import numpy as np
import pandas as pd
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
import matplotlib.pyplot as plt

# Load the dataset
data = sns.load_dataset('titanic')

# Drop unnecessary columns
data = data.drop(['deck', 'embark_town', 'alive', 'who', 'adult_male', 'class'], axis=1)

# Handle missing values
data['age'] = data['age'].fillna(data['age'].median())
data['embarked'] = data['embarked'].fillna(data['embarked'].mode()[0])

# Encode categorical variables
encoder = LabelEncoder()
data['sex'] = encoder.fit_transform(data['sex'])
data['embarked'] = encoder.fit_transform(data['embarked'])

# Split the dataset into training and testing sets
X = data.drop('survived', axis=1)
y = data['survived']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Create a random forest classifier with additional hyperparameters
rf_clf = RandomForestClassifier(
    n_estimators=100,      # Number of trees in the forest
    criterion='gini',      # Function to measure the quality of a split ('gini' or 'entropy')
    max_depth=None,        # Maximum depth of the tree (None means nodes are expanded until all leaves are pure)
    min_samples_split=2,   # Minimum number of samples required to split an internal node
    min_samples_leaf=1,    # Minimum number of samples required to be at a leaf node
    max_features='auto',   # Number of features to consider when looking for the best split ('auto', 'sqrt', 'log2', or an integer)
    bootstrap=True,        # Whether bootstrap samples are used when building trees
    oob_score=False,       # Whether to use out-of-bag samples to estimate the generalization accuracy
    n_jobs=None,           # Number of jobs to run in parallel for both fit and predict (-1 means using all processors)
    random_state=42,       # Controls both the randomness of the bootstrapping and feature sampling
    verbose=0,             # Controls the verbosity when fitting and predicting
    warm_start=False,      # Reuse the solution of the previous call to fit and add more estimators to the ensemble
    class_weight=None      # Weights associated with classes (None or 'balanced')
)

# Train the model
rf_clf.fit(X_train, y_train)

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

# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy:.2f}")
print("Classification Report:")
print(classification_report(y_test, y_pred))
print("Confusion Matrix:")
print(confusion_matrix(y_test, y_pred))

Accuracy: 0.78
Classification Report:
              precision    recall  f1-score   support

           0       0.80      0.83      0.81       157
           1       0.74      0.70      0.72       111

    accuracy                           0.78       268
   macro avg       0.77      0.77      0.77       268
weighted avg       0.77      0.78      0.78       268

Confusion Matrix:
[[130  27]
 [ 33  78]]

# Calculate feature importances
importances = rf_clf.feature_importances_

# Sort feature importances in descending order
indices = np.argsort(importances)[::-1]

# Rearrange feature names so they match the sorted feature importances
names = [X.columns[i] for i in indices]

# Create a bar plot
plt.figure(figsize=(10, 5))
plt.title("Feature Importance")
plt.bar(range(X.shape[1]), importances[indices])

# Add feature names as x-axis labels
plt.xticks(range(X.shape[1]), names, rotation=90)

# Show the plot
plt.show()