Major Visual Change

app.py

@@ -26,6 +26,15 @@ import datetime as dt
 enableDenoise = False
 earlyCleanup = True
 
+# [None,Low,Medium,High,Debug]
+# [0,1,2,3,4]
+verbosity=4
+
+def printV(message,verbosityLevel):
+    global verbosity
+    if verbosity>=verbosityLevel:
+        print(message)
+        
 def save_data(
     config_dict: Dict[str,str], audio_paths: List[str], userid: str,
     ) -> None:
@@ -138,18 +147,21 @@ def analyze(inFileName):
         currFileIndex = file_names.index(inFileName)
         print(f"Found at index {currFileIndex}")
         if len(st.session_state.results) > currFileIndex and len(st.session_state.summaries) > currFileIndex and len(st.session_state.results[currFileIndex]) > 0:
+            
+            printV(f'In if',4)
             # Handle 
             currAnnotation, currTotalTime = st.session_state.results[currFileIndex]
             speakerNames = currAnnotation.labels()
-    
+            printV(f'Loaded results',4)
             # Update other categories
             unusedSpeakers = st.session_state.unusedSpeakers[currFileIndex]
             categorySelections = st.session_state["categorySelect"][currFileIndex]
-            
+            printV(f'Loaded speaker selections',4)
             noVoice, oneVoice, multiVoice = su.calcSpeakingTypes(currAnnotation,currTotalTime)
             sumNoVoice = su.sumTimes(noVoice)
             sumOneVoice = su.sumTimes(oneVoice)
             sumMultiVoice = su.sumTimes(multiVoice)
+            printV(f'Calculated speaking types',4)
             
             df3 = pd.DataFrame(
                 {
@@ -161,6 +173,7 @@ def analyze(inFileName):
             )
             df3.name = "df3"
             st.session_state.summaries[currFileIndex]["df3"] = df3
+            printV(f'Set df3',4)
             
             df4_dict = {}
             nameList = st.session_state.categories
@@ -181,13 +194,17 @@ def analyze(inFileName):
                 else:
                     extraNames.append(sp)
                     extraValues.append(su.sumTimes(currAnnotation.subset([sp])))
+            extraPairsSorted = sorted(zip(extraNames, extraValues), key=lambda pair: pair[0])
+            extraNames, extraValues = zip(*extraPairsSorted)
             df4_dict = {
-                    "values": valueList+extraValues,
-                    "names": nameList+extraNames,
+                    "values": valueList+list(extraValues),
+                    "names": nameList+list(extraNames),
                 }
             df4 = pd.DataFrame(data=df4_dict)
             df4.name = "df4"
             st.session_state.summaries[currFileIndex]["df4"] = df4
+
+            printV(f'Set df4',4)
             
             speakerList,timeList = su.sumTimesPerSpeaker(oneVoice)
             multiSpeakerList, multiTimeList = su.sumMultiTimesPerSpeaker(multiVoice)
@@ -228,6 +245,7 @@ def analyze(inFileName):
             )
             df5.name = "df5"
             st.session_state.summaries[currFileIndex]["df5"] = df5
+            printV(f'Set df5',4)
             
             speakers_dataFrame,speakers_times = su.annotationToDataFrame(currAnnotation)
             st.session_state.summaries[currFileIndex]["speakers_dataFrame"] = speakers_dataFrame
@@ -239,6 +257,7 @@ def analyze(inFileName):
             }
             df2 = pd.DataFrame(df2_dict)
             st.session_state.summaries[currFileIndex]["df2"] = df2
+            printV(f'Set df2',4)
     except ValueError as e:
         print(f"Value Error: {e}")
         pass
@@ -420,9 +439,9 @@ else:
             print(f"Took {time.time() - start_time} seconds to analyze {totalFiles} files!")
             st.success(f"Took {time.time() - start_time} seconds to analyze {totalFiles} files!")
 
-summaryRadio = st.sidebar.empty()
+
 currFile = st.sidebar.selectbox('Current File', file_names,on_change=updateMultiSelect,key="select_currFile")
-viewSelection = st.sidebar.selectbox('View', viewChoices)
+
 if currFile is None and len(st.session_state.results) > 0 and len(st.session_state.results[0]) > 0:
     st.write("Select a file to view from the sidebar")
 try:
@@ -430,9 +449,16 @@ try:
     currFileIndex = file_names.index(currFile)
     if len(st.session_state.results) > currFileIndex and len(st.session_state.summaries) > currFileIndex and len(st.session_state.results[currFileIndex]) > 0:
         st.header(f"Analysis of file {currFile}")
+        graphNames = ["Data","Voice Categories","Speaker Percentage","Speakers with Categories","Treemap","Timeline","Time Spoken"]
+        dataTab, pie1, pie2, sunburst1, treemap1, timeline, bar1 = st.tabs(graphNames)
         # Handle 
         currAnnotation, currTotalTime = st.session_state.results[currFileIndex]
         speakerNames = currAnnotation.labels()
+    
+        speakers_dataFrame = st.session_state.summaries[currFileIndex]["speakers_dataFrame"]
+        currDF = speakers_dataFrame
+        speakers_times = st.session_state.summaries[currFileIndex]["speakers_times"]
+        
         # Update other categories
         unusedSpeakers = st.session_state.unusedSpeakers[currFileIndex]
         categorySelections = st.session_state["categorySelect"][currFileIndex]
@@ -450,6 +476,11 @@ try:
        
         newCategory = st.sidebar.text_input('Add category', key='categoryInput',on_change=addCategory) 
 
+        catTypeColors = su.colorsCSS(3)
+        allColors = su.colorsCSS(len(speakerNames)+len(st.session_state.categories))
+        speakerColors = allColors[:len(speakerNames)]
+        catColors = allColors[len(speakerNames):]
+        
         df4_dict = {}
         nameList = st.session_state.categories
         extraNames = []
@@ -472,25 +503,39 @@ try:
         df4.name = "df4"
         st.session_state.summaries[currFileIndex]["df4"] = df4
 
-        viewSelection = [viewSelection]
-
-        if viewChoices[0] in viewSelection:
+        with dataTab:
+            st.dataframe(currDF)
+        with pie1:
             df3 = st.session_state.summaries[currFileIndex]["df3"]
             fig1 = go.Figure()
             fig1.update_layout(
                 title_text="Percentage of each Voice Category",
+            colorway=catTypeColors,
+            plot_bgcolor='rgba(0, 0, 0, 0)',
+            paper_bgcolor='rgba(0, 0, 0, 0)',
             )
-            fig1.add_trace(go.Pie(values=df3["values"],labels=df3["names"]))
+            fig1.add_trace(go.Pie(values=df3["values"],labels=df3["names"],sort=False))
             st.plotly_chart(fig1, use_container_width=True)
-        if viewChoices[1] in viewSelection:
+
+        with pie2:
             df4 = st.session_state.summaries[currFileIndex]["df4"]
+        
+            # Some speakers may be missing, so fix colors
+            figColors = []
+            for n in df4["names"]:
+                if n in speakerNames:
+                    figColors.append(speakerColors[speakerNames.index(n)])
             fig2 = go.Figure()
             fig2.update_layout(
                 title_text="Percentage of Speakers and Custom Categories",
+                colorway=catColors+figColors,
+                plot_bgcolor='rgba(0, 0, 0, 0)',
+                paper_bgcolor='rgba(0, 0, 0, 0)',
             )
-            fig2.add_trace(go.Pie(values=df4["values"],labels=df4["names"]))
+            fig2.add_trace(go.Pie(values=df4["values"],labels=df4["names"],sort=False))
             st.plotly_chart(fig2, use_container_width=True)
-        if viewChoices[2] in viewSelection:
+
+        with sunburst1:
             df5 = st.session_state.summaries[currFileIndex]["df5"]
             fig3_1 = px.sunburst(df5,
                                 branchvalues = 'total',
@@ -501,6 +546,7 @@ try:
                                 custom_data=['labels','valueStrings','percentiles','parentNames','parentPercentiles'],
                                 color = 'labels',
                                 title="Percentage of each Voice Category with Speakers",
+                                color_discrete_sequence=catTypeColors+speakerColors,
                                 )
             fig3_1.update_traces(
                 hovertemplate="<br>".join([
@@ -511,8 +557,13 @@ try:
                     'Percentage of Parent: %{customdata[4]:.2f}%'
                 ])
             )
+            fig3_1.update_layout(
+                plot_bgcolor='rgba(0, 0, 0, 0)',
+                paper_bgcolor='rgba(0, 0, 0, 0)',
+            )
             st.plotly_chart(fig3_1, use_container_width=True)
-        if viewChoices[3] in viewSelection:
+    
+        with treemap1:
             df5 = st.session_state.summaries[currFileIndex]["df5"]
             fig3 = px.treemap(df5,
                             branchvalues = "total",
@@ -523,6 +574,7 @@ try:
                             custom_data=['labels','valueStrings','percentiles','parentNames','parentPercentiles'],
                             color='labels',
                             title="Division of Speakers in each Voice Category",
+                            color_discrete_sequence=catTypeColors+speakerColors,
                              )
             fig3.update_traces(
                 hovertemplate="<br>".join([
@@ -532,17 +584,19 @@ try:
                     'Parent: %{customdata[3]}',
                     'Percentage of Parent: %{customdata[4]:.2f}%'
                 ])
+            ))
+            fig3.update_layout(
+                plot_bgcolor='rgba(0, 0, 0, 0)',
+                paper_bgcolor='rgba(0, 0, 0, 0)',
             )
             st.plotly_chart(fig3, use_container_width=True)
-        if viewChoices[4] in viewSelection:
-            speakers_dataFrame = st.session_state.summaries[currFileIndex]["speakers_dataFrame"]
-            currDF = speakers_dataFrame
-            speakers_times = st.session_state.summaries[currFileIndex]["speakers_times"]
-           
-            # generate plotting window
-    
-    
-            fig_la = px.timeline(speakers_dataFrame, x_start="Start", x_end="Finish", y="Resource", color="Resource",title="Timeline of Audio with Speakers")
+       
+        # generate plotting window
+
+
+        with timeline:
+            fig_la = px.timeline(speakers_dataFrame, x_start="Start", x_end="Finish", y="Resource", color="Resource",title="Timeline of Audio with Speakers",
+                                color_discrete_sequence=speakerColors)
             fig_la.update_yaxes(autorange="reversed") 
             
             hMax = int(currTotalTime//3600)
@@ -561,20 +615,26 @@ try:
                     ),
                 xaxis_title="Time",
                 yaxis_title="Speaker",
-                legend_title=None
+                legend_title=None,
+                plot_bgcolor='rgba(0, 0, 0, 0)',
+                paper_bgcolor='rgba(0, 0, 0, 0)',
             )
             
             st.plotly_chart(fig_la, use_container_width=True)
-        if viewChoices[5] in viewSelection:
+    
+        with bar1:
             df2 = st.session_state.summaries[currFileIndex]["df2"]
             fig2_la = px.bar(df2, x="values", y="names", color="names", orientation='h',
-                            custom_data=["names","values"],title="Time Spoken by each Speaker")
+                            custom_data=["names","values"],title="Time Spoken by each Speaker",
+                            color_discrete_sequence=catColors+speakerColors)
             fig2_la.update_xaxes(ticksuffix="%")
             fig2_la.update_yaxes(autorange="reversed") 
             fig2_la.update_layout(
                 xaxis_title="Percentage Time Spoken",
                 yaxis_title="Speaker",
-                legend_title=None
+                legend_title=None,
+                plot_bgcolor='rgba(0, 0, 0, 0)',
+                paper_bgcolor='rgba(0, 0, 0, 0)',
                 
             )
             fig2_la.update_traces(
@@ -587,11 +647,9 @@ try:
 
 except ValueError:
     pass
-    
+
 if len(st.session_state.results) > 0:
-    st.session_state.showSummary = st.radio('Display Multi-file Summary?',['Yes','No'])
-    
-    if st.session_state.showSummary == 'Yes':
+    with st.expander("Multi-file Summary Data"):
         st.header("Multi-file Summary Data")
         with st.spinner(text='Processing summary results...'):
             fileNames = st.session_state.file_names