Update app.py

app.py

@@ -1,30 +1,51 @@
-# here are some examples for sadness, joy, anger, and optimism.
 import gradio as gr
-
-# Load model directly
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-from transformers import pipeline
-
-tokenizer = AutoTokenizer.from_pretrained("barbieheimer/MND_TweetEvalBert_model")
-model_load = AutoModelForSequenceClassification.from_pretrained("barbieheimer/MND_TweetEvalBert_model")
-
-# We can now use the model in the pipeline.
-classifier = pipeline("text-classification", model=model_load, tokenizer=tokenizer)
-
-
-def predict(prompt):
-    completion = classifier(prompt)
-    return completion[0]["label"], completion[0]["score"]
-
-examples = [
-    ["The movie was a bummer."],
-    ["I cannot wait to watch all these movies!"],
-    ["The ending of the movie really irks me, gives me the ick fr."],
-    ["The protagonist seems to have a lot of hope...."]
-]
-
-model = "models/barbieheimer/MND_TweetEvalBert_model"
-
-gr.Interface.load("models/barbieheimer/MND_TweetEvalBert_model", fn=predict, title="Sentiment Analysis", examples=examples,
-    inputs=gr.inputs.Textbox(lines=5, label="Type a Sentence here."),
-    outputs=[gr.outputs.Textbox(label="Label"),gr.outputs.Textbox(label="Score")],).launch()
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+
+class EmotionClassifier:
+    def __init__(self, model_name: str):
+        self.model = AutoModelForSequenceClassification.from_pretrained(model_name)
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.pipeline = pipeline(
+            "text-classification",
+            model=self.model,
+            tokenizer=self.tokenizer,
+            return_all_scores=True,
+        )
+
+
+    def predict(self, input_text: str):
+        pred = self.pipeline(input_text)[0]
+        result = {
+            "Anger 😠": pred[0]["score"],
+            "Joy 😂": pred[1]["score"],
+            "Optimism 😍": pred[2]["score"],
+            "Anger 😭": pred[3]["score"],
+        }
+        return result
+
+
+def main():
+    model = EmotionClassifier("models/barbieheimer/MND_TweetEvalBert_model")
+    iface = gr.Interface(
+        fn=model.predict,
+        inputs=gr.inputs.Textbox(
+            lines=3,
+            placeholder="Type a phrase that has some emotion",
+            label="Input Text",
+        ),
+        outputs="label",
+        title="Emotion Classification",
+        examples=[
+            "I get so down when I'm alone",
+            "I believe that today everything will work out",
+            "It was so dark there I was afraid to go",
+            "I loved the gift you gave me",
+            "I was very surprised by your presentation.",
+        ],
+    )
+
+    iface.launch()
+
+
+if __name__ == "__main__":
+    main()