Application Deploment

.ipynb_checkpoints/app-checkpoint.py

@@ -0,0 +1,147 @@
+import joblib
+
+model = joblib.load("xgb.pkl")
+
+
+def predict(*args):
+    input_data = []
+    
+    for i in args:
+        input_data.append(float(i))
+
+    input_data = np.asarray(input_data)
+    # reshape the array as we are predicting for one instance
+    input_data_reshaped = input_data.reshape(1, -1)
+
+    prediction = model.predict(input_data_reshaped)
+
+    if prediction[0] == 0:
+        return "The Credit Score is Good"
+    elif prediction[0] == 1:
+        return "The Credit Score is Poor"
+    else:
+        return "The Credit Score is Standard"
+
+with gr.Blocks() as app:
+    gr.Markdown(
+        """
+    **Credit Score Classification**"""
+    )
+    with gr.Row():
+        with gr.Column():
+            Annual_Income = gr.TextArea(label="Annual Income")
+            Monthly_Inhand_Salary = gr.TextArea(label="Monthly Inhand Salary")
+            Interest_Rate = gr.TextArea(label="Interest Rate")
+            Num_of_Loan = gr.Slider(
+                label="Number of Loans", minimum=1, maximum=10, step=1, randomize=True
+            )
+            Delay_from_due_date = gr.Slider(
+                label="Number of Delayed Days",
+                minimum=-100,
+                maximum=100,
+                step=1,
+                randomize=True,
+            )
+            Num_of_Delayed_Payment = gr.Slider(
+                label="Number of Delayed Payments",
+                minimum=1,
+                maximum=10,
+                step=1,
+                randomize=True,
+            )
+            Credit_Mix = gr.Dropdown(
+                label="Credit Mix (Bad: 0, Don't Have: 1, Good: 2, Standard: 3)",
+                choices=[0,1,2,3],
+                value=lambda: random.choice([0,1,2,3]),
+            )
+            Outstanding_Debt = gr.TextArea(label="Outstanding Debt")
+            Credit_Utilization_Ratio = gr.TextArea(label="Credit Utilization Ratio")
+            Payment_of_Min_Amount = gr.Dropdown(
+                label="Payment of Minimum Amount (NM: 0, No: 1, Yes: 2)",
+                choices=[0,1,2],
+                value=lambda: random.choice([0,1,2]),
+            )
+            Total_EMI_per_month = gr.TextArea(label="Total Equated Monthly Installment")
+            Amount_invested_monthly = gr.TextArea(label="Amount Invested Monthly")
+            Monthly_Balance = gr.TextArea(label="Monthly Balance")
+            Credit_History_Age_In_Years = gr.TextArea(label="Credit History in Years")
+            StudentLoan = gr.Dropdown(
+                label="Student Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            MortgageLoan= gr.Dropdown(
+                label="Mortage Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            PersonalLoan = gr.Dropdown(
+                label="Personal Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            DebtConsolidationLoan = gr.Dropdown(
+                label="Debt Consolidation Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            Credit_BuilderLoan = gr.Dropdown(
+                label="Credit Builder Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            HomeEquityLoan = gr.Dropdown(
+                label="Home Equity Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            NotSpecified = gr.Dropdown(
+                label="Unspecified Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            AutoLoan = gr.Dropdown(
+                label="Auto Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            PaydayLoan = gr.Dropdown(
+                label="Payday Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+        with gr.Column():
+            label = gr.Label()
+            with gr.Row():
+                predict_btn = gr.Button(value="Predict")
+            predict_btn.click(
+                predict,
+                inputs=[
+                    Annual_Income,
+                    Monthly_Inhand_Salary,
+                    Interest_Rate,
+                    Num_of_Loan,
+                    Delay_from_due_date,
+                    Num_of_Delayed_Payment,
+                    Credit_Mix,
+                    Outstanding_Debt,
+                    Credit_Utilization_Ratio,
+                    Payment_of_Min_Amount,
+                    Total_EMI_per_month,
+                    Amount_invested_monthly,
+                    Monthly_Balance,
+                    Credit_History_Age_In_Years,
+                    StudentLoan,
+                    MortgageLoan,
+                    PersonalLoan,
+                    DebtConsolidationLoan,
+                    Credit_BuilderLoan,
+                    HomeEquityLoan,
+                    NotSpecified,
+                    AutoLoan,
+                    PaydayLoan,
+                ],
+                outputs=[label],
+            )
+
+app.launch()

app.py

@@ -0,0 +1,147 @@
+import joblib
+
+model = joblib.load("xgb.pkl")
+
+
+def predict(*args):
+    input_data = []
+    
+    for i in args:
+        input_data.append(float(i))
+
+    input_data = np.asarray(input_data)
+    # reshape the array as we are predicting for one instance
+    input_data_reshaped = input_data.reshape(1, -1)
+
+    prediction = model.predict(input_data_reshaped)
+
+    if prediction[0] == 0:
+        return "The Credit Score is Good"
+    elif prediction[0] == 1:
+        return "The Credit Score is Poor"
+    else:
+        return "The Credit Score is Standard"
+
+with gr.Blocks() as app:
+    gr.Markdown(
+        """
+    **Credit Score Classification**"""
+    )
+    with gr.Row():
+        with gr.Column():
+            Annual_Income = gr.TextArea(label="Annual Income")
+            Monthly_Inhand_Salary = gr.TextArea(label="Monthly Inhand Salary")
+            Interest_Rate = gr.TextArea(label="Interest Rate")
+            Num_of_Loan = gr.Slider(
+                label="Number of Loans", minimum=1, maximum=10, step=1, randomize=True
+            )
+            Delay_from_due_date = gr.Slider(
+                label="Number of Delayed Days",
+                minimum=-100,
+                maximum=100,
+                step=1,
+                randomize=True,
+            )
+            Num_of_Delayed_Payment = gr.Slider(
+                label="Number of Delayed Payments",
+                minimum=1,
+                maximum=10,
+                step=1,
+                randomize=True,
+            )
+            Credit_Mix = gr.Dropdown(
+                label="Credit Mix (Bad: 0, Don't Have: 1, Good: 2, Standard: 3)",
+                choices=[0,1,2,3],
+                value=lambda: random.choice([0,1,2,3]),
+            )
+            Outstanding_Debt = gr.TextArea(label="Outstanding Debt")
+            Credit_Utilization_Ratio = gr.TextArea(label="Credit Utilization Ratio")
+            Payment_of_Min_Amount = gr.Dropdown(
+                label="Payment of Minimum Amount (NM: 0, No: 1, Yes: 2)",
+                choices=[0,1,2],
+                value=lambda: random.choice([0,1,2]),
+            )
+            Total_EMI_per_month = gr.TextArea(label="Total Equated Monthly Installment")
+            Amount_invested_monthly = gr.TextArea(label="Amount Invested Monthly")
+            Monthly_Balance = gr.TextArea(label="Monthly Balance")
+            Credit_History_Age_In_Years = gr.TextArea(label="Credit History in Years")
+            StudentLoan = gr.Dropdown(
+                label="Student Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            MortgageLoan= gr.Dropdown(
+                label="Mortage Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            PersonalLoan = gr.Dropdown(
+                label="Personal Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            DebtConsolidationLoan = gr.Dropdown(
+                label="Debt Consolidation Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            Credit_BuilderLoan = gr.Dropdown(
+                label="Credit Builder Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            HomeEquityLoan = gr.Dropdown(
+                label="Home Equity Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            NotSpecified = gr.Dropdown(
+                label="Unspecified Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            AutoLoan = gr.Dropdown(
+                label="Auto Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+            PaydayLoan = gr.Dropdown(
+                label="Payday Loan (Don't Have: 0, Have: 1)",
+                choices=[0,1],
+                value=lambda: random.choice([0,1]),
+            )
+        with gr.Column():
+            label = gr.Label()
+            with gr.Row():
+                predict_btn = gr.Button(value="Predict")
+            predict_btn.click(
+                predict,
+                inputs=[
+                    Annual_Income,
+                    Monthly_Inhand_Salary,
+                    Interest_Rate,
+                    Num_of_Loan,
+                    Delay_from_due_date,
+                    Num_of_Delayed_Payment,
+                    Credit_Mix,
+                    Outstanding_Debt,
+                    Credit_Utilization_Ratio,
+                    Payment_of_Min_Amount,
+                    Total_EMI_per_month,
+                    Amount_invested_monthly,
+                    Monthly_Balance,
+                    Credit_History_Age_In_Years,
+                    StudentLoan,
+                    MortgageLoan,
+                    PersonalLoan,
+                    DebtConsolidationLoan,
+                    Credit_BuilderLoan,
+                    HomeEquityLoan,
+                    NotSpecified,
+                    AutoLoan,
+                    PaydayLoan,
+                ],
+                outputs=[label],
+            )
+
+app.launch()

xgb.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9513f93dbdeda53310324f391d0186442155192b6c5128505dfdfb3fcaf7cbe
+size 28917068