updated error handling

ChemID.py

@@ -70,7 +70,7 @@ def ResolveChemical(chemName, IDtype, debug=False):
             name = cas2name(cas)
             rho, rho_origin = string2density(cas)
             mp, mp_origin = mol2mp(cas, name, smiles)
-            if rho is None and name:
+            if pd.isna(rho) and name:
                 rho, rho_origin = string2density(name)
             try:
                 mol = Chem.MolFromSmiles(smiles)
@@ -92,7 +92,7 @@ def ResolveChemical(chemName, IDtype, debug=False):
         if name:
             cas = name2cas(name)
             rho, rho_origin = string2density(name)
-        if rho is None and cas:
+        if pd.isna(rho) and cas:
             rho, rho_origin = string2density(cas)
 
         mp, mp_origin = mol2mp(cas, name, smiles)
@@ -111,19 +111,19 @@ def ResolveChemical(chemName, IDtype, debug=False):
     elif IDtype == 'common':
         name = chemName
 
-        # try this first because sometimes iupac names don't work
-        rho, rho_origin = string2density(name)
-
         name, name_origin = name2iupac(name)
         smiles = name2smiles(name)
         cas = name2cas(name)
         if not smiles:
             smiles = cas2smiles(cas)
 
-        if rho is None and cas:
+        if pd.isna(rho) and cas:
             rho, rho_origin = string2density(cas)
-        if rho is None:
+        if pd.isna(rho):
             rho, rho_origin = string2density(name)
+        if pd.isna(rho):
+            # try this because sometimes iupac names don't work
+            rho, rho_origin = string2density(chemName)
 
         if smiles:
             mp, mp_origin = mol2mp(cas, name, smiles)
@@ -502,11 +502,11 @@ def string2density(name):
         mask = df_pred['CASRN'] == name
         if sum(mask):
             rho = float(df_pred[mask]['DENSITY_G/CM^3_TEST_PRED'])
-            rho_origin = 'pred'
+            rho_origin = 'comptox/pred'
     # try to scrape from PubChem
     if pd.isna(rho):
+        content = None
         try:
-            content = None
             compounds = pcp.get_compounds(name, namespace='name')
             c = compounds[0]
             cid = c.cid
@@ -603,7 +603,7 @@ def string2density(name):
                         value = re.sub(' \([0-9]*\)', '', text.strip())
                         try:
                             rho = float(value)
-                            rho_origin = 'expt/dsstox'
+                            rho_origin = 'dsstox/expt'
                         except:
                             rho, rho_origin = None, None
                         if pd.isna(rho):
@@ -612,16 +612,14 @@ def string2density(name):
                             value = re.sub(' \([0-9]*\)', '', text.strip())
                             try:
                                 rho = float(value)
-                                rho_origin = 'pred/dsstox'
+                                rho_origin = 'dsstox/pred'
                             except:
                                 rho, rho_origin = None, None
                     else:
                         rho, rho_origin = None, None
             else:
                 rho, rho_origin = None, None
-    if pd.isna(rho):
-        rho = None
-        rho_origin = None
+    if pd.isna(rho): rho,rho_origin = None, None
     return rho, rho_origin
 
 def return_non_duplicate_index(tuples): ##Given a list of sets return index of non_duplicate items
@@ -860,13 +858,13 @@ def string2mp(name):
     # try the chemicals package
     if is_cas(name):
         cas = name
-        if mp is None:
+        if pd.isna(mp):
             mp = chemicals.Tm(cas)
             if mp: mp = mp-273.15
             methods = chemicals.Tm_methods(cas)
             if methods: mp_origin = 'chem/'+methods[0]
         # experimental values
-        if mp is None:
+        if pd.isna(mp):
             # some rows have multiple comma-separated cas numbers
             mask = dfmp_expt['CAS'].str.contains(cas)
             if sum(mask):
@@ -876,21 +874,21 @@ def string2mp(name):
                         mp = float(dfmp_expt.iloc[index]['MP'])
                         mp_origin = 'expt'
         # predicted values from Mansouri
-        #if mp is None:
+        #if pd.isna(mp):
         #    mask = dfmp_pred['Substance_CASRN'] == cas
         #    if sum(mask):
         #        mp = float(dfmp_pred[mask]['NCCT_MP'])
         #        mp_origin = 'pred'
         # predicted values from OPERA (CompTox dashboard)
-        if mp is None:
+        if pd.isna(mp):
             mask = df_pred['CASRN'] == cas
             if sum(mask):
                 mp = float(df_pred[mask]['MELTING_POINT_DEGC_OPERA_PRED'])
-                mp_origin = 'pred'
+                mp_origin = 'comptox/pred'
     # try to scrape from PubChem
-    if mp is None:
+    if pd.isna(mp):
+        content = None
         try:
-            content = None
             compounds = pcp.get_compounds(name, namespace='name')
             c = compounds[0]
             cid = c.cid
@@ -954,7 +952,7 @@ def string2mp(name):
                 mp, mp_origin = None, None
     # try to scrape from DSSTOX website...
     if try_dsstox:
-        if mp is None:
+        if pd.isna(mp):
             dtxsid = None
             # try to find it via the dsstox dashboard
             try:
@@ -1004,24 +1002,23 @@ def string2mp(name):
                         value = re.sub(' \([0-9]*\)', '', text.strip())
                         try:
                             mp = float(value)
-                            mp_origin = 'expt/dsstox'
+                            mp_origin = 'dsstox/expt'
                         except:
                             mp, mp_origin = None, None
-                        if mp is None:
+                        if pd.isna(mp):
                             rows = mysoup.find_all('div', attrs={'col-id':'predavg'})
                             text = rows[ifound].text
                             value = re.sub(' \([0-9]*\)', '', text.strip())
                             try:
                                 mp = float(value)
-                                mp_origin = 'pred/dsstox'
+                                mp_origin = 'dsstox/pred'
                             except:
                                 mp, mp_origin = None, None
                     else:
                         mp, mp_origin = None, None
             else:
                 mp, mp_origin = None, None
-    if mp is not None and np.isnan(mp): mp = None
-    if mp is None: mp_origin = None
+    if pd.isna(mp): mp, mp_origin = None, None
     return mp, mp_origin
 
 def smiles2mp(smiles):
@@ -1038,15 +1035,15 @@ def mol2mp(cas, name, smiles):
             mp, mp_origin = string2mp(cas)
         except:
             mp, mp_origin = None, None
-    if mp is None and name:
+    if pd.isna(mp) and name:
         try:
             mp, mp_origin = string2mp(name)
         except:
             mp, mp_origin = None, None
-    if mp is None and smiles:
+    if pd.isna(mp) and smiles:
         try:
             mp = smiles2mp(smiles)
-            mp_origin = 'calc'
+            mp_origin = 'joback-reid/calc'
         except:
             mp, mp_origin = None, None
     return mp, mp_origin
@@ -1057,9 +1054,9 @@ def getLogP(cas,mol):
         mask = df_pred['CASRN'] == cas
         if sum(mask):
             LogP = float(df_pred[mask]['OCTANOL_WATER_PARTITION_LOGP_OPERA_PRED'])
-            LogP_origin = 'pred'
+            LogP_origin = 'comptox/pred'
     if pd.isna(LogP) and mol:
         LogP = Crippen.MolLogP(mol)
-        LogP_origin = 'calc'
+        LogP_origin = 'rdkit/calc'
     return LogP, LogP_origin