cyber-security-resources/ai_research/ML_Fundamentals/ai_generated/data/ai_generated_python_scripts/Support_Vector_Machines_(SVM).md

Sure! Here's an example script demonstrating the use of Support Vector Machines (SVM) for a binary classification problem using the famous iris dataset:

# Importing the required libraries
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score

# Loading the iris dataset
iris = datasets.load_iris()
X = iris.data
y = iris.target

# Splitting the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Creating the SVM classifier
svm = SVC(kernel='linear')

# Training the SVM classifier
svm.fit(X_train, y_train)

# Making predictions on the testing set
y_pred = svm.predict(X_test)

# Calculating the accuracy of the model
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy}")

In this script, the iris dataset is first loaded using the datasets.load_iris() method from the sklearn library. The features matrix X and the target vector y are then initialized. Next, the dataset is split into training and testing sets using train_test_split() function from the model_selection module.

A Support Vector Machine classifier is created using SVC() class from the svm module, with the kernel parameter set to 'linear'. The classifier is then trained on the training set using the fit() method.

Predictions are made on the testing set using the predict() method, and the accuracy of the model is calculated using the accuracy_score() function from the metrics module. Finally, the accuracy is printed to the console.

You can modify this script according to your specific use case or dataset. Remember to install the required packages (scikit-learn) in your Python environment before running the script.