Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 import pickle
 import numpy as np
-import pandas as pd
 import matplotlib.pyplot as plt
 import matplotlib
 matplotlib.use("Agg")
@@ -15,113 +14,84 @@ try:
 except:
     model = None
 
-# =========================
-# 🔹 Load Dataset (REAL or DUMMY)
-# =========================
-try:
-    data = pd.read_csv("churn_data.csv")
-except:
-    np.random.seed(42)
-    data = pd.DataFrame({
-        "gender": np.random.choice(["Male","Female"], 300),
-        "tenure": np.random.randint(1, 60, 300),
-        "MonthlyCharges": np.random.randint(500, 8000, 300),
-        "Contract": np.random.choice(["Monthly","Quarterly","Yearly"], 300),
-        "Churn": np.random.choice([0,1], 300)
-    })
 
 # =========================
-# 🔹 KPI FUNCTION
+# 🔹 DASHBOARD ANALYSIS
 # =========================
-def get_kpis(df):
-    total = len(df)
-    churn_rate = df["Churn"].mean() * 100
-    avg_spend = df["MonthlyCharges"].mean()
-    avg_tenure = df["tenure"].mean()
-
-    return f"""
-### 📊 Key Metrics
-- Total Customers: **{total}**
-- Churn Rate: **{churn_rate:.2f}%**
-- Avg Spend: **₹{avg_spend:.0f}**
-- Avg Tenure: **{avg_tenure:.1f} months**
+def dashboard_analysis(age, gender, tenure, usage, support, delay,
+                      subscription, contract, spend, interaction):
+
+    try:
+        # Convert inputs
+        age = float(age)
+        tenure = float(tenure)
+        usage = float(usage)
+        support = float(support)
+        delay = float(delay)
+        spend = float(spend)
+        interaction = float(interaction)
+
+        # KPI Summary
+        kpi = f"""
+### 📊 Customer Summary
+- Age: **{age}**
+- Tenure: **{tenure} months**
+- Spend: **₹{spend}**
+- Contract: **{contract}**
+- Subscription: **{subscription}**
 """
 
-# =========================
-# 🔹 FILTER FUNCTION
-# =========================
-def apply_filters(gender, contract):
-    df = data.copy()
-    if gender != "All":
-        df = df[df["gender"] == gender]
-    if contract != "All":
-        df = df[df["Contract"] == contract]
-    return df
+        # Chart 1: Profile
+        fig1, ax1 = plt.subplots()
+        features = ["Age","Tenure","Usage","Support","Delay"]
+        values = [age, tenure, usage, support, delay]
+        ax1.bar(features, values)
+        ax1.set_title("Customer Profile")
+        plt.close(fig1)
+
+        # Chart 2: Financial
+        fig2, ax2 = plt.subplots()
+        ax2.bar(["Spend","Interaction"], [spend, interaction])
+        ax2.set_title("Financial & Interaction")
+        plt.close(fig2)
+
+        # Chart 3: Risk indicators
+        risk_scores = [
+            delay/30,
+            support/20,
+            (6-tenure)/6 if tenure < 6 else 0
+        ]
+        labels = ["Delay Risk","Support Risk","Tenure Risk"]
+
+        fig3, ax3 = plt.subplots()
+        ax3.bar(labels, risk_scores)
+        ax3.set_title("Risk Indicators")
+        plt.close(fig3)
+
+        # Chart 4: Subscription level
+        fig4, ax4 = plt.subplots()
+        sub_map = {"Basic":1, "Standard":2, "Premium":3}
+        ax4.bar(["Subscription Level"], [sub_map[subscription]])
+        ax4.set_title("Subscription Level")
+        plt.close(fig4)
+
+        return kpi, fig1, fig2, fig3, fig4
 
-# =========================
-# 🔹 CHARTS
-# =========================
-def churn_dist(df):
-    fig, ax = plt.subplots()
-    counts = df["Churn"].value_counts()
-    ax.bar(["No Churn","Churn"], counts)
-    ax.set_title("Churn Distribution")
-    plt.close(fig)
-    return fig
-
-def contract_chart(df):
-    fig, ax = plt.subplots()
-    pd.crosstab(df["Contract"], df["Churn"]).plot(kind="bar", ax=ax)
-    ax.set_title("Churn by Contract")
-    plt.close(fig)
-    return fig
-
-def tenure_chart(df):
-    fig, ax = plt.subplots()
-    ax.scatter(df["tenure"], df["Churn"])
-    ax.set_title("Tenure vs Churn")
-    plt.close(fig)
-    return fig
-
-def risk_pie(df):
-    fig, ax = plt.subplots()
-    counts = df["Churn"].value_counts()
-    ax.pie(counts, labels=["No Churn","Churn"], autopct="%1.1f%%")
-    ax.set_title("Risk Segmentation")
-    plt.close(fig)
-    return fig
+    except Exception as e:
+        return f"Error: {str(e)}", None, None, None, None
 
-# =========================
-# 🔹 FEATURE IMPORTANCE
-# =========================
-def feature_importance():
-    if model is None or not hasattr(model, "feature_importances_"):
-        return None
-
-    features = [
-        "age","gender","tenure","usage","support","delay",
-        "spend","interaction",
-        "sub_premium","sub_standard",
-        "contract_monthly","contract_quarterly"
-    ]
-
-    fig, ax = plt.subplots()
-    ax.barh(features, model.feature_importances_)
-    ax.set_title("Feature Importance")
-    plt.close(fig)
-    return fig
 
 # =========================
-# 🔹 PREDICTION
+# 🔹 PREDICTION FUNCTION
 # =========================
 def predict_churn(age, gender, tenure, usage, support, delay,
-                 subscription, contract, spend, interaction):
+                  subscription, contract, spend, interaction):
 
     try:
         if model is None:
             return "Model not loaded ❌", "", "", None, ""
 
-        # 🔹 Convert inputs safely
+        # Convert inputs
         age = float(age)
         tenure = float(tenure)
         usage = float(usage)
@@ -130,11 +100,10 @@ def predict_churn(age, gender, tenure, usage, support, delay,
         spend = float(spend)
         interaction = float(interaction)
 
+        # Encoding
         gender_val = 1 if gender == "Female" else 0
-
         sub_premium = 1 if subscription == "Premium" else 0
         sub_standard = 1 if subscription == "Standard" else 0
-
         contract_monthly = 1 if contract == "Monthly" else 0
         contract_quarterly = 1 if contract == "Quarterly" else 0
 
@@ -161,14 +130,14 @@ def predict_churn(age, gender, tenure, usage, support, delay,
         else:
             risk = "🟢 Low Risk"
 
-        # 📊 Probability Chart
+        # Probability chart
         fig, ax = plt.subplots()
         ax.bar(["No Churn","Churn"], [1-prob, prob])
         ax.set_ylim(0,1)
         ax.set_title("Prediction Probability")
         plt.close(fig)
 
-        # 🧠 Explanation
+        # Explanation
         reasons = []
         if delay > 15: reasons.append("High payment delay")
         if tenure < 6: reasons.append("Low tenure")
@@ -181,20 +150,35 @@ def predict_churn(age, gender, tenure, usage, support, delay,
     except Exception as e:
         return f"Error: {str(e)}", "", "", None, ""
 
+
 # =========================
 # 🎨 UI
 # =========================
 with gr.Blocks() as demo:
 
-    gr.Markdown("# 🚀 Customer Churn Analytics Dashboard")
+    gr.Markdown("# 🚀 Customer Churn Interactive Dashboard")
 
     # ---------------------
     # 📊 DASHBOARD TAB
     # ---------------------
     with gr.Tab("📊 Dashboard"):
 
-        gender_filter = gr.Dropdown(["All","Male","Female"], value="All")
-        contract_filter = gr.Dropdown(["All","Monthly","Quarterly","Yearly"], value="All")
+        with gr.Row():
+            d_age = gr.Number(value=30, label="Age")
+            d_gender = gr.Dropdown(["Male","Female"], value="Male")
+            d_tenure = gr.Number(value=12, label="Tenure")
+            d_usage = gr.Number(value=10, label="Usage")
+
+        with gr.Row():
+            d_support = gr.Number(value=2, label="Support Calls")
+            d_delay = gr.Number(value=5, label="Payment Delay")
+            d_subscription = gr.Dropdown(["Basic","Standard","Premium"], value="Basic")
+            d_contract = gr.Dropdown(["Monthly","Quarterly","Yearly"], value="Monthly")
+
+        d_spend = gr.Number(value=2000, label="Total Spend")
+        d_interaction = gr.Number(value=20, label="Interaction")
+
+        analyze_btn = gr.Button("Analyze Dashboard")
 
         kpi_text = gr.Markdown()
         chart1 = gr.Plot()
@@ -202,33 +186,21 @@ with gr.Blocks() as demo:
         chart3 = gr.Plot()
         chart4 = gr.Plot()
 
-        def update_dashboard(g, c):
-            df = apply_filters(g, c)
-            return (
-                get_kpis(df),
-                churn_dist(df),
-                contract_chart(df),
-                tenure_chart(df),
-                risk_pie(df)
-            )
-
-        demo.load(update_dashboard, [gender_filter, contract_filter],
-                  [kpi_text, chart1, chart2, chart3, chart4])
-
-        gender_filter.change(update_dashboard, [gender_filter, contract_filter],
-                             [kpi_text, chart1, chart2, chart3, chart4])
-
-        contract_filter.change(update_dashboard, [gender_filter, contract_filter],
-                               [kpi_text, chart1, chart2, chart3, chart4])
+        analyze_btn.click(
+            dashboard_analysis,
+            inputs=[d_age, d_gender, d_tenure, d_usage, d_support, d_delay,
+                    d_subscription, d_contract, d_spend, d_interaction],
+            outputs=[kpi_text, chart1, chart2, chart3, chart4]
+        )
 
     # ---------------------
-    # 🔍 PREDICTION TAB (UPDATED)
+    # 🔍 PREDICTION TAB
     # ---------------------
     with gr.Tab("🔍 Prediction"):
 
         with gr.Row():
             age = gr.Number(value=30, label="Age")
-            gender = gr.Dropdown(["Male","Female"], value="Male", label="Gender")
+            gender = gr.Dropdown(["Male","Female"], value="Male")
             tenure = gr.Number(value=12, label="Tenure")
             usage = gr.Number(value=10, label="Usage")
 
@@ -239,7 +211,7 @@ with gr.Blocks() as demo:
             contract = gr.Dropdown(["Monthly","Quarterly","Yearly"], value="Monthly")
 
         spend = gr.Number(value=2000, label="Total Spend")
-        interaction = gr.Number(value=20, label="Last Interaction")
+        interaction = gr.Number(value=20, label="Interaction")
 
         btn = gr.Button("Predict")
 
@@ -260,8 +232,21 @@ with gr.Blocks() as demo:
     # 📈 INSIGHTS TAB
     # ---------------------
     with gr.Tab("📈 Insights"):
-        gr.Markdown("### Feature Importance")
-        gr.Plot(feature_importance())
+
+        if model is not None and hasattr(model, "feature_importances_"):
+            fig, ax = plt.subplots()
+            features = [
+                "age","gender","tenure","usage","support","delay",
+                "spend","interaction",
+                "sub_premium","sub_standard",
+                "contract_monthly","contract_quarterly"
+            ]
+            ax.barh(features, model.feature_importances_)
+            ax.set_title("Feature Importance")
+            plt.close(fig)
+            gr.Plot(fig)
+        else:
+            gr.Markdown("⚠️ Feature importance not available")
 
 # =========================
 # 🚀 LAUNCH