add test coverage

.github/workflows/R-CMD-check.yaml

@@ -2,9 +2,9 @@
 # Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
 on:
   push:
-    branches: [main, master, develop]
+    branches: [main, master]
   pull_request:
-    branches: [main, master, develop]
+    branches: [main, master]
 
 name: R-CMD-check
 

.github/workflows/test-coverage.yaml

@@ -0,0 +1,50 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+
+name: test-coverage
+
+jobs:
+  test-coverage:
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::covr
+          needs: coverage
+
+      - name: Test coverage
+        run: |
+          covr::codecov(
+            quiet = FALSE,
+            clean = FALSE,
+            install_path = file.path(Sys.getenv("RUNNER_TEMP"), "package")
+          )
+        shell: Rscript {0}
+
+      - name: Show testthat output
+        if: always()
+        run: |
+          ## --------------------------------------------------------------------
+          find ${{ runner.temp }}/package -name 'testthat.Rout*' -exec cat '{}' \; || true
+        shell: bash
+
+      - name: Upload test results
+        if: failure()
+        uses: actions/upload-artifact@v3
+        with:
+          name: coverage-test-failures
+          path: ${{ runner.temp }}/package

DESCRIPTION

@@ -21,6 +21,7 @@ URL: https://github.com/GlenMartin31/predRupdate,
     https://glenmartin31.github.io/predRupdate/
 BugReports: https://github.com/GlenMartin31/predRupdate/issues
 Suggests: 
+    covr,
     knitr,
     rmarkdown,
     testthat (>= 3.0.0)
@@ -30,7 +31,8 @@ Imports:
     survival,
     pROC,
     ggplot2,
-    ggExtra
+    ggExtra,
+    rlang
 Depends: 
     R (>= 2.10)
 VignetteBuilder: knitr

NAMESPACE

@@ -27,3 +27,4 @@ export(pred_predict)
 export(pred_stacked_regression)
 export(pred_update)
 export(pred_validate)
+importFrom(rlang,.data)

R/map_newdata.R

@@ -182,6 +182,10 @@ map_newdata.predinfo_survival <- function(x,
     stop("'new_data' contains factor variables - convert to dummy/indicator variables first \n dummayvar() can help with this")
   }
 
+  if (any(sapply(new_data, function(x) is.character(x)))) {
+    warning("'new_data' contains character variables - should these be indicator variables (see dummy_vars())?")
+  }
+
   if (!is.null(binary_outcome)) {
     stop("'binary_outcome' should be set to NULL if model_type=survival")
   }

R/predRupdate-package.R

@@ -0,0 +1,7 @@
+#' @keywords internal
+"_PACKAGE"
+
+## usethis namespace: start
+#' @importFrom rlang .data
+## usethis namespace: end
+NULL

R/pred_validate.R

@@ -330,12 +330,6 @@ print.predvalidate_survival <- function(x, ...) {
                    round((x$harrell_C - (stats::qnorm(0.975)*x$harrell_C_SE)), 4),
                    round((x$harrell_C + (stats::qnorm(0.975)*x$harrell_C_SE)), 4))
   print(results)
-  # cat("\n")
-  # cat("\nOverall Performance Measures \n",
-  #     "================================= \n", sep = "")
-  # cat("Cox-Snell R-squared: ", round(x$R2_CoxSnell, 4), "\n", sep = "")
-  # cat("Nagelkerke R-squared: ", round(x$R2_Nagelkerke, 4), "\n", sep = "")
-  # cat("Brier Score: ", round(x$BrierScore, 4), "\n", sep = "")
 
   cat("\n Also examine the histogram of predicted risks. \n")
 }
@@ -409,7 +403,7 @@ validate_logistic <- function(ObservedOutcome,
   if (cal_plot == FALSE){
     plot_df <- data.frame("Prob" = Prob)
     print(ggplot2::ggplot(plot_df,
-                          ggplot2::aes_string(x = "Prob")) +
+                          ggplot2::aes(x = .data$Prob)) +
             ggplot2::geom_histogram(bins = 30,
                                     colour = "black") +
             ggplot2::ggtitle("Histogram of the Probability Distribution") +
@@ -506,7 +500,7 @@ validate_survival <- function(ObservedOutcome,
     if (cal_plot == FALSE){
       plot_df <- data.frame("Prob" = Prob)
       print(ggplot2::ggplot(plot_df,
-                            ggplot2::aes_string(x = "Prob")) +
+                            ggplot2::aes(x = .data$Prob)) +
               ggplot2::geom_histogram(bins = 30,
                                       colour = "black") +
               ggplot2::ggtitle("Histogram of the Probability Distribution") +
@@ -571,8 +565,8 @@ flex_calplot <- function(model_type = c("logistic", "survival"),
                           "o" = spline_preds$fit)
 
     print(ggExtra::ggMarginal(ggplot2::ggplot(plot_df,
-                                              ggplot2::aes_string(x = "p",
-                                                                  y = "o")) +
+                                              ggplot2::aes(x = .data$p,
+                                                           y = .data$o)) +
                                 ggplot2::geom_line(ggplot2::aes(linetype = "Calibration Curve",
                                                                 colour = "Calibration Curve")) +
                                 ggplot2::xlim(xlim) +
@@ -613,8 +607,8 @@ flex_calplot <- function(model_type = c("logistic", "survival"),
     plot_df$observed_risk <- 1 - (exp(-bh[(max(which(bh[,2] <= time_horizon))),1])^(exp(stats::predict(vcal, type = "lp"))))
 
     print(ggExtra::ggMarginal(ggplot2::ggplot(plot_df,
-                                              ggplot2::aes_string(x = "Prob",
-                                                                  y = "observed_risk")) +
+                                              ggplot2::aes(x = .data$Prob,
+                                                           y = .data$observed_risk)) +
                                 ggplot2::geom_line(ggplot2::aes(linetype = "Calibration Curve",
                                                                 colour = "Calibration Curve")) +
                                 ggplot2::xlim(xlim) +

README.Rmd

@@ -17,6 +17,7 @@ knitr::opts_chunk$set(
 
 <!-- badges: start -->
 [![R-CMD-check](https://github.com/GlenMartin31/predRupdate/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/GlenMartin31/predRupdate/actions/workflows/R-CMD-check.yaml)
+[![Codecov test coverage](https://codecov.io/gh/GlenMartin31/predRupdate/branch/master/graph/badge.svg)](https://app.codecov.io/gh/GlenMartin31/predRupdate?branch=master)
 <!-- badges: end -->
 
 The goal of predRupdate is to provide a suite of functions for validating a existing (i.e. previously developed) prediction/ prognostic model, and for applying model updating methods to said model, according to an available dataset.

README.md

@@ -6,6 +6,8 @@
 <!-- badges: start -->
 
 [![R-CMD-check](https://github.com/GlenMartin31/predRupdate/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/GlenMartin31/predRupdate/actions/workflows/R-CMD-check.yaml)
+[![Codecov test
+coverage](https://codecov.io/gh/GlenMartin31/predRupdate/branch/master/graph/badge.svg)](https://app.codecov.io/gh/GlenMartin31/predRupdate?branch=master)
 <!-- badges: end -->
 
 The goal of predRupdate is to provide a suite of functions for

codecov.yml

@@ -0,0 +1,14 @@
+comment: false
+
+coverage:
+  status:
+    project:
+      default:
+        target: auto
+        threshold: 1%
+        informational: true
+    patch:
+      default:
+        target: auto
+        threshold: 1%
+        informational: true

tests/testthat/_snaps/pred_stacked_regression.md

@@ -0,0 +1,16 @@
+# pred_stacked_regression has expected output
+
+    Code
+      summary(SR)
+    Output
+      Information about 1 existing model(s) of type 'logistic' 
+      
+      Model Coefficients 
+      ================================= 
+        Intercept         Age      SexM Smoking_Status  Diabetes  Creatine
+      1  -2.67512 0.005346913 0.1589209      0.5232909 0.2542794 0.4553747
+      
+      Model Functional Form 
+      ================================= 
+      Age + SexM + Smoking_Status + Diabetes + Creatine
+

tests/testthat/_snaps/pred_validate_logistic.md

@@ -0,0 +1,32 @@
+# output of pred_validate is as expected - single models
+
+    Code
+      print(val_results)
+    Output
+      Calibration Measures 
+      ================================= 
+                               Estimate Std. Err Lower 95% Confidence Interval
+      Calibration-in-the-large   0.7323   0.0206                        0.6921
+      Calibration Slope          0.6484   0.0463                        0.5576
+                               Upper 95% Confidence Interval
+      Calibration-in-the-large                        0.7726
+      Calibration Slope                               0.7392
+      
+       Also examine the calibration plot, if produced. 
+      
+      Discrimination Measures 
+      ================================= 
+          Estimate Std. Err Lower 95% Confidence Interval
+      AUC   0.5814   0.0057                        0.5702
+          Upper 95% Confidence Interval
+      AUC                        0.5927
+      
+      
+      Overall Performance Measures 
+      ================================= 
+      Cox-Snell R-squared: -0.0481
+      Nagelkerke R-squared: -0.0863
+      Brier Score: 0.1249
+      
+       Also examine the histogram of predicted risks. 
+

tests/testthat/_snaps/pred_validate_survival.md

@@ -0,0 +1,25 @@
+# output of pred_validate is as expected - single models
+
+    Code
+      print(val_results)
+    Output
+      Calibration Measures 
+      ================================= 
+                              Estimate Std. Err Lower 95% Confidence Interval
+      Observed:Expected Ratio   0.6319   0.0113                        0.6181
+      Calibration Slope         1.0757   0.0389                        0.9994
+                              Upper 95% Confidence Interval
+      Observed:Expected Ratio                        0.6461
+      Calibration Slope                              1.1519
+      
+       Also examine the calibration plot, if produced. 
+      
+      Discrimination Measures 
+      ================================= 
+                Estimate Std. Err Lower 95% Confidence Interval
+      Harrell C   0.5869   0.0032                        0.5806
+                Upper 95% Confidence Interval
+      Harrell C                        0.5932
+      
+       Also examine the histogram of predicted risks. 
+