_db.csv'):
                 if not sanity_check:

{robert-2.0.1 → robert-2.0.2}/robert.egg-info/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.1
 Name: robert
-Version: 2.0.1
+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/2.0.1.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
@@ -34,5 +36,6 @@ 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-2.0.1 → robert-2.0.2}/robert.egg-info/requires.txt

@@ -13,3 +13,4 @@ weasyprint==63.1
 PySide6
 PyMuPDF
 ansi2html
+rdkit==2024.3.3

{robert-2.0.1 → robert-2.0.2}/setup.py

@@ -1,5 +1,5 @@
 from setuptools import setup, find_packages
-version="2.0.1"
+version="2.0.2"
 setup(
     name="robert",
     packages=find_packages(exclude=["tests"]),
@@ -30,6 +30,8 @@ setup(
         "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
     ],
     install_requires=[
         "PyYAML==6.0.2",
@@ -46,7 +48,8 @@ setup(
         "weasyprint==63.1",
         "PySide6",
         "PyMuPDF",
-        "ansi2html"
+        "ansi2html",
+        "rdkit==2024.3.3"
     ],
     python_requires=">=3.10",
     include_package_data=True,

{robert-2.0.1 → robert-2.0.2}/tests/test_2generate.py

@@ -130,7 +130,7 @@ def test_GENERATE(test_job):
                 finding_line += 1
             elif f"2. 50% = RMSE from the bottom or top (worst performing) fold in a sorted 5-fold CV (extrapolation)" in line:
                 finding_line += 1
-            elif f"o  Before hyproptimization, 20% of the data (or 4 points at least) was separated as test set, using an even distribution of data points across the range of y values." in line:
+            elif f"o  Before hyperoptimization, 20% of the data (or 4 points at least) was separated as test set, using an even distribution of data points across the range of y values." in line:
                 finding_line += 0.5 # it appears two times, in PFI and no PFI
                 # this elif adds 4 points to the standard test (0.5*2(PFI and no PFI)*4(models)
             elif f"o Best combined RMSE (target) found in BO for RF (no PFI filter): 0.53" in line: