Merge pull request #84 from fasrc/release_v_0.2.5

Release v 0.2.5

.Rbuildignore

@@ -9,3 +9,5 @@
 index.md
 ^doc$
 ^Meta$
+^CRAN-RELEASE$
+^cran-comments\.md$

CRAN-RELEASE

@@ -0,0 +1,2 @@
+This package was submitted to CRAN on 2021-07-22.
+Once it is accepted, delete this file and tag the release (commit 6e9691a).

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: CausalGPS
 Type: Package
-Title: Matching on generalized propensity scores with continuous exposures
-Version: 0.2.4
+Title: Matching on Generalized Propensity Scores with Continuous Exposures
+Version: 0.2.5
 Authors@R: c(
     person("Naeem", "Khoshnevis", email = "nkhoshnevis@g.harvard.edu",
            role=c("aut","cre"), 
@@ -13,14 +13,14 @@ Authors@R: c(
            role=c("aut"),     
            comment = c(ORCID = "0000-0002-5177-8598", AFFILIATION="HSPH")))
 Maintainer: Naeem Khoshnevis <nkhoshnevis@g.harvard.edu>
-Description: An R package for implementing matching on generalized propensity
-    scores with continuous exposures. We developed an innovative approach for
-    estimating causal effects using observational data in settings with
-    continuous exposures, and introduce a new framework for GPS caliper matching. 
+Description: Provides a framework for estimating causal effects of a continuous 
+    exposure using observational data, and implementing matching and weighting 
+    on the generalized propensity score.
     Wu, X., Mealli, F., Kioumourtzoglou, M.A., Dominici, F. and Braun, D., 
     2018. Matching on generalized propensity scores with continuous exposures. 
-    arXiv preprint arXiv:1812.06575.
+    arXiv preprint <arXiv:1812.06575>.
 License: GPL-3
+Language: en-US
 URL: https://github.com/fasrc/CausalGPS
 BugReports: https://github.com/fasrc/CausalGPS/issues
 Copyright: Harvard University
@@ -45,7 +45,6 @@ Imports:
     gnm,
     tidyr
 Encoding: UTF-8
-LazyData: true
 RoxygenNote: 7.1.1
 Suggests: 
     knitr,

NAMESPACE

@@ -18,6 +18,7 @@ export(estimate_pmetric_erf)
 export(estimate_semipmetric_erf)
 export(generate_pseudo_pop)
 export(generate_syn_data)
+export(get_logger)
 export(set_logger)
 import(KernSmooth)
 import(SuperLearner)
@@ -27,6 +28,7 @@ import(gam)
 import(parallel)
 import(polycor)
 import(ranger)
+import(wCorr)
 import(xgboost)
 importFrom(Rcpp,sourceCpp)
 importFrom(ggplot2,autoplot)

NEWS.md

@@ -1,12 +1,16 @@
 
-## CausalGPS (devloping version)
+## CausalGPS 0.2.5 (2021-07-09)
 
 ### Added
 
 ### Changed
 
+* User needs to activate the logger
+
 ### Fixed
 
+* CRAN package URLs are in canonical forms.
+
 ### Removed
 
 ## CausalGPS 0.2.4 (2021-07-11)
@@ -40,7 +44,7 @@
 
 ### Fixed
 
-* RCpp parLapply worker processors arguments
+* Rcpp parLapply worker processors arguments
 
 ### Removed
 
@@ -85,7 +89,7 @@
 *  create_weighting.R
 *  Steps for adding test data into 'sysdata.rda'.
 *  `weighting` option as causal inference approach.  
-*  absoulte_weighted_corr_fun.R
+*  absolute_weighted_corr_fun.R
 *  Testing and running example guidelines for developers
 *  Customized wrapper for xgboost package.
 *  `param` as an argument to accept hyperparameters from users.
@@ -97,8 +101,8 @@
 * mclapply --> parLapply
 * estimate_erf output returns S3 object.
 * test-Covariate_balance.R --> test-absolute_corr_fun.R
-* covarate_balance.R --> absolute_corr_fun.R
-* User needs to pass `m_xgboost` instead of `SL.xgboost` to  use XGBoost package for prediciton purposes.
+* covariate_balance.R --> absolute_corr_fun.R
+* User needs to pass `m_xgboost` instead of `SL.xgboost` to  use XGBoost package for prediction purposes.
 
 ### Fixed
 

R/causalgps_package.R

@@ -25,6 +25,7 @@
 #' @import gam
 #' @import KernSmooth
 #' @import polycor
+#' @import wCorr
 #' @importFrom Rcpp sourceCpp
 #' @useDynLib CausalGPS, .registration = TRUE
 #'
@@ -33,7 +34,7 @@
 #'  Matching on generalized propensity scores with continuous exposures.
 #'  arXiv preprint arXiv:1812.06575.
 #'
-#' Kennedy, E.H., Ma, Z., McHugh, M.D. and Small, D.S., 2017. Non‐parametric
+#' Kennedy, E.H., Ma, Z., McHugh, M.D. and Small, D.S., 2017. Non-parametric
 #'  methods for doubly robust estimation of continuous treatment effects.
 #'  Journal of the Royal Statistical Society: Series B (Statistical Methodology),
 #'  79(4), pp.1229-1245.

R/create_matching.R

@@ -54,16 +54,17 @@ create_matching <- function(dataset, bin_seq = NULL, gps_model = "parametric",
 
   }
 
-  logger::log_debug(used_bin, "bin seq is used. Min: {min(bin_num)} ",
-                      "Max: {max(bin_num)}, count: {length(bin_num)}.")
+    logger::log_debug(used_bin, "bin seq is used. Min: {min(bin_num)} ",
+                        "Max: {max(bin_num)}, count: {length(bin_num)}.")
 
-  logger::log_debug("Started generating matched set ...")
-  st_t_m <- proc.time()
+    logger::log_debug("Started generating matched set ...")
+    st_t_m <- proc.time()
 
+    lfp <- get_options("logger_file_path")
 
     p_c_t_s <- proc.time()
     cl <- parallel::makeCluster(nthread, type="PSOCK",
-                                outfile="CausalGPS.log")
+                                outfile= lfp)
 
 
     parallel::clusterEvalQ(cl, {library("CausalGPS")})

R/create_weighting.R

@@ -15,7 +15,7 @@
 #'  - counter
 #'  - row_index
 #'  - ipw
-#'  - covaraites
+#'  - covariates
 #'
 #' @keywords internal
 #'

R/generate_pseudo_pop.R

@@ -15,7 +15,7 @@
 #'   - "matching": Matching by GPS
 #'   - "weighting": Weighting by GPS
 #'   - "adjusting": Adjusting by GPS
-#' @param pred_model a prediction model
+#' @param pred_model a prediction model (use "sl" for SuperLearner)
 #' @param gps_model Model type which is used for estimating GPS value, including
 #' parametric (default) and non-parametric.
 #' @param use_cov_transform If TRUE, the function uses transformer to meet the
@@ -33,10 +33,6 @@
 #' (default: c(0.01,0.99)).
 #' @param optimized_compile If TRUE, uses counts to keep track of number of
 #' replicated pseudo population.
-#' @param save_output If TRUE, output results will be stored at the save.path.
-#'  Default is FALSE.
-#' @param save_path location for storing the final results, format of the saved
-#' file will be detected by the file name extension.
 #' @param params Includes list of params that is used internally. Unrelated
 #'  parameters will be ignored.
 #' @param nthread An integer value that represents the number of threads to be
@@ -57,7 +53,7 @@
 #'   - *max_attempt*: maximum number of attempt to satisfy covariate balance.
 #'   - See [create_matching()] for more details about the parameters and default
 #'   values.
-#' - if ci.appr = 'weightig':
+#' - if ci.appr = 'weighting':
 #'   - *covar_bl_method*: Covariate balance method.
 #'   - *covar_bl_trs*: Covariate balance threshold
 #'   - *max_attempt*: Maximum number of attempt to satisfy covariate balance.
@@ -113,8 +109,6 @@ generate_pseudo_pop <- function(Y,
                                 bin_seq = NULL,
                                 trim_quantiles = c(0.01,0.99),
                                 optimized_compile = FALSE,
-                                save_output = FALSE,
-                                save_path = NULL,
                                 params = list(),
                                 nthread = 1,
                                 ...){
@@ -309,17 +303,6 @@ generate_pseudo_pop <- function(Y,
   message(paste("Best Mean absolute correlation: ", best_ach_covar_balance,
                 "| Covariate balance threshold: ", covar_bl_trs))
 
-  ## Store output ---------------------------------
-
-  if (save_output){
-    if (!missing(save_path)){
-      #TODO: Implement a function to write the output into disk or database.
-      message('Saving data on disk is not implemented.')
-    } else {
-      warning('The output for storing data is not provided. This command is
-              ignored.')
-    }
-  }
   result <- list()
   class(result) <- "gpsm_pspop"
 
@@ -360,7 +343,7 @@ pow3 <- function(x) {x^3}
 #'
 #' @param c_name column (attribute) name.
 #' @param c_val column value
-#' @param transformer transformer funciton.
+#' @param transformer transformer function.
 #'
 #' @keywords internal
 #'

R/generate_wrap_sl_lib.R

@@ -13,6 +13,11 @@
 #'
 #' @keywords internal
 #'
+#' @return
+#' Returns A Boolean value. TRUE if the modified library for the given library is
+#' implemented; otherwise, it returns FALSE. This function is called for side
+#' effects.
+#'
 gen_wrap_sl_lib <- function(lib_name, params, nthread){
 
   # ------------------------------------------------------

R/matching_l1.R

@@ -5,7 +5,7 @@
 #' Matching function using L1 distance on single exposure level w
 #'
 #' @param dataset a completed observational data frame or matrix containing
-#'  (Y, w, gps, couner, row_index, c).
+#'  (Y, w, gps, counter, row_index, c).
 #' @param e_gps_pred a vector of predicted gps values obtained by Machine
 #' learning methods.
 #' @param e_gps_std_pred a vector of predicted std of gps obtained by

R/plot.R

@@ -59,6 +59,9 @@ autoplot.gpsm_erf <- function(object, ...){
 #' @param x  A gpsm_erf object.
 #' @param ... Additional arguments passed to customize the plot.
 #'
+#' @return
+#' Returns a ggplot2 object, invisibly. This function is called for side effects.
+#'
 #' @export
 #'
 plot.gpsm_erf <- function(x, ...){
@@ -156,10 +159,13 @@ autoplot.gpsm_pspop <- function(object, ...){
 #' @param x  A gpsm_erf object.
 #' @param ... Additional arguments passed to customize the plot.
 #'
+#' @return
+#' Returns a ggplot2 object, invisibly. This function is called for side effects.
+#'
 #' @export
 #'
 plot.gpsm_pspop <- function(x, ...){
   g <- ggplot2::autoplot(x, ...)
   print(g)
   invisible(g)
-}
+}

R/print.R

@@ -5,7 +5,8 @@
 #' @param ... Additional arguments passed to customize the results.
 #'
 #' @return
-#' NULL
+#' No return value. This function is called for side effects.
+#'
 #' @export
 #'
 print.gpsm_erf <- function(x, ...){
@@ -67,7 +68,8 @@ summary.gpsm_erf <- function(object, ...){
 #' @param ... Additional arguments passed to customize the results.
 #'
 #' @return
-#' NULL
+#' No return value. This function is called for side effects.
+#'
 #' @export
 #'
 print.gpsm_pspop <- function(x, ...){

R/set_logger.R

@@ -5,26 +5,44 @@
 #' Updates logger settings, including log level and location of the file.
 #'
 #' @param logger_file_path A path (including file name) to log the messages.
+#' (Default: CausalGPS.log)
 #' @param logger_level The log level. Available levels include:
 #'   - TRACE
 #'   - DEBUG
-#'   - INFO
+#'   - INFO (Default)
 #'   - SUCESS
 #'   - WARN
 #'   - ERROR
 #'   - FATAL
 #'
 #' @export
 #'
+#' @return
+#' No return value. This function is called for side effects.
+#'
 #' @examples
 #'
 #' set_logger("Debug")
 #'
-set_logger <- function(logger_file_path=NULL, logger_level=NULL){
+set_logger <- function(logger_file_path= "CausalGPS.log", logger_level="INFO"){
 
   available_levels <- c("TRACE", "DEBUG", "INFO", "SUCCESS", "WARN",
                         "ERROR", "FATAL")
 
+  if (!is.element(logger_level, available_levels)){
+    stop(paste("logger_level: ", logger_level, " is not valid."))
+  }
+
+  #assign("logger_file_path", logger_file_path, envir = log_env)
+
+ logger::log_appender(appender = logger::appender_file(logger_file_path),
+                       index = 1)
+
+  set_options("logger_file_path", logger_file_path)
+  set_options("logger_level", logger_level)
+
+  #create_matching$logger_file_path <- logger_file_path
+
   if (!is.null(logger_level)){
     if (is.element(logger_level, available_levels)){
 
@@ -33,10 +51,32 @@ set_logger <- function(logger_file_path=NULL, logger_level=NULL){
     } else {
       stop(paste("Logger level is not valid. Available levels: ", paste(available_levels, collapse = " ")))
     }
+  } else {
+    logger::log_threshold(logger::INFO,index = 1)
   }
+}
 
-  if (!is.null(logger_file_path)){
-    logger::log_appender(appender = logger::appender_file(logger_file_path),
-                         index = 2)
-  }
+#' @title
+#' Get Logger Settings
+#'
+#' @description
+#' Returns current logger settings.
+#'
+#'
+#' @return
+#' Returns a list that includes **logger_file_path** and **logger_level**.
+#'
+#' @export
+#'
+#' @examples
+#'
+#' set_logger("mylogger.log", "INFO")
+#' log_meta <- get_logger()
+#'
+get_logger <- function(){
+
+  return(list(logger_file_path = get_options("logger_file_path"),
+              logger_level = get_options("logger_level")))
 }
+
+

R/train_it.R

@@ -1,4 +1,8 @@
-#' Funtction to develop prediction model based on user's preferences.
+#' @title 
+#' Generate Prediction Model
+#' 
+#' @description 
+#' Function to develop prediction model based on user's preferences.
 #'
 #' @param target A vector of target data.
 #' @param input A vector, matrix, or dataframe of input data.