Upload app.py

app.py

@@ -0,0 +1,91 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+from wordcloud import WordCloud
+from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
+
+# ✅ MUST be first Streamlit command
+st.set_page_config(page_title="📰 News Classifier & Q&A App", layout="wide")
+
+# ----------------- Model Loader -----------------
+@st.cache_resource
+def load_text_classifier():
+    model_name = "MihanTilk/News_Classifier"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSequenceClassification.from_pretrained(
+        model_name
+    )
+    return pipeline("text-classification", model=model, tokenizer=tokenizer)
+
+# Load Classifier & QA pipeline
+classifier = load_text_classifier()
+qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
+
+# ----------------- CSS Styling -----------------
+st.markdown(
+    """
+    <style>
+        .main { background-color: #f4f4f4; }
+        .stTextInput, .stFileUploader { border: 2px solid #ff4b4b; border-radius: 10px; }
+        .stButton>button { background-color: #ff4b4b; color: white; border-radius: 10px; }
+        .stDownloadButton>button { background-color: #4CAF50; color: white; border-radius: 10px; }
+        h1, h2, h3, h4, h5, h6, p { color: #333333; }
+    </style>
+    """,
+    unsafe_allow_html=True
+)
+
+# ----------------- App Title -----------------
+st.title("📰 News Classification & Q&A App")
+st.markdown("<h4 style='color:#ff4b4b;'>Upload a CSV to classify news headlines and ask questions!</h4>", unsafe_allow_html=True)
+
+# ----------------- Upload CSV -----------------
+st.subheader("📂 Upload a CSV File")
+uploaded_file = st.file_uploader("Choose a CSV file...", type=["csv"])
+
+if uploaded_file:
+    # Read and preprocess
+    df = pd.read_csv(uploaded_file)
+    if "content" not in df.columns:
+        st.error("❌ The uploaded CSV must contain a 'content' column.")
+        st.stop()
+
+    # Preprocess text
+    df['cleaned_text'] = df['content'].astype(str).str.lower().str.strip()
+    st.write("📊 Preview of Uploaded Data:", df.head())
+
+    # ----------------- Classification -----------------
+    with st.spinner("🔍 Classifying news articles..."):
+        df['class'] = df['cleaned_text'].apply(lambda text: classifier(text)[0]['label'])
+
+    st.success("✅ Classification Complete!")
+    st.write("🔎 Classified Results:", df[['content', 'class']].head())
+
+    # ----------------- Download -----------------
+    st.subheader("📥 Download Results")
+    csv_output = df.to_csv(index=False).encode('utf-8')
+    st.download_button("Download Output CSV", data=csv_output, file_name="output.csv", mime="text/csv")
+
+    # ----------------- Q&A Section -----------------
+    st.subheader("💬 Ask a Question")
+    question = st.text_input("🔍 What do you want to know about the content?")
+
+    if st.button("Get Answer"):
+        context = " ".join(df['cleaned_text'].tolist())
+        with st.spinner("Answering..."):
+            result = qa_pipeline(question=question, context=context)
+        st.success(f"📝 **Answer:** {result['answer']}")
+
+    # ----------------- Word Cloud -----------------
+    st.subheader("☁️ Word Cloud of News Text")
+    text = " ".join(df['cleaned_text'].tolist())
+    wordcloud = WordCloud(width=800, height=400, background_color="white").generate(text)
+
+    fig, ax = plt.subplots()
+    ax.imshow(wordcloud, interpolation="bilinear")
+    ax.axis("off")
+    st.pyplot(fig)
+
+# ----------------- Footer -----------------
+st.markdown("---")
+st.markdown("<p style='text-align:center; color:#666;'>🚀 Built with using Streamlit & Hugging Face</p>", unsafe_allow_html=True)