Create app.py

app.py

@@ -0,0 +1,93 @@
+import pandas as pd
+from sklearn.svm import SVC
+from sklearn.preprocessing import LabelEncoder
+from sklearn.model_selection import train_test_split
+import joblib
+import gradio as gr
+
+# Load data function
+def load_data():
+    data = pd.read_excel('cleaned1.xlsx')
+    label = LabelEncoder()
+    for col in data.columns:
+        data[col] = label.fit_transform(data[col])
+    return data
+
+# Split data into features and target
+def split(df):
+    y = df.Current_Stage
+    x = df.drop(columns=['Current_Stage'])
+    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=0)
+    return x_train, x_test, y_train, y_test
+
+# Train the model
+def train_model():
+    df = load_data()
+    x_train, x_test, y_train, y_test = split(df)
+    model = SVC(C=0.1, kernel='linear', gamma='scale')
+    model.fit(x_train, y_train)
+    accuracy = model.score(x_test, y_test)
+    print(f'Model accuracy: {accuracy * 100}%')
+    
+    # Save the model using joblib
+    joblib.dump(model, 'svm_model.pkl')
+    print('Model saved as svm_model.pkl')
+
+# Load the saved model
+def load_model():
+    return joblib.load('svm_model.pkl')
+
+# Function to preprocess the input and predict
+def preprocess_inputs(inputs):
+    # Ensure that all columns required during training are present
+    feature_columns = [
+        'Credit Expiration', 'DPD', 'FS', 'CDR', 'SICR', 'Follow Up', 
+        'Rescheduled ', 'Restructuring', 'Covenant', 'Turnover', 'Group Reason',
+        ' Stage As last Month'
+    ]
+    
+    # Convert "Yes" -> 1 and "No" -> 0 for encoding the radio inputs
+    encoded_inputs = [1 if i == 'Yes' else 0 if i == 'No' else i for i in inputs[:11]]
+    
+    # Convert "Stage As last Month" to an integer (choices 1, 2, or 3)
+    stage_as_last_month = int(inputs[11])
+    
+    # Append the selected "Stage As last Month" to the list of inputs
+    encoded_inputs.append(stage_as_last_month)
+    
+    # Ensure the inputs match the feature columns order
+    return pd.DataFrame([encoded_inputs], columns=feature_columns)
+
+# Prediction function for Gradio interface
+def predict(*inputs):
+    model = load_model()
+    
+    # Preprocess the inputs to match the training format
+    input_data = preprocess_inputs(inputs)
+    
+    # Make prediction
+    y_pred = model.predict(input_data)
+    return f"The predicted class is: {y_pred[0]}"
+
+# Train the model and save it (only run once)
+train_model()
+
+# Build the Gradio interface with radio buttons and textboxes
+gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Textbox(label="Credit Expiration"),
+        gr.Textbox(label="DPD"),
+        gr.Radio(choices=["Yes", "No"], label="FS"),
+        gr.Radio(choices=["Yes", "No"], label="CDR"),
+        gr.Radio(choices=["Yes", "No"], label="SICR"),
+        gr.Radio(choices=["Yes", "No"], label="Follow Up"),
+        gr.Radio(choices=["Yes", "No"], label="Rescheduled"),
+        gr.Radio(choices=["Yes", "No"], label="Restructuring"),
+        gr.Radio(choices=["Yes", "No"], label="Covenant"),
+        gr.Radio(choices=["Yes", "No"], label="Turnover"),
+        gr.Radio(choices=["Yes", "No"], label="Group Reason"),
+        gr.Radio(choices=["1", "2", "3"], label="Stage As last Month")  # Updated with choices 1, 2, 3
+    ],
+    outputs="text"
+).launch()