Update app.py

app.py

@@ -2,7 +2,6 @@
 import streamlit as st
 import pandas as pd
 import plotly.express as px
-import plotly.figure_factory as ff
 import subprocess
 import threading
 import re
@@ -84,14 +83,12 @@ def parse_time(time_str):
     """
     if pd.isna(time_str):
         return 0
-
     time_str = str(time_str).strip()
     if not time_str:
         return 0
 
     # If the string contains a colon, assume mm:ss or hh:mm:ss format.
     if ":" in time_str:
-        # Remove non-digit/colon characters.
         clean_str = re.sub(r"[^\d:]", "", time_str)
         parts = clean_str.split(":")
         try:
@@ -122,11 +119,16 @@ df["Video_length_seconds"] = df["video length"].apply(parse_time)
 # -----------------------------
 # Compute Aggregated Insights
 # -----------------------------
+# Overall average processing time by whisper model
 avg_time_by_model = df.groupby("whisper model")["Time_required_seconds"].mean().reset_index()
+
+# Average processing time by target audio
 avg_time_by_target = df.groupby("Target Audio")["Time_required_seconds"].mean().reset_index()
 
 # Mark run type based on the "run" column (if "First" appears then it's First Run)
 df["Run_type"] = df["run"].apply(lambda x: "First Run" if "First" in str(x) else "Subsequent Run")
+
+# Run counts by whisper model and run type
 run_counts = df.groupby(["whisper model", "Run_type"]).size().reset_index(name="count")
 
 # -----------------------------
@@ -228,20 +230,6 @@ fig_corr = px.imshow(
     labels=dict(color="Correlation")
 )
 
-# # 3D Scatter Plot: Whisper Model vs Processing Time vs Video Length
-# fig_model_time_video = px.scatter_3d(
-#     df,
-#     x="whisper model",
-#     y="Time_required_seconds",
-#     z="Video_length_seconds",
-#     color="whisper model",
-#     title="Whisper Model vs Processing Time vs Video Length",
-#     labels={
-#         "whisper model": "Whisper Model",
-#         "Time_required_seconds": "Processing Time (seconds)",
-#         "Video_length_seconds": "Video Length (seconds)"
-#     }
-# )
 # 3D Scatter Plot: Whisper Model vs Processing Time vs Video Length
 fig_model_time_video = px.scatter_3d(
     df,
@@ -256,17 +244,23 @@ fig_model_time_video = px.scatter_3d(
         "Video_length_seconds": "Video Length (seconds)"
     }
 )
-
-# Update the layout to enlarge the graph in the UI
+# Enlarge the 3D graph layout
 fig_model_time_video.update_layout(height=1000, width=1200)
 
-# -----------------------------
-# Build the Streamlit App Layout
-# -----------------------------
-st.title("Video Processing Dashboard")
-# ... [rest of the code remains unchanged]
-st.subheader("Whisper Model vs Processing Time vs Video Length (3D)")
-st.plotly_chart(fig_model_time_video, use_container_width=True)
+# New Graph:
+# First Run Average Processing Time by Whisper Model Grouped by Video Duration
+first_run_df = df[df["Run_type"] == "First Run"]
+avg_time_first_run = first_run_df.groupby(["whisper model", "video length"])["Time_required_seconds"].mean().reset_index()
+fig_first_run = px.bar(
+    avg_time_first_run,
+    x="whisper model",
+    y="Time_required_seconds",
+    color="video length",
+    barmode="group",
+    title="First Run Average Processing Time by Whisper Model (Grouped by Video Duration)",
+    labels={"Time_required_seconds": "Avg Time (seconds)", "whisper model": "Whisper Model"}
+)
+
 # -----------------------------
 # Build the Streamlit App Layout
 # -----------------------------
@@ -315,6 +309,9 @@ st.plotly_chart(fig_corr, use_container_width=True)
 st.subheader("Whisper Model vs Processing Time vs Video Length (3D)")
 st.plotly_chart(fig_model_time_video, use_container_width=True)
 
+st.subheader("First Run Avg Processing Time by Whisper Model and Video Duration")
+st.plotly_chart(fig_first_run, use_container_width=True)
+
 # -----------------------------
 # Optional: Start LocalTunnel for Public Access
 # -----------------------------
@@ -330,7 +327,6 @@ def start_localtunnel(port=8501):
             stderr=subprocess.PIPE,
             text=True,
         )
-
         def read_tunnel_output(process):
             while True:
                 line = process.stdout.readline()
@@ -340,11 +336,10 @@ def start_localtunnel(port=8501):
                 if "your url is:" in line.lower():
                     public_url = line.split("your url is:")[-1].strip()
                     st.success(f"LocalTunnel URL: {public_url}")
-
         thread = threading.Thread(target=read_tunnel_output, args=(proc,), daemon=True)
         thread.start()
     except Exception as e:
         st.error(f"Error starting LocalTunnel: {e}")
 
 # Uncomment the following line to start LocalTunnel when the app runs.
-# start_localtunnel(port=8501)
+# start_localtunnel(port=8501)