Update app.py

app.py

@@ -1,34 +1,139 @@
 import gradio as gr
 import pandas as pd
-from huggingface_hub import hf_hub_download
 import os
+import gradio as gr
+import plotly.express as px
+import pandas as pd
+import numpy as np
+from scipy.optimize import curve_fit
 import plotly.graph_objects as go
+import os
+import datetime
+import logging
+
+# Example paths for engagement data
+tiktok_csv_path = "tiktok_histogram.csv"
+facebook_csv_path = "facebook_histogram.csv"
+video_folder = "videos"
+image_folder = "images"
+
+# Function to extract the prediction label from filenames
+def extract_prediction_label(filename, media_type):
+    if media_type == "video":
+        return filename.split('_')[3]  # Extracting the label from video filenames
+    elif media_type == "image":
+        return filename.split('_')[3]  # Extracting the label from image filenames
+
+# Function to extract the version number from filenames
+def extract_version_number(filename):
+    version_with_v = filename.split('_')[1]  # Extracting something like 'v1'
+    version_number = version_with_v[1:]  # Remove the 'v' and keep only the number
+    return version_number
+
+# Function to get the highest prediction for each TikTok/Static type (e.g., TikTok1, Static2)
+def get_highest_prediction_for_media(folder_path, media_type, media_identifier):
+    highest_file = None
+    highest_score = None
+
+    # Loop over all files in the folder
+    for filename in os.listdir(folder_path):
+        if (media_type == "video" and filename.endswith('.mp4')) or (media_type == "image" and filename.endswith('.jpeg')):
+            if media_identifier in filename:  # Check for TikTok1, TikTok2, etc.
+                # Extract the prediction label from the file
+                prediction_label = extract_prediction_label(filename, media_type)
+
+                label_map = {"normal": 1, "good": 2, "very good": 3, "exceptional": 4, "viral": 5}
+                score = label_map.get(prediction_label.lower(), 1)  # Default to 1 if not found
+
+                # Check for highest score
+                if highest_score is None or score > highest_score:
+                    highest_score = score
+                    highest_file = filename
+
+    return highest_file
+
+# Function to load and plot CSV data directly
+def load_and_plot_csv(csv_path):
+    df = pd.read_csv(csv_path)
+
+    # Assuming the CSV has columns 'Engagement' and 'Density'
+    x_data = df['Engagement']
+    y_data = df['Density']
+
+    # Get x_max and y_max for graph range
+    x_max = max(x_data)
+    y_max = max(y_data)
+
+    # Create the plot with just the actual data
+    fig = go.Figure()
+    fig.add_trace(go.Scatter(x=x_data, y=y_data, mode='lines', name="Actual Data"))
+
+    return fig, x_data.min(), x_max, y_data.min(), y_max
+
+# Function to highlight the quintile based on prediction label
+def highlight_quintile(fig, label, x_max):
+    label_map = {"normal": 1, "good": 2, "very good": 3, "exceptional": 4, "viral": 5}
+    quintile = label_map.get(label.lower(), 1)  # Default to normal if label not found
+
+    # Dynamically adjust the x0 and x1 ranges based on x_max
+    quintile_width = x_max / 5  # Divide x_max into 5 quintiles
+    x0 = (quintile - 1) * quintile_width
+    x1 = quintile * quintile_width
+
+    # Add a shaded region in the graph corresponding to the quintile
+    fig.add_vrect(
+        x0=x0, x1=x1,
+        fillcolor="green", opacity=0.25, line_width=0,
+        annotation_text=f"Predicted: {label.capitalize()}"
+    )
+    return fig
+
+# Function to load video/image and its corresponding engagement data and plot the graph
+def load_data_and_plot(media_type, media_identifier, csv_path, folder_path):
+    # Get the file with the highest prediction for the given TikTok/Static type
+    media_file = get_highest_prediction_for_media(folder_path, media_type, media_identifier)
+
+    # Proceed if we found a valid file
+    if media_file:
+        prediction_label = extract_prediction_label(media_file, media_type)
+        version_number = extract_version_number(media_file)
+
+        # Get the full path to the media file
+        media_path = os.path.join(folder_path, media_file)
+
+        # Load and plot the actual data from the CSV
+        fig, x_min, x_max, y_min, y_max = load_and_plot_csv(csv_path)
+
+        # Highlight the quintile based on the label
+        fig = highlight_quintile(fig, prediction_label, x_max)
+
+        # Ensure the x-axis and y-axis start from 0 and dynamically set max values
+        fig.update_layout(
+            title=f"Predicted Engagement for {media_identifier} (Version {version_number})",  # Show version in title as "Version #"
+            xaxis=dict(range=[0, x_max]),  # Start from 0 and go up to the max x value
+            yaxis=dict(range=[0, y_max])   # Start from 0 and go up to the max y value
+        )
+
+        return media_path, fig
+    return None, None
 
-# Hugging Face API token and repo setup
-hf_token = os.getenv("hfkeymeow")  # Ensure your token is correctly stored
-repo_id = "conhllnd/Playper-V2"  # Repository ID on Hugging Face
-repo_type = "space"  # Repository type
 
-# Function to download file from Hugging Face repo
-def download_file_from_repo(filename):
-    file_path = hf_hub_download(repo_id=repo_id, filename=filename, repo_type=repo_type, token=hf_token)
-    return file_path
 
 # Function to calculate the follower increase from the CSV
 def calculate_follower_increase():
-    csv_path = download_file_from_repo("Followers.csv")  # Download the file from Hugging Face
+    csv_path = "/content/drive/My Drive/Client Folder: Playper/Email Updates/Dashboard/Followers.csv"  # Use the hardcoded path directly
     df = pd.read_csv(csv_path)
 
     # Ensure proper column naming and strip out any extra spaces
     df.columns = df.columns.str.strip()
-    
+
     # Sort by date to get the two most recent entries
     df['Date'] = pd.to_datetime(df['Date'])
     df = df.sort_values(by='Date', ascending=False)
 
     # Get the two most recent entries
     recent_data = df.head(2)
-    
+
     # Calculate the differences for each platform
     tiktok_increase = recent_data.iloc[0]['TikTok Followers'] - recent_data.iloc[1]['TikTok Followers']
     facebook_increase = recent_data.iloc[0]['Facebook Followers'] - recent_data.iloc[1]['Facebook Followers']
@@ -40,103 +145,27 @@ def calculate_follower_increase():
 
 # Function to calculate the engagement increase from the CSV
 def calculate_engagement_increase():
-    csv_path = download_file_from_repo("Total Engagement.csv")  # Download the file from Hugging Face
+    csv_path = "/content/drive/My Drive/Client Folder: Playper/Email Updates/Dashboard/Total Engagement.csv"  # Path to the uploaded CSV
     df = pd.read_csv(csv_path)
 
     # Ensure proper column naming and strip out any extra spaces
     df.columns = df.columns.str.strip()
-    
+
     # Sort by date to get the two most recent entries
     df['Date'] = pd.to_datetime(df['Date'])
     df = df.sort_values(by='Date', ascending=False)
 
     # Get the two most recent entries
     recent_data = df.head(2)
-    
+
     # Calculate the difference in total engagement
     engagement_increase = recent_data.iloc[0]['Total Engagement Across Our Posts'] - recent_data.iloc[1]['Total Engagement Across Our Posts']
 
     return f"Leonardo got you {int(engagement_increase)} more engagements across TikTok & Facebook!"
 
-# Function to load and plot the masterpiece data (video and graph)
-def load_masterpiece_video_and_plot():
-    # Download the video file from the Hugging Face repository
-    masterpiece_video_path = download_file_from_repo("starperformer_viral.mp4")
-
-    # Replace [actual outcome] with the correct label (here it's 'viral' from the filename)
-    actual_outcome = "viral"
-    
-    # Load the data for the TikTok graph
-    tiktok_csv_path = download_file_from_repo("tiktok_histogram.csv")
-    df = pd.read_csv(tiktok_csv_path)
-
-    # Assuming the CSV has columns 'Engagement' and 'Density'
-    x_data = df['Engagement']
-    y_data = df['Density']
-
-    # Get x_max for the quintile calculation
-    x_max = max(x_data)
-
-    # Create the plot with actual data
-    fig = go.Figure()
-    fig.add_trace(go.Scatter(x=x_data, y=y_data, mode='lines', name="Actual Data"))
-
-    # Highlight the quintile based on the actual outcome
-    fig = highlight_masterpiece_quintile(fig, actual_outcome, x_max)
-
-    # Return the video path and graph
-    return masterpiece_video_path, fig
-
-# Function to highlight the quintile based on prediction label for the masterpiece
-def highlight_masterpiece_quintile(fig, actual_outcome, x_max):
-    label_map = {"normal": 1, "good": 2, "very good": 3, "exceptional": 4, "viral": 5}
-    quintile = label_map.get(actual_outcome.lower(), 1)
-
-    # Dynamically adjust the x0 and x1 ranges based on x_max
-    quintile_width = x_max / 5  # Divide x_max into 5 quintiles
-    x0 = (quintile - 1) * quintile_width
-    x1 = quintile * quintile_width
-
-    # Add a shaded region in the graph corresponding to the quintile
-    fig.add_vrect(
-        x0=x0, x1=x1,
-        fillcolor="green", opacity=0.25, line_width=0,
-        annotation_text=f"Actual Outcome: {actual_outcome.capitalize()}"
-    )
-    return fig
-
-# Function to load and plot data (TikTok, Facebook)
-def load_data_and_plot(media_type, media_identifier, csv_path, folder_path):
-    df = pd.read_csv(csv_path)
-
-    # Assuming the CSV has columns 'Engagement' and 'Density'
-    x_data = df['Engagement']
-    y_data = df['Density']
-
-    # Create the plot with actual data
-    fig = go.Figure()
-    fig.add_trace(go.Scatter(x=x_data, y=y_data, mode='lines', name="Actual Data"))
-
-    # Adjust the x-axis and y-axis
-    fig.update_layout(
-        title=f"Predicted Engagement for {media_identifier}",
-        xaxis=dict(range=[0, max(x_data)]),
-        yaxis=dict(range=[0, max(y_data)])
-    )
-
-    media_file_path = None  # Assuming you aren't showing media in this function
-    return media_file_path, fig
-
 # Create the Gradio interface
 with gr.Blocks() as dashboard:
 
-    # Section for Leonardo's Last-Week Masterpiece
-    gr.Markdown("## Leonardo's Last-Week Masterpiece")
-    with gr.Row():
-        masterpiece_video, masterpiece_graph = load_masterpiece_video_and_plot()
-        gr.Video(masterpiece_video, label="Star Performer TikTok Video")
-        gr.Plot(masterpiece_graph, label="Star Performer TikTok Performance")
-
     # Add a header for follower impact
     gr.Markdown("## Leonardo's Follower Impact")
 
@@ -163,19 +192,19 @@ with gr.Blocks() as dashboard:
     # Section for TikTok projections (Videos)
     with gr.Row():
         with gr.Column():
-            video_path_1, graph_1 = load_data_and_plot("video", "TikTok1", download_file_from_repo("tiktok_histogram.csv"), download_file_from_repo("video_folder"))
+            video_path_1, graph_1 = load_data_and_plot("video", "TikTok1", tiktok_csv_path, video_folder)
             if video_path_1:
                 gr.Video(video_path_1, label="TikTok 1 Video")
                 gr.Plot(graph_1, label="TikTok 1 Performance")
 
         with gr.Column():
-            video_path_2, graph_2 = load_data_and_plot("video", "TikTok2", download_file_from_repo("tiktok_histogram.csv"), download_file_from_repo("video_folder"))
+            video_path_2, graph_2 = load_data_and_plot("video", "TikTok2", tiktok_csv_path, video_folder)
             if video_path_2:
                 gr.Video(video_path_2, label="TikTok 2 Video")
                 gr.Plot(graph_2, label="TikTok 2 Performance")
 
         with gr.Column():
-            video_path_3, graph_3 = load_data_and_plot("video", "TikTok3", download_file_from_repo("tiktok_histogram.csv"), download_file_from_repo("video_folder"))
+            video_path_3, graph_3 = load_data_and_plot("video", "TikTok3", tiktok_csv_path, video_folder)
             if video_path_3:
                 gr.Video(video_path_3, label="TikTok 3 Video")
                 gr.Plot(graph_3, label="TikTok 3 Performance")
@@ -183,23 +212,22 @@ with gr.Blocks() as dashboard:
     # Section for Facebook projections (Statics)
     with gr.Row():
         with gr.Column():
-            image_path_1, graph_4 = load_data_and_plot("image", "Static1", download_file_from_repo("facebook_histogram.csv"), download_file_from_repo("image_folder"))
+            image_path_1, graph_4 = load_data_and_plot("image", "Static1", facebook_csv_path, image_folder)
             if image_path_1:
                 gr.Image(image_path_1, label="Facebook Static 1")
                 gr.Plot(graph_4, label="Facebook Static 1 Performance")
 
         with gr.Column():
-            image_path_2, graph_5 = load_data_and_plot("image", "Static2", download_file_from_repo("facebook_histogram.csv"), download_file_from_repo("image_folder"))
+            image_path_2, graph_5 = load_data_and_plot("image", "Static2", facebook_csv_path, image_folder)
             if image_path_2:
                 gr.Image(image_path_2, label="Facebook Static 2")
                 gr.Plot(graph_5, label="Facebook Static 2 Performance")
 
         with gr.Column():
-            image_path_3, graph_6 = load_data_and_plot("image", "Static3", download_file_from_repo("facebook_histogram.csv"), download_file_from_repo("image_folder"))
+            image_path_3, graph_6 = load_data_and_plot("image", "Static3", facebook_csv_path, image_folder)
             if image_path_3:
                 gr.Image(image_path_3, label="Facebook Static 3")
                 gr.Plot(graph_6, label="Facebook Static 3 Performance")
 
 # Launch the dashboard
-dashboard.launch(debug=True)
-
+dashboard.launch(share=True, debug=True))