svm.py

import time
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
import warnings
warnings.filterwarnings("ignore")

# Load data from CSV file
file_path = 'data.csv'  # Replace with your actual file path
df = pd.read_csv(file_path)

# Feature engineering (if needed)
# For example, adding a new feature 'mean_radius_squared'
df['mean_radius_squared'] = df['mean radius'] ** 2

# Split the data into features (X) and target variable (y)
X = df.drop('diagnosis', axis=1)
y = df['diagnosis']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

start_time = time.time()

# Train the Support Vector Machine (SVM) model
svm_model = SVC(kernel='linear', random_state=42)
svm_model.fit(X_train, y_train)

# Make predictions on the test set
y_pred = svm_model.predict(X_test)

# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
conf_matrix = confusion_matrix(y_test, y_pred)
classification_rep = classification_report(y_test, y_pred)

# Display evaluation metrics
print("Accuracy:", accuracy)
print("\nConfusion Matrix:")
print(conf_matrix)
print("\nClassification Report:")
print(classification_rep)
end_time = time.time()
elapsed_time = end_time - start_time