identify_unknown_sptypes: use vizier tic catalogue and print best match

This reverts commit 87f71c386e.

identify_unknown_sptypes.py

@@ -1,8 +1,25 @@
 from astroquery.simbad import Simbad
+from astroquery.vizier import Vizier
+from astropy.coordinates import Angle
 import pandas as pd
+import numpy as np
+
+from main.astrodatagui.db.StarsDB import StarDB
+
+class bcolors:
+    HEADER = '\033[95m'
+    OKBLUE = '\033[94m'
+    OKGREEN = '\033[92m'
+    WARNING = '\033[93m'
+    FAIL = '\033[91m'
+    ENDC = '\033[0m'
+    BOLD = '\033[1m'
+    UNDERLINE = '\033[4m'
 
 simbad = Simbad()
 
+starDB: StarDB = StarDB.getInstance("stars.db")
+
 bvStars = ["1RXS J064643.6-770027", "BD-08   995", "CPD-19   878", "PM J07058-5848", "TYC 1360-957-1", "TYC 4595-107-1"]
 jhcStars = ["2MASS J18524052+4156057", "2MASS J18534407+4208274", "2MASS J18535462+4135227", "2MASS J19335656+4010546"]
 
@@ -10,21 +27,62 @@ filters = ["U", "B", "V", "R", "I", "J", "H", "K", "u", "g", "r", "i", "z", "G",
 for f in filters:
     simbad.add_votable_fields(f"flux({f})")
 
+vizierTIC = Vizier(catalog="IV/38/tic",
+                   columns=["TIC", "HIP", "TYC", "UCAC4", "2MASS", "GAIA", "KIC", "S/G", "Teff", "Rad", "Mass", "LClass", "Dist"])
+
 spTypeTable = pd.read_csv("cousins.cols")
 
 weights = {"SpType": 0.0,
-           "U-B": 1.0,
+           "U-B": 2.0,
-           "B-V": 1.0,
+           "B-V": 2.0,
-           "V-R": 0.0,
+           "V-R": 0.8,
-           "V-I": 0.0,
+           "V-I": 0.7,
-           "V-J": 0.0,
+           "V-J": 0.6,
-           "V-H": 0.0,
+           "V-H": 0.5,
-           "V-K": 0.0,
+           "V-K": 0.4,
            "V-L": 0.0,
            "V-M": 0.0,
            "V-N": 0.0}
 
-for star in bvStars:
+spTypeTeffMinTable = {2700: "M",
+                      4000: "K",
+                      5440: "G",
+                      6300: "F",
+                      7920: "A"}
+
+def getSpTypeFromTeff(Teff):
+    if(Teff >= 30000):
+        return "O"
+    elif(Teff >= 10000):
+        return "B"
+    elif(Teff >= 7500):
+        return "A"
+    elif(Teff >= 6000):
+        return "F"
+    elif(Teff >= 5200):
+        return "G"
+    elif(Teff >= 3700):
+        return "K"
+    elif(Teff >= 2400):
+        return "M"
+    else:
+        return "L"
+
+resTable = {"StarID": [],
+            "simbad B-V": [],
+            "simbad SpType": [],
+            "vizier Teff": [],
+            "vizier Mass": [],
+            "vizier Radius": [],
+            "vizier SpType": [],
+            "vizier Lum. Class": [],
+            "Final SpType": []}
+resTable = pd.DataFrame(resTable)
+
+allStars = []
+allStars.extend(bvStars)
+allStars.extend(jhcStars)
+for star in allStars:
     star = simbad.query_object(star)
     U_B = star["FLUX_U"] - star["FLUX_B"]
     B_V = star["FLUX_B"] - star["FLUX_V"]
@@ -44,26 +102,78 @@ for star in bvStars:
     fluxDiff = pd.DataFrame(fluxDiff)
     fluxDiffValColumns = fluxDiff.columns[fluxDiff.notna().iloc[0]]
 
-    matchingColumnsUBV = spTypeTable.columns.intersection(fluxDiffValColumns)
+    matchingColumnsUBVIJHK = spTypeTable.columns.intersection(fluxDiffValColumns)
-    distancesUBV = spTypeTable[matchingColumnsUBV].sub(fluxDiff.iloc[0]).pow(2).sum(axis=1)
+    distancesUBV = spTypeTable[matchingColumnsUBVIJHK].sub(fluxDiff.iloc[0]).pow(2).sum(axis=1)
-    bestMatchIndexUBV = distancesUBV.idxmin()
+    bestMatchIndexUBVIJHK = distancesUBV.idxmin()
-    bestMatchNameUBV = spTypeTable.iloc[bestMatchIndexUBV, 0]
+    bestMatchNameUBV = spTypeTable.iloc[bestMatchIndexUBVIJHK, 0]
 
-    distancesUBVweighted = (
+    distancesUBVIJHKweighted = (
-        spTypeTable[matchingColumnsUBV]
+        spTypeTable[matchingColumnsUBVIJHK]
-        .sub(fluxDiff.iloc[0][matchingColumnsUBV])
+        .sub(fluxDiff.iloc[0][matchingColumnsUBVIJHK])
         .pow(2)
-        .multiply([weights[col] for col in matchingColumnsUBV], axis=1)
+        .multiply([weights[col] for col in matchingColumnsUBVIJHK], axis=1)
         .sum(axis=1)
     )
-    bestMatchIndexUBVweighted = distancesUBVweighted.idxmin()
+    bestMatchIndexUBVIJHKweighted = distancesUBVIJHKweighted.idxmin()
-    bestMatchNameUBVweighted = spTypeTable.iloc[bestMatchIndexUBVweighted, 0]
+    bestMatchNameUBVweighted = spTypeTable.iloc[bestMatchIndexUBVIJHKweighted, 0]
 
-    print(f"{star['MAIN_ID'].value[0]}: {bestMatchNameUBV}/{bestMatchNameUBVweighted} type star")
+    distancesUBVonlyWeighted = (
-    print("Table entry: ")
+        spTypeTable[matchingColumnsUBVIJHK]
-    print(spTypeTable.iloc[bestMatchIndexUBV:bestMatchIndexUBV+1])
+        .sub(fluxDiff.iloc[0][matchingColumnsUBVIJHK])
-    print("Weighted Table entry:")
+        .pow(2)
-    print(spTypeTable.iloc[bestMatchIndexUBVweighted:bestMatchIndexUBVweighted+1])
+        .multiply([1.0 if(col == "U-B" or col == "B-V") else 0.0 for col in matchingColumnsUBVIJHK], axis=1)
-    print("Star: ")
+        .sum(axis=1)
-    print(fluxDiff)
+    )
-    print("-------------------------------------------------------------------------------------")
+    bestMatchIndexUBVonlyWeighted = distancesUBVonlyWeighted.idxmin()
+    bestMatchNameUBVonlyWeighted = spTypeTable.iloc[bestMatchIndexUBVonlyWeighted, 0] if (not np.isnan(U_B) or not np.isnan(B_V)) else ""
+
+    starName = star['MAIN_ID'].value[0]
+    regionResults = vizierTIC.query_region(starName,
+                                           radius=Angle(5, "arcsec"))
+    altNames = [an[0] for an in starDB.getStarAltNames(starName)[:-1]]
+    vizierTable = None
+    for reg in regionResults:
+        for row in reg:
+            for aN in altNames:
+                if((str(row["TIC"]) in aN or
+                    str(row["GAIA"]) in aN or
+                    str(row["_2MASS"]) in aN) and
+                   row["LClass"] == "DWARF"):
+                    vizierTable = row
+                    break
+            else:
+                continue
+            break
+        else:
+            continue
+        break
+
+    Teff = vizierTable["Teff"]
+    vizierSpType = getSpTypeFromTeff(Teff)
+
+    finalSpType = ""
+    if(bestMatchNameUBVonlyWeighted == "" or
+       bestMatchNameUBVonlyWeighted[0] == vizierSpType):
+        finalSpType = vizierSpType
+    else:
+        if(bestMatchNameUBVonlyWeighted[1] == "0"):
+            finalSpType = vizierSpType
+        else:
+            finalSpType = bestMatchNameUBVonlyWeighted[0]
+
+    if(vizierTable is None):
+        resTable = pd.concat([resTable,
+                             pd.DataFrame([[starName, B_V[0], bestMatchNameUBVonlyWeighted,
+                                             "", "", "", "", "",
+                                             finalSpType]],
+                                        columns=resTable.columns)],
+                             ignore_index=True)
+    else:
+        resTable = pd.concat([resTable,
+                             pd.DataFrame([[starName, B_V[0], bestMatchNameUBVonlyWeighted,
+                                             vizierTable["Teff"], vizierTable["Mass"], vizierTable["Rad"], vizierSpType, vizierTable["LClass"],
+                                             finalSpType]],
+                                        columns=resTable.columns)],
+                             ignore_index=True)
+
+print(resTable.to_string())