smazzanti

mrmr. mRMR (minimum-Redundancy-Maximum-Relevance) for automatic feature selection at scale.

are_you_still_using_elbow_method. Jupyter Notebook

tds_black_box_models_more_explainable. Jupyter Notebook used for writing the article "Black-Box models are actually more explainable than a Logistic Regression" published in Towards Data Science: https://towardsdatascience.com/black-box-models-are-actually-more-explainable-than-a-logistic-regression-f263c22795d

tds_features_important_doesnt_mean_good. Jupyter Notebook

valicast. Validation for forecasts

tds_this_line_of_code_will_turn_your_model_into_a_causal_model. Jupyter Notebook

confusion_viz. Interactive visualization of the output of any binary classifier.

tds_you_dont_need_statistics_to_run_experiments. Jupyter Notebook

general_vs_specialized_models. Jupyter Notebook

standardized_wasserstein_distance. Jupyter Notebook

beyond_one_hot. Comparing 17 types of encoding for categorical variables

tds_partial_correlation. Jupyter Notebook

tds_approximate_predictions_for_feature_selection. Jupyter Notebook

tds_why_statistical_significance_is_pointless. Jupyter Notebook

tds_thompson_sampling. Jupyter Notebook

few_vital_causes. Jupyter Notebook

post_it_took_me_6_years_to_find_the_best_metric_for_classification_models. Jupyter Notebook

tds_best_or_luckiest. Jupyter Notebook

walk-backward. Jupyter Notebook

why_you_should_stop_using_the_roc_curve. Jupyter Notebook

correlation_explained_visually. Jupyter Notebook

tds_are_outliers_harder_to_predict. Jupyter Notebook

medium_how_to_test_if_your_model_probabilities_are_good_enough. Jupyter Notebook

never_use_cross_validation. Jupyter Notebook

direct_loss_estimation. Jupyter Notebook

post_what_happened_when_i_put_a_causal_ml_model_to_the_test. Jupyter Notebook

tds-scraping. Jupyter Notebook

tds_scraping. Jupyter Notebook

misc. Python

tds_your_dataset_has_missing_values_do_nothing. Jupyter Notebook

category_encoders. A library of sklearn compatible categorical variable encoders