stratiply.RdSplit a data.frame by any number of columns and apply a function to subset.
stratiply(
data,
f,
by,
...
)A data.frame.
A function that takes a data.frame as an argument.
A vector of quoted/unquoted columns, positions, and/or tidyselect::select_helpers
Additional arguments passed to f.
A list
#Unquoted selection
heart_disease %>%
stratiply(
head,
Sex
)
#> $Female
#> # A tibble: 6 × 8
#> Age ChestPain BP Cholesterol BloodSugar MaximumHR Exerci…¹ Heart…²
#> <dbl> <fct> <dbl> <dbl> <lgl> <dbl> <fct> <fct>
#> 1 41 Atypical angina 130 204 FALSE 172 No No
#> 2 62 Asymptomatic 140 268 FALSE 160 No Yes
#> 3 57 Asymptomatic 120 354 FALSE 163 Yes No
#> 4 56 Atypical angina 140 294 FALSE 153 No No
#> 5 48 Non-anginal pain 130 275 FALSE 139 No No
#> 6 58 Typical angina 150 283 TRUE 162 No No
#> # … with abbreviated variable names ¹ExerciseInducedAngina, ²HeartDisease
#>
#> $Male
#> # A tibble: 6 × 8
#> Age ChestPain BP Cholesterol BloodSugar MaximumHR Exerci…¹ Heart…²
#> <dbl> <fct> <dbl> <dbl> <lgl> <dbl> <fct> <fct>
#> 1 63 Typical angina 145 233 TRUE 150 No No
#> 2 67 Asymptomatic 160 286 FALSE 108 Yes Yes
#> 3 67 Asymptomatic 120 229 FALSE 129 Yes Yes
#> 4 37 Non-anginal pain 130 250 FALSE 187 No No
#> 5 56 Atypical angina 120 236 FALSE 178 No No
#> 6 63 Asymptomatic 130 254 FALSE 147 No Yes
#> # … with abbreviated variable names ¹ExerciseInducedAngina, ²HeartDisease
#>
#Select helper
heart_disease %>%
stratiply(
f = head,
by = starts_with("S")
)
#> $Female
#> # A tibble: 6 × 8
#> Age ChestPain BP Cholesterol BloodSugar MaximumHR Exerci…¹ Heart…²
#> <dbl> <fct> <dbl> <dbl> <lgl> <dbl> <fct> <fct>
#> 1 41 Atypical angina 130 204 FALSE 172 No No
#> 2 62 Asymptomatic 140 268 FALSE 160 No Yes
#> 3 57 Asymptomatic 120 354 FALSE 163 Yes No
#> 4 56 Atypical angina 140 294 FALSE 153 No No
#> 5 48 Non-anginal pain 130 275 FALSE 139 No No
#> 6 58 Typical angina 150 283 TRUE 162 No No
#> # … with abbreviated variable names ¹ExerciseInducedAngina, ²HeartDisease
#>
#> $Male
#> # A tibble: 6 × 8
#> Age ChestPain BP Cholesterol BloodSugar MaximumHR Exerci…¹ Heart…²
#> <dbl> <fct> <dbl> <dbl> <lgl> <dbl> <fct> <fct>
#> 1 63 Typical angina 145 233 TRUE 150 No No
#> 2 67 Asymptomatic 160 286 FALSE 108 Yes Yes
#> 3 67 Asymptomatic 120 229 FALSE 129 Yes Yes
#> 4 37 Non-anginal pain 130 250 FALSE 187 No No
#> 5 56 Atypical angina 120 236 FALSE 178 No No
#> 6 63 Asymptomatic 130 254 FALSE 147 No Yes
#> # … with abbreviated variable names ¹ExerciseInducedAngina, ²HeartDisease
#>
#Use additional arguments for the function
heart_disease %>%
stratiply(
f = glm,
by = Sex,
formula = HeartDisease ~ .,
family = "binomial"
)
#> $Female
#>
#> Call: .f(formula = ..1, family = "binomial", data = .x[[i]])
#>
#> Coefficients:
#> (Intercept) Age
#> -26.201202 0.063173
#> ChestPainAtypical angina ChestPainNon-anginal pain
#> 16.672159 14.881710
#> ChestPainAsymptomatic BP
#> 18.613467 0.045810
#> Cholesterol BloodSugarTRUE
#> 0.002053 1.766565
#> MaximumHR ExerciseInducedAnginaYes
#> -0.021872 1.040728
#>
#> Degrees of Freedom: 96 Total (i.e. Null); 87 Residual
#> Null Deviance: 110.7
#> Residual Deviance: 56.66 AIC: 76.66
#>
#> $Male
#>
#> Call: .f(formula = ..1, family = "binomial", data = .x[[i]])
#>
#> Coefficients:
#> (Intercept) Age
#> 0.141398 0.024326
#> ChestPainAtypical angina ChestPainNon-anginal pain
#> -0.470775 0.107361
#> ChestPainAsymptomatic BP
#> 1.552618 0.011718
#> Cholesterol BloodSugarTRUE
#> 0.009023 -0.343345
#> MaximumHR ExerciseInducedAnginaYes
#> -0.037817 0.524487
#>
#> Degrees of Freedom: 205 Total (i.e. Null); 196 Residual
#> Null Deviance: 283.2
#> Residual Deviance: 191.5 AIC: 211.5
#>
#Use mixed selections to split by desired columns
heart_disease %>%
stratiply(
f = glm,
by = c(Sex, where(is.logical)),
formula = HeartDisease ~ Age,
family = "binomial"
)
#> $Female
#> $Female$`FALSE`
#>
#> Call: .f(formula = ..1, family = "binomial", data = .x[[i]])
#>
#> Coefficients:
#> (Intercept) Age
#> -5.17802 0.06904
#>
#> Degrees of Freedom: 84 Total (i.e. Null); 83 Residual
#> Null Deviance: 90.33
#> Residual Deviance: 84.84 AIC: 88.84
#>
#> $Female$`TRUE`
#>
#> Call: .f(formula = ..1, family = "binomial", data = .x[[i]])
#>
#> Coefficients:
#> (Intercept) Age
#> 4.29409 -0.07303
#>
#> Degrees of Freedom: 11 Total (i.e. Null); 10 Residual
#> Null Deviance: 16.64
#> Residual Deviance: 15.96 AIC: 19.96
#>
#>
#> $Male
#> $Male$`FALSE`
#>
#> Call: .f(formula = ..1, family = "binomial", data = .x[[i]])
#>
#> Coefficients:
#> (Intercept) Age
#> -3.58959 0.07275
#>
#> Degrees of Freedom: 172 Total (i.e. Null); 171 Residual
#> Null Deviance: 236.8
#> Residual Deviance: 220.3 AIC: 224.3
#>
#> $Male$`TRUE`
#>
#> Call: .f(formula = ..1, family = "binomial", data = .x[[i]])
#>
#> Coefficients:
#> (Intercept) Age
#> -4.28261 0.07483
#>
#> Degrees of Freedom: 32 Total (i.e. Null); 31 Residual
#> Null Deviance: 45.72
#> Residual Deviance: 43.66 AIC: 47.66
#>
#>