pull

2a_emotion_detection.txt

@@ -0,0 +1,27 @@
+import requests
+import json
+
+def emotion_detector(text_to_analyze):
+    """
+    This function sends a POST request to the Watson NLP Emotion Predict API
+    and returns the response text.
+    """
+
+    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",
+        "Content-Type": "application/json"
+    }
+
+    payload = {
+        "raw_document": {
+            "text": text_to_analyze
+        }
+    }
+
+    try:
+        response = requests.post(url, headers=headers, json=payload)
+        return response.text
+    except Exception as e:
+        return f"Error: {str(e)}"

2b_application_creation.txt

@@ -0,0 +1,3 @@
+>>> print(result)
+{"emotionPredictions":[{"emotion":{"anger":0.0043339236, "disgust":0.00037549555, "fear":0.0034732423, "joy":0.9947189, "sadness":0.012704818}, "target":"", "emotionMentions":[{"span":{"begin":0, "end":30, "text":"I am so happy I am doing this."}, "emotion":{"anger":0.0043339236, "disgust":0.00037549555, "fear":0.0034732423, "joy":0.9947189, "sadness":0.012704818}}]}], "producerId":{"name":"Ensemble Aggregated Emotion Workflow", "version":"0.0.1"}}
+>>> 

3a_output_formatting.txt

@@ -0,0 +1,58 @@
+import requests
+import json
+
+def emotion_detector(text_to_analyze):
+    """
+    Sends text to Watson NLP Emotion API and returns a formatted dictionary
+    with emotion scores and dominant emotion.
+    """
+
+    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",
+        "Content-Type": "application/json"
+    }
+
+    payload = {
+        "raw_document": {
+            "text": text_to_analyze
+        }
+    }
+
+    try:
+        response = requests.post(url, headers=headers, json=payload)
+        response_dict = json.loads(response.text)
+
+        # Extract emotion scores
+        emotions = response_dict["emotionPredictions"][0]["emotion"]
+
+        anger = emotions["anger"]
+        disgust = emotions["disgust"]
+        fear = emotions["fear"]
+        joy = emotions["joy"]
+        sadness = emotions["sadness"]
+
+        # Find dominant emotion
+        emotion_scores = {
+            "anger": anger,
+            "disgust": disgust,
+            "fear": fear,
+            "joy": joy,
+            "sadness": sadness
+        }
+
+        dominant_emotion = max(emotion_scores, key=emotion_scores.get)
+
+        # Return formatted result
+        return {
+            "anger": anger,
+            "disgust": disgust,
+            "fear": fear,
+            "joy": joy,
+            "sadness": sadness,
+            "dominant_emotion": dominant_emotion
+        }
+
+    except Exception as e:
+        return {"error": str(e)}

3b_formatted_output_test.txt

@@ -0,0 +1,3 @@
+>>> print(result)
+{'anger': 0.0043339236, 'disgust': 0.00037549555, 'fear': 0.0034732423, 'joy': 0.9947189, 'sadness': 0.012704818, 'dominant_emotion': 'joy'}
+>>> 

4b_packaging_test .txt

@@ -0,0 +1,5 @@
+>>> from EmotionDetection import emotion_detector
+>>> result = emotion_detector("I hate working long hours")
+>>> print(result)
+{'anger': 0.64949876, 'disgust': 0.03718168, 'fear': 0.05612277, 'joy': 0.00862553, 'sadness': 0.1955148, 'dominant_emotion': 'anger'}
+>>> 

5a_unit_testing.txt

@@ -0,0 +1,29 @@
+import unittest
+from EmotionDetection import emotion_detector
+
+
+class TestEmotionDetector(unittest.TestCase):
+
+    def test_joy(self):
+        result = emotion_detector("I am glad this happened")
+        self.assertEqual(result["dominant_emotion"], "joy")
+
+    def test_anger(self):
+        result = emotion_detector("I am really mad about this")
+        self.assertEqual(result["dominant_emotion"], "anger")
+
+    def test_disgust(self):
+        result = emotion_detector("I feel disgusted just hearing about this")
+        self.assertEqual(result["dominant_emotion"], "disgust")
+
+    def test_sadness(self):
+        result = emotion_detector("I am so sad about this")
+        self.assertEqual(result["dominant_emotion"], "sadness")
+
+    def test_fear(self):
+        result = emotion_detector("I am really afraid that this will happen")
+        self.assertEqual(result["dominant_emotion"], "fear")
+
+
+if __name__ == "__main__":
+    unittest.main()

5b_unit_testing_result.txt

@@ -0,0 +1,6 @@
+ct-emb-ai$ python3 test_emotion_detection.py
+.....
+----------------------------------------------------------------------
+Ran 5 tests in 0.604s
+
+OK

EmotionDetection/__init__.py

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

EmotionDetection/emotion_detection.py

@@ -0,0 +1,58 @@
+import requests
+import json
+
+def emotion_detector(text_to_analyze):
+    """
+    Sends text to Watson NLP Emotion API and returns a formatted dictionary
+    with emotion scores and dominant emotion.
+    """
+
+    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",
+        "Content-Type": "application/json"
+    }
+
+    payload = {
+        "raw_document": {
+            "text": text_to_analyze
+        }
+    }
+
+    try:
+        response = requests.post(url, headers=headers, json=payload)
+        response_dict = json.loads(response.text)
+
+        # Extract emotion scores
+        emotions = response_dict["emotionPredictions"][0]["emotion"]
+
+        anger = emotions["anger"]
+        disgust = emotions["disgust"]
+        fear = emotions["fear"]
+        joy = emotions["joy"]
+        sadness = emotions["sadness"]
+
+        # Find dominant emotion
+        emotion_scores = {
+            "anger": anger,
+            "disgust": disgust,
+            "fear": fear,
+            "joy": joy,
+            "sadness": sadness
+        }
+
+        dominant_emotion = max(emotion_scores, key=emotion_scores.get)
+
+        # Return formatted result
+        return {
+            "anger": anger,
+            "disgust": disgust,
+            "fear": fear,
+            "joy": joy,
+            "sadness": sadness,
+            "dominant_emotion": dominant_emotion
+        }
+
+    except Exception as e:
+        return {"error": str(e)}

README.md

@@ -1 +1,2 @@
 # Repository for final project
+# Project name - Final project

test_emotion_detection.py

@@ -0,0 +1,29 @@
+import unittest
+from EmotionDetection import emotion_detector
+
+
+class TestEmotionDetector(unittest.TestCase):
+
+    def test_joy(self):
+        result = emotion_detector("I am glad this happened")
+        self.assertEqual(result["dominant_emotion"], "joy")
+
+    def test_anger(self):
+        result = emotion_detector("I am really mad about this")
+        self.assertEqual(result["dominant_emotion"], "anger")
+
+    def test_disgust(self):
+        result = emotion_detector("I feel disgusted just hearing about this")
+        self.assertEqual(result["dominant_emotion"], "disgust")
+
+    def test_sadness(self):
+        result = emotion_detector("I am so sad about this")
+        self.assertEqual(result["dominant_emotion"], "sadness")
+
+    def test_fear(self):
+        result = emotion_detector("I am really afraid that this will happen")
+        self.assertEqual(result["dominant_emotion"], "fear")
+
+
+if __name__ == "__main__":
+    unittest.main()