Upload 4 files

encoder_categories.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5153392d11e8ec872d73c6b732298af6c8384d120d4a4d6cb6c05cc14cd4b3a0
+size 100

interface.py

@@ -0,0 +1,123 @@
+import gradio as gr
+import pandas as pd
+import joblib
+from math import radians, sin, cos, sqrt, atan2
+import folium
+
+# Load saved scaler and model
+scaler = joblib.load('scaler.pkl')
+kmeans_model = joblib.load('kmeans_model.pkl')
+
+# Load the dataset
+csv_file_path = 'properties.csv'
+df = pd.read_csv(csv_file_path)
+
+# Define the haversine function for distance calculation
+def haversine(lat1, lon1, lat2, lon2):
+    R = 6371  # Radius of the Earth in kilometers
+    dlat = radians(lat2 - lat1)
+    dlon = radians(lon2 - lon1)
+    a = sin(dlat / 2) ** 2 + cos(radians(lat1)) * cos(radians(lat2)) * sin(dlon / 2) ** 2
+    c = 2 * atan2(sqrt(a), sqrt(1 - a))
+    return R * c
+
+# Calculate the centroid for distance computation
+centroid_lat = df['Latitude'].mean()
+centroid_lon = df['Longitude'].mean()
+
+# OneHotEncoder category mapping
+property_type_mapping = joblib.load('encoder_categories.pkl')
+
+# Cluster descriptions
+cluster_descriptions = {
+    0: "Hotel/Others - Away from City Center",
+    1: "Apartments",
+    2: "Medium-large hotels - Close to the city centre",
+    3: "Guest House",
+    4: "Homestay",
+    5: "Resorts",
+    6: "Villa",
+    7: "Apart-hotels",
+    8: "Lodge",
+    9: "Small hotels - Close to the city centre"
+}
+
+# Gradio prediction function
+def predict_cluster(property_name, star_rating, latitude, longitude, property_type):
+    # Validate inputs
+    if not (-90 <= latitude <= 90) or not (-180 <= longitude <= 180):
+        return "Error: Latitude must be between -90 and 90, and longitude must be between -180 and 180."
+    if not (0 <= star_rating <= 5):
+        return "Error: Star rating must be between 0 and 5."
+
+    # Calculate distance from the center
+    distance_from_center = haversine(latitude, longitude, centroid_lat, centroid_lon)
+
+    # One-hot encode the property type
+    try:
+        property_type_index = property_type_mapping.index(property_type)
+    except ValueError:
+        return f"Error: Property type '{property_type}' is not in the recognized categories."
+
+    # Create a one-hot-encoded vector with the correct length
+    encoded_property_type = [0] * len(property_type_mapping)
+    encoded_property_type[property_type_index] = 1
+
+    # Prepare the feature vector
+    feature_vector = [star_rating, distance_from_center] + encoded_property_type
+
+    # Standardize the feature vector
+    try:
+        scaled_features = scaler.transform([feature_vector])
+    except ValueError as e:
+        return f"Error during scaling: {e}"
+
+    # Predict the cluster
+    cluster = kmeans_model.predict(scaled_features)[0]
+    description = cluster_descriptions.get(cluster, "Unknown cluster")
+
+    # Create a map
+    m = folium.Map(location=[latitude, longitude], zoom_start=12)
+    folium.Marker([latitude, longitude], popup=f"Cluster {cluster}: {description}").add_to(m)
+    map_html = m._repr_html_()
+
+    return f"The property '{property_name}' belongs to cluster {cluster}: {description}", map_html
+
+# Create the Gradio interface
+inputs = [
+    gr.Textbox(label="Property Name"),
+    gr.Slider(minimum=0, maximum=5, step=0.1, label="Star Rating", value=3.0),
+    gr.Number(label="Latitude"),
+    gr.Number(label="Longitude"),
+    gr.Dropdown(choices=property_type_mapping, label="Property Type")
+]
+
+outputs = [
+    gr.Textbox(label="Cluster Prediction"),
+    gr.HTML(label="Property Location on Map")
+]
+
+examples = [
+    ["HOTEL SHREEMAN", 0, 22.719764, 75.861520, "Hotel"],
+    ["Playotel Premier Vijay Nagar", 4, 22.756761, 75.903342, "Hotel"],
+    ["Papaya Tree", 3, 22.626778, 75.804808, "Hotel"],
+    ["ENRISE BY SAYAJI", 4, 22.625697, 75.803255, "Hotel"],
+    ["Chokhi Dhani Indore", 3, 22.589608, 75.900815, "Resort"]
+]
+
+app = gr.Interface(
+    fn=predict_cluster,
+    inputs=inputs,
+    outputs=outputs,
+    examples=examples,
+    title="Property Clustering Prediction",
+    description=(
+        "Enter the details of a property to predict its cluster. "
+        "The model uses star rating, geographical location, and property type for clustering. "
+        "Clusters represent property categories such as hotels, apartments, resorts, etc."
+    ),
+    theme="default"
+)
+
+# Run the Gradio app
+app.launch()

kmeans_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401803ee19647ea5c6938548623432575172b1b7ec659de0994d09a83513a0ac
+size 3391

scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6ebf8518bc3e8333d4c931a029cf06b979a6960cdefbcd29c1b870540c09db
+size 855