app.py

'''import pandas as pd
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import gradio as gr
import tempfile

def cluster_tourism(file, n_clusters):
    # Load CSV
    df = pd.read_csv(file)  

    # Clustering
    features = df[['AvgMonthlyTourists', 'AvgTemp', 'Hotels']]
    kmeans = KMeans(n_clusters=n_clusters, random_state=42, n_init=10)
    df['Cluster'] = kmeans.fit_predict(features)

    # Save clustered CSV to a temporary file
    tmp_csv = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
    df.to_csv(tmp_csv.name, index=False)

    # Plot clusters
    plt.figure(figsize=(6,4))
    for cluster in range(n_clusters):
        subset = df[df['Cluster'] == cluster]
        plt.scatter(subset['AvgMonthlyTourists'], subset['AvgTemp'], label=f'Cluster {cluster}')
    plt.xlabel('Avg Monthly Tourists')
    plt.ylabel('Avg Temp')
    plt.title('City Clusters')
    plt.legend()

    # Save plot to a temporary file
    tmp_plot = tempfile.NamedTemporaryFile(delete=False, suffix=".png")
    plt.savefig(tmp_plot.name)
    plt.close()

    return tmp_csv.name, tmp_plot.name

demo = gr.Interface(
    fn=cluster_tourism,
    inputs=[
        gr.File(file_types=[".csv"], type="filepath", label="Upload CSV"),
        gr.Slider(minimum=2, maximum=10, step=1, label="Number of Clusters")
    ],
    outputs=[
        gr.File(label="CSV with Cluster Labels"),
        gr.Image(label="Cluster Plot")
    ],
    title="Tourlandia City Clustering",
    description="Upload a CSV of cities with AvgMonthlyTourists, AvgTemp, and Hotels. Choose number of clusters to group similar cities."
)

demo.launch()'''

import pandas as pd
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt
import gradio as gr
import tempfile

def cluster_tourism(file, n_clusters):
    # Load CSV
    df = pd.read_csv(file)

    # Features to cluster on
    features = df[['AvgMonthlyTourists', 'AvgTemp', 'Hotels']]

    # Standardize features
    scaler = StandardScaler()
    features_scaled = scaler.fit_transform(features)

    # KMeans clustering
    kmeans = KMeans(n_clusters=n_clusters, random_state=42, n_init=10)
    df['Cluster'] = kmeans.fit_predict(features_scaled)

    # Save clustered CSV to temporary file
    tmp_csv = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
    df.to_csv(tmp_csv.name, index=False)

    # Plot clusters 
    plt.figure(figsize=(6,4))
    for cluster in range(n_clusters):
        subset = df[df['Cluster'] == cluster]
        plt.scatter(subset['AvgMonthlyTourists'], subset['AvgTemp'], label=f'Cluster {cluster}')
    plt.xlabel('Avg Monthly Tourists')
    plt.ylabel('Avg Temp')
    plt.title('City Clusters')
    plt.legend()

    # Save plot to temporary file
    tmp_plot = tempfile.NamedTemporaryFile(delete=False, suffix=".png")
    plt.savefig(tmp_plot.name)
    plt.close()

    return tmp_csv.name, tmp_plot.name

demo = gr.Interface(
    fn=cluster_tourism,
    inputs=[
        gr.File(file_types=[".csv"], type="filepath", label="Upload CSV"),
        gr.Slider(minimum=2, maximum=10, step=1, label="Number of Clusters")
    ],
    outputs=[
        gr.File(label="CSV with Cluster Labels"),
        gr.Image(label="Cluster Plot")
    ],
    title="City Clustering",
    description="Upload a CSV of cities with AvgMonthlyTourists, AvgTemp, and Hotels. Choose number of clusters to group similar cities."
)

demo.launch()