├── Assessing performance of a regression model (MAE vs MSE) ├── papers │ ├── Advantages of the MAE over the RMSE in assessing average model performance.pdf │ └── RMSE or MAE - Arguments against avoiding RMSE in the literature.pdf └── source code │ ├── chai_draxler_14 (RMSE or MAE - Arguments against avoiding RMSE in the literature).pdf │ └── willmott_matsuura_05 (Advantages of the MAE over the RMSE in assessing average model performance).pdf ├── Ensemble methods (bagging vs voting) ├── papers │ ├── Bagging predictors.pdf │ └── Ensemble methods in machine learning.pdf └── source code │ ├── Ensemble-methods.ipynb │ ├── Ensemble-of-neural-networks.ipynb │ ├── bagging-classifier.py │ ├── hard-vote.py │ ├── single-classifier.py │ └── soft-vote.py ├── Evaluation metrics for unbalanced data (ROC vs Informedness) ├── papers │ ├── An introduction to ROC analysis.pdf │ └── Evaluation - from precision, recall, and f-measure to roc, informedness, markedness, and correlation.pdf └── source code │ ├── base_metrics.py │ ├── evaluation-metrics-for-unbalanced-data.ipynb │ ├── informedness.py │ └── roc.py ├── Feature scaling (mean substraction vs normalization) ├── ppt │ └── cs231n_2017_lecture6.pdf └── source code │ ├── feature scaling.ipynb │ ├── mean-subtraction.py │ ├── normalization-1.py │ ├── normalization-2.py │ └── wo-feature-scaling.py ├── Hyperparameter Tuning (Grid search vs Random search) ├── papers │ └── Random Search for Hyper-Parameter Optimization(Bergstra et al 2012).pdf └── source code │ ├── grid-search.py │ ├── parameter tuning with grid search and random search.ipynb │ └── randon-search.py ├── Model selection (cross-validation vs bootstrap) ├── papers │ └── A study of cross-validation and bootstrap for accuracy estimation and model selection.pdf └── source code │ ├── bootstrap-vs-cross-validation.ipynb │ ├── bootstrapping.py │ ├── naive-cross-validation.py │ └── stratified-cross-validation.py ├── Optimization methods (first-order vs second-order) ├── papers │ ├── adam - a method for stochastic optimization.pdf │ └── on the limited memory BFGS method for large scale optimization.pdf └── source code │ ├── adam-optimizer.py │ ├── first-and-secod-order-optimization-methods.ipynb │ └── lbfgs-optimizer.py ├── README.md ├── Regularization and feature selection (L1 vs L2 regularization) ├── papers │ └── Feature selection, L1 vs L2 regularization, and rotational invariance.pdf └── source code │ ├── L1-and-L2-regularization.ipynb │ ├── l1.py │ └── l2.py └── Tradeoff when using SGD (batch_size and learning_rate) ├── paper └── Optimization methods for large-scale machine learning.pdf └── source code ├── big-bs-high-lr.py ├── big-bs-low-lr.py ├── small-bs-high-lr.py ├── small-bs-low-lr.py └── tradeoff-bw-batch_size-and-learning_rate.ipynb /Assessing performance of a regression model (MAE vs MSE)/papers/Advantages of the MAE over the RMSE in assessing average model performance.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Assessing performance of a regression model (MAE vs MSE)/papers/Advantages of the MAE over the RMSE in assessing average model performance.pdf -------------------------------------------------------------------------------- /Assessing performance of a regression model (MAE vs MSE)/papers/RMSE or MAE - Arguments against avoiding RMSE in the literature.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Assessing performance of a regression model (MAE vs MSE)/papers/RMSE or MAE - Arguments against avoiding RMSE in the literature.pdf -------------------------------------------------------------------------------- /Assessing performance of a regression model (MAE vs MSE)/source code/chai_draxler_14 (RMSE or MAE - Arguments against avoiding RMSE in the literature).pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Assessing performance of a regression model (MAE vs MSE)/source code/chai_draxler_14 (RMSE or MAE - Arguments against avoiding RMSE in the literature).pdf -------------------------------------------------------------------------------- /Assessing performance of a regression model (MAE vs MSE)/source code/willmott_matsuura_05 (Advantages of the MAE over the RMSE in assessing average model performance).pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Assessing performance of a regression model (MAE vs MSE)/source code/willmott_matsuura_05 (Advantages of the MAE over the RMSE in assessing average model performance).pdf -------------------------------------------------------------------------------- /Ensemble methods (bagging vs voting)/papers/Bagging predictors.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Ensemble methods (bagging vs voting)/papers/Bagging predictors.pdf -------------------------------------------------------------------------------- /Ensemble methods (bagging vs voting)/papers/Ensemble methods in machine learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Ensemble methods (bagging vs voting)/papers/Ensemble methods in machine learning.pdf -------------------------------------------------------------------------------- /Ensemble methods (bagging vs voting)/source code/Ensemble-methods.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Ensemble methods (bagging vs voting)/source code/Ensemble-methods.ipynb -------------------------------------------------------------------------------- /Ensemble methods (bagging vs voting)/source code/Ensemble-of-neural-networks.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Ensemble methods (bagging vs voting)/source code/Ensemble-of-neural-networks.ipynb -------------------------------------------------------------------------------- /Ensemble methods (bagging vs voting)/source code/bagging-classifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Ensemble methods (bagging vs voting)/source code/bagging-classifier.py -------------------------------------------------------------------------------- /Ensemble methods (bagging vs voting)/source code/hard-vote.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Ensemble methods (bagging vs voting)/source code/hard-vote.py -------------------------------------------------------------------------------- /Ensemble methods (bagging vs voting)/source code/single-classifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Ensemble methods (bagging vs voting)/source code/single-classifier.py -------------------------------------------------------------------------------- /Ensemble methods (bagging vs voting)/source code/soft-vote.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Ensemble methods (bagging vs voting)/source code/soft-vote.py -------------------------------------------------------------------------------- /Evaluation metrics for unbalanced data (ROC vs Informedness)/papers/An introduction to ROC analysis.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Evaluation metrics for unbalanced data (ROC vs Informedness)/papers/An introduction to ROC analysis.pdf -------------------------------------------------------------------------------- /Evaluation metrics for unbalanced data (ROC vs Informedness)/papers/Evaluation - from precision, recall, and f-measure to roc, informedness, markedness, and correlation.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Evaluation metrics for unbalanced data (ROC vs Informedness)/papers/Evaluation - from precision, recall, and f-measure to roc, informedness, markedness, and correlation.pdf -------------------------------------------------------------------------------- /Evaluation metrics for unbalanced data (ROC vs Informedness)/source code/base_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Evaluation metrics for unbalanced data (ROC vs Informedness)/source code/base_metrics.py -------------------------------------------------------------------------------- /Evaluation metrics for unbalanced data (ROC vs Informedness)/source code/evaluation-metrics-for-unbalanced-data.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Evaluation metrics for unbalanced data (ROC vs Informedness)/source code/evaluation-metrics-for-unbalanced-data.ipynb -------------------------------------------------------------------------------- /Evaluation metrics for unbalanced data (ROC vs Informedness)/source code/informedness.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Evaluation metrics for unbalanced data (ROC vs Informedness)/source code/informedness.py -------------------------------------------------------------------------------- /Evaluation metrics for unbalanced data (ROC vs Informedness)/source code/roc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Evaluation metrics for unbalanced data (ROC vs Informedness)/source code/roc.py -------------------------------------------------------------------------------- /Feature scaling (mean substraction vs normalization)/ppt/cs231n_2017_lecture6.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Feature scaling (mean substraction vs normalization)/ppt/cs231n_2017_lecture6.pdf -------------------------------------------------------------------------------- /Feature scaling (mean substraction vs normalization)/source code/feature scaling.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Feature scaling (mean substraction vs normalization)/source code/feature scaling.ipynb -------------------------------------------------------------------------------- /Feature scaling (mean substraction vs normalization)/source code/mean-subtraction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Feature scaling (mean substraction vs normalization)/source code/mean-subtraction.py -------------------------------------------------------------------------------- /Feature scaling (mean substraction vs normalization)/source code/normalization-1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Feature scaling (mean substraction vs normalization)/source code/normalization-1.py -------------------------------------------------------------------------------- /Feature scaling (mean substraction vs normalization)/source code/normalization-2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Feature scaling (mean substraction vs normalization)/source code/normalization-2.py -------------------------------------------------------------------------------- /Feature scaling (mean substraction vs normalization)/source code/wo-feature-scaling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Feature scaling (mean substraction vs normalization)/source code/wo-feature-scaling.py -------------------------------------------------------------------------------- /Hyperparameter Tuning (Grid search vs Random search)/papers/Random Search for Hyper-Parameter Optimization(Bergstra et al 2012).pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Hyperparameter Tuning (Grid search vs Random search)/papers/Random Search for Hyper-Parameter Optimization(Bergstra et al 2012).pdf -------------------------------------------------------------------------------- /Hyperparameter Tuning (Grid search vs Random search)/source code/grid-search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Hyperparameter Tuning (Grid search vs Random search)/source code/grid-search.py -------------------------------------------------------------------------------- /Hyperparameter Tuning (Grid search vs Random search)/source code/parameter tuning with grid search and random search.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Hyperparameter Tuning (Grid search vs Random search)/source code/parameter tuning with grid search and random search.ipynb -------------------------------------------------------------------------------- /Hyperparameter Tuning (Grid search vs Random search)/source code/randon-search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Hyperparameter Tuning (Grid search vs Random search)/source code/randon-search.py -------------------------------------------------------------------------------- /Model selection (cross-validation vs bootstrap)/papers/A study of cross-validation and bootstrap for accuracy estimation and model selection.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Model selection (cross-validation vs bootstrap)/papers/A study of cross-validation and bootstrap for accuracy estimation and model selection.pdf -------------------------------------------------------------------------------- /Model selection (cross-validation vs bootstrap)/source code/bootstrap-vs-cross-validation.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Model selection (cross-validation vs bootstrap)/source code/bootstrap-vs-cross-validation.ipynb -------------------------------------------------------------------------------- /Model selection (cross-validation vs bootstrap)/source code/bootstrapping.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Model selection (cross-validation vs bootstrap)/source code/bootstrapping.py -------------------------------------------------------------------------------- /Model selection (cross-validation vs bootstrap)/source code/naive-cross-validation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Model selection (cross-validation vs bootstrap)/source code/naive-cross-validation.py -------------------------------------------------------------------------------- /Model selection (cross-validation vs bootstrap)/source code/stratified-cross-validation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Model selection (cross-validation vs bootstrap)/source code/stratified-cross-validation.py -------------------------------------------------------------------------------- /Optimization methods (first-order vs second-order)/papers/adam - a method for stochastic optimization.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Optimization methods (first-order vs second-order)/papers/adam - a method for stochastic optimization.pdf -------------------------------------------------------------------------------- /Optimization methods (first-order vs second-order)/papers/on the limited memory BFGS method for large scale optimization.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Optimization methods (first-order vs second-order)/papers/on the limited memory BFGS method for large scale optimization.pdf -------------------------------------------------------------------------------- /Optimization methods (first-order vs second-order)/source code/adam-optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Optimization methods (first-order vs second-order)/source code/adam-optimizer.py -------------------------------------------------------------------------------- /Optimization methods (first-order vs second-order)/source code/first-and-secod-order-optimization-methods.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Optimization methods (first-order vs second-order)/source code/first-and-secod-order-optimization-methods.ipynb -------------------------------------------------------------------------------- /Optimization methods (first-order vs second-order)/source code/lbfgs-optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Optimization methods (first-order vs second-order)/source code/lbfgs-optimizer.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/README.md -------------------------------------------------------------------------------- /Regularization and feature selection (L1 vs L2 regularization)/papers/Feature selection, L1 vs L2 regularization, and rotational invariance.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Regularization and feature selection (L1 vs L2 regularization)/papers/Feature selection, L1 vs L2 regularization, and rotational invariance.pdf -------------------------------------------------------------------------------- /Regularization and feature selection (L1 vs L2 regularization)/source code/L1-and-L2-regularization.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Regularization and feature selection (L1 vs L2 regularization)/source code/L1-and-L2-regularization.ipynb -------------------------------------------------------------------------------- /Regularization and feature selection (L1 vs L2 regularization)/source code/l1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Regularization and feature selection (L1 vs L2 regularization)/source code/l1.py -------------------------------------------------------------------------------- /Regularization and feature selection (L1 vs L2 regularization)/source code/l2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Regularization and feature selection (L1 vs L2 regularization)/source code/l2.py -------------------------------------------------------------------------------- /Tradeoff when using SGD (batch_size and learning_rate)/paper/Optimization methods for large-scale machine learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Tradeoff when using SGD (batch_size and learning_rate)/paper/Optimization methods for large-scale machine learning.pdf -------------------------------------------------------------------------------- /Tradeoff when using SGD (batch_size and learning_rate)/source code/big-bs-high-lr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Tradeoff when using SGD (batch_size and learning_rate)/source code/big-bs-high-lr.py -------------------------------------------------------------------------------- /Tradeoff when using SGD (batch_size and learning_rate)/source code/big-bs-low-lr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Tradeoff when using SGD (batch_size and learning_rate)/source code/big-bs-low-lr.py -------------------------------------------------------------------------------- /Tradeoff when using SGD (batch_size and learning_rate)/source code/small-bs-high-lr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Tradeoff when using SGD (batch_size and learning_rate)/source code/small-bs-high-lr.py -------------------------------------------------------------------------------- /Tradeoff when using SGD (batch_size and learning_rate)/source code/small-bs-low-lr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Tradeoff when using SGD (batch_size and learning_rate)/source code/small-bs-low-lr.py -------------------------------------------------------------------------------- /Tradeoff when using SGD (batch_size and learning_rate)/source code/tradeoff-bw-batch_size-and-learning_rate.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/buomsoo-kim/Machine-learning-toolkits-with-python/HEAD/Tradeoff when using SGD (batch_size and learning_rate)/source code/tradeoff-bw-batch_size-and-learning_rate.ipynb --------------------------------------------------------------------------------