Master

EmotionDetection/emotion_detection.py

@@ -0,0 +1,54 @@
+import requests
+import json
+
+def emotion_detector(text_to_analyze):
+    if not text_to_analyze:
+        return {
+            'anger': None,
+            'disgust': None,
+            'fear': None,
+            'joy': None,
+            'sadness': None,
+            'dominant_emotion': None
+        }
+
+    url = 'https://sn-watson-emotion.labs.skills.network/v1/watson.runtime.nlp.v1/NlpService/EmotionPredict'
+    headers = {"grpc-metadata-mm-model-id": "emotion_aggregated-workflow_lang_en_stock"}
+    myobj = { "raw_document": { "text": text_to_analyze } }
+
+    response = requests.post(url, json = myobj, headers=headers)
+
+    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_data = formatted_response['emotionPredictions'][0]['emotion']
+
+    anger_score = emotion_data['anger']
+    disgust_score = emotion_data['disgust']
+    fear_score = emotion_data['fear']
+    joy_score = emotion_data['joy']
+    sadness_score = emotion_data['sadness']
+
+    scores = {
+    'anger': anger_score,
+    'disgust': disgust_score,
+    'fear': fear_score,
+    'joy': joy_score,
+    'sadness': sadness_score,
+    }
+
+    dominant_emotion = max(scores, key=scores.get)
+
+    return {'anger': anger_score, 'disgust': disgust_score,'fear': fear_score,
+            'joy': joy_score, 'sadness': sadness_score,
+            'dominant_emotion': dominant_emotion}
+

server.py

@@ -0,0 +1,31 @@
+""" Import flask, render_tempalate, request from flask
+import emotion_detector from EmotionDetection.emotion_detection package
+"""
+from flask import Flask, render_template, request
+from EmotionDetection.emotion_detection import emotion_detector
+#  Initiate the Flask app
+app = Flask('Emotion Detection')
+
+@app.route('/emotionDetector')
+def analyzer():
+    """ Analysis the response and return the sentiment emotion and dominent emotion """
+    # Retrieve the text to analyze from the request arguments
+    text_to_analyze = request.args.get('textToAnalyze')
+    # Pass the text to the sentiment_analyzer function and store the response
+    response = emotion_detector(text_to_analyze)
+
+    if response['dominant_emotion'] is None:
+        return 'Invalid text! Please try again!.'
+    # Return a formatted string with the sentiment emotion and dominent emotion
+    return f"For the given statement, the system response is 'anger': {response['anger']},\
+     'disgust': {response['disgust']}, 'fear': {response['fear']}, 'joy': {response['joy']},\
+     and 'sadness': {response['sadness']}. The dominant emotion is {response['dominant_emotion']}."
+
+@app.route('/')
+def render_index_page():
+    """ Render an index.html file"""
+    return render_template('index.html')
+
+if __name__ == "__main__":
+    # Host on the 5000 port
+    app.run(host="0.0.0.0", port=5000)

test_emotion_detection.py

@@ -0,0 +1,23 @@
+from EmotionDetection.emotion_detection import emotion_detector
+import unittest
+
+class TestEmotionDetector(unittest.TestCase):
+    def test_emotion_detector(self):
+
+        result1 = emotion_detector('I am glad this happened')
+        self.assertEqual(result1['dominant_emotion'],'joy')
+
+        result2 = emotion_detector('I am really mad about this')
+        self.assertEqual(result2['dominant_emotion'],'anger')
+
+        result3 = emotion_detector('I feel disgusted just hearing about this')
+        self.assertEqual(result3['dominant_emotion'],'disgust')
+
+        result4 = emotion_detector('I am so sad about this')
+        self.assertEqual(result4['dominant_emotion'],'sadness')
+
+        result5 = emotion_detector('I am really afraid that this will happen')
+        self.assertEqual(result5['dominant_emotion'],'fear')
+
+
+unittest.main()