app.py

import gradio as gr
import cv2
from deepface import DeepFace
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
import tempfile

analyzer = SentimentIntensityAnalyzer()

def analyze_text(text):
    score = analyzer.polarity_scores(text)
    if score['compound'] >= 0.05:
        return "Positive 😊"
    elif score['compound'] <= -0.05:
        return "Negative 😠"
    else:
        return "Neutral 😐"

def process_all(text, video):
    text_sentiment = analyze_sentiment(text)
    video_emotion = analyze_video_emotion(video)
    return f"Text Sentiment: {text_sentiment}\nFacial Emotion: {video_emotion}"

iface = gr.Interface(
    fn=process_all,
    inputs=[gr.Textbox(label="Social Media Post"), gr.Video(label="Upload Video")],
    outputs="text",
    title="Emotion & Sentiment Analyzer"
)

iface.launch()

def analyze_video(video_file):
    if video_file is None:
        return "No video uploaded"

    # Save uploaded file temporarily
    temp_path = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4").name
    with open(temp_path, "wb") as f:
        f.write(video_file.read())

    cap = cv2.VideoCapture(temp_path)
    success, frame = cap.read()
    cap.release()
    
def analyze_video_emotion(video_file):
    # Save the uploaded video to a temp file
    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as tmp:
        tmp.write(video_file.read())
        tmp_path = tmp.name

    cap = cv2.VideoCapture(tmp_path)
    emotions = []
    frame_count = 0

    import cv2
import tempfile
from deepface import DeepFace

def analyze_video_emotion(video_file):
    # Save the uploaded video to a temp file
    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as tmp:
        tmp.write(video_file.read())
        tmp_path = tmp.name

    cap = cv2.VideoCapture(tmp_path)
    emotions = []
    frame_count = 0

    while cap.isOpened():
        ret, frame = cap.read()
        if not ret or frame_count > 60:  # Limit to first 60 frames
            break
        try:
            result = DeepFace.analyze(frame, actions=['emotion'], enforce_detection=False)
            emotions.append(result[0]['dominant_emotion'])
        except Exception as e:
            print("Error analyzing frame:", e)
        frame_count += 1

    cap.release()

    if emotions:
        # Return most frequent emotion
        return max(set(emotions), key=emotions.count)
    else:
        return "No emotion detected or face not found"


    while cap.isOpened():
        ret, frame = cap.read()
        if not ret or frame_count > 60:  # Limit to 60 frames max
            break
        try:
            result = DeepFace.analyze(frame, actions=['emotion'], enforce_detection=False)
            emotions.append(result[0]['dominant_emotion'])
        except:
            pass
        frame_count += 1

    cap.release()

    if emotions:
        # Return most common emotion
        return max(set(emotions), key=emotions.count)
    else:
        return "No face detected"


    if not success:
        return "Could not read video"

    try:
        result = DeepFace.analyze(frame, actions=["emotion"], enforce_detection=False)
        return result[0]['dominant_emotion'].capitalize()
    except Exception as e:
        return f"Error: {str(e)}"

def analyze_post(text, video):
    sentiment = analyze_text(text)
    emotion = analyze_video(video)
    return f"📝 Sentiment: {sentiment}\n🎥 Emotion: {emotion}"
import gradio as gr

def analyze_text(text):
    from transformers import pipeline
    classifier = pipeline("sentiment-analysis")
    return classifier(text)[0]['label']

def process_all(text_input, video_input):
    text_result = analyze_text(text_input)
    video_result = analyze_video_emotion(video_input)
    return f"Text Sentiment: {text_result}\nFacial Emotion: {video_result}"

gr.Interface(
    fn=process_all,
    inputs=[
        gr.Textbox(label="Enter Social Media Text"),
        gr.Video(label="Upload a Video Clip")
    ],
    outputs="text",
    title="Emotion & Sentiment Decoder",
    description="Analyzes social media text & facial expressions from video."
).launch()
    

interface = gr.Interface(
    fn=analyze_post,
    inputs=[
        gr.Textbox(label="Post Text", placeholder="Enter your message here"),
        gr.File(label="Upload video (.mp4)", file_types=[".mp4"])
    ],
    outputs="text",
    title="📱 Emotion & Sentiment Analyzer",
    description="Analyze text sentiment and facial emotion from video. No re-running needed. Permanent on Hugging Face."
)

interface.launch()import gradio as gr
import cv2
from deepface import DeepFace
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
import tempfile

analyzer = SentimentIntensityAnalyzer()

def analyze_text(text):
    score = analyzer.polarity_scores(text)
    if score['compound'] >= 0.05:
        return "Positive 😊"
    elif score['compound'] <= -0.05:
        return "Negative 😠"
    else:
        return "Neutral 😐"

def process_all(text, video):
    text_sentiment = analyze_sentiment(text)
    video_emotion = analyze_video_emotion(video)
    return f"Text Sentiment: {text_sentiment}\nFacial Emotion: {video_emotion}"

iface = gr.Interface(
    fn=process_all,
    inputs=[gr.Textbox(label="Social Media Post"), gr.Video(label="Upload Video")],
    outputs="text",
    title="Emotion & Sentiment Analyzer"
)

iface.launch()

def analyze_video(video_file):
    if video_file is None:
        return "No video uploaded"

    # Save uploaded file temporarily
    temp_path = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4").name
    with open(temp_path, "wb") as f:
        f.write(video_file.read())

    cap = cv2.VideoCapture(temp_path)
    success, frame = cap.read()
    cap.release()
    
def analyze_video_emotion(video_file):
    # Save the uploaded video to a temp file
    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as tmp:
        tmp.write(video_file.read())
        tmp_path = tmp.name

    cap = cv2.VideoCapture(tmp_path)
    emotions = []
    frame_count = 0

    import cv2
import tempfile
from deepface import DeepFace

def analyze_video_emotion(video_file):
    # Save the uploaded video to a temp file
    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as tmp:
        tmp.write(video_file.read())
        tmp_path = tmp.name

    cap = cv2.VideoCapture(tmp_path)
    emotions = []
    frame_count = 0

    while cap.isOpened():
        ret, frame = cap.read()
        if not ret or frame_count > 60:  # Limit to first 60 frames
            break
        try:
            result = DeepFace.analyze(frame, actions=['emotion'], enforce_detection=False)
            emotions.append(result[0]['dominant_emotion'])
        except Exception as e:
            print("Error analyzing frame:", e)
        frame_count += 1

    cap.release()

    if emotions:
        # Return most frequent emotion
        return max(set(emotions), key=emotions.count)
    else:
        return "No emotion detected or face not found"


    while cap.isOpened():
        ret, frame = cap.read()
        if not ret or frame_count > 60:  # Limit to 60 frames max
            break
        try:
            result = DeepFace.analyze(frame, actions=['emotion'], enforce_detection=False)
            emotions.append(result[0]['dominant_emotion'])
        except:
            pass
        frame_count += 1

    cap.release()

    if emotions:
        # Return most common emotion
        return max(set(emotions), key=emotions.count)
    else:
        return "No face detected"


    if not success:
        return "Could not read video"

    try:
        result = DeepFace.analyze(frame, actions=["emotion"], enforce_detection=False)
        return result[0]['dominant_emotion'].capitalize()
    except Exception as e:
        return f"Error: {str(e)}"

def analyze_post(text, video):
    sentiment = analyze_text(text)
    emotion = analyze_video(video)
    return f"📝 Sentiment: {sentiment}\n🎥 Emotion: {emotion}"
import gradio as gr

def analyze_text(text):
    from transformers import pipeline
    classifier = pipeline("sentiment-analysis")
    return classifier(text)[0]['label']

def process_all(text_input, video_input):
    text_result = analyze_text(text_input)
    video_result = analyze_video_emotion(video_input)
    return f"Text Sentiment: {text_result}\nFacial Emotion: {video_result}"

gr.Interface(
    fn=process_all,
    inputs=[
        gr.Textbox(label="Enter Social Media Text"),
        gr.Video(label="Upload a Video Clip")
    ],
    outputs="text",
    title="Emotion & Sentiment Decoder",
    description="Analyzes social media text & facial expressions from video."
).launch()
    

interface = gr.Interface(
    fn=analyze_post,
    inputs=[
        gr.Textbox(label="Post Text", placeholder="Enter your message here"),
        gr.File(label="Upload video (.mp4)", file_types=[".mp4"])
    ],
    outputs="text",
    title="📱 Emotion & Sentiment Analyzer",
  description="Analyze text sentiment and facial emotion from video. No re-running needed. Permanent on Hugging Face."
    if text_input:
    # Process text only
elif video_input:
    # Process video only
else:
    return "No input provided"
)

interface.launch()