REFAC: Remove unused streamlit app files and clean up imports in streamlit_app.py

src/streamlit_app.py

@@ -11,7 +11,7 @@ import tempfile
 import cv2
 from moviepy.editor import VideoFileClip
 import time
-import shutil # Import the shutil library for file copying
+import shutil
 
 # --- Create a cross-platform, writable cache directory for all libraries ---
 CACHE_DIR = os.path.join(tempfile.gettempdir(), "affectlink_cache")
@@ -19,7 +19,6 @@ os.makedirs(CACHE_DIR, exist_ok=True)
 os.environ['DEEPFACE_HOME'] = CACHE_DIR
 os.environ['HF_HOME'] = CACHE_DIR
 
-# === THIS IS THE NEW CODE TO PRELOAD THE DEEPFACE MODEL ===
 # Define paths for the pre-included model weights
 MODEL_NAME = "facial_expression_model_weights.h5"
 SOURCE_PATH = os.path.join("src", "weights", MODEL_NAME)
@@ -37,7 +36,6 @@ if not os.path.exists(DEST_PATH):
         print(f"Warning: Local model file not found at {SOURCE_PATH}. App will attempt to download it.")
     except Exception as e:
         print(f"Error copying model file: {e}")
-# =========================================================
 
 # --- Page Configuration ---
 st.set_page_config(page_title="AffectLink Demo", page_icon="😊", layout="wide")
@@ -45,8 +43,6 @@ st.title("AffectLink: Post-Hoc Emotion Analysis")
 st.write("Upload a short video clip (under 30 seconds) to analyze facial expressions, speech-to-text, and the emotional tone of the audio.")
 
 # --- Logger Configuration ---
-# [The rest of your code remains the same]
-# [I have included the full script below for clarity]
 
 logging.basicConfig(level=logging.INFO)
 logging.getLogger('deepface').setLevel(logging.ERROR)

src/streamlit_app_full.py

@@ -1,178 +0,0 @@
-import os
-import streamlit as st
-
-# Set home directories for model caching to the writable /tmp folder
-os.environ['DEEPFACE_HOME'] = '/tmp/.deepface'
-os.environ['HF_HOME'] = '/tmp/huggingface'
-
-import numpy as np
-import torch
-import whisper
-from transformers import pipeline, AutoModelForAudioClassification, AutoFeatureExtractor
-from deepface import DeepFace
-import logging
-import soundfile as sf
-from scipy.io.wavfile import write as write_wav
-import tempfile
-from PIL import Image
-import cv2
-from moviepy.editor import VideoFileClip
-
-# Set home directories for model caching inside the app's writable directory
-os.environ['DEEPFACE_HOME'] = '/tmp/.deepface'
-os.environ['HF_HOME'] = '/tmp/huggingface'
-
-# --- Page Configuration ---
-st.set_page_config(
-    page_title="AffectLink Batch Demo",
-    page_icon="😊",
-    layout="wide"
-)
-
-st.title("AffectLink: Post-Hoc Emotion Analysis")
-st.write("Upload a short video clip to analyze facial expressions, speech-to-text, and the emotional tone of the audio.")
-
-# --- Logger Configuration ---
-logging.basicConfig(level=logging.INFO)
-logging.getLogger('deepface').setLevel(logging.ERROR)
-logging.getLogger('huggingface_hub').setLevel(logging.WARNING)
-logging.getLogger('moviepy').setLevel(logging.ERROR)
-
-
-# --- Emotion Mappings ---
-UNIFIED_EMOTIONS = ['neutral', 'happy', 'sad', 'angry']
-TEXT_TO_UNIFIED = {
-    'neutral': 'neutral', 'joy': 'happy', 'sadness': 'sad', 'anger': 'angry',
-    'fear': None, 'surprise': None, 'disgust': None
-}
-SER_TO_UNIFIED = {
-    'neu': 'neutral', 'hap': 'happy', 'sad': 'sad', 'ang': 'angry'
-}
-AUDIO_SAMPLE_RATE = 16000
-
-# --- Model Loading ---
-@st.cache_resource
-def load_models():
-    with st.spinner("Loading AI models, this may take a moment..."):
-        whisper_model = whisper.load_model("base", download_root="/tmp/whisper_cache")
-        text_classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", top_k=None)
-        ser_model_name = "superb/hubert-large-superb-er"
-        ser_feature_extractor = AutoFeatureExtractor.from_pretrained(ser_model_name)
-        ser_model = AutoModelForAudioClassification.from_pretrained(ser_model_name)
-        return whisper_model, text_classifier, ser_model, ser_feature_extractor
-
-whisper_model, text_classifier, ser_model, ser_feature_extractor = load_models()
-
-
-# --- UI and Processing Logic ---
-uploaded_file = st.file_uploader("Choose a video file...", type=["mp4", "mov", "avi"])
-
-if uploaded_file is not None:
-    # Save the uploaded file to a temporary location
-    with tempfile.NamedTemporaryFile(delete=False, suffix='.mp4') as tfile:
-        tfile.write(uploaded_file.read())
-        temp_video_path = tfile.name
-
-    st.video(temp_video_path)
-
-    if st.button("Analyze Video"):
-        facial_analysis_results = []
-        audio_analysis_results = {}
-
-        # --- Video Processing for Facial Emotion ---
-        with st.spinner("Analyzing video for facial expressions..."):
-            try:
-                cap = cv2.VideoCapture(temp_video_path)
-                fps = cap.get(cv2.CAP_PROP_FPS)
-                frame_count = 0
-                while cap.isOpened():
-                    ret, frame = cap.read()
-                    if not ret:
-                        break
-                    
-                    # Process one frame per second
-                    if frame_count % int(fps) == 0:
-                        timestamp = frame_count / fps
-                        analysis = DeepFace.analyze(frame, actions=['emotion'], enforce_detection=False, silent=True)
-                        if isinstance(analysis, list) and len(analysis) > 0:
-                            dominant_emotion = analysis[0]['dominant_emotion']
-                            facial_analysis_results.append((timestamp, dominant_emotion.capitalize()))
-                    
-                    frame_count += 1
-                cap.release()
-            except Exception as e:
-                st.error(f"An error occurred during facial analysis: {e}")
-
-
-        # --- Audio Extraction and Processing ---
-        with st.spinner("Extracting and analyzing audio..."):
-            try:
-                # Extract audio using moviepy
-                video_clip = VideoFileClip(temp_video_path)
-                with tempfile.NamedTemporaryFile(delete=False, suffix='.wav') as taudio:
-                    video_clip.audio.write_audiofile(taudio.name, fps=AUDIO_SAMPLE_RATE, logger=None)
-                    temp_audio_path = taudio.name
-
-                # 1. Speech-to-Text (Whisper)
-                result = whisper_model.transcribe(temp_audio_path, fp16=False)
-                transcribed_text = result['text']
-                audio_analysis_results['Transcription'] = transcribed_text
-
-                # 2. Text-based Emotion
-                if transcribed_text:
-                    text_emotions = text_classifier(transcribed_text)[0]
-                    unified_text_scores = {e: 0.0 for e in UNIFIED_EMOTIONS}
-                    for emo in text_emotions:
-                        unified_emo = TEXT_TO_UNIFIED.get(emo['label'])
-                        if unified_emo:
-                            unified_text_scores[unified_emo] += emo['score']
-                    dominant_text_emotion = max(unified_text_scores, key=unified_text_scores.get)
-                    audio_analysis_results['Text Emotion'] = dominant_text_emotion.capitalize()
-                
-                # 3. Speech Emotion Recognition (SER)
-                audio_array, _ = sf.read(temp_audio_path)
-                inputs = ser_feature_extractor(audio_array, sampling_rate=AUDIO_SAMPLE_RATE, return_tensors="pt", padding=True)
-                with torch.no_grad():
-                    logits = ser_model(**inputs).logits
-                scores = torch.nn.functional.softmax(logits, dim=1).squeeze()
-                unified_ser_scores = {e: 0.0 for e in UNIFIED_EMOTIONS}
-                for i, score in enumerate(scores):
-                    raw_emo = ser_model.config.id2label[i]
-                    unified_emo = SER_TO_UNIFIED.get(raw_emo)
-                    if unified_emo:
-                        unified_ser_scores[unified_emo] += score.item()
-                dominant_ser_emotion = max(unified_ser_scores, key=unified_ser_scores.get)
-                audio_analysis_results['Speech Emotion'] = dominant_ser_emotion.capitalize()
-                
-                # Clean up temp audio file
-                os.unlink(temp_audio_path)
-
-            except Exception as e:
-                st.error(f"An error occurred during audio analysis: {e}")
-            finally:
-                video_clip.close()
-
-
-        # --- Display Results ---
-        st.header("Analysis Results")
-        col1, col2 = st.columns(2)
-
-        with col1:
-            st.subheader("Audio Analysis")
-            if audio_analysis_results:
-                st.write(f"**Transcription:** \"{audio_analysis_results.get('Transcription', 'N/A')}\"")
-                st.metric("Emotion from Text", audio_analysis_results.get('Text Emotion', 'N/A'))
-                st.metric("Emotion from Speech", audio_analysis_results.get('Speech Emotion', 'N/A'))
-            else:
-                st.write("No audio results to display.")
-
-        with col2:
-            st.subheader("Facial Expression Timeline")
-            if facial_analysis_results:
-                for timestamp, emotion in facial_analysis_results:
-                    st.write(f"**Time {int(timestamp // 60):02d}:{int(timestamp % 60):02d}:** {emotion}")
-            else:
-                st.write("No faces detected or video processing failed.")
-
-    # Clean up temp video file
-    os.unlink(temp_video_path)

src/streamlit_app_imageFER.py

@@ -1,56 +0,0 @@
-import os
-import streamlit as st
-
-# Point the cache directory to the guaranteed writable /tmp folder
-os.environ['DEEPFACE_HOME'] = '/tmp/.deepface'
-
-from PIL import Image
-import numpy as np
-from deepface import DeepFace
-import logging
-import cv2
-
-# --- Page Configuration ---
-st.set_page_config(
-    page_title="FER Test",
-    page_icon="😀",
-    layout="centered"
-)
-
-st.title("Step 1: Facial Emotion Recognition (FER) Test")
-st.write("Upload an image with a face to test the DeepFace library.")
-
-# --- Logger Configuration ---
-logging.basicConfig(level=logging.INFO)
-logging.getLogger('deepface').setLevel(logging.ERROR)
-
-
-# --- UI and Processing Logic ---
-uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
-
-if uploaded_file is not None:
-    pil_image = Image.open(uploaded_file)
-    numpy_image = np.array(pil_image)
-    image_bgr = cv2.cvtColor(numpy_image, cv2.COLOR_RGB2BGR)
-
-    st.image(pil_image, caption="Image Uploaded", use_column_width=True)
-
-    with st.spinner("Analyzing image for emotion..."):
-        try:
-            # This will now download its models to /tmp/.deepface
-            analysis = DeepFace.analyze(
-                img_path=image_bgr,
-                actions=['emotion'],
-                enforce_detection=False,
-                silent=True
-            )
-
-            if isinstance(analysis, list) and len(analysis) > 0:
-                dominant_emotion = analysis[0]['dominant_emotion']
-                st.success(f"Dominant Emotion Detected: **{dominant_emotion.capitalize()}**")
-                st.write(analysis[0]['emotion'])
-            else:
-                st.warning("No face detected in the image.")
-
-        except Exception as e:
-            st.error(f"An error occurred during analysis: {e}")