public static void RunProportionExperiment(Excel.Application app, Excel.Workbook wbh, int nboots, double significance, double threshold, UserSimulation.Classification c, Random r, String outfile, long max_duration_in_ms, String logfile, ProgBar pb, bool ignore_parse_errors)
{
pb.setMax(5);
// record intitial state of spreadsheet
var prepdata = Prep.PrepSimulation(app, wbh, pb, ignore_parse_errors);
// init error generator
var eg = new ErrorGenerator();
// get inputs as an array of addresses to facilitate random selection
// DATA INPUTS ONLY
AST.Address[] inputs = prepdata.dag.terminalInputCells();
// sanity check: all of the inputs should also be in prepdata.original_inputs
foreach (AST.Address addr in inputs)
{
if (!prepdata.original_inputs.ContainsKey(addr))
{
throw new Exception("Missing address!");
}
}
for (int i = 0; i < 100; i++)
{
// randomly choose an input address
AST.Address rand_addr = inputs[r.Next(inputs.Length)];
// get the value
String input_value = prepdata.original_inputs[rand_addr];
// perturb it
String erroneous_input = eg.GenerateErrorString(input_value, c);
// create an error dictionary with this one perturbed value
var errors = new CellDict();
errors.Add(rand_addr, erroneous_input);
// run simulations; simulation code does insertion of errors and restore of originals
RunSimulation(app, wbh, nboots, significance, threshold, c, r, outfile, max_duration_in_ms, logfile, pb, prepdata, errors);
}
}
public static bool RunSubletyExperiment(Excel.Application app, Excel.Workbook wbh, int nboots, double significance, double threshold, UserSimulation.Classification c, Random r, String outfile, long max_duration_in_ms, String logfile, ProgBar pb, bool ignore_parse_errors)
{
pb.setMax(5);
// record intitial state of spreadsheet
var prepdata = Prep.PrepSimulation(app, wbh, pb, ignore_parse_errors);
// init error generator
var eg = new ErrorGenerator();
// get inputs as an array of addresses to facilitate random selection
// DATA INPUTS ONLY
AST.Address[] inputs = prepdata.dag.terminalInputCells();
for (int i = 0; i < 100; i++)
{
// randomly choose a *numeric* input
// TODO: use Fischer-Yates and take values until
// either we have a satisfactory input value or none
// remain
var rnd_addrs = inputs.Shuffle().ToList();
bool num_found = false;
String input_string;
double input_value;
AST.Address rand_addr;
do
{
// randomly choose an address; if there are none left, fail
if (rnd_addrs.Count == 0) {
return false;
}
rand_addr = rnd_addrs.First();
rnd_addrs = rnd_addrs.Skip(1).ToList();
// get the value
input_string = prepdata.original_inputs[rand_addr];
// try parsing it
if (Double.TryParse(input_string, out input_value))
{
num_found = true;
}
} while (!num_found);
// perturb it
String erroneous_input = eg.GenerateSubtleErrorString(input_value, c);
// create an error dictionary with this one perturbed value
var errors = new CellDict();
errors.Add(rand_addr, erroneous_input);
// run simulations; simulation code does insertion of errors and restore of originals
RunSimulation(app, wbh, nboots, significance, threshold, c, r, outfile, max_duration_in_ms, logfile, pb, prepdata, errors);
}
return true;
}
// num_bootstraps: the number of bootstrap samples to get
// inputs: a list of inputs; each TreeNode represents an entire input range
// outputs: a list of outputs; each TreeNode represents a function
public static TreeScore DataDebug(int num_bootstraps,
DAG dag,
Excel.Application app,
bool weighted,
bool all_outputs,
long max_duration_in_ms,
Stopwatch sw,
double significance,
ProgBar pb)
{
// this modifies the weights of each node
PropagateWeights(dag);
// filter out non-terminal functions
var output_fns = dag.terminalFormulaNodes(all_outputs);
// filter out non-terminal inputs
var input_rngs = dag.terminalInputVectors();
// first idx: the index of the TreeNode in the "inputs" array
// second idx: the ith bootstrap
var resamples = new InputSample[input_rngs.Length][];
// RNG for sampling
var rng = new Random();
// we save initial inputs and outputs here
var initial_inputs = StoreInputs(input_rngs, dag);
var initial_outputs = StoreOutputs(output_fns, dag);
// Set progress bar max
pb.setMax(input_rngs.Length * 2);
#region RESAMPLE
// populate bootstrap array
// for each input range (a TreeNode)
for (int i = 0; i < input_rngs.Length; i++)
{
// this TreeNode
var t = input_rngs[i];
// resample
resamples[i] = Resample(num_bootstraps, initial_inputs[t], rng);
// update progress bar
pb.IncrementProgress();
}
#endregion RESAMPLE
#region INFERENCE
return Inference(
num_bootstraps,
resamples,
initial_inputs,
initial_outputs,
input_rngs,
output_fns,
dag,
weighted,
significance,
pb);
#endregion INFERENCE
}
public static void RunSimulationPaperMain(Excel.Application app, Excel.Workbook wbh, int nboots, double significance, double threshold, UserSimulation.Classification c, Random r, String outfile, long max_duration_in_ms, String logfile, ProgBar pb, bool ignore_parse_errors)
{
pb.setMax(5);
// record intitial state of spreadsheet
var prepdata = Prep.PrepSimulation(app, wbh, pb, ignore_parse_errors);
// generate errors
CellDict errors = UserSimulation.Utility.GenImportantErrors(prepdata.terminal_formula_nodes,
prepdata.original_inputs,
5,
prepdata.correct_outputs,
app,
wbh,
c,
prepdata.dag);
// run paper simulations
RunSimulation(app, wbh, nboots, significance, threshold, c, r, outfile, max_duration_in_ms, logfile, pb, prepdata, errors);
}
// num_bootstraps: the number of bootstrap samples to get
// inputs: a list of inputs; each TreeNode represents an entire input range
// outputs: a list of outputs; each TreeNode represents a function
public static TreeScore DataDebug(int num_bootstraps,
DAG dag,
Excel.Application app,
bool weighted,
bool all_outputs,
long max_duration_in_ms,
Stopwatch sw,
double significance,
ProgBar pb)
{
// this modifies the weights of each node
PropagateWeights(dag);
// filter out non-terminal functions
var output_fns = dag.terminalFormulaNodes(all_outputs);
// filter out non-terminal inputs
var input_rngs = dag.terminalInputVectors();
// first idx: the index of the TreeNode in the "inputs" array
// second idx: the ith bootstrap
var resamples = new InputSample[input_rngs.Length][];
// RNG for sampling
var rng = new Random();
// we save initial inputs and outputs here
var initial_inputs = StoreInputs(input_rngs, dag);
var initial_outputs = StoreOutputs(output_fns, dag);
// Set progress bar max
pb.setMax(input_rngs.Length * 2);
#region RESAMPLE
// populate bootstrap array
// for each input range (a TreeNode)
for (int i = 0; i < input_rngs.Length; i++)
{
// this TreeNode
var t = input_rngs[i];
// resample
resamples[i] = Resample(num_bootstraps, initial_inputs[t], rng);
// update progress bar
pb.IncrementProgress();
}
#endregion RESAMPLE
#region INFERENCE
return(Inference(
num_bootstraps,
resamples,
initial_inputs,
initial_outputs,
input_rngs,
output_fns,
dag,
weighted,
significance,
pb));
#endregion INFERENCE
}
