keywords by sdg proportion

appStore/sdg_analysis.py

@@ -108,7 +108,7 @@ def app():
                 with st.spinner("Running SDG Classification{}".format(warning_msg)):
 
                     df, x = sdg_classification(allDocuments['documents'])
-                    sdg_labels = df.SDG.unique()
+                    sdg_labels = x.count.unique()
                     textrankkeywordlist = []
                     for label in sdg_labels:
                         sdgdata = " ".join(df[df.SDG == label].text.to_list())

utils/sdg_classifier.py

@@ -96,7 +96,7 @@ def sdg_classification(haystackdoc:List[Document])->Tuple[DataFrame,Series]:
     x = x.rename('count')
     x = x.rename_axis('SDG').reset_index()
     x["SDG"] = pd.to_numeric(x["SDG"])
-    x = x.sort_values(by=['SDG'])
+    x = x.sort_values(by=['count'])
     x['SDG_name'] = x['SDG'].apply(lambda x: _lab_dict[x])
     x['SDG'] = x['SDG'].apply(lambda x: "SDG "+str(x))
     df= df.drop(['Relevancy'], axis = 1)