API¶
This is the full API documentation of the mlresearch package.
mlresearch
¶
Toolbox to develop research in Machine Learning.
ml-research
is a library containing the implementation of various algorithms
developed in Machine Learning research, as well as utilities to facilitate the formatting
of pandas dataframes into LaTeX tables.
|
Print debugging information. |
mlresearch.active_learning
¶
Module which contains Active Learning implementations.
|
Standard Active Learning model with a random initial data selection |
|
Active Learning with pipelined Data Augmentation. |
mlresearch.datasets
¶
Download, transform and simulate various datasets.
|
Class to download, transform and save binary class datasets. |
|
Class to download, transform and save binary class imbalanced datasets. |
Class to download, transform and save datasets with both continuous and categorical features. |
|
|
Class to download, transform and save multi-class datasets. |
|
Class to download, transform and save remote sensing datasets. |
mlresearch.latex
¶
This module contains several functions to prepare and format tables for LaTeX documents.
|
Sort and rename rows and columns. |
|
Make bold the lowest or highest values, or values lower than, or higher than the passed value in |
|
Generate table with rounded decimals, bold maximum/minimum values or values above/below a given threshold, and combine mean and sem values. |
|
Exports a pandas dataframe to LaTeX (longtable) format. |
mlresearch.metrics
¶
This module contains various performance metrics/scorers that are not included in scikit-learn’s scorers’ dictionary. Additionally, an expanded dictionary of scorers (as compared with scikit-learn’s) is also provided.
|
Get a scorer from string. |
Get the names of all available scorers. |
|
|
Geometric mean score with macro average. |
|
Calculate precision at |
|
Area under the learning curve. |
|
Data Utilization Rate. |
|
Make an Active Learning scorer from a AL-specific metric or loss function. |
|
Measures synthetic data fidelity. |
|
Checks whether the synthetic data is diverse enough to cover the variability of real data, i.e., a model should be able to generate a wide variety of good samples. |
|
Quantifies the rate by which a model generates new samples. |
mlresearch.model_selection
¶
The mlresearch.model_selection
module includes the
model and parameter search methods.
|
Exhaustive search over specified parameter values for a collection of estimators. |
|
Search over specified parameter values for a collection of estimators with successive halving. |
mlresearch.neural_network
¶
|
Unsupervised One-Class neural network. |
mlresearch.preprocessing
¶
Data preprocessing methods adapted or modified from sklearn.
|
Pipeline-compatible wrapper of Scikit-learn's Transformer objects. |
mlresearch.synthetic_data
¶
Module which contains the implementation of variations of oversampling/data augmentation algorithms, as well as helper classes to use oversampling algorithms as data augmentation techniques.
Class to to perform over-sampling using Geometric SMOTE. |
|
A wrapper to facilitate the use of imblearn.over_sampling objects for data augmentation. |
mlresearch.utils
¶
This module contains a variety of general utility functions and tools used to format and prepare tables to incorporate into LaTeX code.
|
Converts an image array (height, width, bands) to a pandas dataframe (height * width, bands). |
|
Converts a pandas dataframe to an image. |
|
Load all datasets in a directory from sqlite databases and/or csv files. |
|
Extract estimators and parameter grids to be passed to ModelSearchCV. |
|
Extract estimators within a wrapper object and parameter grids to be passed to ModelSearchCV. |
|
Create random states for experiments. |
|
Load LaTeX-style configurations for Matplotlib Visualizations. |
Returns a list of available fonts in the current system. |
|
|
Check and display the available fonts in matplotlib. |
|
Converts a column of values to hex-type colors. |
|
Parallelize a loop and optionally add a progress bar. |
|
Generate data, results and analysis paths. |