Regressionizer 0.1.2

Regression workflows package based on Least Squares Regression and Quantile Regression.

Regressionizer

Python package with a class that allows pipeline-like specification and execution of regression workflows.

Extensive guide is given in the Jupyter notebook "Regressionizer-demo.ipynb".

---

Details

• Regressionizer allows for rapid and specification regression workflows.

  • To quickly specify:
    • data rescaling and summary,
    • regression computations,
    • outliers finding
    • conditional Cumulative Distribution Functions (CDFs) reconstruction
    • visualization of data, fits, residual errors, outliers, CDFs

• Regressionizer works with data frames, numpy arrays, and lists of numbers, and lists of numeric pairs.

• The curves computed with quantile regression are called regression quantiles.

• Regressionizer has three regression methods:

  • quantile_regression
  • quantile_regression_fit
  • least_squares_fit

• The regression quantiles computed with the method quantile_regression correspond to the specified probabilities

  • The regression quantiles are linear combinations of B-splines generated over the specified knots.

• In other words, the methodquantile_regression computes fits using a B-spline functions basis.

  • The basis is specified with the knots argument and the option order.
  • order is 3 by default.

• The methods quantile_regession_fit and least_squares_fit require a list of basis functions (to fit with.)

---

Usage examples

Import libraries:

from Regressionizer import *
import numpy as np

Generate random data:

np.random.seed(0)
x = np.linspace(0, 2, 300)
y = np.sin(2 * np.pi * x) + np.random.normal(0, 0.4, x.shape)
data = np.column_stack((x, y)

Compute quantile regression and make the corresponding plot:

obj = (Regressionizer(data)
       .quantile_regression(knots=8, probs=[0.2, 0.5, 0.8])
       .plot(title="B-splines fit", template="plotly")
       )

Show the plot obtained above:

obj.take_value().show()

---

References

Articles, books

[RK1] Roger Koenker, Quantile Regression, Cambridge University Press, 2005.

[RK2] Roger Koenker, "Quantile Regression in R: a vignette", (2006), CRAN.

[AA1] Anton Antonov, "A monad for Quantile Regression workflows", (2018), MathematicaForPrediction at GitHub.

Packages, paclets

[RKp1] Roger Koenker, quantreg, CRAN.

[AAp1] Anton Antonov, Quantile Regression WL paclet, (2014-2023), GitHub/antononcube.

[AAp2] Anton Antonov, Monadic Quantile Regression WL paclet, (2018-2024), GitHub/antononcube.

[AAp3] Anton Antonov, QuantileRegression, (2019), Wolfram Function Repository.

Repositories

[AAr1] Anton Antonov, DSL::English::QuantileRegressionWorkflows in Raku, (2020), GitHub/antononcube.

Videos

[AAv1] Anton Antonov, "Boston useR! QuantileRegression Workflows 2019-04-18", (2019), Anton Antonov at YouTube.

[AAv2] Anton Antonov, "useR! 2020: How to simplify Machine Learning workflows specifications", (2020), R Consortium at YouTube.