Update app.py

app.py

@@ -17,12 +17,16 @@ import pandas as pd
 PARQUET_DATASET_DIR = Path("parquet_dataset")
 PARQUET_DATASET_DIR.mkdir(parents=True,exist_ok=True)
 
+sample_data = [f"CHEM1402_gt/24F_CHEM1402_Night_Class_Week_{i}_gt.rttm" for i in range(1,11)]
+
 
 scheduler = ps.ParquetScheduler(repo_id="Sonogram/SampleDataset")
 
-# Store results for viewing
+# Store results for viewing and further processing
 if 'results' not in st.session_state:
     st.session_state.results = []
+if 'summaries' not in st.session_state:
+    st.session_state.summaries = []
     
 def save_data(
     config_dict: Dict[str,str], audio_paths: List[str], userid: str,
@@ -76,6 +80,7 @@ if uploaded_file_paths is not None:
         audio_tabs = st.tabs([f.name for f in valid_files])
     while (len(st.session_state.results) < len(valid_files)):
         st.session_state.results.append([])
+        st.session_state.summaries.append([])
     st.info(f'{len(valid_files)} valid files: {[fi.name for fi in valid_files]}')
 for j, tab in enumerate(audio_tabs):
     if tab.button("Analyze Audio",key=f"button_{j}"):
@@ -85,11 +90,11 @@ for j, tab in enumerate(audio_tabs):
             # Process
             # Pretend to take time as an example
             with st.spinner(text='NOT ACTUALLY ANALYZING, JUST A FILLER ANIMATION'):
-                time.sleep(5)
+                time.sleep(1)
                 st.success('Done')
                 
             # RTTM load as filler
-            speakerList, annotations = su.loadAudioRTTM("24F CHEM1402 Night Class Week 4.rttm")
+            speakerList, annotations = su.loadAudioRTTM(sample_data[j])
             st.session_state.results[j] = (speakerList,annotations)
             
     if len(st.session_state.results) > j and len(st.session_state.results[j]) > 0:
@@ -247,14 +252,40 @@ for j, tab in enumerate(audio_tabs):
             tab.write("Total length of audio: {}h:{:02d}m:{:02d}s".format(int(totalSeconds/3600),int((totalSeconds%3600)/60),int(totalSeconds%60)))
             tab.table(df)
             
-            #for i,speaker in enumerate(all_speaker_times):
-            #    tab.write("Speaker {} spoke: {}h:{:02d}m:{:02d}s -> {:.2f}% of time".format(i,
-            #                                                                               int(speaker/3600),
-            #                                                                               int((speaker%3600)/60),
-            #                                                                               int(speaker%60),
-            #                                                                               100*speaker/totalSeconds))
+            st.session_state.summaries[j] = [totalSeconds,lecturer_speaker_times,all_speaker_times]
+
+with st.spinner(text='Processing summary results...'):
+    summary_count = 0
+    for su in st.session_state.summaries:
+        if len(su) > 0:
+            summary_count += 1
+
 
+    lecturer_data = pd.DataFrame({
+        'ds' : range(summary_count) ,
+        'y' : [100*ssm[1][0]/ssm[0] for ssm in enumerate(st.session_state.summaries)]
+                                 
+    })
+    audience_data = pd.DataFrame({
+        'ds' : range(summary_count) ,
+        'y' : [100*ssm[1][1]/ssm[0] for ssm in enumerate(st.session_state.summaries)]
+                                 
+    })
+    speaker_data = pd.DataFrame({
+        'ds' : range(summary_count) ,
+        'y' : [len(ssm[2]) for ssm in enumerate(st.session_state.summaries)]
+                                 
+    })
+    fig_la = px.line(lecturer_data, x="ds", y="y", color_discrete_sequence=["#0514C0"], labels={'y': 'Lecturer Time'})
+    fig_la.add_scatter(x=audience_data['ds'], y=audience_data['y'], mode='lines', name='Audience Time', line=dict(color='#4CC005'))
+    fig_la.update_layout(title='Percentage of Time Speaking for Lecturer and Audience', xaxis_title='File', yaxis_title='Percent Time Spoken')
+    st.plotly_chart(fig_la, use_container_width=True)
 
+    fig_spc = px.line(speaker_data, x="ds", y="y", color_discrete_sequence=["#0514C0"], labels={'y': 'Speaker Count'})
+    fig_spc.update_layout(title='Number of Distinct Speakers over Time', xaxis_title='File', yaxis_title='# of Distinct Speakers')
+    st.plotly_chart(fig_spc, use_container_width=True)
+
+    
 userid = st.text_input("user id:", "Guest")
 colorPref = st.text_input("Favorite color?", "None")
 radio = st.radio('Pick one:', ['Left','Right'])
@@ -263,5 +294,4 @@ if st.button("Upload Files to Dataset"):
     save_data({"color":colorPref,"direction":radio,"number":selection},
              file_paths,
              userid)
-    st.success('I think it worked!')
-    
+    st.success('I think it worked!')