svm_classifier.py

# Filename: svm_classifier.py
# Description: SVM-based classifier for a given dataset
# Author: Haider Marouf

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import classification_report, confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sns

def load_data(path):
    """Loads dataset from a CSV file."""
    return pd.read_csv(path)

def preprocess_data(df, label_column):
    """Splits features and labels."""
    X = df.drop(columns=[label_column])
    y = df[label_column]
    return train_test_split(X, y, test_size=0.2, random_state=42)

def train_svm(X_train, y_train, kernel='linear', C=1.0):
    """Trains an SVM model."""
    model = SVC(kernel=kernel, C=C)
    model.fit(X_train, y_train)
    return model

def evaluate_model(model, X_test, y_test):
    """Evaluates the model and prints metrics."""
    predictions = model.predict(X_test)
    print(confusion_matrix(y_test, predictions))
    print(classification_report(y_test, predictions))
    return predictions

def plot_confusion_matrix(y_true, y_pred):
    cm = confusion_matrix(y_true, y_pred)
    sns.heatmap(cm, annot=True, fmt="d", cmap="Blues")
    plt.xlabel("Predicted")
    plt.ylabel("Actual")
    plt.title("Confusion Matrix")
    plt.show()

if __name__ == "__main__":
    df = load_data("your_dataset.csv")  # replace with your dataset
    X_train, X_test, y_train, y_test = preprocess_data(df, label_column="your_target") # replace with your target
    model = train_svm(X_train, y_train, kernel='rbf', C=1.0)
    predictions = evaluate_model(model, X_test, y_test)
    plot_confusion_matrix(y_test, predictions)