ff.python

f.python

@@ -0,0 +1,100 @@
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+# Install necessary dependencies
+!pip install -q gradio transformers
+
+# Define the house price estimation function
+def house_price_estimation(area, rooms, kitchens, doors, washrooms, manzalas, land_measurement, garden=False, garage=False, storage_room=False, electricity=False, gas=False, water=False, ac=False, geyser=False, roof=False):
+    # Perform calculations to estimate the house price based on the provided details
+    price = area * 100 + rooms * 2000 + kitchens * 1500
+    
+    # Increase price based on land measurement
+    if land_measurement == "Marlas":
+        price += 500 * area
+    elif land_measurement == "Canals":
+        price += 1000 * area
+
+    # Increase price based on optional facilities
+    if garden:
+        price += 5000
+    if garage:
+        price += 4000
+    if storage_room:
+        price += 3000
+    if electricity:
+        price += 2000
+    if gas:
+        price += 3000
+    if water:
+        price += 2000
+    if ac:
+        price += 2000
+    if geyser:
+        price += 1000
+    if roof:
+        price += 2000
+
+    return price
+
+# Define the inputs and outputs for the Gradio interface
+input_area = gr.inputs.Slider(minimum=0, maximum=5000, step=100, default=1000, label="Area (in square feet)")
+input_rooms = gr.inputs.Slider(minimum=0, maximum=10, step=1, default=3, label="Number of Rooms")
+input_kitchens = gr.inputs.Slider(minimum=0, maximum=5, step=1, default=1, label="Number of Kitchens")
+input_doors = gr.inputs.Slider(minimum=0, maximum=20, step=1, default=4, label="Number of Doors")
+input_washrooms = gr.inputs.Slider(minimum=0, maximum=10, step=1, default=2, label="Number of Washrooms")
+input_manzalas = gr.inputs.Slider(minimum=0, maximum=5, step=1, default=1, label="Number of Manzalas")
+input_land_measurement = gr.inputs.Radio(["Marlas", "Canals"], label="Land Measurement")
+
+input_garden = gr.inputs.Checkbox(label="Garden")
+input_garage = gr.inputs.Checkbox(label="Garage")
+input_storage_room = gr.inputs.Checkbox(label="Storage Room")
+input_electricity = gr.inputs.Checkbox(label="Electricity")
+input_gas = gr.inputs.Checkbox(label="Gas")
+input_water = gr.inputs.Checkbox(label="Water")
+input_ac = gr.inputs.Checkbox(label="Air Conditioning (AC)")
+input_geyser = gr.inputs.Checkbox(label="Geyser")
+input_roof = gr.inputs.Checkbox(label="Roof")
+
+output_price = gr.outputs.Textbox(label="Estimated House Price")
+
+# Load the pre-trained model and tokenizer from Hugging Face
+model_name = "your_model_name"  # Replace with the name or path of your pre-trained model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+# Define the function to perform house price estimation using the loaded model
+def estimate_house_price(area, rooms, kitchens, doors, washrooms, manzalas, land_measurement, garden=False, garage=False, storage_room=False, electricity=False, gas=False, water=False, ac=False, geyser=False, roof=False):
+    # Convert the input data to a formatted string
+    input_text = f"{area}, {rooms}, {kitchens}, {doors}, {washrooms}, {manzalas}, {land_measurement}, {garden}, {garage}, {storage_room}, {electricity}, {gas}, {water}, {ac}, {geyser}, {roof}"
+    
+    # Tokenize the input text
+    inputs = tokenizer(input_text, padding=True, truncation=True, return_tensors="pt")
+    
+    # Make predictions with the pre-trained model
+    outputs = model(**inputs)
+    predicted_price = outputs.logits.item()
+    
+    return predicted_price
+
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=estimate_house_price,
+    inputs=[
+        input_area, input_rooms, input_kitchens, input_doors, input_washrooms, input_manzalas,
+        input_land_measurement, input_garden, input_garage, input_storage_room,
+        input_electricity, input_gas, input_water, input_ac, input_geyser, input_roof
+    ],
+    outputs=output_price,
+    examples=[
+        [1000, 3, 1, 4, 2, 1, "Marlas", True, False, True, True, False, True, False, False, True],
+        [1500, 4, 2, 6, 3, 1, "Canals", False, True, False, False, True, True, False, False, True],
+        [800, 2, 1, 2, 1, 1, "Marlas", True, False, False, True, True, True, False, True, False]
+    ],
+    title="House Price Estimation",
+    description="Estimate the price of a house based on the provided requirements."
+)
+
+# Launch the Gradio interface
+interface.launch()