automatic update

following https://gitlab.renkulab.io/astronomy/mmoda/analyse-short-astro-text/-/commit/7ecb986ba17773c42b965b2f8e81476366b43afc
esg-epfl-apc · Nov 27, 2024 · c840c85 · c840c85
1 parent d07dbe0
commit c840c85
Show file tree

Hide file tree

Showing 3 changed files with 29 additions and 34 deletions.
diff --git a/tools/analyse-short-astro-text/analyse_short_astro_text_astro_tool.xml b/tools/analyse-short-astro-text/analyse_short_astro_text_astro_tool.xml
@@ -9,7 +9,7 @@
     <requirement type="package" version="3.9.2">matplotlib</requirement>
     <requirement type="package" version="1.26.4">numpy</requirement>
     <requirement type="package" version="1.14.1">scipy</requirement>
-    <requirement type="package" version="6.1.6">astropy</requirement>
+    <requirement type="package" version="7.0.0">astropy</requirement>
     <requirement type="package" version="2.5.1">pytorch-cpu</requirement>
     <requirement type="package" version="0.33.0">accelerate</requirement>
     <requirement type="package" version="4.43.2">transformers</requirement>

diff --git a/tools/analyse-short-astro-text/pipeline_astrobert.py b/tools/analyse-short-astro-text/pipeline_astrobert.py
@@ -88,12 +88,12 @@ def get_astroBERT_cleaned_result(text_id, body_text_0):
             df_tmp1 = df_tmp0[df_tmp0["Phrase"]==phrase_]
             if len(df_tmp1) == 1:
                 dict_out["TEXT_ID"].append(text_id)
+                dict_out["Phrase"].append(df_tmp1.Phrase.values[0])
                 dict_out["word"].append(df_tmp1.word.values[0])
-                dict_out["Score"].append(df_tmp1.score.values[0])
-                dict_out["entity_group"].append(entity_to_study)
                 dict_out["start"].append(df_tmp1.start.values[0])
                 dict_out["end"].append(df_tmp1.end.values[0])
-                dict_out["Phrase"].append(df_tmp1.Phrase.values[0])
+                dict_out["Score"].append(df_tmp1.score.values[0])
+                dict_out["entity_group"].append(entity_to_study)
 
             else:
                 df_tmp1.sort_values(by=['start'])
@@ -137,3 +137,6 @@ def get_astroBERT_cleaned_result(text_id, body_text_0):
                         dict_out["entity_group"].append(entity_to_study)
 
     return pd.DataFrame(dict_out)
+
+
+def clean_ra_dec
diff --git a/tools/analyse-short-astro-text/pipeline_sources.py b/tools/analyse-short-astro-text/pipeline_sources.py
@@ -209,36 +209,28 @@ def rule_based_source_detector(atel_, atel_text):
             if source_.replace(" ","").lower() not in atel_sources:
                 atel_sources.append(source_)
 
+    atel_sources = list(set(atel_sources))
     if len(atel_sources) != 0:
-        atel_sources = list(set(atel_sources))
-        if "at2018xyz" in atel_sources:
-            atel_sources.remove("at2018xyz")
-        if "asassn18xx" in atel_sources:
-            atel_sources.remove("asassn18xx")
-
-        if len(atel_sources) != 0:
-
-            otype_list = []
-            mainid_list = []
-            ra_list     = []
-            dec_list    = []
-            for source_name in atel_sources:
-
-                dict_otype = query_simbad(source_name)
-                if dict_otype[source_name]["MAIN_ID"] == None:
-                    dict_otype = query_tns(source_name)
-                if dict_otype[source_name]["MAIN_ID"] == None:
-                    dict_otype = query_fink(source_name)
-
-                mainid_list.append(dict_otype[source_name]["MAIN_ID"])
-                otype_list.append(dict_otype[source_name]["OTYPES"])
-                ra_list.append(dict_otype[source_name]["RA"])
-                dec_list.append(dict_otype[source_name]["DEC"])
-
-            dict_data = {"ATELNO": [atel_] * len(atel_sources), "Raw Source Name": atel_sources, "Main ID Name": mainid_list, "OTYPE": otype_list, "RA": ra_list, "Dec": dec_list}
-
-            df_save = pd.DataFrame(dict_data)
-            df_save.replace({None: "NotKnown"}, inplace=True)
-            return df_save
+        otype_list = []
+        mainid_list = []
+        ra_list     = []
+        dec_list    = []
+        for source_name in atel_sources:
+
+            dict_otype = query_simbad(source_name)
+            if dict_otype[source_name]["MAIN_ID"] == None:
+                dict_otype = query_tns(source_name)
+            if dict_otype[source_name]["MAIN_ID"] == None:
+                dict_otype = query_fink(source_name)
+
+            mainid_list.append(dict_otype[source_name]["MAIN_ID"])
+            otype_list.append(dict_otype[source_name]["OTYPES"])
+            ra_list.append(dict_otype[source_name]["RA"])
+            dec_list.append(dict_otype[source_name]["DEC"])
+
+        dict_data = {"ATELNO": [atel_] * len(atel_sources), "Raw Source Name": atel_sources, "Main ID Name": mainid_list, "OTYPE": otype_list, "RA": ra_list, "Dec": dec_list}
+        df_save = pd.DataFrame(dict_data)
+        df_save.replace({None: "NotKnown"}, inplace=True)
+        return df_save
 
     return pd.DataFrame()