first commit

app.py

@@ -0,0 +1,31 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+# Load pre-trained model and tokenizer
+model_name = "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis"  # Replace with your chosen model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+def predict_sentiment(text):
+    inputs = tokenizer(text, return_tensors="pt")
+    outputs = model(**inputs)
+    sentiment_class = outputs.logits.argmax(dim=1).item()
+    sentiment_mapping = {0: 'Negative', 1: 'Neutral', 2: 'Positive'}
+    predicted_sentiment = sentiment_mapping.get(sentiment_class, 'Unknown')
+    return predicted_sentiment
+
+def main():
+    st.title("Financial Sentiment Analysis")
+
+    # Get user input
+    text = st.text_area("Enter financial content:")
+
+    if st.button("Classify Sentiment"):
+        if text:
+            predicted_sentiment = predict_sentiment(text)
+            st.success(f"Predicted sentiment: {predicted_sentiment}")
+        else:
+            st.warning("Please enter some text.")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+transformers
+torch

sentiment_analysis.py

@@ -0,0 +1,17 @@
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+# Load pre-trained model and tokenizer
+#model_name = "ProsusAI/finbert"
+#model_name = "ahmedrachid/FinancialBERT-Sentiment-Analysis"
+model_name="mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+# Example: Classify a financial text
+text = "With the launch of Apple Silicon, Apple shares have increased"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model(**inputs)
+predictions = outputs.logits.argmax(dim=1).item()
+
+# 'predictions' will contain the sentiment class (e.g., 0 for negative, 1 for neutral, 2 for positive)
+print("Predicted sentiment class:", predictions)