Changes based on Meghana's comments/questions

00_globals.R

@@ -9,9 +9,6 @@ library(magrittr)
 library(stringr)
 library(SigOptR)
 
-### declare GLOBAL variables ----
-random_seed <- 8675309
-
 ### declare functions ----
 
 # Function to train random forest model
@@ -29,7 +26,4 @@ predict_classifier <- function(object, new_data){
   predict(object = object, newdata = new_data, type = "prob")
 }
 
-# Function to get AUC from the random forest model
-
-
 

01_download_format_data.R

@@ -2,10 +2,6 @@
 # This script splits data into two training sets and a test set
 ################################################################################
 
-rm(list = ls())
-
-set.seed(90210)
-
 ### Load necessary libraries ----
 library(textmineR)
 
@@ -41,7 +37,10 @@ doc_class <- stringr::str_split(docnames, pattern = "/") %>%
 
 doc_class <- factor(doc_class)
 
-dtm <- CreateDtm(doc_vec = docs) # stopwords English and SMART
+# Using the default stopwords from textmineR. 
+# The default is the "english" set and "SMART" set.
+# Pretty common choice and it shouldn't make much of a difference on this data set.
+dtm <- CreateDtm(doc_vec = docs) 
 
 dim(dtm)
 
@@ -51,12 +50,13 @@ dtm <- dtm[, colSums(dtm > 0) >= 5]
 dim(dtm)
 
 ### sample rows into three groups ----
+set.seed(90210) # Setting a seed for reproducibility since we call sample below
 
 idx <- seq_len(nrow(dtm))
 
-train1 <- sample(idx, 6665)
+train1 <- sample(x = idx, size = 6665)
 
-train2 <- sample(setdiff(idx, train1), 6665)
+train2 <- sample(x = setdiff(idx, train1), size = 6665)
 
 test <- setdiff(idx, c(train1, train2))
 

02_lsa_sigopt.R

@@ -94,7 +94,9 @@ create_model <- function(assignments) {
 
 ### run the optimization loop ----
 
-Sys.sleep(60)
+# need to pause the execution so the parallel workers don't get ahead of the 
+# API call
+Sys.sleep(60) 
 
 output <- parallel::mclapply(seq_len(experiment$observation_budget), function(j){
 

03_lda_sigopt.R

@@ -91,6 +91,9 @@ create_model <- function(assignments) {
 }
 
 ### run the optimization loop ----
+
+# need to pause the execution so the parallel workers don't get ahead of the 
+# API call
 Sys.sleep(60)
 
 output <- parallel::mclapply(seq_len(experiment$observation_budget), function(j){

README.md

@@ -1 +1,35 @@
-# topic-modeling-optimization-example
+# topic-modeling-optimization-example
+
+To successfully run the code in this repository you will need to have a SigOpt API key. Save it to a text file called "sigopt_api_key" in the root folder of this repository. The file should be a single line, with your API key saved on it.
+
+You will also need to install the dependencies with the following commands:
+```
+install.packages("parallel")
+install.packages("textmineR"")
+install.packages("randomForest")
+install.packages("magrittr")
+install.packages("stringr")
+install.packages("SigOptR")
+```
+
+You will also have to run this code from the root folder by doing one of the follwing:
+
+1. From the command line: enter your R environment from the root directory of the folder
+2. From any start point: run `setwd("X")` where `"X"` is the root folder of this repo.
+3. Use RStudio and open the project "topic-modeing-optimization-example.Rproj" from your RStudio IDE. This will handle all working diretory issues.
+
+Note that if you choose option "2" above [Jenny Bryan will set your computer on fire.](https://www.tidyverse.org/blog/2017/12/workflow-vs-script/)
+
+## To run these files locally
+Run the scripts in the following order:
+
+1. 01_download_format_data.R
+2. 02_lsa_sigopt.R
+3. 03_lda_sigopt.R
+4. 04_lda_optimal.R
+
+# To run these files on google cloud compute
+
+1. Install one more package with `install.packages("cloudml")`
+2. If this is your first time using the `cloudml` package
+