Conteúdo do Curso

Ensemble Learning

1. Basic Principles of Building Ensemble Models

What is Ensemble of Models?Bagging Models Boosting Models Stacking Models

2. Commonly Used Bagging Models

Bagging Classifier Challenge: Solving Task Using Bagging Classifier Bagging Regressor Challenge: Solving Task Using Bagging Regressor Random Forest Challenge: Determining Feature Importances Using Random Forest ExtraTrees

3. Commonly Used Boosting Models

AdaBoost Classifier Challenge: Solving Task Using AdaBoost Classifier Challenge: Solving Task Using AdaBoost Regressor Gradient Boosting XGBoost Challenge: Solving Task Using XGBoost

4. Commonly Used Stacking Models

Stacking Classifier Challenge: Solving Task Using Stacking Classifier Challenge: Solving Task Using Stacking Regressor Using Ensembles As Base Models Course Summary

XGBoost

XGBoost (Extreme Gradient Boosting) is a popular and powerful machine learning algorithm for classification and regression tasks. It's an ensemble learning technique that belongs to the gradient-boosting family of algorithms. XGBoost is known for its efficiency, scalability, and effectiveness in handling various machine-learning problems.

Key features of XGBoost

Gradient Boosting: XGBoost is a variant of gradient boosting with shallow decision trees as base models. These trees are created in a greedy manner by recursively partitioning the data based on the feature that leads to the best split;
Regularization: XGBoost incorporates regularization techniques to prevent overfitting. It includes terms in the objective function that penalize complex models, which helps in better generalization;
Objective Function: XGBoost optimizes an objective function that combines the loss function (e.g., mean squared error for regression, log loss for classification) and regularization terms. The algorithm seeks to find the best model that minimizes this objective function;
Parallel and Distributed Computing: XGBoost is designed to be efficient and scalable. It utilizes parallel and distributed computing techniques to speed up the training process, making it suitable for large datasets.

XGBoost's effectiveness lies in its ability to produce accurate predictions while managing issues like overfitting and underfitting. It has gained popularity in various machine-learning competitions and real-world applications due to its strong predictive performance and versatility.

Example

Firstly, we have to admit that XGBoost has no realization in the sklearn library, so we have to install xgboost manually using the following command in the console of your interpreter:
pip install xgboost.
After the installation is finished, we can use XGBoost to solve the tasks.

What is DMatrix?

Before we start working with the XGBoost ensemble model, we must get familiar with a specific data structure - DMatrix.
In XGBoost, DMatrix is a data structure that is optimized for efficiency and used to store the dataset during training and prediction. It's a core concept in the xgboost library and is designed to handle large datasets memory-efficient and fast. DMatrix serves as an input container for the training and testing data.

DMatrix example


              1234567891011
            
import xgboost as xgb
import numpy as np

# Sample data
X_train = np.array([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]])
y_train = np.array([0, 1, 0])

# Create DMatrix objects
dtrain = xgb.DMatrix(X_train, label=y_train)

print(type(dtrain))

XGBoost usage example


              12345678910111213141516171819202122232425262728293031323334
            
import numpy as np
import pandas as pd
import xgboost as xgb
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import f1_score

# Load the Iris dataset
data = load_iris()
X = data.data
y = data.target

# 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)

# Create DMatrix objects for XGBoost
dtrain = xgb.DMatrix(X_train, label=y_train)
dtest = xgb.DMatrix(X_test, label=y_test)

# Set hyperparameters
params = {
    'objective': 'multi:softmax',
    'num_class': 3
}

# Train the XGBoost classifier
model = xgb.train(params, dtrain)

# Make predictions
y_pred = model.predict(dtest)

# Calculate accuracy
f1 = f1_score(y_test, y_pred, average='weighted')
print(f'F1-score: {f1:.4f}')

Tudo estava claro?

Obrigado pelo seu feedback!

Seção 3. Capítulo 5