#5)Train and fine-tune a Decision Tree for Moon dataset. 
#1. Import Libraries and Generate Moons Dataset:
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.datasets import make_moons
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.tree import plot_tree

#Generate Data
# Generate moons data
X, y = make_moons(n_samples=1000, noise=0.3)

#2. Exploratory Data Analysis (EDA)
# 1. Data Shape and Description
print("Data Shape:", X.shape)
print("Description of first 5 rows:")
print(X[:5])
print("Description of target variable:")
print(pd.Series(y).value_counts()) # Convert y to pandas Series
################################
# 2. Check for Missing Values
import numpy as np
print("Missing values in features:", np.isnan(X).sum(axis=0))
###############
# 3. Visualize the moons data
plt.scatter(X[:, 0], X[:, 1], c=y)
plt.title("Moons Dataset")
plt.xlabel("Feature 1")
plt.ylabel("Feature 2")
plt.show() 
#####################
#3. Train-Test Split:
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

#4. Define Decision Tree Classifier:
# Define the decision tree classifier
clf = DecisionTreeClassifier()

#5. Hyperparameter Tuning with GridSearchCV:
# Define hyperparameter grid
param_grid = {
 'max_depth': [2, 3, 4, 5],
 'min_samples_split': [2, 5, 10]
}
# Create GridSearchCV object
grid_clf = GridSearchCV(clf, param_grid, scoring='accuracy')
# Train the model
grid_clf.fit(X_train, y_train)
# Get the best model
best_model = grid_clf.best_estimator_
# Print the best hyperparameters
print("Best Hyperparameters:", grid_clf.best_params_) 
###########################
#6. Evaluate the Model:
# Predict on test set
y_pred = best_model.predict(X_test)

# Calculate accuracy
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y_test, y_pred)
print("Test Accuracy:", accuracy) 
##########################
#7. Visualize the Decision Tree:
# Visualize the decision tree
plot_tree(best_model)
plt.show()