From dfc7658426a0c63acecca159ddab071f28b251a9 Mon Sep 17 00:00:00 2001 From: Thomas Breloff Date: Tue, 13 Oct 2015 16:51:19 -0400 Subject: [PATCH] misc --- examples/facets.ipynb | 305 +++++++++++++++++++++++++++++++++++++++++- src/backends/qwt.jl | 6 +- src/recipes.jl | 8 +- src/utils.jl | 2 + 4 files changed, 311 insertions(+), 10 deletions(-) diff --git a/examples/facets.ipynb b/examples/facets.ipynb index 66342e58..f4252294 100644 --- a/examples/facets.ipynb +++ b/examples/facets.ipynb @@ -151,6 +151,13 @@ "collapsed": false }, "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "INFO: Recompiling stale cache file /home/tom/.julia/lib/v0.4/Plots.ji for module Plots.\n" + ] + }, { "name": "stdout", "output_type": "stream", @@ -195,13 +202,305 @@ "text": [ "WARNING: Only Range types are supported for Qwt xticks/yticks. typeof(ticks)=Symbol\n", "WARNING: Only Range types are supported for Qwt xticks/yticks. typeof(ticks)=Symbol\n", - "WARNING: Only Range types are supported for Qwt xticks/yticks. typeof(ticks)=Symbol\n", + "WARNING: Only Range types are supported for Qwt xticks/yticks. typeof(ticks)=Symbol\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y1 idx=1 npoints=0},[Inf,-Inf])" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "ERROR: ArgumentError: collection must be non-empty\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "WARNING: handleLinkInner isn't implemented for qwt\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", + "ERROR: ArgumentError: collection must be non-empty\n", "WARNING: handleLinkInner isn't implemented for qwt\n" ] }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y1 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y3 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y3 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y4 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y4 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y5 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y5 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y6 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y6 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y7 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y7 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y8 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y8 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y9 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y9 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y10 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y10 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y11 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y11 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y12 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y12 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y13 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y13 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y14 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y14 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y15 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y15 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y16 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y16 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y17 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y17 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y18 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y18 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y19 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y19 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y20 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y20 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y21 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y21 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y22 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y22 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y23 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y23 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y24 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y24 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",true,Series{axis=left label=y25 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",true,Series{axis=left label=y25 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(k,lims[k]) = (1,[0.005121831968471158,0.9976543129681468])\n", + "(k,lims[k]) = (2,[-6.349553761472921,7.04344825216217])\n", + "(k,lims[k]) = (3,[99.03050321453688,100.75251250777524])\n", + "(k,lims[k]) = (4,[-73.85696150084576,-66.74340136889572])\n", + "(k,lims[k]) = (5,[-0.22727750427848636,1.245495475460562])\n", + "(k,lims[k]) = (1,[0.005121831968471158,0.9976543129681468])\n", + "(k,lims[k]) = (2,[-6.349553761472921,7.04344825216217])\n", + "(k,lims[k]) = (3,[99.03050321453688,100.75251250777524])\n", + "(k,lims[k]) = (4,[-73.85696150084576,-66.74340136889572])\n", + "(k,lims[k]) = (5,[-0.22727750427848636,1.245495475460562])\n", + "(k,lims[k]) = (1,[0.005121831968471158,0.9976543129681468])\n", + "(k,lims[k]) = (2,[-6.349553761472921,7.04344825216217])\n", + "(k,lims[k]) = (3,[99.03050321453688,100.75251250777524])\n", + "(k,lims[k]) = (4,[-73.85696150084576,-66.74340136889572])\n", + "(k,lims[k]) = (5,[-0.22727750427848636,1.245495475460562])\n", + "(k,lims[k]) = (1,[0.005121831968471158,0.9976543129681468])\n", + "(k,lims[k]) = (2,[-6.349553761472921,7.04344825216217])\n", + "(k,lims[k]) = (3,[99.03050321453688,100.75251250777524])\n", + "(k,lims[k]) = (4,[-73.85696150084576,-66.74340136889572])\n", + "(k,lims[k]) = (5,[-0.22727750427848636,1.245495475460562])\n", + "(k,lims[k]) = (1,[0.005121831968471158,0.9976543129681468])\n", + "(k,lims[k]) = (2,[-6.349553761472921,7.04344825216217])\n", + "(k,lims[k]) = (3,[99.03050321453688,100.75251250777524])\n", + "(k,lims[k]) = (4,[-73.85696150084576,-66.74340136889572])\n", + "(k,lims[k]) = (5,[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y3 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y3 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y4 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y4 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y5 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y5 idx=1 npoints=0},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[0.005121831968471158,0.9976543129681468])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y6 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y6 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y8 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y8 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y9 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y9 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y10 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y10 idx=1 npoints=0},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-6.349553761472921,7.04344825216217])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y11 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y11 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y12 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y12 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y14 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y14 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y15 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y15 idx=1 npoints=0},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[99.03050321453688,100.75251250777524])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y16 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y16 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y17 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y17 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y18 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y18 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y20 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y20 idx=1 npoints=0},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-73.85696150084576,-66.74340136889572])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y21 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y21 idx=1 npoints=0},[Inf,-Inf])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[Inf,-Inf])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y22 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y22 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y23 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y23 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y24 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y24 idx=1 npoints=0},[-0.22727750427848636,1.245495475460562])\n", + "(\"before\",isx,series,lims) = (\"before\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(\"after\",isx,series,lims) = (\"after\",false,Series{axis=left label=y2 idx=2 npoints=1000},[-0.22727750427848636,1.245495475460562])\n", + "(k,lims[k]) = (1,[0.005121831968471158,0.9976543129681468])\n" + ] + }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "Subplot{Plots.QwtPackage() p=25 n=25}" ] @@ -228,7 +527,7 @@ "C = cor(CovarianceMatrix(M))\n", "\n", "# debugplots()\n", - "p = corrplot(M, C, labels=[\"item1\",\"item2\",\"item3\"]) #, size=(600,600), colors=[colorant\"orange\", colorant\"black\", colorant\"green\"])" + "p = corrplot(M, C, labels=[\"item$i\" for i in 1:size(M,2)]) #, size=(600,600), colors=[colorant\"orange\", colorant\"black\", colorant\"green\"])" ] }, { diff --git a/src/backends/qwt.jl b/src/backends/qwt.jl index da1c5df2..b9e9d555 100644 --- a/src/backends/qwt.jl +++ b/src/backends/qwt.jl @@ -249,13 +249,13 @@ end function buildSubplotObject!(subplt::Subplot{QwtPackage}, isbefore::Bool) isbefore && return false i = 0 - rows = [] - row = [] + rows = Any[] + row = Any[] for (i,(r,c)) in enumerate(subplt.layout) push!(row, subplt.plts[i].o) if c == ncols(subplt.layout, r) push!(rows, Qwt.hsplitter(row...)) - row = [] + row = Any[] end end # for rowcnt in subplt.layout.rowcounts diff --git a/src/recipes.jl b/src/recipes.jl index 6987998d..d6c97dc8 100644 --- a/src/recipes.jl +++ b/src/recipes.jl @@ -79,16 +79,16 @@ function corrplot{T<:Real,S<:Real}(mat::AMat{T}, corrmat::AMat{S}; if i==j # histogram on diagonal histogram!(plt, mat[:,i], c=:black, leg=false) - i > 1 && plot!(yticks = :none) + i > 1 && plot!(plt, yticks = :none) else # scatter plots off-diagonal, color determined by correlation c = RGBA(RGB(getColorZ(cgrad, corrmat[i,j])), 0.3) - scatter!(plt, mat[:,j], mat[:,i], w=0, ms=3, c=c, leg=false) + scatter!(plt, mat[:,j], mat[:,i], w=1, ms=3, c=c, leg=false) end if labels != nothing && length(labels) >= m - i == m && xlabel!(string(labels[j])) - j == 1 && ylabel!(string(labels[i])) + i == m && xlabel!(plt, string(labels[j])) + j == 1 && ylabel!(plt, string(labels[i])) end # # replace the plt diff --git a/src/utils.jl b/src/utils.jl index 0b63aa39..2344cc79 100644 --- a/src/utils.jl +++ b/src/utils.jl @@ -122,6 +122,8 @@ function expandLimits!(lims, x) e1, e2 = extrema(x) lims[1] = min(lims[1], e1) lims[2] = max(lims[2], e2) + catch err + warn(err) end nothing end