app.py

import streamlit as st
import pandas as pd
import numpy as np
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

df = pd.read_csv("mycardata.csv")

# Main content
st.title('Interactive Car Data Clustering :blue_car:')

st.write('**Data Preview:**')
st.dataframe(df)

st.write('**Data Processed:**')
df['Selling_Price'] *= 10000
df['Present_Price'] *= 10000
df = pd.get_dummies(df, columns=['Transmission', 'Seller_Type', 'Fuel_Type'])
# Outlier
clip_limits = df[['Selling_Price', 'Present_Price', 'Kms_Driven']].quantile(0.97)
df[['Selling_Price', 'Present_Price', 'Kms_Driven']] = df[['Selling_Price', 'Present_Price', 'Kms_Driven']].clip(upper=clip_limits, axis=1)
st.dataframe(df)

n_clusters = st.slider('Pick Number Of Clusters',min_value=2, max_value=10, value=4)

# Perform K-means clustering
X = df[['Selling_Price', 'Kms_Driven']]
kmeans = KMeans(n_clusters=n_clusters, random_state=42)
df['cluster'] = kmeans.fit_predict(X)


# Create a 2x2 grid of subplots
fig, axs = plt.subplots(nrows=2, ncols=2, figsize=(12, 8))

# Define the colors for the clusters
colors = ['red', 'blue', 'green', 'orange', 'purple', 'brown', 'pink', 'gray', 'olive', 'cyan']

# Plot 1: Price vs. Kilometers Driven
for i in range(n_clusters):
    cluster_data = df[df['cluster'] == i]
    axs[0, 0].scatter(cluster_data['Selling_Price'], cluster_data['Kms_Driven'], c=colors[i], label=f'Cluster {i+1}')
axs[0, 0].set_xlabel('Price')
axs[0, 0].set_ylabel('Kilometers Driven')
axs[0, 0].set_title('KM to Price')

# Plot 2: Year vs. Kilometers Driven
for i in range(n_clusters):
    cluster_data = df[df['cluster'] == i]
    axs[0, 1].scatter(cluster_data['Year'], cluster_data['Kms_Driven'], c=colors[i], label=f'Cluster {i+1}')
axs[0, 1].set_xlabel('Year')
axs[0, 1].set_ylabel('Kilometers Driven')
axs[0, 1].set_title('KM to Years')

# Plot 3: Year vs. Price
for i in range(n_clusters):
    cluster_data = df[df['cluster'] == i]
    axs[1, 0].scatter(cluster_data['Year'], cluster_data['Selling_Price'], c=colors[i], label=f'Cluster {i+1}')
axs[1, 0].set_xlabel('Year')
axs[1, 0].set_ylabel('Price')
axs[1, 0].set_title('Price to Year')

# Plot 4: Retail vs. Price
for i in range(n_clusters):
    cluster_data = df[df['cluster'] == i]
    axs[1, 1].scatter(cluster_data['Present_Price'], cluster_data['Selling_Price'], c=colors[i], label=f'Cluster {i+1}')
axs[1, 1].set_xlabel('Retail')
axs[1, 1].set_ylabel('Price')
axs[1, 1].set_title('Price to Retail')

# Adjust the spacing between subplots
fig.tight_layout()

# Display the plot
st.pyplot(fig)