add docs

OnRunning.md

@@ -0,0 +1,27 @@
+# Running Experiments with Lambda:
+This is not supposed to be a instruction on how to do it properly, but it is a writeup on how i did it.
+If you want to do it properly, extend the command line Arguments for haga-lambda and allow runtime tweaking of Hyperparams and Datasets. While at it, generalizing LamdaCalculusV1 would be smart, too. You can use LamdaCalculusV2 as a template on how to do it more properly. (I wrote that later, and was IMO quite a bit smarter about it. I sadly didn't have time to fix up V1...)
+
+You just want to do the same hack i did or know about it?
+
+create a branch for each Dataset-experiment pair. e.g. iris_1 ... iris_9
+
+here git is your friend, especially if you inevitably screw up.
+e.g. echo git\ checkout\ iris_{1..9}\;\ git\ cherry-pick\ 7ced1e1\; will create a command for applying the commit 7ced1e1 to every iris branch.
+
+Adapt the build.sbatch and run.sbatch and **commit them**!
+clone the branch you committed to on the cluster.
+create the required folders! If you forget the output one, slurm will fail silently!
+
+Make sure to sbatch an adapted **build.sbatch before run.sbatch**!
+build.sbatch will need to be adapted for and run on every node you will use!
+Otherwise stuff WILL break!
+
+sbatch run.sbatch
+
+You can use squeue to monitor progress.
+
+A huge slew of raw data will be dumped into the output Folder. The error files contain results, the output files stats during training.
+
+On how to process these results, see: https://merl.dnshome.de/git/Hans/haga-graphics
+

build.sbatch

@@ -1,9 +1,28 @@
 #!/usr/bin/env bash
 #SBATCH --time=00:10:00
 #SBATCH --partition=cpu
-#SBATCH --output=./output/output_build.txt
-#SBATCH --error=./output/error_build.txt
+# 9 Experiments * 3 Datasets
+#SBATCH --array=0-27
+# ensure output exists, is a folder and is writable in your working directory
+#SBATCH --output=./output/output_run_%a.txt
+#SBATCH --error=./output/error_run_%a.txt
+# run once for every node you plan to use
 #SBATCH --nodelist=oc-compute02
-#SBATCH --mem=4G
-#SBATCH -c16
-srun nix develop --command stack --no-nix --system-ghc --no-install-ghc build
+#SBATCH --mem=2G
+
+
+# list your branches
+problems=("iris" "nurse" "german")
+
+#9 Experiments
+current_problem=${problems[(${SLURM_ARRAY_TASK_ID}/9)]}
+#9 Experiments
+current_variant=$(((${SLURM_ARRAY_TASK_ID}) % 9 + 1))
+current_branch="${current_problem}_${current_variant}"
+
+# ensure [full path to writable folder on node *] exists
+git clone -b $current_branch --single-branch "[your git repo]" [full path to writable folder on node 1]/$current_branch
+git clone -b $current_branch --single-branch "[your git repo]" [full path to writable folder on node 1]/$current_branch
+#... for every node
+
+srun bash -c "cd /data/$SLURMD_NODENAME/merljoha/$current_branch; nix develop --command stack --no-nix --system-ghc --no-install-ghc build"

lambda/src/LambdaDatasets/GermanDataset.hs

@@ -89,10 +89,10 @@ lE =
       maxDepth = 9,
       weights =
         ExpressionWeights
-          { lambdaSpucker = 1,
-            lambdaSchlucker = 2,
-            symbol = 30,
-            variable = 10,
+          { lambdaSpucker = 0,
+            lambdaSchlucker = 10,
+            symbol = 100,
+            variable = 5,
             constant = 5
           }
     }

lambda/src/LambdaDatasets/IrisDataset.hs

@@ -56,10 +56,10 @@ lE =
       maxDepth = 9,
       weights =
         ExpressionWeights
-          { lambdaSpucker = 1,
-            lambdaSchlucker = 2,
-            symbol = 30,
-            variable = 10,
+          { lambdaSpucker = 0,
+            lambdaSchlucker = 10,
+            symbol = 100,
+            variable = 5,
             constant = 5
           }
     }

lambda/src/LambdaDatasets/NurseryDataset.hs

@@ -77,10 +77,10 @@ lE =
       maxDepth = 9,
       weights =
         ExpressionWeights
-          { lambdaSpucker = 1,
-            lambdaSchlucker = 2,
-            symbol = 30,
-            variable = 10,
+          { lambdaSpucker = 0,
+            lambdaSchlucker = 10,
+            symbol = 100,
+            variable = 5,
             constant = 5
           }
     }

lambda/src/Main.hs

@@ -8,8 +8,8 @@ import Pipes
 import Pretty
 import Protolude hiding (for)
 import System.IO
--- import LambdaDatasets.IrisDataset
-import LambdaDatasets.NurseryDataset
+import LambdaDatasets.IrisDataset
+-- import LambdaDatasets.NurseryDataset
 -- import LambdaDatasets.GermanDataset
 import Debug.Trace as DB
 import qualified Data.Map.Strict as Map

run.sbatch

@@ -1,9 +1,31 @@
 #!/usr/bin/env bash
-#SBATCH --time=18:00:00
+# test this timing, it scales with result sizes
+#SBATCH --time=12:00:00
 #SBATCH --partition=cpu
-#SBATCH --array=0-30
-#SBATCH --output=./output/output_run_%j.txt
-#SBATCH --error=./output/error_run_%j.txt
-#SBATCH --nodelist=oc-compute02
-#SBATCH --mem=3G
-srun nix develop --command stack --no-nix --system-ghc --no-install-ghc run haga-lambda
+# 30 Runs * 9 Experiments * 3 Datasets
+#SBATCH --array=0-809
+# ensure output exists, is a folder and is writable in your working directory
+#SBATCH --output=./output/output_run_%a.txt
+#SBATCH --error=./output/error_run_%a.txt
+# exclude nodes with weaker CPUs
+#SBATCH --exclude=oc222
+# test memory usage, it scales **Exponentially** with max Depth. Implement some countermeasures if that's a problem, e.g. raise max depth over time.
+#SBATCH --mem=6G
+#SBATCH --nodes=1
+
+
+# list your branches
+problems=("iris" "nurse" "german")
+
+# 30 Runs * 9 Experiments
+current_problem=${problems[(${SLURM_ARRAY_TASK_ID}/270)]}
+# 30 Runs, 9 Experiments
+current_variant=$(((${SLURM_ARRAY_TASK_ID} / 30) % 9 + 1))
+current_branch="${current_problem}_${current_variant}"
+
+# ensure [full path to writable folder on node *] exists
+git clone -b $current_branch --single-branch "[your git repo]" [full path to writable folder on node 1]/$current_branch
+git clone -b $current_branch --single-branch "[your git repo]" [full path to writable folder on node 2]/$current_branch
+#... for every node
+
+srun bash -c "cd /data/$SLURMD_NODENAME/merljoha/$current_branch; nix develop --command stack --no-nix --system-ghc --no-install-ghc run haga-lambda"