kludge for several specific ceramics

ChemID.py

@@ -1120,9 +1120,10 @@ def smiles2mp(smiles):
 
 def smiles2mp_opera(smiles):
     descs = padelpy.from_smiles(smiles, descriptortypes='mp/descriptors.xml')
-    dfd = pd.DataFrame(descs,index=[0])
-    dfd = dfd.replace('',0)
-    dfd = pd.DataFrame(dfd, dtype=float)
+    #dfd = pd.DataFrame(descs,index=[0])
+    #dfd = dfd.replace('',0).infer_objects(copy=False)
+    #dfd = pd.DataFrame(dfd, dtype=float)
+    dfd = pd.DataFrame(descs, index=[0]).apply(pd.to_numeric, errors="coerce").fillna(0.0).astype(float)
     X = np.array(dfd[my_opera_data_mp.desc_list])
     X_scale = my_opera_data_mp.scaler_X.transform(X)
     y_pred = my_opera_data_mp.scaler_y.inverse_transform(my_opera_data_mp.knn_all.predict(X_scale))
@@ -1130,7 +1131,13 @@ def smiles2mp_opera(smiles):
 
 def mol2mp(cas, name, smiles):
     mp, mp_origin = None, None
-    if cas:
+    if pd.isna(mp) and smiles:
+        try:
+            mp = smiles2mp_opera(smiles)
+            mp_origin = 'opera/calc'
+        except:
+            mp, mp_origin = None, None
+    if pd.isna(mp) and cas:
         try:
             mp, mp_origin = string2mp(cas)
         except:
@@ -1146,12 +1153,6 @@ def mol2mp(cas, name, smiles):
             mp_origin = 'joback-reid/calc'
         except:
             mp, mp_origin = None, None
-    if pd.isna(mp) and smiles:
-        try:
-            mp = smiles2mp_opera(smiles)
-            mp_origin = 'opera/calc'
-        except:
-            mp, mp_origin = None, None
     return mp, mp_origin
 
 def getLogP(cas,mol):

data/ceramics_list.txt

@@ -93,6 +93,7 @@ Ba,O,Y,Zr
 Ba,O,Zr
 Be,C,O,Si
 Be,O
+Bi,O,V
 C,Ce,N,O,Si
 C,Ce,N,O,Si,Ti
 C,Co,W

data/custom_chemicals_db.tsv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc9cf2c56f141aad1c46cc168d1a133d288a7fb51ee3290a62041fd117897f3
-size 13049
+oid sha256:7a9183ad38e8e8c7e82cdf693be2a3b92f2fec1e29a9a55e910c4d6fcf617732
+size 14568