Posted on Categories data science, Exciting Techniques, Programming, TutorialsTags , , , , , , , 2 Comments on Sharing Modeling Pipelines in R

Sharing Modeling Pipelines in R

Reusable modeling pipelines are a practical idea that gets re-developed many times in many contexts. wrapr supplies a particularly powerful pipeline notation, and a pipe-stage re-use system (notes here). We will demonstrate this with the vtreat data preparation system.

Continue reading Sharing Modeling Pipelines in R

Posted on Categories data science, Programming, StatisticsTags , , Leave a comment on More on sigr

More on sigr

If you’ve read our previous R Tip on using sigr with linear models, you might have noticed that the lm() summary object does in fact carry the R-squared and F statistics, both in the printed form:

model_lm <- lm(formula = Petal.Length ~ Sepal.Length, data = iris)
(smod_lm <- summary(model_lm))
## 
## Call:
## lm(formula = Petal.Length ~ Sepal.Length, data = iris)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2.47747 -0.59072 -0.00668  0.60484  2.49512 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  -7.10144    0.50666  -14.02   <2e-16 ***
## Sepal.Length  1.85843    0.08586   21.65   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.8678 on 148 degrees of freedom
## Multiple R-squared:   0.76,  Adjusted R-squared:  0.7583 
## F-statistic: 468.6 on 1 and 148 DF,  p-value: < 2.2e-16

and also in the summary() object:

c(R2 = smod_lm$r.squared, F = smod_lm$fstatistic[1])

##          R2     F.value 
##   0.7599546 468.5501535

Note, though, that while the summary reports the model’s significance, it does not carry it as a specific summary() object item. sigr::wrapFTest() is a convenient way to extract the model’s R-squared and F statistic and simultaneously calculate the model significance, as is required by many scientific publications.

sigr is even more helpful for logistic regression, via glm(), which reports neither the model’s chi-squared statistic nor its significance.

iris$isVersicolor <- iris$Species == "versicolor"

model_glm <- glm(
  isVersicolor ~ Sepal.Length + Sepal.Width,
  data = iris,
  family = binomial)

(smod_glm <- summary(model_glm))

## 
## Call:
## glm(formula = isVersicolor ~ Sepal.Length + Sepal.Width, family = binomial, 
##     data = iris)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -1.9769  -0.8176  -0.4298   0.8855   2.0855  
## 
## Coefficients:
##              Estimate Std. Error z value Pr(>|z|)    
## (Intercept)    8.0928     2.3893   3.387 0.000707 ***
## Sepal.Length   0.1294     0.2470   0.524 0.600247    
## Sepal.Width   -3.2128     0.6385  -5.032 4.85e-07 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 190.95  on 149  degrees of freedom
## Residual deviance: 151.65  on 147  degrees of freedom
## AIC: 157.65
## 
## Number of Fisher Scoring iterations: 5

To get the significance of a logistic regression model, call wrapr::wrapChiSqTest():

library(sigr)
(chi2Test <- wrapChiSqTest(model_glm))

## [1] “Chi-Square Test summary: pseudo-R2=0.21 (X2(2,N=150)=39, p<1e-05).”

Notice that the fit summary also reports a pseudo-R-squared. You can extract the values directly off the sigr object, as well:

str(chi2Test)

## List of 10
##  $ test          : chr "Chi-Square test"
##  $ df.null       : int 149
##  $ df.residual   : int 147
##  $ null.deviance : num 191
##  $ deviance      : num 152
##  $ pseudoR2      : num 0.206
##  $ pValue        : num 2.92e-09
##  $ sig           : num 2.92e-09
##  $ delta_deviance: num 39.3
##  $ delta_df      : int 2
##  - attr(*, "class")= chr [1:2] "sigr_chisqtest" "sigr_statistic"

And of course you can render the sigr object into one of several formats (Latex, html, markdown, and ascii) for direct inclusion in a report or publication.

render(chi2Test, format = "html")

Chi-Square Test summary: pseudo-R2=0.21 (χ2(2,N=150)=39, p<1e-05).

By the way, if you are interested, we give the explicit formula for calculating the significance of a logistic regression model in Practical Data Science with R.

Posted on Categories data science, Practical Data Science, Pragmatic Data Science, Pragmatic Machine Learning, Programming, TutorialsTags , , Leave a comment on The blocks and rows theory of data shaping

The blocks and rows theory of data shaping

We have our latest note on the theory of data wrangling up here. It discusses the roles of “block records” and “row records” in the cdata data transform tool. With that and the theory of how to design transforms, we think we have a pretty complete description of the system.

Rowrecs to blocks

Posted on Categories data science, Practical Data Science, Pragmatic Data Science, Pragmatic Machine Learning, TutorialsTags , Leave a comment on Designing Transforms for Data Reshaping with cdata

Designing Transforms for Data Reshaping with cdata

Authors: John Mount, and Nina Zumel 2018-10-25

As a followup to our previous post, this post goes a bit deeper into reasoning about data transforms using the cdata package. The cdata packages demonstrates the "coordinatized data" theory and includes an implementation of the "fluid data" methodology for general data re-shaping.

cdata adheres to the so-called "Rule of Representation":

Fold knowledge into data, so program logic can be stupid and robust.

The Art of Unix Programming, Erick S. Raymond, Addison-Wesley , 2003

The design principle expressed by this rule is that it is much easier to reason about data than to try to reason about code, so using data to control your code is often a very good trade-off.

We showed in the last post how cdata takes a transform control table to specify how you want your data reshaped. The question then becomes: how do you come up with the transform control table?

Let’s discuss that using the example from the previous post: "plotting the iris data faceted".

Continue reading Designing Transforms for Data Reshaping with cdata

Posted on Categories data science, Practical Data Science, Pragmatic Data Science, Pragmatic Machine Learning, Statistics, TutorialsTags , , , Leave a comment on Modeling multi-category Outcomes With vtreat

Modeling multi-category Outcomes With vtreat

vtreat is a powerful R package for preparing messy real-world data for machine learning. We have further extended the package with a number of features including rquery/rqdatatable integration (allowing vtreat application at scale on Apache Spark or data.table!).

In addition vtreat and can now effectively prepare data for multi-class classification or multinomial modeling.

Continue reading Modeling multi-category Outcomes With vtreat

Posted on Categories Coding, data science, Programming, TutorialsTags , , , , 15 Comments on Using a Column as a Column Index

Using a Column as a Column Index

We recently saw a great recurring R question: “how do you use one column to choose a different value for each row?” That is: how do you use a column as an index? Please read on for some idiomatic base R, data.table, and dplyr solutions.

Continue reading Using a Column as a Column Index

Posted on Categories data science, Opinion, Practical Data Science, Pragmatic Data Science, TutorialsTags , , , , 7 Comments on R Tip: Give data.table a Try

R Tip: Give data.table a Try

If your R or dplyr work is taking what you consider to be a too long (seconds instead of instant, or minutes instead of seconds, or hours instead of minutes, or a day instead of an hour) then try data.table.

For some tasks data.table is routinely faster than alternatives at pretty much all scales (example timings here).

If your project is large (millions of rows, hundreds of columns) you really should rent an an Amazon EC2 r4.8xlarge (244 GiB RAM) machine for an hour for about $2.13 (quick setup instructions here) and experience speed at scale.

Posted on Categories data science, Pragmatic Data Science, TutorialsTags , , 2 Comments on Timings of a Grouped Rank Filter Task

Timings of a Grouped Rank Filter Task

Introduction

This note shares an experiment comparing the performance of a number of data processing systems available in R. Our notional or example problem is finding the top ranking item per group (group defined by three string columns, and order defined by a single numeric column). This is a common and often needed task.

Continue reading Timings of a Grouped Rank Filter Task

Posted on Categories Administrativia, data science, Practical Data Science, Pragmatic Data Science, StatisticsTags , 4 Comments on Announcing Practical Data Science with R, 2nd Edition

Announcing Practical Data Science with R, 2nd Edition

We are pleased and excited to announce that we are working on a second edition of Practical Data Science with R!

NewImage

Continue reading Announcing Practical Data Science with R, 2nd Edition

Posted on Categories data science, Opinion, StatisticsTags , 11 Comments on Meta-packages, nails in CRAN’s coffin

Meta-packages, nails in CRAN’s coffin

Derek Jones recently discussed a possible future for the R ecosystem in “StatsModels: the first nail in R’s coffin”.

This got me thinking on the future of CRAN (which I consider vital to R, and vital in distributing our work) in the era of super-popular meta-packages. Meta-packages are convenient, but they have a profoundly negative impact on the packages they exclude.

For example: tidyverse advertises a popular R universe where the vital package data.table never existed.

NewImage

And now tidymodels is shaping up to be a popular universe where our own package vtreat never existed, except possibly as a footnote to embed.

NewImage

NewImage

Users currently (with some luck) discover packages like ours and then (because they trust CRAN) feel able to try them. With popular walled gardens that becomes much less likely. It is one thing for a standard package to duplicate another package (it is actually hard to avoid, and how work legitimately competes), it is quite another for a big-brand meta-package to pre-pick winners (and losers).

All I can say is: please give vtreat a chance and a try. It is a package for preparing messy real-world data for predictive modeling. In addition to re-coding high cardinality categorical variables (into what we call effect-codes after Cohen, or impact-codes), it deals with missing values, can be parallelized, can be run on databases, and has years of production experience baked in.

Some places to start with vtreat: