Create app.py

app.py

@@ -0,0 +1,53 @@
+import joblib
+import pandas as pd
+import gradio as gr
+from datetime import datetime
+
+# Load the trained model
+model = joblib.load('power_consumption_model.pkl')
+
+# Function to preprocess input and make predictions
+def predict_power_consumption(global_reactive_power, voltage, global_intensity, sub_metering_1, sub_metering_2, sub_metering_3, hour, day, month):
+    # Create a DataFrame from the input
+    input_data = pd.DataFrame({
+        'Global_reactive_power': [global_reactive_power],
+        'Voltage': [voltage],
+        'Global_intensity': [global_intensity],
+        'Sub_metering_1': [sub_metering_1],
+        'Sub_metering_2': [sub_metering_2],
+        'Sub_metering_3': [sub_metering_3],
+        'Hour': [hour],
+        'Day': [day],
+        'Month': [month]
+    })
+    
+    # Make a prediction
+    prediction = model.predict(input_data)
+    return prediction[0]
+
+# Gradio interface
+inputs = [
+    gr.Number(label="Global Reactive Power"),
+    gr.Number(label="Voltage"),
+    gr.Number(label="Global Intensity"),
+    gr.Number(label="Sub Metering 1"),
+    gr.Number(label="Sub Metering 2"),
+    gr.Number(label="Sub Metering 3"),
+    gr.Slider(0, 23, step=1, label="Hour"),
+    gr.Slider(1, 31, step=1, label="Day"),
+    gr.Slider(1, 12, step=1, label="Month")
+]
+
+outputs = gr.Number(label="Predicted Global Active Power")
+
+# Create the Gradio app
+app = gr.Interface(
+    fn=predict_power_consumption,
+    inputs=inputs,
+    outputs=outputs,
+    title="Power Consumption Prediction",
+    description="Predict global active power consumption based on input features."
+)
+
+# Launch the app
+app.launch()