# main.py

# A demonstration of key classification algorithms using scikit-learn.

#

# Before running, you may need to install scikit-learn and pandas:

# pip install scikit-learn pandas

import pandas as pd

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import StandardScaler

from sklearn.neighbors import KNeighborsClassifier

from sklearn.tree import DecisionTreeClassifier

from sklearn.svm import SVC

from sklearn.metrics import accuracy_score, classification_report

print("--- Starting Classification Algorithms Demonstration ---")

# --- Section 1: Load and Prepare the Dataset ---

# We will use the famous Iris dataset, which is included with scikit-learn.

# The goal is to predict the species of an iris flower based on its measurements.

print("\n--- 1. Loading and Preparing the Iris Dataset ---")

iris = load_iris()

X = iris.data  # The features (sepal length, sepal width, petal length, petal width)

y = iris.target # The target (species of iris)

# For clarity, let's see the feature and target names

print(f"Features: {iris.feature_names}")

print(f"Target Classes: {iris.target_names}")

# Split the data into training and testing sets (80% train, 20% test)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)

print(f"\nData split into {len(X_train)} training samples and {len(X_test)} testing samples.")

# Scale the features. This is important for distance-based algorithms like KNN and SVM.

scaler = StandardScaler()

X_train_scaled = scaler.fit_transform(X_train)

X_test_scaled = scaler.transform(X_test)

print("Feature data has been scaled.")

# --- Section 2: Train and Evaluate Classification Models ---

# We will create a dictionary of models to train and evaluate them in a loop.

models = {

    "K-Nearest Neighbors (KNN)": KNeighborsClassifier(n_neighbors=5),

    "Decision Tree": DecisionTreeClassifier(random_state=42),

    "Support Vector Machine (SVM)": SVC(kernel='linear', random_state=42)

}

print("\n--- 2. Training and Evaluating Models ---")

for name, model in models.items():

    print(f"\n----- Evaluating: {name} -----")

    # Use scaled data for KNN and SVM, unscaled for Decision Tree

    if name in ["K-Nearest Neighbors (KNN)", "Support Vector Machine (SVM)"]:

        model.fit(X_train_scaled, y_train)

        y_pred = model.predict(X_test_scaled)

    else: # Decision Tree does not require feature scaling

        model.fit(X_train, y_train)

        y_pred = model.predict(X_test)

    # Calculate accuracy

    accuracy = accuracy_score(y_test, y_pred)

    print(f"Accuracy: {accuracy:.4f}")

    # Print a detailed classification report

    print("\nClassification Report:")

    # The report shows precision, recall, and F1-score for each class.

    print(classification_report(y_test, y_pred, target_names=iris.target_names))

print("\n--- End of Demonstration ---")