Update app.py

app.py

@@ -198,92 +198,108 @@ def analyze(inFileName):
             st.session_state.summaries[currFileIndex]["df3"] = df3
             printV(f'Set df3',4)
             
-            df4_dict = {}
+            # --- Build df4 ---
             nameList = st.session_state.categories
             extraNames = []
             valueList = [0 for i in range(len(nameList))]
             extraValues = []
-            
+
             for sp in speakerNames:
                 foundSp = False
                 for i, categoryName in enumerate(nameList):
                     if sp in categorySelections[i]:
-                        #st.info(categoryName)
                         valueList[i] += su.sumTimes(currAnnotation.subset([sp]))
                         foundSp = True
                         break
-                if foundSp:
-                    continue
-                else:
+                if not foundSp:
                     extraNames.append(sp)
                     extraValues.append(su.sumTimes(currAnnotation.subset([sp])))
+
             if extraNames:
                 extraPairsSorted = sorted(zip(extraNames, extraValues), key=lambda pair: pair[0])
                 extraNames, extraValues = list(zip(*extraPairsSorted))
+                extraNames = list(extraNames)
+                extraValues = list(extraValues)
             else:
                 extraNames, extraValues = [], []
+
             df4_dict = {
-                    "values": valueList+list(extraValues),
-                    "names": nameList+list(extraNames),
-                }
+                "values": valueList + extraValues,
+                "names": nameList + extraNames,
+            }
             df4 = pd.DataFrame(data=df4_dict)
             df4.name = "df4"
             st.session_state.summaries[currFileIndex]["df4"] = df4
+            printV(f'Set df4', 4)
 
-            printV(f'Set df4',4)
-            
-            speakerList,timeList = su.sumTimesPerSpeaker(oneVoice)
+            # --- Build df5 ---
+            speakerList, timeList = su.sumTimesPerSpeaker(oneVoice)
             multiSpeakerList, multiTimeList = su.sumMultiTimesPerSpeaker(multiVoice)
+
+            speakerList = list(speakerList) if speakerList else []
+            timeList = list(timeList) if timeList else []
+            multiSpeakerList = list(multiSpeakerList) if multiSpeakerList else []
+            multiTimeList = list(multiTimeList) if multiTimeList else []
+
             summativeMultiSpeaker = sum(multiTimeList) if multiTimeList else 1
-            basePercentiles = [sumNoVoice/currTotalTime,
-                                 sumOneVoice/currTotalTime,
-                                 sumMultiVoice/currTotalTime
-                                ]
-            df5 = pd.DataFrame(
-                {
-                    "ids" : ["NV","OV","MV"]+[f"OV_{i}" for i in range(len(speakerList))]
-                                +[f"MV_{i}" for i in range(len(multiSpeakerList))],
-                    "labels" : ["No Voice","One Voice","Multi Voice"] + speakerList + multiSpeakerList,
-                    "parents" : ["","",""]+["OV" for i in range(len(speakerList))]
-                                +["MV" for i in range(len(multiSpeakerList))],
-                    "parentNames" : ["Total","Total","Total"]+["One Voice" for i in range(len(speakerList))]
-                                +["Multi Voice" for i in range(len(multiSpeakerList))],
-                    "values" : [sumNoVoice,
-                                sumOneVoice,
-                                sumMultiVoice,
-                                ] + timeList + multiTimeList,
-                    "valueStrings" : [su.timeToString(sumNoVoice),
-                                su.timeToString(sumOneVoice),
-                                su.timeToString(sumMultiVoice),
-                                ] + su.timeToString(timeList) + su.timeToString(multiTimeList),
-                    "percentiles" : [basePercentiles[0]*100,
-                                     basePercentiles[1]*100,
-                                     basePercentiles[2]*100] +
-                                    [(t*100) / sumOneVoice * basePercentiles[1] for t in timeList] if sumOneVoice > 0 else [0]*len(timeList) +
-                                    [(t*100) / summativeMultiSpeaker * basePercentiles[2] for t in multiTimeList],
-                    "parentPercentiles" : [basePercentiles[0]*100,
-                                     basePercentiles[1]*100,
-                                     basePercentiles[2]*100] +
-                                    [(t*100) / sumOneVoice for t in timeList] +
-                                    [(t*100) / summativeMultiSpeaker for t in multiTimeList],
-                    
-                }
-            )
+            safeOneVoice = sumOneVoice if sumOneVoice > 0 else 1
+
+            basePercentiles = [
+                sumNoVoice / currTotalTime,
+                sumOneVoice / currTotalTime,
+                sumMultiVoice / currTotalTime,
+            ]
+
+            timeStrings = su.timeToString(timeList) if timeList else []
+            multiTimeStrings = su.timeToString(multiTimeList) if multiTimeList else []
+            if isinstance(timeStrings, str):
+                timeStrings = [timeStrings]
+            if isinstance(multiTimeStrings, str):
+                multiTimeStrings = [multiTimeStrings]
+
+            n_ov = len(speakerList)
+            n_mv = len(multiSpeakerList)
+
+            df5 = pd.DataFrame({
+                "ids": ["NV", "OV", "MV"] + [f"OV_{i}" for i in range(n_ov)] + [f"MV_{i}" for i in range(n_mv)],
+                "labels": ["No Voice", "One Voice", "Multi Voice"] + speakerList + multiSpeakerList,
+                "parents": ["", "", ""] + ["OV"] * n_ov + ["MV"] * n_mv,
+                "parentNames": ["Total", "Total", "Total"] + ["One Voice"] * n_ov + ["Multi Voice"] * n_mv,
+                "values": [sumNoVoice, sumOneVoice, sumMultiVoice] + timeList + multiTimeList,
+                "valueStrings": [
+                    su.timeToString(sumNoVoice),
+                    su.timeToString(sumOneVoice),
+                    su.timeToString(sumMultiVoice),
+                ] + timeStrings + multiTimeStrings,
+                "percentiles": [
+                    basePercentiles[0] * 100,
+                    basePercentiles[1] * 100,
+                    basePercentiles[2] * 100,
+                ] + [(t * 100) / safeOneVoice * basePercentiles[1] for t in timeList]
+                  + [(t * 100) / summativeMultiSpeaker * basePercentiles[2] for t in multiTimeList],
+                "parentPercentiles": [
+                    basePercentiles[0] * 100,
+                    basePercentiles[1] * 100,
+                    basePercentiles[2] * 100,
+                ] + [(t * 100) / safeOneVoice for t in timeList]
+                  + [(t * 100) / summativeMultiSpeaker for t in multiTimeList],
+            })
             df5.name = "df5"
             st.session_state.summaries[currFileIndex]["df5"] = df5
-            printV(f'Set df5',4)
-            
-            speakers_dataFrame,speakers_times = su.annotationToDataFrame(currAnnotation)
+            printV(f'Set df5', 4)
+
+            # --- Build speakers_dataFrame, df2 ---
+            speakers_dataFrame, speakers_times = su.annotationToDataFrame(currAnnotation)
             st.session_state.summaries[currFileIndex]["speakers_dataFrame"] = speakers_dataFrame
             st.session_state.summaries[currFileIndex]["speakers_times"] = speakers_times
 
             df2_dict = {
-                "values":[100*t/currTotalTime for t in df4_dict["values"]],
-                "names":df4_dict["names"]
+                "values": [100 * t / currTotalTime for t in df4_dict["values"]],
+                "names": df4_dict["names"],
             }
             df2 = pd.DataFrame(df2_dict)
             st.session_state.summaries[currFileIndex]["df2"] = df2
-            printV(f'Set df2',4)
+            printV(f'Set df2', 4)
     except Exception as e:
         import traceback
         print(f"Error in analyze: {e}")