feldtruby 0.3.13 → 0.3.14

data/lib/feldtruby/statistics.rb

@@ -232,49 +232,36 @@ module FeldtRuby::Statistics::Plotting
 
   end
 
-  def plot_2dims(csvFilePath, graphFilePath, xName, yName, title = "scatterplot", format = "pdf", width = nil, height = nil)
+  def plot_2dims(csvFilePath, plotCommand, xlabel, ylabel, title = "scatterplot")
 
-    include_library("ggplot2")
-
-    gfxFile = File.dirname(graphFilePath) + "/" + File.basename(graphFilePath, "." + format) + "." + format
+    script = <<-EOS
+      data <- read.csv(#{csvFilePath.inspect})
+      #{plotCommand}
+      #{ggplot2_setup_and_theme()}
+      f
+    EOS
 
-    pre = [
-      "data <- read.csv(#{csvFilePath.inspect})",
-      gfx_device(format, width, height)
-    ]
+    subst_eval script, {:title => title,
+      :xlabel => xlabel, :ylabel => ylabel}
 
-    #plot = ["suppressWarnings( " + yield().join(" ") + " + theme_bw(base_size = 12, base_family = \"\") )"]
-    #plot = [yield().join(" ") + " + theme_bw(base_size = 12, base_family = \"\")"]
-    plot = yield()
-    plot << " + theme_bw(base_size = 12, base_family = \"\")"
+  end
 
-    post = [
-      "dev.off()"
-    ]
+  def hexbin_heatmap(csvFilePath, xlabel, ylabel, title = "heatmap", bins = 20)
+    plot_2dims(csvFilePath,
+      "f <- ggplot(data, aes(#{ylabel}, #{ylabel})) + geom_hex( bins = #{bins} )",
+      xlabel, ylabel, title)
+  end
 
-    lines = pre + plot + post
-    eval lines.join("\n")
+  def scatter_plot(csvFilePath, xlabel, ylabel, title = "scatterplot")
 
-  end
+    script = <<-EOS
+      # smoothing_method <- if(nrow(data) > 1000) {'gam'} else {'loess'}
+      f <- ggplot(data, aes(#{xlabel}, #{ylabel})) + geom_point(shape = 1)
+      f <- f + stat_smooth()
+    EOS
 
-  # Scatter plot of columns xName vs yName in csvFilePath is saved to graphFilePath.
-  def scatter_plot(csvFilePath, graphFilePath, xName, yName, title = "scatterplot", smoothFit = true, format = nil, width = 7, height = 5)
-    plot_2dims(csvFilePath, graphFilePath, xName, yName, title, format, width, height) {
-      [
-        "smoothing_method <- if(nrow(data) > 1000) {'gam'} else {'loess'}",
-        "ggplot(data, aes(#{xName}, #{yName})) + ",
-        "  geom_point(shape = 1) + ", # Each point is non-filled circle
-        (smoothFit ? "  geom_smooth(method = smoothing_method) + " : nil),
-        "  ggtitle(#{title.inspect})"
-      ].compact
-    }
-  end
+    plot_2dims(csvFilePath, script, xlabel, ylabel, title)
 
-  # Scatter plot of columns xName vs yName in csvFilePath is saved to graphFilePath.
-  def hexbin_heatmap(csvFilePath, graphFilePath, xName, yName, title = "heatmap", bins = 30, format = "pdf", width = 7, height = 5)
-    plot_2dims(csvFilePath, graphFilePath, xName, yName, title, format, width, height) {
-      [ "ggplot(data, aes(#{xName}, #{yName})) + geom_hex( bins = #{bins} ) + ggtitle(\"#{title}\")"]
-    }
   end
 
   GfxFormatToGfxParams = {
@@ -305,14 +292,28 @@ module FeldtRuby::Statistics::Plotting
 
   end
 
+  def ggplot2_setup_and_theme
+
+    include_library("ggplot2")
+    include_library("reshape2")
+
+    script = <<-EOS
+      f <- f + ggtitle(_title_) + xlab(_xlabel_) + ylab(_ylabel_)
+      f <- f + theme_bw()
+      f <- f + theme(
+              plot.title = element_text(face="bold", size=12), 
+              axis.title.x = element_text(face="bold", size=10),
+              axis.title.y = element_text(face="bold", size=10)
+            )
+    EOS
+
+  end
+
   # Overlaid density graph of the observations (sampled distributions) in data1
   # and data2. The _dataMap_ maps the name of each data series to an array with
   # its observations.
   def overlaid_densities(dataMap, title = "Densities of distributions", datasetsName = "distribution", xlabel = "values", ylabel = "density")
 
-    include_library("ggplot2")
-    include_library("reshape2")
-
     cardinalities = dataMap.values.map {|vs| vs.length}.uniq
 
     unless cardinalities.length == 1
@@ -327,13 +328,7 @@ module FeldtRuby::Statistics::Plotting
       names(df.m)[2] <- _datasetsName_
       f <- ggplot(df.m, aes(value, fill=#{datasetsName}))
       f <- f + geom_density(alpha = 0.2, size = 0.5) + scale_color_brewer()
-      f <- f + ggtitle(_title_) + xlab(_xlabel_) + ylab(_ylabel_)
-      f <- f + theme_bw()
-      f <- f + theme(
-              plot.title = element_text(face="bold", size=12), 
-              axis.title.x = element_text(face="bold", size=10),
-              axis.title.y = element_text(face="bold", size=10)
-            )
+      #{ggplot2_setup_and_theme()}
       f
     EOS
 

data/lib/feldtruby/version.rb

@@ -1,3 +1,3 @@
 module FeldtRuby
-  VERSION = "0.3.13"
+  VERSION = "0.3.14"
 end

data/test/test_statistics.rb

@@ -141,34 +141,40 @@ describe "Plotting" do
 
   end
 
-#  it "can do a scatter plot" do
-#
-#    d = File.dirname(__FILE__) + "/"
-#    filename = d + "tmp.csv"
-#    out = d + "scatterplot.pdf"
-#    RC.scatter_plot(filename, out, "size", "height", 
-#      "Scatterplot", true)
-#
-#    File.exist?(out).must_equal true
-#
-#    File.delete out
-#
-#  end
-#
-#  it "can do a hexbin heatmap plot" do
-#
-#    d = File.dirname(__FILE__) + "/"
-#    filename = d + "tmp.csv"
-#    out = d + "heatmap.pdf"
-#
-#    RC.hexbin_heatmap(filename, out, "size", "height", 
-#      "Hexbin heatmap", 30)
-#
-#    File.exist?(out).must_equal true
-#
-#    File.delete out
-#
-#  end
+  it "can do a scatter plot" do
+
+    d = File.dirname(__FILE__) + "/"
+    filename = d + "tmp.csv"
+
+    out = "scatterplot.pdf"
+
+    RC.save_graph(out) do
+      RC.scatter_plot(filename, "size", "height", "Scatterplot")
+    end
+
+    File.exist?(out).must_equal true
+
+    #File.delete out
+
+  end
+
+  it "can do a hexbin heatmap plot" do
+
+    d = File.dirname(__FILE__) + "/"
+    filename = d + "tmp.csv"
+
+    out = "hexbin.pdf"
+
+    RC.save_graph(out) do
+      RC.hexbin_heatmap(filename, "size", "height", 
+        "Hexbin heatmap", 30)
+    end
+
+    File.exist?(out).must_equal true
+
+    File.delete out
+
+  end
 
   it "can do overlaid density plot of three arrays" do