Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,121 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+import google.generativeai as genai
+import json
+import os
+from datetime import datetime
 
-"""
-# Welcome to Streamlit!
+# ====== CONFIG ======
+st.set_page_config(page_title="ECL Risk Analyzer", layout="wide")
+genai.configure(api_key=os.getenv("GEMINI_API_KEY"))
 
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+# ====== FUNCTIONS ======
+@st.cache_data
+def process_loan_data(df: pd.DataFrame):
+    """Compute PD, LGD, EAD, and ECL by loan_intent."""
+    df = df.dropna(subset=["loan_intent", "credit_score", "loan_amnt", "loan_status"])
+    df["loan_status"] = df["loan_status"].astype(int)
+    group = df.groupby("loan_intent")
+    pd_seg = group["loan_status"].mean()
+    lgd_seg = (1 - group["credit_score"].mean() / 850)
+    ead_seg = group["loan_amnt"].sum()
+    ecl_seg = pd_seg * lgd_seg * ead_seg
+    ecl_df = pd.concat([pd_seg, lgd_seg, ead_seg, ecl_seg], axis=1)
+    ecl_df.columns = ["PD", "LGD", "EAD", "ECL"]
+    ecl_df = ecl_df.reset_index()
+    return ecl_df
 
-In the meantime, below is an example of what you can do with just a few lines of code:
+def get_gemini_decision(segment, pd_val, lgd_val, ead_val, ecl_val):
+    """Ask Gemini to decide the recommended action for a segment."""
+    model = genai.GenerativeModel("gemini-1.5-pro")
+    system_prompt = """You are a financial risk advisor.
+Return only JSON: {"action":"increase_interest"|"reduce_disbursement"|"maintain","rationale":"string","confidence":float}"""
+    user_prompt = f"""
+Segment: {segment}
+PD: {pd_val:.3f}
+LGD: {lgd_val:.3f}
+EAD: {ead_val:,.0f}
+ECL: {ecl_val:,.0f}
+Rules:
+- PD > 0.25 ⇒ increase_interest
+- PD > 0.20 and ECL rising ⇒ reduce_disbursement
+- PD < 0.15 ⇒ maintain
 """
+    try:
+        response = model.generate_content(
+            [{"role": "system", "parts": [system_prompt]},
+             {"role": "user", "parts": [user_prompt]}],
+            generation_config={"temperature": 0.2}
+        )
+        result = json.loads(response.text)
+    except Exception:
+        result = {"action": "maintain", "rationale": "Fallback - invalid JSON", "confidence": 0.0}
+    return result
+
+# ====== UI ======
+st.title("📊 Expected Credit Loss (ECL) Risk Dashboard")
+st.write("Upload your **bank loan dataset** to compute segment-level Expected Credit Loss (ECL) and get AI-driven recommendations.")
+
+uploaded = st.file_uploader("Upload CSV dataset", type=["csv"])
+
+if uploaded:
+    df = pd.read_csv(uploaded)
+    st.success("Dataset loaded successfully.")
+    st.dataframe(df.head())
+
+    ecl_df = process_loan_data(df)
+    st.subheader("Segment-level ECL Summary")
+    st.dataframe(ecl_df, use_container_width=True, hide_index=True)
+
+    # --- Visualization: ECL by segment ---
+    st.subheader("ECL by Segment")
+    fig, ax = plt.subplots(figsize=(8, 4))
+    ax.bar(ecl_df["loan_intent"], ecl_df["ECL"])
+    ax.set_xlabel("Segment")
+    ax.set_ylabel("ECL")
+    ax.set_title("Expected Credit Loss per Segment")
+    plt.xticks(rotation=45)
+    st.pyplot(fig)
+
+    # --- Visualization: PD by segment ---
+    st.subheader("PD by Segment")
+    fig2, ax2 = plt.subplots(figsize=(8, 4))
+    ax2.bar(ecl_df["loan_intent"], ecl_df["PD"], color="gray")
+    ax2.set_xlabel("Segment")
+    ax2.set_ylabel("PD")
+    ax2.set_title("Probability of Default (PD) per Segment")
+    plt.xticks(rotation=45)
+    st.pyplot(fig2)
+
+    # --- AI Decision Section ---
+    st.subheader("AI Recommendations (Gemini)")
+    decisions = []
+    for _, row in ecl_df.iterrows():
+        decision = get_gemini_decision(row["loan_intent"], row["PD"], row["LGD"], row["EAD"], row["ECL"])
+        decisions.append({
+            "Segment": row["loan_intent"],
+            "Action": decision["action"],
+            "Rationale": decision["rationale"],
+            "Confidence": decision["confidence"],
+            "ECL": row["ECL"],
+            "PD": row["PD"]
+        })
+    result_df = pd.DataFrame(decisions)
+    result_df["Timestamp"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    st.dataframe(result_df, use_container_width=True, hide_index=True)
+
+    # --- Plot action summary ---
+    st.subheader("Recommended Actions Distribution")
+    fig3, ax3 = plt.subplots(figsize=(6, 4))
+    action_counts = result_df["Action"].value_counts()
+    ax3.pie(action_counts, labels=action_counts.index, autopct="%1.1f%%", startangle=140)
+    ax3.set_title("Recommended Actions per Segment")
+    st.pyplot(fig3)
+
+    # Option to export report
+    csv_out = result_df.to_csv(index=False).encode("utf-8")
+    st.download_button("Download ECL + Decision Report", csv_out, "ECL_Decisions.csv", "text/csv")
 
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+else:
+    st.info("Upload your CSV file to begin analysis.")