Updated Final Project

.gitignore

@@ -85,7 +85,7 @@ ipython_config.py
 .python-version
 
 # pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control
 #   However, in case of collaboration, if having platform-specific dependencies or dependencies
 #   having no cross-platform support, pipenv may install dependencies that don't work, or not
 #   install all needed dependencies.

EmotionDetection/__init__.py

@@ -0,0 +1 @@
+from . import emotion_detection

EmotionDetection/emotion_detection.py

@@ -0,0 +1,32 @@
+import requests
+import json
+
+def emotion_detector(text_to_analyse):
+    url = 'https://sn-watson-emotion.labs.skills.network/v1/watson.runtime.nlp.v1/NlpService/EmotionPredict'
+    header = {"grpc-metadata-mm-model-id": "emotion_aggregated-workflow_lang_en_stock"}
+    myobj = {"raw_document": {"text": text_to_analyse}}
+    response = requests.post(url, json=myobj, headers=header)
+
+    # Handle blank entry (status_code = 400)
+    if response.status_code == 400:
+        return {
+            'anger': None,
+            'disgust': None,
+            'fear': None,
+            'joy': None,
+            'sadness': None,
+            'dominant_emotion': None
+        }
+
+    formatted_response = json.loads(response.text)
+    emotion_scores = formatted_response['emotionPredictions'][0]['emotion']
+    dominant_emotion = max(emotion_scores, key=emotion_scores.get)
+
+    return {
+        'anger': emotion_scores['anger'],
+        'disgust': emotion_scores['disgust'],
+        'fear': emotion_scores['fear'],
+        'joy': emotion_scores['joy'],
+        'sadness': emotion_scores['sadness'],
+        'dominant_emotion': dominant_emotion
+    }

README.md

@@ -1 +1,40 @@
-# Repository for final project
+# Emotion Detection Flask Application
+
+A lightweight Flask-based web application that analyzes user-provided text to detect emotions such as anger, disgust, fear, joy, and sadness. The application uses a pre-trained emotion detection model and provides detailed emotion scores along with the dominant emotion.
+
+## Features
+
+- Analyze text to predict emotions (anger, disgust, fear, joy, sadness).
+- Returns emotion scores and identifies the dominant emotion.
+- Handles blank or invalid text inputs with proper error messages.
+- Easy-to-deploy Flask application for local or cloud hosting.
+
+## Installation
+
+1. Clone the repository:
+   ```bash
+   git clone  https://github.com/athrocks/Emotion-Detection-Flask-Application/
+   cd emotion-detection-flask
+   ```
+2. Install dependencies:
+
+3. Start the Flask server:
+   ```bash
+     python3.11 server.py
+   ```
+
+4. Access the application in your browser:  
+   Visit http://127.0.0.1:5005.
+
+
+#### Response
+   ```
+   {
+     "anger": 0.0136,
+     "disgust": 0.0017,
+     "fear": 0.0089,
+     "joy": 0.9719,
+     "sadness": 0.0552,
+     "dominant_emotion": "joy"
+   }
+   ```

server.py

@@ -0,0 +1,55 @@
+"""
+This module implements a Flask web server for emotion detection.
+It uses a predefined emotion detection function to analyze text input
+and returns the corresponding emotion scores and dominant emotion.
+"""
+
+from flask import Flask, render_template, request, jsonify
+from EmotionDetection.emotion_detection import emotion_detector
+
+app = Flask("Emotion Detector")
+
+@app.route("/emotionDetector")
+def sent_detector():
+    """
+    Handle the emotion detection request.
+
+    Expects a query parameter 'textToAnalyze'. 
+    Validates the input and calls the emotion_detector function. 
+
+    Returns:
+        JSON response:
+            - If input is valid: Emotion scores and the dominant emotion.
+            - If input is invalid or empty: Error message with status 400.
+    """
+    text_to_analyze = request.args.get('textToAnalyze', "").strip()
+
+    if not text_to_analyze:
+        return jsonify({"message": "Invalid text! Please try again!"}), 400
+
+    response = emotion_detector(text_to_analyze)
+
+    if response['dominant_emotion'] is None:
+        return jsonify({"message": "Invalid text! Please try again!"}), 400
+
+    return jsonify({
+        "anger": response['anger'],
+        "disgust": response['disgust'],
+        "fear": response['fear'],
+        "joy": response['joy'],
+        "sadness": response['sadness'],
+        "dominant_emotion": response['dominant_emotion']
+    }), 200
+
+@app.route("/")
+def render_index_page():
+    """
+    Render the index page for the application.
+
+    Returns:
+        Rendered HTML content from the index.html template.
+    """
+    return render_template('index.html')
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=5005)

static/mywebscript.js

@@ -10,3 +10,4 @@ let RunSentimentAnalysis = ()=>{
     xhttp.open("GET", "emotionDetector?textToAnalyze"+"="+textToAnalyze, true);
     xhttp.send();
 }
+

templates/index.html

@@ -23,7 +23,7 @@ <h2 class="mb-3">
             </div>
             <div style="padding: 25px 25px 25px 25px;"></div>
             <h2 class="mb-3">
-                <label class="form-label">Result of Emotion Detection</label>
+                <label class="form-label">Result of Emotion Detection:</label>
             </h2>
 
             <div id="system_response" style="padding: 25px 25px 25px 25px;"></div>

test_emotion_detection.py

@@ -0,0 +1,22 @@
+from EmotionDetection.emotion_detection import emotion_detector
+import unittest
+
+class TestEmotionDetector(unittest.TestCase):
+    def test_emotion_detector(self):
+
+        result_1 = emotion_detector('I am glad this happened')
+        self.assertEqual(result_1['dominant_emotion'], 'joy')
+
+        result_2 = emotion_detector('I am really mad about this	')
+        self.assertEqual(result_2['dominant_emotion'], 'anger')
+
+        result_3 = emotion_detector('I feel disgusted just hearing about this	')
+        self.assertEqual(result_3['dominant_emotion'], 'disgust')
+
+        result_4 = emotion_detector('I am so sad about this')
+        self.assertEqual(result_4['dominant_emotion'], 'sadness')
+
+        result_5 = emotion_detector('I am really afraid that this will happen	')
+        self.assertEqual(result_5['dominant_emotion'], 'fear')
+
+unittest.main()