Final touches for version 3.0.0

ipqa-research · Jan 9, 2025 · 68710bf · 68710bf
1 parent 2390e42
commit 68710bf
Show file tree

Hide file tree

Showing 15 changed files with 124 additions and 165 deletions.
diff --git a/README.md b/README.md
@@ -25,9 +25,14 @@ OS.
 You can try `ugropy` without installing it by clicking on the Colab badge.
 
 # Models implemented
+
+## Gibbs / EoS models
 - Classic liquid-vapor UNIFAC
 - Predictive Soave-Redlich-Kwong (PSRK)
+
+## Property estimators
 - Joback
+- Abdulelah-Gani (beta)
 
 # Writers
 `ugropy` allows you to convert the obtained functional groups or estimated

diff --git a/docs/source/tutorial/gibbs_models.ipynb b/docs/source/tutorial/gibbs_models.ipynb
@@ -103,57 +103,43 @@
     "class. The Groups class is only intended to be used when you want all the \n",
     "groups from all the models with a single call.\n",
     "\n",
-    "The signature of the UNIFAC model is:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[0;31mSignature:\u001b[0m\n",
-      "\u001b[0munifac\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_groups\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
-      "\u001b[0;34m\u001b[0m    \u001b[0midentifier\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrdkit\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mChem\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrdchem\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mMol\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
-      "\u001b[0;34m\u001b[0m    \u001b[0midentifier_type\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'name'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
-      "\u001b[0;34m\u001b[0m    \u001b[0msolver\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mugropy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0milp_solvers\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0milp_solver\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mILPSolver\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m<\u001b[0m\u001b[0;32mclass\u001b[0m \u001b[0;34m'ugropy.core.ilp_solvers.default_solver.DefaultSolver'\u001b[0m\u001b[0;34m>\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
-      "\u001b[0;34m\u001b[0m    \u001b[0msearch_multiple_solutions\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mbool\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
-      "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mugropy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrag_classes\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgibbs_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgibbs_result\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mGibbsFragmentationResult\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mList\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mugropy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrag_classes\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgibbs_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgibbs_result\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mGibbsFragmentationResult\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mDocstring:\u001b[0m\n",
-      "Get the groups of a molecule.\n",
-      "\n",
-      "Parameters\n",
-      "----------\n",
-      "identifier : Union[str, Chem.rdchem.Mol]\n",
-      "    Identifier of the molecule. You can use either the name of the\n",
-      "    molecule, the SMILEs of the molecule or a rdkit Mol object.\n",
-      "identifier_type : str, optional\n",
-      "    Identifier type of the molecule. Use \"name\" if you are providing\n",
-      "    the molecules' name, \"smiles\" if you are providing the SMILES\n",
-      "    or \"mol\" if you are providing a rdkir mol object, by default \"name\"\n",
-      "solver : ILPSolver, optional\n",
-      "    ILP solver class, by default DefaultSolver\n",
-      "search_multiple_solutions : bool, optional\n",
-      "    Weather search for multiple solutions or not, by default False\n",
-      "    If False the return will be a FragmentationResult object, if True\n",
-      "    the return will be a list of FragmentationResult objects.\n",
-      "\n",
-      "Returns\n",
-      "-------\n",
-      "Union[GibbsFragmentationResult, List[GibbsFragmentationResult]]\n",
-      "    Fragmentation result. If search_multiple_solutions is False the\n",
-      "    return will be a FragmentationResult object, if True the return\n",
-      "    will be a list of FragmentationResult objects.\n",
-      "\u001b[0;31mFile:\u001b[0m      ~/code/ugropy/ugropy/core/frag_classes/gibbs_model/gibbs_model.py\n",
-      "\u001b[0;31mType:\u001b[0m      method"
-     ]
-    }
-   ],
-   "source": [
-    "?unifac.get_groups"
+    "The signature of the UNIFAC model is:\n",
+    "\n",
+    "\n",
+    "```\n",
+    "Signature:\n",
+    "unifac.get_groups(\n",
+    "    identifier: Union[str, rdkit.Chem.rdchem.Mol],\n",
+    "    identifier_type: str = 'name',\n",
+    "    solver: ugropy.core.ilp_solvers.ilp_solver.ILPSolver = <class 'ugropy.core.ilp_solvers.default_solver.DefaultSolver'>,\n",
+    "    search_multiple_solutions: bool = False,\n",
+    ") -> Union[ugropy.core.frag_classes.gibbs_model.gibbs_result.GibbsFragmentationResult, List[ugropy.core.frag_classes.gibbs_model.gibbs_result.GibbsFragmentationResult]]\n",
+    "Docstring:\n",
+    "Get the groups of a molecule.\n",
+    "\n",
+    "Parameters\n",
+    "----------\n",
+    "identifier : Union[str, Chem.rdchem.Mol]\n",
+    "    Identifier of the molecule. You can use either the name of the\n",
+    "    molecule, the SMILEs of the molecule or a rdkit Mol object.\n",
+    "identifier_type : str, optional\n",
+    "    Identifier type of the molecule. Use \"name\" if you are providing\n",
+    "    the molecules' name, \"smiles\" if you are providing the SMILES\n",
+    "    or \"mol\" if you are providing a rdkir mol object, by default \"name\"\n",
+    "solver : ILPSolver, optional\n",
+    "    ILP solver class, by default DefaultSolver\n",
+    "search_multiple_solutions : bool, optional\n",
+    "    Weather search for multiple solutions or not, by default False\n",
+    "    If False the return will be a FragmentationResult object, if True\n",
+    "    the return will be a list of FragmentationResult objects.\n",
+    "\n",
+    "Returns\n",
+    "-------\n",
+    "Union[GibbsFragmentationResult, List[GibbsFragmentationResult]]\n",
+    "    Fragmentation result. If search_multiple_solutions is False the\n",
+    "    return will be a FragmentationResult object, if True the return\n",
+    "    will be a list of FragmentationResult objects.\n",
+    "```"
    ]
   },
   {
@@ -172,8 +158,8 @@
     {
      "data": {
       "text/plain": [
-       "[<ugropy.core.frag_classes.gibbs_model.gibbs_result.GibbsFragmentationResult at 0x7fb7ed97a2f0>,\n",
-       " <ugropy.core.frag_classes.gibbs_model.gibbs_result.GibbsFragmentationResult at 0x7fb7ed979150>]"
+       "[<ugropy.core.frag_classes.gibbs_model.gibbs_result.GibbsFragmentationResult at 0x7fbd95affc40>,\n",
+       " <ugropy.core.frag_classes.gibbs_model.gibbs_result.GibbsFragmentationResult at 0x7fbd95aff040>]"
       ]
      },
      "execution_count": 5,
@@ -381,7 +367,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -390,7 +376,7 @@
        "(np.float64(4.0464), np.float64(3.24))"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -403,7 +389,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -436,7 +422,7 @@
        "<IPython.core.display.SVG object>"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -456,7 +442,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -465,7 +451,7 @@
        "{'ACH': 5, 'ACCH3': 1}"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -487,7 +473,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -524,7 +510,7 @@
        "<IPython.core.display.SVG object>"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -535,7 +521,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
@@ -544,64 +530,14 @@
        "(np.float64(3.9227999999999996), np.float64(2.968))"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "toluene.r, toluene.q"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[0;31mSignature:\u001b[0m\n",
-      "\u001b[0mpsrk\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_groups\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
-      "\u001b[0;34m\u001b[0m    \u001b[0midentifier\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrdkit\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mChem\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrdchem\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mMol\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
-      "\u001b[0;34m\u001b[0m    \u001b[0midentifier_type\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'name'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
-      "\u001b[0;34m\u001b[0m    \u001b[0msolver\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mugropy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0milp_solvers\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0milp_solver\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mILPSolver\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m<\u001b[0m\u001b[0;32mclass\u001b[0m \u001b[0;34m'ugropy.core.ilp_solvers.default_solver.DefaultSolver'\u001b[0m\u001b[0;34m>\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
-      "\u001b[0;34m\u001b[0m    \u001b[0msearch_multiple_solutions\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mbool\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
-      "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mugropy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrag_classes\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgibbs_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgibbs_result\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mGibbsFragmentationResult\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mList\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mugropy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrag_classes\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgibbs_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgibbs_result\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mGibbsFragmentationResult\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mDocstring:\u001b[0m\n",
-      "Get the groups of a molecule.\n",
-      "\n",
-      "Parameters\n",
-      "----------\n",
-      "identifier : Union[str, Chem.rdchem.Mol]\n",
-      "    Identifier of the molecule. You can use either the name of the\n",
-      "    molecule, the SMILEs of the molecule or a rdkit Mol object.\n",
-      "identifier_type : str, optional\n",
-      "    Identifier type of the molecule. Use \"name\" if you are providing\n",
-      "    the molecules' name, \"smiles\" if you are providing the SMILES\n",
-      "    or \"mol\" if you are providing a rdkir mol object, by default \"name\"\n",
-      "solver : ILPSolver, optional\n",
-      "    ILP solver class, by default DefaultSolver\n",
-      "search_multiple_solutions : bool, optional\n",
-      "    Weather search for multiple solutions or not, by default False\n",
-      "    If False the return will be a FragmentationResult object, if True\n",
-      "    the return will be a list of FragmentationResult objects.\n",
-      "\n",
-      "Returns\n",
-      "-------\n",
-      "Union[GibbsFragmentationResult, List[GibbsFragmentationResult]]\n",
-      "    Fragmentation result. If search_multiple_solutions is False the\n",
-      "    return will be a FragmentationResult object, if True the return\n",
-      "    will be a list of FragmentationResult objects.\n",
-      "\u001b[0;31mFile:\u001b[0m      ~/code/ugropy/ugropy/core/frag_classes/gibbs_model/gibbs_model.py\n",
-      "\u001b[0;31mType:\u001b[0m      method"
-     ]
-    }
-   ],
-   "source": [
-    "?psrk.get_groups"
-   ]
   }
  ],
  "metadata": {

diff --git a/reminder.md → tests/tools/reminder.md b/reminder.md → tests/tools/reminder.md
diff --git a/ugropy/core/get_rdkit_object.py b/ugropy/core/get_rdkit_object.py
@@ -11,7 +11,10 @@
 def instantiate_mol_object(
     identifier: Union[str, Chem.rdchem.Mol], identifier_type: str = "name"
 ) -> Chem.rdchem.Mol:
-    """Instantiate a RDKit Mol object from molecule's name or SMILES.
+    """Instantiate a RDKit Mol object from molecule's name, SMILES or mol.
+
+    In case that the input its already a RDKit Mol object, the function will
+    return the input object.
 
     Parameters
     ----------

diff --git a/ugropy/core/ilp_solvers/default_solver.py b/ugropy/core/ilp_solvers/default_solver.py
@@ -16,7 +16,7 @@ class DefaultSolver(ILPSolver):
     """Default ILP solver for the set cover problem."""
 
     def solve_one_problem(self, not_valid_solutions: List = []) -> List[int]:
-        """Solve one problem with the Pulp library.
+        """Solve one `Set Cover` problem with the Pulp library.
 
         Parameters
         ----------
@@ -50,15 +50,15 @@ def solve_one_problem(self, not_valid_solutions: List = []) -> List[int]:
 
             problem += pulp.lpSum(sum_list) == 1
 
-        # Constaints 2: if are not_valid_solutions, the newones cannot use less
-        # elements than the previous ones, otherwise the first one was not
+        # Constaints 2: if are not_valid_solutions, the new ones cannot use
+        # less elements than the previous ones, otherwise the first one was not
         # optimal.
         if not_valid_solutions:
             opt = np.sum(np.array(not_valid_solutions[0], dtype=int))
 
             problem += pulp.lpSum([x[i] for i in range(n_frag)]) == opt
 
-        # Constaints 3: already get solutions not allowed
+        # Constaints 3: already got solutions not allowed
         for solution in not_valid_solutions:
             problem += (
                 pulp.lpSum([x[i] * solution[i] for i in range(n_frag)])
@@ -83,6 +83,7 @@ def solve_one_problem(self, not_valid_solutions: List = []) -> List[int]:
 
             return [pulp.value(x[i]) for i in range(n_frag)]
         else:
+            # No feasible problem
             return None
 
     def solve(self) -> None:
@@ -96,4 +97,4 @@ def solve(self) -> None:
                     break
                 not_valid_solutions.append(solution)
         else:
-            self.solve_one_problem()
+            _ = self.solve_one_problem()