initial loading of activity_data

.gitignore

@@ -0,0 +1,10 @@
+# ignore the R studio docker image needed by hyak 
+rstudio_latest.sif
+
+
+# do not need to include any R items 
+.Rhistory
+.cache/
+.config/
+.local/
+

bot_activity_analysis/bot_activity_exploration.R

@@ -0,0 +1,37 @@
+library(tidyverse)
+# data directory: /gscratch/comdata/users/mjilg/mw-repo-lifecycles/bot_activity_counts
+# load in the paritioned directories
+library(dplyr)
+monthly_file_dir = "/gscratch/comdata/users/mjilg/mw-repo-lifecycles/bot_activity_counts/011625_dab_monthly/"
+yearly_file_dir = "/gscratch/comdata/users/mjilg/mw-repo-lifecycles/bot_activity_counts/011625_dab_yearly/"
+single_file_dir = "/gscratch/comdata/users/mjilg/mw-repo-lifecycles/bot_activity_counts/011625_dab_single/"
+column_names <- c("wiki_db", "date", "event_entity", "event_action", "count")
+# define a function to combing the multiple csv files in each directory
+consolidate_csv <- function(directory, column_names) {
+  file_list <- list.files(path = directory, pattern = "*.csv", full.names = TRUE)
+  df_list <- lapply(file_list, function(file){
+    df = read.csv(file, header = FALSE) 
+    colnames(df) <- column_names
+    return(df)
+    })
+  combined_df <- do.call(rbind, df_list)
+  return(combined_df)
+}
+#apply the function to our three directories of data 
+monthly_df <- consolidate_csv(monthly_file_dir, column_names)
+yearly_df <- consolidate_csv(yearly_file_dir, column_names)
+single_df <- consolidate_csv(single_file_dir, column_names)
+#rbind 
+combined_df <- rbind(monthly_df, yearly_df, single_df)
+rm(monthly_df)
+rm(yearly_df)
+rm(single_df)
+#making sure data columns are of the right type
+combined_df <- combined_df |> 
+  mutate( 
+    wiki_db = as.factor(wiki_db),
+    date = as.Date(date),
+    event_entity = as.factor(event_entity),
+    event_action = as.factor(event_action),
+    count = as.numeric(count)
+  )

rstudio-server.job

@@ -0,0 +1,100 @@
+#!/bin/sh
+
+#SBATCH --job-name=mgaughan-rstudio-server
+#SBATCH --partition=cpu-g2-mem2x
+
+#SBATCH --time=02:00:00
+#SBATCH --nodes=1
+#SBATCH --ntasks=4
+#SBATCH --mem=20G
+
+#SBATCH --signal=USR2
+#SBATCH --output=%x_%j.out
+
+# This script will request a single CPU with four threads with 20GB of RAM for 2 hours. 
+# You can adjust --time, --nodes, --ntasks, and --mem above to adjust these settings for your session.
+
+# --output=%x_%j.out creates a output file called rstudio-server_XXXXXXXX.out 
+# where the %x is short hand for --job-name above and the X's are an 8-digit 
+# jobID assigned by SLURM when our job is submitted.
+
+RSTUDIO_CWD="/mmfs1/home/mjilg/git/mw-lifecycle-analysis"
+RSTUDIO_SIF="rstudio_latest.sif"
+
+# Create temp directory for ephemeral content to bind-mount in the container
+RSTUDIO_TMP=$(/usr/bin/python3 -c 'import tempfile; print(tempfile.mkdtemp())')
+
+mkdir -p -m 700 \
+        ${RSTUDIO_TMP}/run \
+        ${RSTUDIO_TMP}/tmp \
+        ${RSTUDIO_TMP}/var/lib/rstudio-server
+
+cat > ${RSTUDIO_TMP}/database.conf <<END
+provider=sqlite
+directory=/var/lib/rstudio-server
+END
+
+# Set OMP_NUM_THREADS to prevent OpenBLAS (and any other OpenMP-enhanced
+# libraries used by R) from spawning more threads than the number of processors
+# allocated to the job.
+#
+# Set R_LIBS_USER to a path specific to rocker/rstudio to avoid conflicts with
+# personal libraries from any R installation in the host environment
+
+cat > ${RSTUDIO_TMP}/rsession.sh <<END
+#!/bin/sh
+
+export OMP_NUM_THREADS=${SLURM_JOB_CPUS_PER_NODE}
+export R_LIBS_USER=/gscratch/scrubbed/mjilg/R
+exec /usr/lib/rstudio-server/bin/rsession "\${@}"
+END
+
+chmod +x ${RSTUDIO_TMP}/rsession.sh
+
+export APPTAINER_BIND="${RSTUDIO_CWD}:${RSTUDIO_CWD},/gscratch:/gscratch,${RSTUDIO_TMP}/run:/run,${RSTUDIO_TMP}/tmp:/tmp,${RSTUDIO_TMP}/database.conf:/etc/rstudio/database.conf,${RSTUDIO_TMP}/rsession.sh:/etc/rstudio/rsession.sh,${RSTUDIO_TMP}/var/lib/rstudio-server:/var/lib/rstudio-server"
+
+# Do not suspend idle sessions.
+# Alternative to setting session-timeout-minutes=0 in /etc/rstudio/rsession.conf
+export APPTAINERENV_RSTUDIO_SESSION_TIMEOUT=0
+
+export APPTAINERENV_USER=$(id -un)
+export APPTAINERENV_PASSWORD=$(openssl rand -base64 15)
+
+# get unused socket per https://unix.stackexchange.com/a/132524
+# tiny race condition between the python & apptainer commands
+readonly PORT=$(/mmfs1/sw/pyenv/versions/3.9.5/bin/python -c 'import socket; s=socket.socket(); s.bind(("", 0)); print(s.getsockname()[1]); s.close()')
+cat 1>&2 <<END
+1. SSH tunnel from your workstation using the following command:
+
+   ssh -N -L 8787:${HOSTNAME}:${PORT} ${APPTAINERENV_USER}@klone.hyak.uw.edu
+
+   and point your web browser to http://localhost:8787
+
+2. log in to RStudio Server using the following credentials:
+
+   user: ${APPTAINERENV_USER}
+   password: ${APPTAINERENV_PASSWORD}
+
+When done using RStudio Server, terminate the job by:
+
+1. Exit the RStudio Session ("power" button in the top right corner of the RStudio window)
+2. Issue the following command on the login node:
+
+      scancel -f ${SLURM_JOB_ID}
+END
+
+source /etc/bashrc
+module load apptainer
+
+apptainer exec --cleanenv --home ${RSTUDIO_CWD} ${RSTUDIO_CWD}/${RSTUDIO_SIF} \
+    rserver --www-port ${PORT} \
+            --auth-none=0 \
+            --auth-pam-helper-path=pam-helper \
+            --auth-stay-signed-in-days=30 \
+            --auth-timeout-minutes=0 \
+            --rsession-path=/etc/rstudio/rsession.sh \
+            --server-user=${APPTAINERENV_USER}
+
+APPTAINER_EXIT_CODE=$?
+echo "rserver exited $APPTAINER_EXIT_CODE" 1>&2
+exit $APPTAINER_EXIT_CODE