Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,6 +1,5 @@
 import os
 
-# Fix permission issues in Hugging Face Spaces or Docker
 os.environ["XDG_CONFIG_HOME"] = "/tmp"
 os.environ["STREAMLIT_RUNTIME_CONFIG_DIR"] = "/tmp"
 os.environ["STREAMLIT_HOME"] = "/tmp"
@@ -12,7 +11,6 @@ from openai import OpenAI
 from sklearn.ensemble import IsolationForest
 from sklearn.preprocessing import LabelEncoder
 
-# Initialize OpenAI client
 client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
 
 PROMPT_INSTRUCTIONS_TEXT = """
@@ -87,18 +85,16 @@ def apply_isolation_forest(df):
 
 # ---------------- Streamlit UI ----------------
 st.set_page_config(page_title="LLM-Assisted Anomaly Detector", layout="wide")
-st.title("🧠 LLM-Assisted + 🛡️ Isolation Forest Anomaly Detector")
+st.title("LLM-Assisted Anomaly Detector")
 
 st.markdown("""
-This tool combines **machine learning** and **large language models** to detect financial anomalies:
-- We first apply **Isolation Forest** to the full dataset to flag data-level outliers.
-- Then, you can select **one column** to perform a second pass of analysis using **OpenAI's GPT-4**, which focuses on semantic and contextual anomalies within that column only.
+This tool combines **machine learning** and **large language models** to detect anomalies in datasets. We first apply **Isolation Forest** to the full dataset to flag data-level outliers. Then, you can select **one column** to perform a second pass of analysis using **OpenAI's GPT-4**, which focuses on semantic and contextual anomalies within that column only.
 """)
 
 # Button to load sample data
 df = None
 sample_loaded = False
-if st.button("Load sample dataset (df_crypto.csv)"):
+if st.button("Load sample dataset"):
     sample_path = "src/df_crypto.csv"
     try:
         df = pd.read_csv(sample_path)
@@ -121,7 +117,7 @@ if df is not None:
     st.dataframe(df, use_container_width=True)
 
     # ---------------- Isolation Forest ----------------
-    st.markdown("### 🛡️ Anomaly Detection with Isolation Forest (whole dataset)")
+    st.markdown("### Anomaly Detection with Isolation Forest (whole dataset)")
     iforest_df = apply_isolation_forest(df)
 
     if iforest_df is not None:
@@ -129,7 +125,7 @@ if df is not None:
         st.dataframe(iforest_df[iforest_df["Anomaly"] == "Yes"], use_container_width=True)
 
     # ---------------- LLM Section ----------------
-    st.markdown("### 🔍 LLM-Based Anomaly Detection (specific column)")
+    st.markdown("### LLM-Based Anomaly Detection (specific column)")
 
     selected_column = st.selectbox("Select a column to analyze with LLM:", df.columns)