app.py

import gradio as gr
import pandas as pd
import duckdb
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
from sklearn.feature_selection import SelectKBest, f_regression
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

# Function to load data from a Parquet file into a DuckDB in-memory database
def load_data(parquet_file):
    con = duckdb.connect(database=':memory:')
    con.execute(f"CREATE TABLE data AS SELECT * FROM read_parquet('{parquet_file}')")
    df = con.execute("SELECT * FROM data").fetchdf()
    return df

# Function to preprocess data and perform PCA
def preprocess_and_pca(df, target_column, n_components=5):
    # Drop non-numeric columns
    X = df.select_dtypes(include=[float, int])
    y = df[target_column]

    # Replace infinity values with NaN
    X.replace([np.inf, -np.inf], np.nan, inplace=True)

    # Handle missing values by imputing with the median
    X = X.fillna(X.median())
    y = y.fillna(y.median())

    # Standardize the data
    scaler = StandardScaler()
    X_scaled = scaler.fit_transform(X)

    # Apply PCA
    pca = PCA(n_components=n_components)
    X_pca = pca.fit_transform(X_scaled)

    return X_pca, y

# Function to visualize the PCA components
def visualize_pca(X_pca, y):
    # Visualize the first two principal components
    plt.figure(figsize=(10, 6))
    plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap='viridis', edgecolor='k', s=50)
    plt.xlabel('Principal Component 1')
    plt.ylabel('Principal Component 2')
    plt.title('PCA - First Two Principal Components')
    plt.colorbar(label='Median Income Household')
    plt.savefig('pca_scatter.png')
    plt.close()

    # Create a DataFrame with the first few principal components for pair plot
    pca_df = pd.DataFrame(X_pca, columns=[f'PC{i+1}' for i in range(X_pca.shape[1])])
    pca_df['Median_Income_Household'] = y

    # Pair plot of the first few principal components
    sns.pairplot(pca_df, vars=[f'PC{i+1}' for i in range(5)], hue='Median_Income_Household', palette='viridis')
    plt.suptitle('Pair Plot of Principal Components', y=1.02)
    plt.savefig('pca_pairplot.png')
    plt.close()

    return 'pca_scatter.png', 'pca_pairplot.png'

# Gradio interface function
def gradio_interface(target_column):
    df = load_data('df_usa_health_features.parquet')
    X_pca, y = preprocess_and_pca(df, target_column)
    scatter_plot, pair_plot = visualize_pca(X_pca, y)
    return scatter_plot, pair_plot

# Create Gradio interface
iface = gr.Interface(
    fn=gradio_interface,
    inputs=[
        gr.inputs.Textbox(label="Target Column")
    ],
    outputs=[
        gr.outputs.Image(type="file", label="PCA Scatter Plot"),
        gr.outputs.Image(type="file", label="PCA Pair Plot")
    ],
    title="PCA Visualization with DuckDB and Gradio",
    description="Specify the target column to visualize PCA components from the df_usa_health_features.parquet file."
)

# Launch the Gradio app
if __name__ == "__main__":
    iface.launch()