Steven P. Sanderson II, MPH
LightNews LightNews
banner
spsanderson.com
Steven P. Sanderson II, MPH
@spsanderson.com
810 followers 330 following 1K posts
New Book: https://packt.link/oTyZJ
Site: https://www.spsanderson.com
Blog: https://www.spsanderson.com/steveondata
R - install.packages("healthyverse")
opinions are mine
Advisor to DoTadda
https://github.com/spsanderson
Posts Replies Media Videos
spsanderson.com
Construction moving along
November 8, 2025 at 3:40 PM
spsanderson.com
Home extension construction underway

#Construction
Foundation dig Foundation dig
November 7, 2025 at 7:03 PM
spsanderson.com
Some intelligence with image playground is pretty cool. I had to after 5.5 years get a new phone last night

#Apple #AppleIntelligence
November 7, 2025 at 6:54 PM
spsanderson.com
Doing some work on my #R package #RandomWalker and looks like we got a nice speedup coming for all of the generating functions. Over 2,000 replications saw a large speedup where the original function takes 2.8x as long as the new.

#RStats #RProgramming #Optimization
Doing some work on my #R package #RandomWalker and looks like we got a nice speedup coming for all of the generating functions. Over 2,000 replications saw a large speedup where the original function takes 2.8x as long as the new. #RStats #RProgramming #Optimization
November 2, 2025 at 12:38 AM
spsanderson.com
Working a script that will add run information after a stored procedure is executed. I want some basic information to run after each scheduled job to see a history, and to see if insert amounts look off if there is a late run or failure some place else.

#SQL #Technology
Working a script that will add run information after a stored procedure is executed. I want some basic information to run after each scheduled job to see a history, and to see if insert amounts look off if there is a late run or failure some place else. #SQL #Technology
October 30, 2025 at 12:56 PM
spsanderson.com
Summarizing health insurance payer policies in #R with #Ollama and #ragnar using qwen3
October 27, 2025 at 7:28 PM
spsanderson.com
Very beginning of learning #Ollama with #Python and #R
Very beginning of learning #Ollama with #Python and #R Very beginning of learning #Ollama with #Python and #R
October 20, 2025 at 4:15 PM
spsanderson.com
I wrote some code to use all of the available util_*_aic functions i have in my #TidyDensity #RStats package. It was a fun exercise. I was trying to see which distribution has the lowest #AIC

#R #Coding #Distribution #Statistics
I wrote some code to use all of the available util_*_aic functions i have in my #TidyDensity #RStats package. It was a fun exercise. I was trying to see which distribution has the lowest #AIC #R #Coding #Distribution #Statistics
October 17, 2025 at 4:12 PM
spsanderson.com
Decided to see what distribution my packages follow in terms of daily downloads and it looks like it's a Negative Binomial.

#R #RStats #Distributions #Download #CountData #GitHub

GitHub: github.com/spsanderson/...
Decided to see what distribution my packages follow in terms of daily downloads and it looks like it's a Negative Binomial. #R #RStats #Distributions #Download #CountData GitHub: https://github.com/spsanderson/random_r_projects/blob/main/density_estimation_for_healthyR_pkgs.r Decided to see what distribution my packages follow in terms of daily downloads and it looks like it's a Negative Binomial. #R #RStats #Distributions #Download #CountData GitHub: https://github.com/spsanderson/random_r_projects/blob/main/density_estimation_for_healthyR_pkgs.r
October 16, 2025 at 7:57 PM
spsanderson.com
Needed to combine .md files in sub-directories into a single one and place that file in the respective sub-dir, so I wrote this: github.com/spsanderson/...

#R #RStats #Script #Coding #Programming
https://github.com/spsanderson/random_r_projects/blob/main/combine_md_files.R
October 16, 2025 at 1:18 PM
spsanderson.com
I'm choice 2, using group_nest and map as it retains the original column types and there is no need to rename, although if I put some effort into it I'm sure I could remove the need to enframe and rename. I just don't feel like doing that this morning.

#tidyr #purrr #dplyr #imap #map #RandomWalker
I'm choice 2, using group_nest and map as it retains the original column types and there is no need to rename, although if I put some effort into it I'm sure I could remove the need to enframe and rename. I just don't feel like doing that this morning. #tidyr #tidyverse #purrr #dplyr #imap #map #RandomWalker
October 7, 2025 at 11:56 AM
spsanderson.com
Using the hai_data_trig() function from my package healthyR.ai

Reference: www.spsanderson.com/healthyR.ai/...

#R #RStats #datatransformation #DataScience #data #tidy #recipes #tidymodels
Using the hai_data_trig() function from my package healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_trig.html #R #RStats #datatransformation #DataScience #data #tidy #recipes #tidymodels Using the hai_data_trig() function from my package healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_trig.html #R #RStats #datatransformation #DataScience #data #tidy #recipes #tidymodels Using the hai_data_trig() function from my package healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_trig.html #R #RStats #datatransformation #DataScience #data #tidy #recipes #tidymodels Using the hai_data_trig() function from my package healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_trig.html #R #RStats #datatransformation #DataScience #data #tidy #recipes #tidymodels
October 3, 2025 at 2:38 PM
spsanderson.com
Doing data transformations with my healthyR.ai package.

#R #RStats #Programming #Data #Transformation

Reference: www.spsanderson.com/healthyR.ai/...
Doing data transformations with my healthyR.ai package. #R #RStats #Programming #Data #Transformation Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_transform.html Doing data transformations with my healthyR.ai package. #R #RStats #Programming #Data #Transformation Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_transform.html Doing data transformations with my healthyR.ai package. #R #RStats #Programming #Data #Transformation Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_transform.html
October 2, 2025 at 1:08 PM
spsanderson.com
did some work with my healthyR.ai #R #RStats #package with the hai_data_poly() function.

Take a look!

Reference: www.spsanderson.com/healthyR.ai/...
did some work with my healthyR.ai #R #RStats #package with the hai_data_poly() function. Take a look! Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_poly.html did some work with my healthyR.ai #R #RStats #package with the hai_data_poly() function. Take a look! Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_poly.html did some work with my healthyR.ai #R #RStats #package with the hai_data_poly() function. Take a look! Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_poly.html
October 1, 2025 at 6:23 PM
spsanderson.com
I see that the #CRAN downloads most likely maintained by @posit.co have not refreshed again, been a wicked few weeks meaning since the last outage.
I see that the #CRAN downloads most likely maintained by @posit.co have not refreshed again, been a wicked few weeks meaning since the last outage.
October 1, 2025 at 2:01 PM
spsanderson.com
Looks like the newest version of #RandomWalker and #TidyDensity are the best yet as seen in the 30 post release downloads. I don't get tidyverse downloads but I'm proud of these works.

#R #RStats
Looks like the newest version of #RandomWalker and #TidyDensity are the best yet as seen in the 30 post release downloads. I don't get tidyverse downloads but I'm proud of these works. #R #RStats Looks like the newest version of #RandomWalker and #TidyDensity are the best yet as seen in the 30 post release downloads. I don't get tidyverse downloads but I'm proud of these works. #R #RStats
September 30, 2025 at 2:38 PM
spsanderson.com
Now using the hai_data_scale() fns from healthyR.ai

Reference: www.spsanderson.com/healthyR.ai/...

#R #Rstats #tidydata #sttistics #data #normalization
Now using the hai_data_scale() fns from healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_scale.html #R #Rstats #tidydata #sttistics #data #normalization Now using the hai_data_scale() fns from healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_scale.html #R #Rstats #tidydata #sttistics #data #normalization Now using the hai_data_scale() fns from healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_scale.html #R #Rstats #tidydata #sttistics #data #normalization Now using the hai_data_scale() fns from healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_scale.html #R #Rstats #tidydata #sttistics #data #normalization
September 26, 2025 at 4:35 PM
spsanderson.com
Visualizing a few different imputation methods using the hai_data_impute() function from my #R package healthyR.ai

Reference: www.spsanderson.com/healthyR.ai/...
Visualizing a few different imputation methods using the hai_data_impute() function from my #R package healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_impute.html Visualizing a few different imputation methods using the hai_data_impute() function from my #R package healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_impute.html Visualizing a few different imputation methods using the hai_data_impute() function from my #R package healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_impute.html Visualizing a few different imputation methods using the hai_data_impute() function from my #R package healthyR.ai Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_impute.html
September 26, 2025 at 12:25 PM
spsanderson.com
I'm super proud of my wife who has passed her Library Media Specialist Certification exam!!!

#Library #LibraryMediaSpecialist #Media #Specialist #NYS
I'm super proud of my wife who has passed her Library Media Specialist Certification exam!!! #Library #LibraryMediaSpecialist #Media #Specialist #NYS
September 25, 2025 at 6:18 PM
spsanderson.com
I call it what it is in my view: The #AmeriKKKan #Christian #Taliban
I call it what it is in my view: The #AmeriKKKan #Christian #Taliban
September 25, 2025 at 1:58 PM
spsanderson.com
Pawlloween!

#GenAI #Flux
Pawlloween! #GenAI #Flux Pawlloween! #GenAI #Flux Pawlloween! #GenAI #Flux
September 24, 2025 at 2:56 PM
spsanderson.com
Pawlloween!

#GenAI #Flux
Pawlloween! #GenAI #Flux Pawlloween! #GenAI #Flux Pawlloween! #GenAI #Flux
September 24, 2025 at 2:56 PM
spsanderson.com
My #R #package healthyR.ai has many data preprocessors. One of them is hai_data_impute()

Reference: www.spsanderson.com/healthyR.ai/...

Give it a go!
My #R #package healthyR.ai has many data preprocessors. One of them is hai_data_impute() Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_impute.html Give it a go! library(healthyR.ai) library(recipes) library(dplyr) library(ggplot2) n <- 10L l <- 3L lo <- n * l date_seq <- seq.Date(from = as.Date("2013-01-01"), length.out = lo, by = "month") date_seq val_seq <- replicate(n = l, c(rnorm(9), NA)) |> as.vector() |> as.double() val_seq df_tbl <- tibble( date_col = date_seq, value = val_seq ) rec_obj <- recipe(value ~ date_col, data = df_tbl) rec_obj imp_obj <- hai_data_impute( .recipe_object = rec_obj, value, .type_of_imputation = "roll", .roll_statistic = median )$impute_rec_obj imputed_data <- get_juiced_data(imp_obj) combined_tbl <- df_tbl |> left_join(imputed_data, by = "date_col") |> setNames(c("date_col", "original_value", "imputed_value")) |> mutate(rec_no = row_number()) |> mutate(color_col = original_value, size_col = original_value) ggplot(data = combined_tbl, aes( x = date_col, y = imputed_value, color = color_col ) ) + geom_point(data = combined_tbl |> filter(is.na(original_value)), aes(shape = 'NA', size = 3)) + scale_shape_manual(values = c('NA' = 3)) + geom_line(aes(x = date_col, y = original_value), color = "black") + geom_line(aes(x = date_col, y = imputed_value), color = "red", linetype = "dashed", a.pha = .328) + geom_vline( data = combined_tbl[combined_tbl$original_value |> is.na(), ], aes(xintercept = date_col), color = "black", linetype = "dashed" ) + labs( x = "Date", y = "Value", title = "Original vs. Imputed Data using HealthyR.ai", subtitle = "Function: hai_data_impute()", caption = "Red line is the imputed data, blue line is the original data" ) + theme_classic() + theme(legend.position = "none") My #R #package healthyR.ai has many data preprocessors. One of them is hai_data_impute() Reference: https://www.spsanderson.com/healthyR.ai/reference/hai_data_impute.html Give it a go! library(healthyR.ai) library(recipes) library(dplyr) library(ggplot2) n <- 10L l <- 3L lo <- n * l date_seq <- seq.Date(from = as.Date("2013-01-01"), length.out = lo, by = "month") date_seq val_seq <- replicate(n = l, c(rnorm(9), NA)) |> as.vector() |> as.double() val_seq df_tbl <- tibble( date_col = date_seq, value = val_seq ) rec_obj <- recipe(value ~ date_col, data = df_tbl) rec_obj imp_obj <- hai_data_impute( .recipe_object = rec_obj, value, .type_of_imputation = "roll", .roll_statistic = median )$impute_rec_obj imputed_data <- get_juiced_data(imp_obj) combined_tbl <- df_tbl |> left_join(imputed_data, by = "date_col") |> setNames(c("date_col", "original_value", "imputed_value")) |> mutate(rec_no = row_number()) |> mutate(color_col = original_value, size_col = original_value) ggplot(data = combined_tbl, aes( x = date_col, y = imputed_value, color = color_col ) ) + geom_point(data = combined_tbl |> filter(is.na(original_value)), aes(shape = 'NA', size = 3)) + scale_shape_manual(values = c('NA' = 3)) + geom_line(aes(x = date_col, y = original_value), color = "black") + geom_line(aes(x = date_col, y = imputed_value), color = "red", linetype = "dashed", a.pha = .328) + geom_vline( data = combined_tbl[combined_tbl$original_value |> is.na(), ], aes(xintercept = date_col), color = "black", linetype = "dashed" ) + labs( x = "Date", y = "Value", title = "Original vs. Imputed Data using HealthyR.ai", subtitle = "Function: hai_data_impute()", caption = "Red line is the imputed data, blue line is the original data" ) + theme_classic() + theme(legend.position = "none")
September 23, 2025 at 4:30 PM
spsanderson.com
Today is all about getting the max value in a row in #R

#RStats #Blog #Technology #Code #Programming #Scripting

Post: www.spsanderson.com/steveondata/...
Today is all about getting the max value in a row in #R #RStats #Blog #Technology #Code #Programming #Scripting Post: https://www.spsanderson.com/steveondata/posts/2025-09-22/
September 22, 2025 at 12:06 PM
spsanderson.com
If you need to generate data from a triangular distribution, then my #R package #TidyDensity has you covered!

#RStats #ggplot2 #Distribution
If you need to generate data from a triangular distribution, then my #R package #TidyDensity has you covered! #RStats #ggplot2 #Distribution If you need to generate data from a triangular distribution, then my #R package #TidyDensity has you covered! #RStats #ggplot2 #Distribution
September 21, 2025 at 12:10 PM