Rename random_charactor_generator.py to sentiment_analysis.py

random_charactor_generator.py

@@ -1,75 +0,0 @@
-import requests
-
-class RandomCharatorGeneratorTool:
-    name = "random_character"
-    description = "This tool fetches a random character from the 'https://randomuser.me/api/' open API."
-
-    inputs = ["text"]  # Adding an empty list for inputs
-
-    outputs = ["json"]
-
-    def __call__(self, inputs: str):
-        API_URL = "https://randomuser.me/api/"
-        
-        response = requests.get(API_URL)
-        data = response.json()['results'][0]
-
-        # Extract the relevant character information
-        character = {
-            "gender": data['gender'],
-            "name": {
-                "title": data['name']['title'],
-                "first": data['name']['first'],
-                "last": data['name']['last']
-            },
-            "location": {
-                "street": {
-                    "number": data['location']['street']['number'],
-                    "name": data['location']['street']['name']
-                },
-                "city": data['location']['city'],
-                "state": data['location']['state'],
-                "country": data['location']['country'],
-                "postcode": data['location']['postcode'],
-                "coordinates": {
-                    "latitude": data['location']['coordinates']['latitude'],
-                    "longitude": data['location']['coordinates']['longitude']
-                },
-                "timezone": {
-                    "offset": data['location']['timezone']['offset'],
-                    "description": data['location']['timezone']['description']
-                }
-            },
-            "email": data['email'],
-            "login": {
-                "uuid": data['login']['uuid'],
-                "username": data['login']['username'],
-                "password": data['login']['password'],
-                "salt": data['login']['salt'],
-                "md5": data['login']['md5'],
-                "sha1": data['login']['sha1'],
-                "sha256": data['login']['sha256']
-            },
-            "dob": {
-                "date": data['dob']['date'],
-                "age": data['dob']['age']
-            },
-            "registered": {
-                "date": data['registered']['date'],
-                "age": data['registered']['age']
-            },
-            "phone": data['phone'],
-            "cell": data['cell'],
-            "id": {
-                "name": data['id']['name'],
-                "value": data['id']['value']
-            },
-            "picture": {
-                "large": data['picture']['large'],
-                "medium": data['picture']['medium'],
-                "thumbnail": data['picture']['thumbnail']
-            },
-            "nat": data['nat']
-        }
-
-        return {"character": character}

sentiment_analysis.py

@@ -0,0 +1,44 @@
+import requests
+
+class SentimentAnalysisTool:
+    name = "sentiment_analysis"
+    description = "This tool analyses the sentiment of a given text input."
+
+    inputs = ["text"]  # Adding an empty list for inputs
+
+    outputs = ["json"]
+    
+    model_id_1 = "nlptown/bert-base-multilingual-uncased-sentiment"
+    model_id_2 = "microsoft/deberta-xlarge-mnli"
+    model_id_3 = "distilbert-base-uncased-finetuned-sst-2-english"
+    model_id_4 = "lordtt13/emo-mobilebert"
+    model_id_5 = "juliensimon/reviews-sentiment-analysis"
+    model_id_6 = "sbcBI/sentiment_analysis_model"
+    model_id_7 = "models/oliverguhr/german-sentiment-bert"
+    
+    def __call__(self, inputs: str):
+        return predict(str)
+
+
+
+    def parse_output(output_json):  
+        list_pred=[]
+        for i in range(len(output_json[0])):
+            label = output_json[0][i]['label']
+            score = output_json[0][i]['score']
+            list_pred.append((label, score))
+        return list_pred
+    
+    def get_prediction(model_id):
+        classifier = pipeline("text-classification", model=model_id, return_all_scores=True)
+                 
+    def predict(review):
+            classifier = get_prediction(model_id_7)
+            prediction = classifier(review)
+            print(prediction)
+            return parse_output(prediction)
+
+
+    
+        
+