MASSA-Algorithm 2.2.2__tar.gz → 2.2.3__tar.gz

{massa_algorithm-2.2.2 → massa_algorithm-2.2.3}/MASSA_Algorithm/MASSAlogos.py

@@ -20,7 +20,7 @@ def initial_print():
        ██░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░█
      ██░░░░▓▓▓▓▓▓░░░░░▓▓▓▓▓▓░░░░░▓▓▓▓▓▓░░░░█                                 MASSA Algorithm:
    ████░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░█████          Molecular data set sampling  —  Training-Test Separation
-  █▓▓▓███░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░███▓▓▓█                            Version: v. 2.2.2
+  █▓▓▓███░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░███▓▓▓█                            Version: v. 2.2.3
  █▒▓▓▒▒▒████░░░░░░░░░░░░░░░░░░░░░░░░░░░░████▒▒▓▓▒█
  ██▓▒▒▒▓▓▓▓██████████████████████████████▓▓▓▒▒▒▒▓█                Developed by: Gabriel Corrêa Veríssimo
  ██▒▒▒▓▓▒▒▒▒▓▓▒▒▒▒▓▓▒▒▒▒▒▒▒▒▒▒▒▒▓▓▒▒▒▒▓▓▒▒▒▓▓▒▒██                           LICENSE: AGPL-3.0
@@ -31,4 +31,4 @@ def initial_print():
 
 
 def python_logo():
-    print("🍕 MASSA Algorithm v. 2.2.0: Molecular data set sampling")
+    print("🍕 MASSA Algorithm v. 2.2.3: Molecular data set sampling")

{massa_algorithm-2.2.2 → massa_algorithm-2.2.3}/MASSA_Algorithm/MASSAopen_files.py

@@ -154,18 +154,13 @@ def read_SMI_smiles(file, write_log, drop_errors):
         df = pd.read_csv(file, sep="\t", header=0)
     else:
         df = pd.read_csv(file, sep="\t", header=None)
-        df = df.iloc[:, :2] # Keep only the first two columns
-        df.columns = ["SMILES", "Name"]
+        df.columns = ["SMILES", "Name"] + [
+            f"Column_{i}" for i in range(3, df.shape[1] + 1)
+        ]
 
     mols_sanitized = read_df_smiles(df, write_log, drop_errors)
     return mols_sanitized
 
-def read_SMI_smiles(file, write_log, drop_errors):
-    df_supplier = pd.read_csv(file, sep="\t", header=None)
-    df_supplier.columns = ["SMILES", "Name"]
-    mols_sanitized = read_df_smiles(df_supplier, write_log, drop_errors)
-    return mols_sanitized
-
 
 def read_SDF(file, write_log, drop_errors):
     """Reads an SDF file and returns a sanitized molecule supplier.
@@ -309,6 +304,8 @@ def read_molecules(file, write_log, drop_errors):
         molecules = read_CSV_smiles(file, write_log, drop_errors)
     elif file.endswith(".smi"):
         molecules = read_SMI_smiles(file, write_log, drop_errors)
+    else:
+        raise ValueError(f"Unsupported file format: {file}")
     return molecules
 
 

{massa_algorithm-2.2.2 → massa_algorithm-2.2.3}/MASSA_Algorithm.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: MASSA-Algorithm
-Version: 2.2.2
+Version: 2.2.3
 Summary: MASSA Algorithm is a Python package to separate data sets of molecules into training and test sets, considering the diversity of structural, physicochemical and biological characteristics of these molecules.
 Home-page: https://github.com/gcverissimo/MASSA_Algorithm
 Author: Gabriel Corrêa Veríssimo

{massa_algorithm-2.2.2 → massa_algorithm-2.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: MASSA-Algorithm
-Version: 2.2.2
+Version: 2.2.3
 Summary: MASSA Algorithm is a Python package to separate data sets of molecules into training and test sets, considering the diversity of structural, physicochemical and biological characteristics of these molecules.
 Home-page: https://github.com/gcverissimo/MASSA_Algorithm
 Author: Gabriel Corrêa Veríssimo

{massa_algorithm-2.2.2 → massa_algorithm-2.2.3}/setup.py

@@ -5,7 +5,7 @@ with open('README.md', 'r') as readme:
 
 setuptools.setup(
     name='MASSA-Algorithm',
-    version='2.2.2',
+    version='2.2.3',
     description='MASSA Algorithm is a Python package to separate data sets of molecules into training and test sets, considering the diversity of structural, physicochemical and biological characteristics of these molecules.',
     long_description=long_description,
     long_description_content_type='text/markdown',