new analysis

utils/visualize.py

@@ -104,47 +104,48 @@ def visualize_spans(
             st.dataframe(
                 df.style.highlight_between(subset='Conf. score', right=.7))
 
-            st.subheader("Label counts & Diagnostic confidence score summary")
-            counts = df['label_'].value_counts().reindex(CATEGORIES, fill_value=0)
-
-            print(counts)
-            print(list(counts))
-            label_counts = df.groupby('label_').agg({
-                "label_":
-                'count',
-                "Conf. score": ['median', 'min', 'max']
-            }).round(4).reindex(CATEGORIES, fill_value=0)
-
-            st.dataframe(label_counts)
-            # print(list(label_counts))
-
-            sequences = list(df['label_'])
-            # Engagement ngrams
-            span_bigrams = ngrammar(seq=sequences, n=2, concat=True)
-            span_trigrams = ngrammar(seq=sequences, n=3, concat=True)
-
-            st.dataframe(pd.DataFrame(span_bigrams))
-            st.code(span_trigrams)
-
-
-            st.subheader("Engagement label by grammatical function")
-            label_dep = pd.crosstab(df['grammatical realization'], df['label_'])
-            st.dataframe(label_dep)
-
-            st.subheader('Quantitative results')
-            # st.markdown(
-            #     f"Shannon's index: {dv.alpha.shannon(list(counts), base=2): .3f}")
-            # st.markdown(
-            #     f"Simpson's e index: {1 - dv.alpha.simpson_e(list(counts)): .3f}")
-            
-            div = diversity_values(list(counts))
-            div_data = pd.DataFrame.from_dict(div, orient='index')
-            st.dataframe(div_data)            
-            
-            doc_data = pd.concat([counts, div_data], axis = 0).T
-            filename = "NA"
-            doc_data.insert(0, "filename", filename, True)
-            doc_data.insert(1, "nwords", len(doc), True)
-            st.dataframe(doc_data)            
+            if not simple:
+                st.subheader("Label counts & Diagnostic confidence score summary")
+                counts = df['label_'].value_counts().reindex(CATEGORIES, fill_value=0)
+
+                print(counts)
+                print(list(counts))
+                label_counts = df.groupby('label_').agg({
+                    "label_":
+                    'count',
+                    "Conf. score": ['median', 'min', 'max']
+                }).round(4).reindex(CATEGORIES, fill_value=0)
+
+                st.dataframe(label_counts)
+                # print(list(label_counts))
+
+                sequences = list(df['label_'])
+                # Engagement ngrams
+                span_bigrams = ngrammar(seq=sequences, n=2, concat=True)
+                span_trigrams = ngrammar(seq=sequences, n=3, concat=True)
+
+                st.dataframe(pd.DataFrame(span_bigrams))
+                st.code(span_trigrams)
+
+
+                st.subheader("Engagement label by grammatical function")
+                label_dep = pd.crosstab(df['grammatical realization'], df['label_'])
+                st.dataframe(label_dep)
+
+                st.subheader('Quantitative results')
+                # st.markdown(
+                #     f"Shannon's index: {dv.alpha.shannon(list(counts), base=2): .3f}")
+                # st.markdown(
+                #     f"Simpson's e index: {1 - dv.alpha.simpson_e(list(counts)): .3f}")
+                
+                div = diversity_values(list(counts))
+                div_data = pd.DataFrame.from_dict(div, orient='index')
+                st.dataframe(div_data)            
+                
+                doc_data = pd.concat([counts, div_data], axis = 0).T
+                filename = "NA"
+                doc_data.insert(0, "filename", filename, True)
+                doc_data.insert(1, "nwords", len(doc), True)
+                st.dataframe(doc_data)            
             # st.markdown(str(dv.alpha_diversity(metric = "shannon", counts=counts, ids = ['ENTERTAIN', 'ATTRIBUTE', 'CITATION', 'COUNTER', 'DENY', 'ENDORSE', 'PRONOUNCE', 'CONCUR', 'MONOGLOSS', 'SOURCES', 'JUSTIFYING'])))
             # print(dv.get_alpha_diversity_metrics())