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

# Step 1.1: Load the Iris dataset
iris = datasets.load_iris()
df = pd.DataFrame(data=iris.data, columns=iris.feature_names)
df['target'] = iris.target
df['species'] = df['target'].map({0: 'setosa', 1: 'versicolor', 2: 'virginica'})
print("Original Iris DataFrame:\n", df.head())

# Step 1.2: Select two classes ('setosa' and 'versicolor')
df_binary = df[df['species'].isin(['setosa', 'versicolor'])]
X = df_binary.iloc[:, :-2].values  # Features
y = df_binary['target'].values     # Target labels

# Step 1.3: Split 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)

# Step 1.4: Load the SVC Model
svc_model = SVC(kernel='linear', random_state=42)
svc_model.fit(X_train, y_train)

# Step 1.5: Perform prediction
y_pred = svc_model.predict(X_test)

# Calculate accuracy
accuracy = accuracy_score(y_test, y_pred)
print("\nAccuracy of SVC Model:", accuracy)

# Confusion Matrix
conf_matrix = confusion_matrix(y_test, y_pred)
print("\nConfusion Matrix:\n", conf_matrix)

# Classification Report
print("\nClassification Report:\n", classification_report(y_test, y_pred, target_names=['setosa', 'versicolor']))

# Plot the Confusion Matrix
plt.figure(figsize=(6, 4))
sns.heatmap(conf_matrix, annot=True, cmap='Blues', fmt='d', xticklabels=['setosa', 'versicolor'], yticklabels=['setosa', 'versicolor'])
plt.title('Confusion Matrix')
plt.xlabel('Predicted Labels')
plt.ylabel('True Labels')
plt.show()