Update app.py

app.py

@@ -0,0 +1,62 @@
+import streamlit as st
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+from sklearn.neighbors import NearestNeighbors
+
+# Function to recommend papers
+def recommend_papers(positive_df, unlabelled_df, model="tfidf"):
+    if model == "tfidf":
+        # Use TF-IDF Vectorizer
+        vectorizer = TfidfVectorizer(stop_words='english')
+        positive_matrix = vectorizer.fit_transform(positive_df['abstract'])
+        unlabelled_matrix = vectorizer.transform(unlabelled_df['abstract'])
+    elif model == "nn":
+        # Use Nearest Neighbors
+        nn_model = NearestNeighbors(n_neighbors=5, algorithm='auto')
+        nn_model.fit(positive_df['abstract'])
+        distances, indices = nn_model.kneighbors(unlabelled_df['abstract'])
+        return indices
+
+# Streamlit app
+def main():
+    st.title("ArXiv Feed Recommendations")
+
+    # User input for model selection
+    model = st.selectbox("Select Model", ["TF-IDF", "Nearest Neighbors"])
+
+    # Upload CSV files
+    st.subheader("Upload Positive Labeled CSV")
+    positive_file = st.file_uploader("Upload CSV", type=['csv'])
+    st.subheader("Upload Unlabelled Data CSV")
+    unlabelled_file = st.file_uploader("Upload CSV", type=['csv'])
+
+    if positive_file is not None and unlabelled_file is not None:
+        # Read CSV files
+        positive_df = pd.read_csv(positive_file)
+        unlabelled_df = pd.read_csv(unlabelled_file)
+
+        # Show uploaded data
+        st.subheader("Positive Labeled Data")
+        st.write(positive_df)
+        st.subheader("Unlabelled Data")
+        st.write(unlabelled_df)
+
+        # Button to trigger recommendation
+        if st.button("Recommend"):
+            # Call recommend_papers function
+            recommended_indices = recommend_papers(positive_df, unlabelled_df, model.lower())
+            st.write(recommended_indices)
+
+            # Download CSV
+            st.markdown(get_csv_download_link(recommended_indices), unsafe_allow_html=True)
+
+# Function to generate a download link for CSV
+def get_csv_download_link(data):
+    csv = data.to_csv(index=False)
+    b64 = base64.b64encode(csv.encode()).decode()  
+    href = f'<a href="data:file/csv;base64,{b64}" download="recommendations.csv">Download CSV</a>'
+    return href
+
+if __name__ == "__main__":
+    main()