galaaz 0.5.0 → 2.1.0

data/examples/islr/ch3_multiple_regression.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.install_and_loads('ISLR', 'MASS')

data/examples/islr/ch6.spec.rb

@@ -23,40 +23,64 @@
 
 require 'galaaz'
 
+using Galaaz::SymbolDSL
 R.install_and_loads('ISLR', 'MASS')
 
 context "ISLR" do
 
   context "Chapter 6 - Subset Selection Methods - page 244" do
 
+    def galaaz_islr_debug(msg)
+      STDERR.puts "[DEBUG islr][ch6.spec][#{Time.now.strftime('%H:%M:%S')}] #{msg}"
+      STDERR.flush
+    end
+
     before(:each) do
       @hitters = ~:Hitters
     end
     
     it "Should access the names of the dataset" do
+      galaaz_islr_debug 'test1 start (names/dim)'
       expect(@hitters.names[1] == "AtBat").to eq true
       expect(@hitters.names[5] == "RBI").to eq true
       expect(@hitters.names[11] == "CRuns").to eq true
       expect(@hitters.dim == R.c(322, 20)).to eq true
+      galaaz_islr_debug 'test1 end'
     end
 
     it "Should count na's using 'R.sum'" do
+      galaaz_islr_debug 'test2 start (R.sum)'
       expect(R.sum(@hitters.Salary.is__na) == 59).to eq true
       expect(R.sum(@hitters.Salary.is__na)).to eq 59
+      galaaz_islr_debug 'test2 end'
     end
 
     it "Should count na's using Ruby Enumerable 'sum'" do
+      galaaz_islr_debug "test3 start (Ruby Enumerable sum over Salary)"
+      yielded = 0
+      salary = @hitters.Salary
+      galaaz_islr_debug "test3 salary fetched; about to salary.size"
+      sz = salary.size
+      galaaz_islr_debug "test3 salary.size=#{sz}; about to Salary.sum"
       # method 'sum' is a Ruby Enumerable method.  To count na's we can loop through
       # every element and check if they are na or not.  Note that the return os
       # is__na is an R::Vector, so we need to 'pop' the value to a Ruby value in
       # ordet to apply the '?' method
-      expect(@hitters.Salary.sum { |e| (e.is__na == true)? 1 : 0 }).to eq 59
+      got = @hitters.Salary.sum do |e|
+        yielded += 1
+        galaaz_islr_debug("test3 yield #{yielded}") if yielded % 100 == 0
+        (e.is__na == true) ? 1 : 0
+      end
+      galaaz_islr_debug "test3 end (yielded=#{yielded}, got=#{got})"
+      expect(got).to eq 59
     end
 
     it "should remove missing values with na__omit" do
+      galaaz_islr_debug 'test4 start (na__omit)'
       @hitters = @hitters.na__omit
       expect(@hitters.dim == R.c(263, 20)).to eq true
       expect(R.sum(@hitters.is__na)).to eq 0
+      galaaz_islr_debug 'test4 end'
     end
     
   end

data/examples/misc/ggplot.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 module LightBlueTheme
@@ -125,7 +126,7 @@ module LightBlueTheme
   
 end
 
-R.awt
+# R.awt
 
 plot = R.grid__arrange(
   LightBlueTheme.graph_title("Cars: wt x mpg"),
@@ -137,7 +138,8 @@ plot = R.grid__arrange(
   heights: R.c(0.050, 0.025, 0.85, 0.05)
 )
 
-plot.print
+# plot.print
+R.ggsave("cars_plot.png", plot)
 
 =begin
 sleep(5)
@@ -153,7 +155,7 @@ R.grid__newpage
  R.geom_point('')).print
 =end
 
-a = gets.chomp
+a = gets.chomp if $stdin.tty?
 
 
 =begin

data/examples/misc/moneyball.rb

@@ -2,6 +2,7 @@
 
 require 'galaaz'
 
+using Galaaz::SymbolDSL
 local_dir = File.expand_path File.dirname(__FILE__)
 
 # This dataset comes from Baseball-Reference.com.

data/examples/misc/subsetting.rb

@@ -2,6 +2,7 @@
 
 require 'galaaz'
 
+using Galaaz::SymbolDSL
 # This examples were extracted from "Advanced R", by Hadley Wickham, available on the
 # web at: http://adv-r.had.co.nz/Subsetting.html#applications
 

data/examples/multithread_shards_to_r/shards_to_r.rb

@@ -0,0 +1,68 @@
+# frozen_string_literal: true
+
+# Multithreaded Ruby → single R workflow
+#
+# Pattern: JRuby runs several threads (e.g. one connection per shard). Each thread
+# performs I/O-bound work (here simulated; replace with Sequel/SQLite/pg per shard).
+# Results are merged in Ruby, then passed to R in one or a few bridge calls for
+# analytics (dplyr on an Arrow table, or a plain data.frame).
+#
+# Run from repo root (JRuby + R as for other examples):
+#   jruby examples/multithread_shards_to_r/shards_to_r.rb
+#
+# See also:
+#   specs/bridge_concurrent_spec.rb — many threads calling R; bridge serializes.
+#   specs/arrow_from_ruby_batches_spec.rb — same merge → R pattern with Arrow.
+
+require 'galaaz'
+
+using Galaaz::SymbolDSL
+SHARD_COUNT = 3
+ROWS_PER_SHARD = 200
+
+# Replace this with a real query, e.g.:
+#   Sequel.connect(ENV.fetch("DATABASE_URL_SHARD_#{shard_id}"))
+#     .fetch("SELECT id, region, amount FROM events WHERE shard_id = ?", shard_id)
+#     .map { |r| r.symbolize_keys }
+def fetch_rows_from_shard(shard_id)
+  base = shard_id * ROWS_PER_SHARD
+  (0...ROWS_PER_SHARD).map do |j|
+    n = base + j
+    {
+      shard: shard_id,
+      id: n,
+      region: "r#{n % 4}",
+      amount: (n % 17) + 1.0
+    }
+  end
+end
+
+batches = []
+batch_mx = Mutex.new
+
+threads = SHARD_COUNT.times.map do |sid|
+  Thread.new do
+    rows = fetch_rows_from_shard(sid)
+    batch_mx.synchronize { batches << rows }
+  end
+end
+threads.each(&:join)
+
+merged = batches.flatten
+puts "Collected #{merged.size} rows from #{SHARD_COUNT} threads in Ruby"
+
+unless R::Support.eval("requireNamespace('arrow', quietly=TRUE) && requireNamespace('dplyr', quietly=TRUE)") == true
+  warn 'Skipping R aggregation: install R packages arrow and dplyr, or use R.data__frame from merged hashes.'
+  exit 0
+end
+
+tbl = R::Arrow.from_ruby_batches(merged)
+grouped = R.dplyr___group_by(tbl, :region)
+summarised = R.dplyr___summarise(
+  grouped,
+  n: E.n,
+  total: E.sum(:amount),
+  mean_amt: E.mean(:amount)
+)
+out = R.dplyr___collect(summarised)
+puts R.as__data__frame(out)

data/examples/sthda_ggplot/RUN.md

@@ -0,0 +1,41 @@
+# Running sthda_ggplot examples
+
+Use the same JRuby and JVM options as the specs (required for Apache Arrow).
+
+## Run all sthda_ggplot examples
+
+From the project root:
+
+```bash
+jruby -I lib -J--add-opens=java.base/java.nio=org.apache.arrow.memory.core,ALL-UNNAMED examples/sthda_ggplot/all.rb
+```
+
+Or with the helper script (if present):
+
+```bash
+bin/run_example examples/sthda_ggplot/all.rb
+```
+
+## Run a single example
+
+```bash
+jruby -I lib -J--add-opens=java.base/java.nio=org.apache.arrow.memory.core,ALL-UNNAMED examples/sthda_ggplot/one_variable_continuous/geom_density.rb
+```
+
+Examples that open a display (e.g. `R.awt` / X11) will show a window; some examples use `sleep(2)` between plots.
+
+## Via Rake (default Ruby)
+
+The default task runs all sthda examples:
+
+```bash
+rake sthda:all
+```
+
+A single example (replace with the file path under `examples/sthda_ggplot/`):
+
+```bash
+rake "sthda:one_variable_continuous/geom_density"
+```
+
+Note: Rake uses `ruby --polyglot --jvm -Ilib/` (TruffleRuby-style). For JRuby + Shadow Bridge, use the `jruby` command above.

data/examples/sthda_ggplot/all.rb

@@ -21,6 +21,7 @@
 
 require 'galaaz'
 
+using Galaaz::SymbolDSL
 # Package Hmisc does not yet install on graalvm because of
 # problems with package data.table
 # install.packages('Hmisc')

data/examples/sthda_ggplot/one_variable_continuous/density_gg.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.set__seed(1234)

data/examples/sthda_ggplot/one_variable_continuous/geom_area.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.set__seed(1234)

data/examples/sthda_ggplot/one_variable_continuous/geom_density.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.set__seed(1234)
@@ -38,6 +39,8 @@ a = wdata.ggplot(E.aes(x: :weight))
 # Aggregate the data by sex
 mu = R.aggregate(wdata.weight, by: R.list(wdata.sex), FUN: :mean)
 mu.names = R.c("sex", "grp_mean")
+puts "MU CLASS: #{R.bridge.eval_r("paste(class(#{mu.r_interop}), collapse=' ')")}"
+puts "MU NAMES: #{R.bridge.eval_r("names(#{mu.r_interop})")}"
 puts mu
 
 R.awt

data/examples/sthda_ggplot/one_variable_continuous/geom_dotplot.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.set__seed(1234)

data/examples/sthda_ggplot/one_variable_continuous/geom_freqpoly.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.set__seed(1234)

data/examples/sthda_ggplot/one_variable_continuous/geom_histogram.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.set__seed(1234)

data/examples/sthda_ggplot/one_variable_continuous/histogram_density.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.set__seed(1234)

data/examples/sthda_ggplot/one_variable_continuous/stat.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.set__seed(1234)

data/examples/sthda_ggplot/one_variable_discrete/bar.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 # puts ~:mpg

data/examples/sthda_ggplot/qplots/box_violin_dot.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.set__seed(1234)

data/examples/sthda_ggplot/qplots/scatter_plots.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 # Load the data

data/examples/sthda_ggplot/scatter_gg.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.awt

data/examples/sthda_ggplot/two_variables_cont_bivariate/geom_bin2d.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 diamonds = ~:diamonds

data/examples/sthda_ggplot/two_variables_cont_bivariate/geom_density2d.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 faithful = ~:faithful

data/examples/sthda_ggplot/two_variables_cont_bivariate/geom_hex.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.install_and_loads('hexbin')

data/examples/sthda_ggplot/two_variables_cont_cont/geom_point.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 mtcars = ~:mtcars

data/examples/sthda_ggplot/two_variables_cont_cont/geom_smooth.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 mtcars = ~:mtcars

data/examples/sthda_ggplot/two_variables_cont_cont/misc.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.install_and_loads('quantreg')

data/examples/sthda_ggplot/two_variables_cont_function/geom_area.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 economics = ~:economics
@@ -46,9 +47,10 @@ R.grid__newpage
 # a subset of economics data set is used
 R.set__seed(1234)
 
-# Remember that nrow is an R::Vector.  To use it in a Ruby range we
-# need to 'pop' its value as Numeric
-ss = economics[R.sample((1..economics.nrow.pop), 20), :all]
+# nrow returns a numeric (or R vector); use it in a Ruby range for sampling row indices
+n = economics.nrow
+n = n.respond_to?(:pop) ? n.pop : n
+ss = economics[R.sample((1..n), 20), :all]
 
 print ss.ggplot(E.aes(x: :date, y: :unemploy)) + 
       R.geom_step

data/examples/sthda_ggplot/two_variables_disc_cont/geom_bar.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 df = R.data__frame(dose: R.c("D0.5", "D1", "D2"),

data/examples/sthda_ggplot/two_variables_disc_cont/geom_boxplot.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 tooth_growth = ~:ToothGrowth

data/examples/sthda_ggplot/two_variables_disc_cont/geom_dotplot.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.install_and_loads('Hmisc')

data/examples/sthda_ggplot/two_variables_disc_cont/geom_jitter.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 R.install_and_loads('Hmisc')
 

data/examples/sthda_ggplot/two_variables_disc_cont/geom_line.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 df = R.data__frame(supp: R.rep(R.c("VC", "OJ"), each: 3),

data/examples/sthda_ggplot/two_variables_disc_cont/geom_violin.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 R.install_and_loads('Hmisc')
 

data/examples/sthda_ggplot/two_variables_disc_disc/geom_jitter.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 diamonds = ~:diamonds

data/examples/sthda_ggplot/two_variables_error/geom_crossbar.rb

@@ -22,6 +22,7 @@
 ##########################################################################################
 
 require 'galaaz'
+using Galaaz::SymbolDSL
 require 'ggplot'
 
 R.install_and_loads('Hmisc')

data/ext/new_bridge/Makefile

@@ -0,0 +1,46 @@
+# Makefile for Galaaz Gatekeeper shared library
+# Usage: make clean all
+
+# R configuration
+R_HOME := $(shell R RHOME)
+R_CPPFLAGS := $(shell $(R_HOME)/bin/R CMD config --cppflags)
+R_LIBS := $(shell $(R_HOME)/bin/R CMD config --ldflags)
+
+# Rcpp configuration
+RCPP_INCLUDE := $(shell $(R_HOME)/bin/Rscript -e "cat(system.file('include', package='Rcpp'))")
+RCPP_CPPFLAGS := -I$(RCPP_INCLUDE)
+
+# Compiler settings
+CXX := $(shell $(R_HOME)/bin/R CMD config CXX)
+CXXFLAGS := $(shell $(R_HOME)/bin/R CMD config CXXFLAGS)
+CPPFLAGS := $(R_CPPFLAGS) $(RCPP_CPPFLAGS) -I.
+# Core R library only (avoid system libs that may not be present)
+LDFLAGS := -L$(R_HOME)/lib -lR -Wl,-rpath,$(R_HOME)/lib
+
+# Target library
+TARGET := galaaz_gatekeeper.so
+SRC := galaaz_gatekeeper_phase1.cpp
+OBJ := $(SRC:.cpp=.o)
+
+.PHONY: all clean check
+
+all: $(TARGET)
+
+$(TARGET): $(OBJ)
+	$(CXX) -shared -o $@ $^ $(LDFLAGS)
+
+%.o: %.cpp
+	$(CXX) $(CXXFLAGS) $(CPPFLAGS) -fPIC -c $< -o $@
+
+check: $(TARGET)
+	@echo "Checking library..."
+	@$(R_HOME)/bin/Rscript -e "dyn.load('$(TARGET)'); cat('Library loads successfully\n')"
+
+clean:
+	rm -f $(OBJ) $(TARGET)
+
+# Development helpers
+install: $(TARGET)
+	@echo "Copying to galaaz lib directory..."
+	mkdir -p ../../lib/new_bridge
+	cp $(TARGET) ../../lib/new_bridge/

data/ext/new_bridge/galaaz_gatekeeper_phase0.cpp

@@ -0,0 +1,12 @@
+#include <Rcpp.h>
+
+// Phase 0 skeleton: compile via Rcpp::sourceCpp; no socket I/O yet.
+
+// [[Rcpp::export]]
+Rcpp::List galaaz_poll() {
+  return Rcpp::List::create();
+}
+
+// [[Rcpp::export]]
+void galaaz_shutdown() {
+}