Data-Mining-Practice-Project/part2.py

import pandas as pd
from sklearn.preprocessing import OneHotEncoder
from sklearn.cluster import KMeans
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score
from typing import Tuple, List
import numpy as np

def process_data_part2(train_path: str, test_path: str) -> Tuple[pd.DataFrame, pd.Series, pd.DataFrame, pd.Series]:
    """
    Processes the adult dataset for part 2 requirements.
    - Removes unknown values.
    - Binarizes numerical attributes based on the mean.
    - One-hot encodes categorical attributes.
    """
    columns: List[str] = [
        'age', 'workclass', 'fnlwgt', 'education', 'education-num', 'marital-status',
        'occupation', 'relationship', 'race', 'sex', 'capital-gain', 'capital-loss',
        'hours-per-week', 'native-country', 'income'
    ]

    # Load datasets
    df_train: pd.DataFrame = pd.read_csv(train_path, header=None, names=columns, sep=r',\s*', engine='python', na_values='?')
    df_test: pd.DataFrame = pd.read_csv(test_path, header=None, names=columns, sep=r',\s*', engine='python', na_values='?', skiprows=1)

    # Remove rows with any missing values
    df_train.dropna(inplace=True)
    df_test.dropna(inplace=True)

    # Separate features and target, and clean target labels
    X_train_raw = df_train.drop('income', axis=1)
    y_train = df_train['income'].str.replace('.', '', regex=False)
    X_test_raw = df_test.drop('income', axis=1)
    y_test = df_test['income'].str.replace('.', '', regex=False)

    # Identify numerical and categorical attributes
    numerical_cols = X_train_raw.select_dtypes(include=np.number).columns.tolist()
    categorical_cols = X_train_raw.select_dtypes(exclude=np.number).columns.tolist()

    # --- Preprocessing ---

    # 1. Binarize numerical attributes
    X_train_numerical_processed = pd.DataFrame()
    X_test_numerical_processed = pd.DataFrame()

    for col in numerical_cols:
        mean_val = X_train_raw[col].mean()
        X_train_numerical_processed[col] = (X_train_raw[col] > mean_val).astype(int)
        X_test_numerical_processed[col] = (X_test_raw[col] > mean_val).astype(int)

    # 2. One-hot encode categorical attributes
    encoder = OneHotEncoder(handle_unknown='ignore', sparse_output=False)

    X_train_categorical_processed = pd.DataFrame(
        encoder.fit_transform(X_train_raw[categorical_cols]),
        columns=encoder.get_feature_names_out(categorical_cols)
    )
    X_test_categorical_processed = pd.DataFrame(
        encoder.transform(X_test_raw[categorical_cols]),
        columns=encoder.get_feature_names_out(categorical_cols)
    )

    # Reset index to ensure concatenation works correctly
    X_train_numerical_processed.index = X_train_categorical_processed.index
    X_test_numerical_processed.index = X_test_categorical_processed.index
    y_train.index = X_train_categorical_processed.index
    y_test.index = X_test_categorical_processed.index

    # 3. Combine processed features
    X_train_processed = pd.concat([X_train_numerical_processed, X_train_categorical_processed], axis=1)
    X_test_processed = pd.concat([X_test_numerical_processed, X_test_categorical_processed], axis=1)

    return X_train_processed, y_train, X_test_processed, y_test

def run_kmeans_clustering(X_train: pd.DataFrame, k_values: List[int]):
    """
    Runs K-Means clustering for different k values and reports centroids.
    """
    print("--- K-Means Clustering ---")
    for k in k_values:
        print(f"\nRunning K-Means with k={k}...")
        kmeans = KMeans(n_clusters=k, random_state=42, n_init=10)
        kmeans.fit(X_train)

        print(f"Centroids for k={k}:")
        # Printing only the first 5 dimensions for brevity
        print(pd.DataFrame(kmeans.cluster_centers_[:, :5], columns=X_train.columns[:5]))
        print("-" * 20)

def run_knn_classification(X_train: pd.DataFrame, y_train: pd.Series, X_test: pd.DataFrame, y_test: pd.Series, k_values: List[int]):
    """
    Runs kNN classification on the last 10 test samples and reports accuracy.
    """
    print("\n--- k-Nearest Neighbors (kNN) Classification ---")

    # Use the last 10 records from the test set
    X_test_sample = X_test.tail(10)
    y_test_sample = y_test.tail(10)

    print(f"Predicting for the last {len(X_test_sample)} records of the test set.\n")

    for k in k_values:
        knn = KNeighborsClassifier(n_neighbors=k)
        knn.fit(X_train, y_train)

        y_pred_sample = knn.predict(X_test_sample)
        accuracy = accuracy_score(y_test_sample, y_pred_sample)

        print(f"kNN with k={k}:")
        print(f"  Prediction Accuracy: {accuracy:.2f}")
        print(f"  Predicted Labels: {y_pred_sample}")
        print(f"  Actual Labels:    {y_test_sample.values}")
        print("-" * 20)

if __name__ == '__main__':
    train_file = 'adult/adult.data'
    test_file = 'adult/adult.test'

    # Process data according to Part 2 requirements
    X_train, y_train, X_test, y_test = process_data_part2(train_file, test_file)

    print("Data processing complete.")
    print(f"Training data shape: {X_train.shape}")
    print(f"Test data shape: {X_test.shape}\n")

    # Run K-Means Clustering
    kmeans_k_values = [3, 5, 10]
    run_kmeans_clustering(X_train, kmeans_k_values)

    # Run kNN Classification
    knn_k_values = [3, 5, 10]
    run_knn_classification(X_train, y_train, X_test, y_test, knn_k_values)