public FunctionOutput <string>[] FastReplace(Excel.Range com, DAG dag, InputSample original, InputSample sample, AST.Address[] outputs, bool replace_original)
{
FunctionOutput <string>[] fo_arr;
if (!_d.TryGetValue(sample, out fo_arr))
{
// replace the COM value
ReplaceExcelRange(com, sample);
// initialize array
fo_arr = new FunctionOutput <string> [outputs.Length];
// grab all outputs
for (var k = 0; k < outputs.Length; k++)
{
// save the output
fo_arr[k] = new FunctionOutput <string>(dag.readCOMValueAtAddress(outputs[k]), sample.GetExcludes());
}
// Add function values to cache
// Don't care about return value
_d.Add(sample, fo_arr);
// restore the COM value
if (replace_original)
{
ReplaceExcelRange(com, original);
}
}
return(fo_arr);
}
private static int PropagateNodeWeight(AST.Address node, DAG dag)
{
// if the node is a formula, recursively
// compute its weight
if (dag.isFormula(node))
{
// get input nodes
var vector_rngs = dag.getFormulaInputVectors(node);
var scinputs = dag.getFormulaSingleCellInputs(node);
var inputs = vector_rngs.SelectMany(vrng => vrng.Addresses()).ToList();
inputs.AddRange(scinputs);
// call recursively and sum components
var weight = 0;
foreach (var input in inputs)
{
weight += PropagateNodeWeight(input, dag);
}
dag.setWeight(node, weight);
return(weight);
}
// node is an input
else
{
dag.setWeight(node, 1);
return(1);
}
}
public FunctionOutput<string>[] FastReplace(Excel.Range com, DAG dag, InputSample original, InputSample sample, AST.Address[] outputs, bool replace_original)
{
FunctionOutput<string>[] fo_arr;
if (!_d.TryGetValue(sample, out fo_arr))
{
// replace the COM value
ReplaceExcelRange(com, sample);
// initialize array
fo_arr = new FunctionOutput<string>[outputs.Length];
// grab all outputs
for (var k = 0; k < outputs.Length; k++)
{
// save the output
fo_arr[k] = new FunctionOutput<string>(dag.readCOMValueAtAddress(outputs[k]), sample.GetExcludes());
}
// Add function values to cache
// Don't care about return value
_d.Add(sample, fo_arr);
// restore the COM value
if (replace_original)
{
ReplaceExcelRange(com, original);
}
}
return fo_arr;
}
public static TreeScore NumericHypothesisTest(DAG dag, AST.Range rangeNode, AST.Address functionNode, FunctionOutput <string>[] boots, string initial_output, bool weighted, double significance)
{
// this function's input cells
var input_cells = rangeNode.Addresses();
var inputs_sz = input_cells.Count();
// scores
var input_exclusion_scores = new TreeScore();
// convert to numeric
var numeric_boots = ConvertToNumericOutput(boots);
// sort
var sorted_num_boots = SortBootstraps(numeric_boots);
// for each excluded index, test whether the original input
// falls outside our bootstrap confidence bounds
for (int i = 0; i < inputs_sz; i++)
{
// default weight
int weight = 1;
// add weight to score if test fails
AST.Address xtree = input_cells[i];
if (weighted)
{
// the weight of the function value of interest
weight = dag.getWeight(functionNode);
}
double outlieriness = RejectNullHypothesis(sorted_num_boots, initial_output, i, significance);
if (outlieriness != 0.0)
{
// get the xth indexed input in input_rng i
if (input_exclusion_scores.ContainsKey(xtree))
{
input_exclusion_scores[xtree] += (int)(weight * outlieriness);
}
else
{
input_exclusion_scores.Add(xtree, (int)(weight * outlieriness));
}
}
else
{
// we need to at least add the value to the tree
if (!input_exclusion_scores.ContainsKey(xtree))
{
input_exclusion_scores.Add(xtree, 0);
}
}
}
return(input_exclusion_scores);
}
// Propagate weights
private static void PropagateWeights(DAG dag)
{
if (dag.containsLoop())
{
throw new ContainsLoopException();
}
// starting set of functions; roots in the forest
var formulas = dag.terminalFormulaNodes(false);
// for each forest
foreach (AST.Address f in formulas)
{
dag.setWeight(f, PropagateNodeWeight(f, dag));
}
}
public static TreeScore StringHypothesisTest(DAG dag, AST.Range rangeNode, AST.Address functionNode, FunctionOutput <string>[] boots, string initial_output, bool weighted, double significance)
{
// this function's input cells
var input_cells = rangeNode.Addresses();
// scores
var iexc_scores = new TreeScore();
var inputs_sz = input_cells.Count();
// exclude each index, in turn
for (int i = 0; i < inputs_sz; i++)
{
// default weight
int weight = 1;
// add weight to score if test fails
AST.Address xtree = input_cells[i];
if (weighted)
{
// the weight of the function value of interest
weight = dag.getWeight(functionNode);
}
if (RejectNullHypothesis(boots, initial_output, i, significance))
{
if (iexc_scores.ContainsKey(xtree))
{
iexc_scores[xtree] += weight;
}
else
{
iexc_scores.Add(xtree, weight);
}
}
else
{
// we need to at least add the value to the tree
if (!iexc_scores.ContainsKey(xtree))
{
iexc_scores.Add(xtree, 0);
}
}
}
return(iexc_scores);
}
public static PrepData PrepSimulation(Excel.Application app, Excel.Workbook wbh, ProgBar pb, bool ignore_parse_errors)
{
// build graph
var dag = new DAG(wbh, app, ignore_parse_errors);
if (dag.containsLoop())
{
throw new DataDebugMethods.ContainsLoopException();
}
pb.IncrementProgress();
// get terminal input and terminal formula nodes once
var terminal_input_nodes = dag.terminalInputVectors();
var terminal_formula_nodes = dag.terminalFormulaNodes(true); ///the boolean indicates whether to use all outputs or not
if (terminal_input_nodes.Length == 0)
{
throw new NoRangeInputs();
}
if (terminal_formula_nodes.Length == 0)
{
throw new NoFormulas();
}
// save original spreadsheet state
CellDict original_inputs = UserSimulation.Utility.SaveInputs(dag);
// force a recalculation before saving outputs, otherwise we may
// erroneously conclude that the procedure did the wrong thing
// based solely on Excel floating-point oddities
UserSimulation.Utility.InjectValues(app, wbh, original_inputs);
// save function outputs
CellDict correct_outputs = UserSimulation.Utility.SaveOutputs(terminal_formula_nodes, dag);
return new PrepData()
{
dag = dag,
original_inputs = original_inputs,
correct_outputs = correct_outputs,
terminal_input_nodes = terminal_input_nodes,
terminal_formula_nodes = terminal_formula_nodes
};
}
// this function returns an address but also updates
// the filtered_high_scores list
public static AST.Address CheckCell_Step(UserResults o,
double significance,
CutoffKind ck,
int nboots,
DAG dag,
Excel.Application app,
bool weighted,
bool all_outputs,
bool run_bootstrap,
HashSet<AST.Address> known_good,
ref List<KeyValuePair<AST.Address, int>> filtered_high_scores,
long max_duration_in_ms,
Stopwatch sw,
ProgBar pb)
{
// Get bootstraps
// The bootstrap should only re-run if there is a correction made,
// not when something is marked as OK (isn't one of the introduced errors)
// The list of suspected cells doesn't change when we mark something as OK,
// we just move on to the next thing in the list
if (run_bootstrap)
{
TreeScore scores = Analysis.DataDebug(nboots, dag, app, weighted, all_outputs, max_duration_in_ms, sw, significance, pb);
// apply a threshold to the scores
filtered_high_scores = ck.applyCutoff(scores, known_good);
}
else //if no corrections were made (a cell was marked as OK, not corrected)
{
//re-filter out cells marked as OK
filtered_high_scores = filtered_high_scores.Where(kvp => !known_good.Contains(kvp.Key)).ToList();
}
if (filtered_high_scores.Count() != 0)
{
// get AST.Address corresponding to most unusual score
return filtered_high_scores[0].Key;
}
else
{
return null;
}
}
private TreeScore _score; // dict of exclusion scores for each input CELL TreeNode
public DataDebugJob(
DAG dag,
FunctionOutput <String>[][] bs,
Dictionary <AST.Address, string> initial_outputs,
AST.Range input,
AST.Address[] output_arr,
bool weighted,
double significance,
ManualResetEvent mre)
{
_dag = dag;
_bs = bs;
_initial_outputs = initial_outputs;
_input = input;
_outputs = output_arr;
_weighted = weighted;
_significance = significance;
_mre = mre;
_score = new TreeScore();
}
public static AST.Address NormalAllOutputs_Step(DAG dag,
Excel.Application app,
Excel.Workbook wb,
HashSet<AST.Address> known_good,
long max_duration_in_ms,
Stopwatch sw)
{
AST.Address flagged_cell = null;
//Generate a normal distribution for the entire set of inputs
var normal_dist = new DataDebugMethods.NormalDistribution(dag.terminalInputVectors(), app);
// Get top outlier
if (normal_dist.getErrorsCount() > 0)
{
for (int i = 0; i < normal_dist.getErrorsCount(); i++)
{
// check for timeout
if (sw.ElapsedMilliseconds > max_duration_in_ms)
{
throw new TimeoutException("Timeout exception in NormalAllOutputs_Step.");
}
var flagged_com = normal_dist.getErrorAtPosition(i);
flagged_cell = AST.Address.AddressFromCOMObject(flagged_com, wb);
if (known_good.Contains(flagged_cell))
{
flagged_cell = null;
}
else
{
break;
}
}
}
return flagged_cell;
}
public static TreeScore StringHypothesisTest(DAG dag, AST.Range rangeNode, AST.Address functionNode, FunctionOutput<string>[] boots, string initial_output, bool weighted, double significance)
{
// this function's input cells
var input_cells = rangeNode.Addresses();
// scores
var iexc_scores = new TreeScore();
var inputs_sz = input_cells.Count();
// exclude each index, in turn
for (int i = 0; i < inputs_sz; i++)
{
// default weight
int weight = 1;
// add weight to score if test fails
AST.Address xtree = input_cells[i];
if (weighted)
{
// the weight of the function value of interest
weight = dag.getWeight(functionNode);
}
if (RejectNullHypothesis(boots, initial_output, i, significance))
{
if (iexc_scores.ContainsKey(xtree))
{
iexc_scores[xtree] += weight;
}
else
{
iexc_scores.Add(xtree, weight);
}
}
else
{
// we need to at least add the value to the tree
if (!iexc_scores.ContainsKey(xtree))
{
iexc_scores.Add(xtree, 0);
}
}
}
return iexc_scores;
}
public static Dictionary<AST.Address, string> StoreOutputs(AST.Address[] outputs, DAG dag)
{
// output dict
var d = new Dictionary<AST.Address, string>();
// partition all of the output addresses by their worksheet
var addr_groups = outputs.GroupBy(addr => dag.getCOMRefForAddress(addr).WorksheetName);
// for each worksheet, do an array read of the formulas
foreach (IEnumerable<AST.Address> ws_fns in addr_groups)
{
// get worksheet used range
var fstcr = dag.getCOMRefForAddress(ws_fns.First());
var rng = fstcr.Worksheet.UsedRange;
// get used range dimensions
var left = rng.Column;
var right = rng.Columns.Count + left - 1;
var top = rng.Row;
var bottom = rng.Rows.Count + top - 1;
// get names
var wsname = new FSharpOption<string>(fstcr.WorksheetName);
var wbname = new FSharpOption<string>(fstcr.WorkbookName);
var path = fstcr.Path;
// sometimes the used range is a range
if (left != right || top != bottom)
{
// y is the first index
// x is the second index
object[,] data = rng.Value2; // fast array read
var x_del = left - 1;
var y_del = top - 1;
foreach (AST.Address addr in ws_fns)
{
// construct address in formulas array
var x = addr.X - x_del;
var y = addr.Y - y_del;
// get string
String s = System.Convert.ToString(data[y, x]);
if (String.IsNullOrWhiteSpace(s))
{
d.Add(addr, "");
}
else
{
d.Add(addr, s);
}
}
}
// and other times it is a single cell
else
{
// construct the appropriate AST.Address
AST.Address addr = AST.Address.NewFromR1C1(top, left, wsname, wbname, path);
// make certain that it is actually a string
String s = System.Convert.ToString(rng.Value2);
// add to dictionary, as appropriate
if (String.IsNullOrWhiteSpace(s))
{
d.Add(addr, "");
}
else
{
d.Add(addr, s);
}
}
}
return d;
}
public static TreeScore NumericHypothesisTest(DAG dag, AST.Range rangeNode, AST.Address functionNode, FunctionOutput<string>[] boots, string initial_output, bool weighted, double significance)
{
// this function's input cells
var input_cells = rangeNode.Addresses();
var inputs_sz = input_cells.Count();
// scores
var input_exclusion_scores = new TreeScore();
// convert to numeric
var numeric_boots = ConvertToNumericOutput(boots);
// sort
var sorted_num_boots = SortBootstraps(numeric_boots);
// for each excluded index, test whether the original input
// falls outside our bootstrap confidence bounds
for (int i = 0; i < inputs_sz; i++)
{
// default weight
int weight = 1;
// add weight to score if test fails
AST.Address xtree = input_cells[i];
if (weighted)
{
// the weight of the function value of interest
weight = dag.getWeight(functionNode);
}
double outlieriness = RejectNullHypothesis(sorted_num_boots, initial_output, i, significance);
if (outlieriness != 0.0)
{
// get the xth indexed input in input_rng i
if (input_exclusion_scores.ContainsKey(xtree))
{
input_exclusion_scores[xtree] += (int)(weight * outlieriness);
}
else
{
input_exclusion_scores.Add(xtree, (int)(weight * outlieriness));
}
}
else
{
// we need to at least add the value to the tree
if (!input_exclusion_scores.ContainsKey(xtree))
{
input_exclusion_scores.Add(xtree, 0);
}
}
}
return input_exclusion_scores;
}
public static TreeScore Inference(
int num_bootstraps,
InputSample[][] resamples,
Dictionary<AST.Range, InputSample> initial_inputs,
Dictionary<AST.Address, string> initial_outputs,
AST.Range[] input_arr,
AST.Address[] output_arr,
DAG dag,
bool weighted,
double significance,
ProgBar pb)
{
// synchronization token
object lock_token = new Object();
// init thread event notification array
var mres = new ManualResetEvent[input_arr.Length];
// init job storage
var ddjs = new DataDebugJob[input_arr.Length];
// init started jobs count
var sjobs = 0;
// init completed jobs count
var cjobs = 0;
// last-ditch effort flag
bool last_try = false;
// init score storage
var scores = new TreeScore();
for (int i = 0; i < input_arr.Length; i++)
{
try
{
#region BOOTSTRAP
// bootstrapping is done in the parent STA thread because
// the .NET threading model prohibits thread pools (which
// are MTA) from accessing STA COM objects directly.
// alloc bootstrap storage for each output (f), for each resample (b)
FunctionOutput<string>[][] bs = new FunctionOutput<string>[initial_outputs.Count][];
for (int f = 0; f < initial_outputs.Count; f++)
{
bs[f] = new FunctionOutput<string>[num_bootstraps];
}
// init memoization table for input vector i
var memo = new BootMemo();
// fetch the input range TreeNode
var input = input_arr[i];
// fetch the input range COM object
var com = dag.getCOMRefForRange(input).Range;
// compute outputs
// replace the values of the COM object with the jth bootstrap,
// save all function outputs, and
// restore the original input
for (var b = 0; b < num_bootstraps; b++)
{
// lookup outputs from memo table; otherwise do replacement, compute outputs, store them in table, and return them
FunctionOutput<string>[] fos = memo.FastReplace(com, dag, initial_inputs[input], resamples[i][b], output_arr, false);
for (var f = 0; f < output_arr.Length; f++)
{
bs[f][b] = fos[f];
}
}
// restore the original inputs; faster to do once, after bootstrapping is done
BootMemo.ReplaceExcelRange(com, initial_inputs[input]);
// TODO: restore formulas if it turns out that they were overwrittern
// this should never be the case
#endregion BOOTSTRAP
#region HYPOTHESIS_TEST
// cancellation token
mres[i] = new ManualResetEvent(false);
// set up job
ddjs[i] = new DataDebugJob(
dag,
bs,
initial_outputs,
input_arr[i],
output_arr,
weighted,
significance,
mres[i]
);
sjobs++;
// hand job to thread pool
ThreadPool.QueueUserWorkItem(ddjs[i].threadPoolCallback, i);
#endregion HYPOTHESIS_TEST
// update progress bar
pb.IncrementProgress();
}
catch (System.OutOfMemoryException e)
{
if (!last_try)
{
// If there are no more jobs running, but
// we still can't allocate memory, try invoking
// GC and then trying again
cjobs = mres.Count(mre => mre.WaitOne(0));
if (sjobs - cjobs == 0)
{
GC.Collect();
last_try = true;
}
}
else
{
// we just don't have enough memory
throw e;
}
// wait for any of the 0..i-1 work items
// to complete and try again
WaitHandle.WaitAny(mres.Take(i).ToArray());
}
}
// Do not proceed until all hypothesis tests are done.
// WaitHandle.WaitAll cannot be called on an STA thread which
// is why we call WaitOne in a loop.
// Merge scores as data becomes available.
for (int i = 0; i < input_arr.Length; i++)
{
mres[i].WaitOne();
scores = DictAdd(scores, ddjs[i].Result);
}
return scores;
}
// Get dictionary of inputs and the error they produce
public Dictionary<AST.Address, Tuple<string, double>> TopOfKErrors(AST.Address[] terminal_formula_nodes, CellDict inputs, int k, CellDict correct_outputs, Excel.Application app, Excel.Workbook wb, string classification_file, DAG dag)
{
var eg = new ErrorGenerator();
var c = Classification.Deserialize(classification_file);
var max_error_produced_dictionary = new Dictionary<AST.Address, Tuple<string, double>>();
foreach (KeyValuePair<AST.Address,string> pair in inputs)
{
AST.Address addr = pair.Key;
string orig_value = pair.Value;
//Load in the classification's dictionaries
double max_error_produced = 0.0;
string max_error_string = "";
// get k strings, in parallel
string[] errorstrings = eg.GenerateErrorStrings(orig_value, c, k);
for (int i = 0; i < k; i++)
{
CellDict cd = new CellDict();
cd.Add(addr, errorstrings[i]);
//inject the typo
Utility.InjectValues(app, wb, cd);
// save function outputs
CellDict incorrect_outputs = Utility.SaveOutputs(terminal_formula_nodes, dag);
//remove the typo that was introduced
cd.Clear();
cd.Add(addr, orig_value);
Utility.InjectValues(app, wb, cd);
double total_error = Utility.CalculateTotalError(correct_outputs, incorrect_outputs);
//keep track of the largest observed max error
if (total_error > max_error_produced)
{
max_error_produced = total_error;
max_error_string = errorstrings[i];
}
}
//Add entry for this TreeNode in our dictionary with its max_error_produced
max_error_produced_dictionary.Add(addr, new Tuple<string, double>(max_error_string, max_error_produced));
}
return max_error_produced_dictionary;
}
// 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
}
private static Dictionary<AST.Range, InputSample> StoreInputs(AST.Range[] inputs, DAG dag)
{
var d = new Dictionary<AST.Range, InputSample>();
foreach (AST.Range input_range in inputs)
{
var com = dag.getCOMRefForRange(input_range);
var s = new InputSample(com.Height, com.Width);
// store the entire COM array as a multiarray
// in one fell swoop.
s.AddArray(com.Range.Value2);
// add stored input to dict
d.Add(input_range, s);
// this is to force excel to recalculate its outputs
// exactly the same way that it will for our bootstraps
BootMemo.ReplaceExcelRange(com.Range, s);
}
return d;
}
public static Dictionary <AST.Address, string> StoreOutputs(AST.Address[] outputs, DAG dag)
{
// output dict
var d = new Dictionary <AST.Address, string>();
// partition all of the output addresses by their worksheet
var addr_groups = outputs.GroupBy(addr => dag.getCOMRefForAddress(addr).WorksheetName);
// for each worksheet, do an array read of the formulas
foreach (IEnumerable <AST.Address> ws_fns in addr_groups)
{
// get worksheet used range
var fstcr = dag.getCOMRefForAddress(ws_fns.First());
var rng = fstcr.Worksheet.UsedRange;
// get used range dimensions
var left = rng.Column;
var right = rng.Columns.Count + left - 1;
var top = rng.Row;
var bottom = rng.Rows.Count + top - 1;
// get names
var wsname = new FSharpOption <string>(fstcr.WorksheetName);
var wbname = new FSharpOption <string>(fstcr.WorkbookName);
var path = fstcr.Path;
// sometimes the used range is a range
if (left != right || top != bottom)
{
// y is the first index
// x is the second index
object[,] data = rng.Value2; // fast array read
var x_del = left - 1;
var y_del = top - 1;
foreach (AST.Address addr in ws_fns)
{
// construct address in formulas array
var x = addr.X - x_del;
var y = addr.Y - y_del;
// get string
String s = System.Convert.ToString(data[y, x]);
if (String.IsNullOrWhiteSpace(s))
{
d.Add(addr, "");
}
else
{
d.Add(addr, s);
}
}
}
// and other times it is a single cell
else
{
// construct the appropriate AST.Address
AST.Address addr = AST.Address.NewFromR1C1(top, left, wsname, wbname, path);
// make certain that it is actually a string
String s = System.Convert.ToString(rng.Value2);
// add to dictionary, as appropriate
if (String.IsNullOrWhiteSpace(s))
{
d.Add(addr, "");
}
else
{
d.Add(addr, s);
}
}
}
return(d);
}
public static TreeScore Inference(
int num_bootstraps,
InputSample[][] resamples,
Dictionary <AST.Range, InputSample> initial_inputs,
Dictionary <AST.Address, string> initial_outputs,
AST.Range[] input_arr,
AST.Address[] output_arr,
DAG dag,
bool weighted,
double significance,
ProgBar pb)
{
// synchronization token
object lock_token = new Object();
// init thread event notification array
var mres = new ManualResetEvent[input_arr.Length];
// init job storage
var ddjs = new DataDebugJob[input_arr.Length];
// init started jobs count
var sjobs = 0;
// init completed jobs count
var cjobs = 0;
// last-ditch effort flag
bool last_try = false;
// init score storage
var scores = new TreeScore();
for (int i = 0; i < input_arr.Length; i++)
{
try
{
#region BOOTSTRAP
// bootstrapping is done in the parent STA thread because
// the .NET threading model prohibits thread pools (which
// are MTA) from accessing STA COM objects directly.
// alloc bootstrap storage for each output (f), for each resample (b)
FunctionOutput <string>[][] bs = new FunctionOutput <string> [initial_outputs.Count][];
for (int f = 0; f < initial_outputs.Count; f++)
{
bs[f] = new FunctionOutput <string> [num_bootstraps];
}
// init memoization table for input vector i
var memo = new BootMemo();
// fetch the input range TreeNode
var input = input_arr[i];
// fetch the input range COM object
var com = dag.getCOMRefForRange(input).Range;
// compute outputs
// replace the values of the COM object with the jth bootstrap,
// save all function outputs, and
// restore the original input
for (var b = 0; b < num_bootstraps; b++)
{
// lookup outputs from memo table; otherwise do replacement, compute outputs, store them in table, and return them
FunctionOutput <string>[] fos = memo.FastReplace(com, dag, initial_inputs[input], resamples[i][b], output_arr, false);
for (var f = 0; f < output_arr.Length; f++)
{
bs[f][b] = fos[f];
}
}
// restore the original inputs; faster to do once, after bootstrapping is done
BootMemo.ReplaceExcelRange(com, initial_inputs[input]);
// TODO: restore formulas if it turns out that they were overwrittern
// this should never be the case
#endregion BOOTSTRAP
#region HYPOTHESIS_TEST
// cancellation token
mres[i] = new ManualResetEvent(false);
// set up job
ddjs[i] = new DataDebugJob(
dag,
bs,
initial_outputs,
input_arr[i],
output_arr,
weighted,
significance,
mres[i]
);
sjobs++;
// hand job to thread pool
ThreadPool.QueueUserWorkItem(ddjs[i].threadPoolCallback, i);
#endregion HYPOTHESIS_TEST
// update progress bar
pb.IncrementProgress();
}
catch (System.OutOfMemoryException e)
{
if (!last_try)
{
// If there are no more jobs running, but
// we still can't allocate memory, try invoking
// GC and then trying again
cjobs = mres.Count(mre => mre.WaitOne(0));
if (sjobs - cjobs == 0)
{
GC.Collect();
last_try = true;
}
}
else
{
// we just don't have enough memory
throw e;
}
// wait for any of the 0..i-1 work items
// to complete and try again
WaitHandle.WaitAny(mres.Take(i).ToArray());
}
}
// Do not proceed until all hypothesis tests are done.
// WaitHandle.WaitAll cannot be called on an STA thread which
// is why we call WaitOne in a loop.
// Merge scores as data becomes available.
for (int i = 0; i < input_arr.Length; i++)
{
mres[i].WaitOne();
scores = DictAdd(scores, ddjs[i].Result);
}
return(scores);
}
private static Dictionary <AST.Range, InputSample> StoreInputs(AST.Range[] inputs, DAG dag)
{
var d = new Dictionary <AST.Range, InputSample>();
foreach (AST.Range input_range in inputs)
{
var com = dag.getCOMRefForRange(input_range);
var s = new InputSample(com.Height, com.Width);
// store the entire COM array as a multiarray
// in one fell swoop.
s.AddArray(com.Range.Value2);
// add stored input to dict
d.Add(input_range, s);
// this is to force excel to recalculate its outputs
// exactly the same way that it will for our bootstraps
BootMemo.ReplaceExcelRange(com.Range, s);
}
return(d);
}
// 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 void Analyze(long max_duration_in_ms)
{
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
using (var pb = new ProgBar())
{
// Disable screen updating during analysis to speed things up
_app.ScreenUpdating = false;
// Build dependency graph (modifies data)
try
{
_dag = new DAG(_app.ActiveWorkbook, _app, IGNORE_PARSE_ERRORS);
var num_input_cells = _dag.numberOfInputCells();
}
catch (ExcelParserUtility.ParseException e)
{
// cleanup UI and then rethrow
_app.ScreenUpdating = true;
throw e;
}
if (_dag.terminalInputVectors().Length == 0)
{
System.Windows.Forms.MessageBox.Show("This spreadsheet contains no vector-input functions.");
_app.ScreenUpdating = true;
_flaggable = new KeyValuePair<AST.Address, int>[0];
return;
}
// Get bootstraps
var scores = Analysis.DataDebug(NBOOTS,
_dag,
_app,
weighted: USE_WEIGHTS,
all_outputs: CONSIDER_ALL_OUTPUTS,
max_duration_in_ms: max_duration_in_ms,
sw: sw,
significance: _tool_significance,
pb: pb)
.OrderByDescending(pair => pair.Value).ToArray();
if (_debug_mode)
{
var score_str = String.Join("\n", scores.Take(10).Select(score => score.Key.A1FullyQualified() + " -> " + score.Value.ToString()));
System.Windows.Forms.MessageBox.Show(score_str);
System.Windows.Forms.Clipboard.SetText(score_str);
}
List<KeyValuePair<AST.Address, int>> high_scores = new List<KeyValuePair<AST.Address, int>>();
// calculate cutoff idnex
int thresh = scores.Length - Convert.ToInt32(scores.Length * _tool_significance);
// filter out cells that are...
_flaggable = scores.Where(pair => pair.Value >= scores[thresh].Value) // below threshold
.Where(pair => !_known_good.Contains(pair.Key)) // known to be good
.Where(pair => pair.Value != 0).ToArray(); // score == 0
// Enable screen updating when we're done
_app.ScreenUpdating = true;
sw.Stop();
}
}
private static int PropagateNodeWeight(AST.Address node, DAG dag)
{
// if the node is a formula, recursively
// compute its weight
if (dag.isFormula(node))
{
// get input nodes
var vector_rngs = dag.getFormulaInputVectors(node);
var scinputs = dag.getFormulaSingleCellInputs(node);
var inputs = vector_rngs.SelectMany(vrng => vrng.Addresses()).ToList();
inputs.AddRange(scinputs);
// call recursively and sum components
var weight = 0;
foreach (var input in inputs)
{
weight += PropagateNodeWeight(input, dag);
}
dag.setWeight(node, weight);
return weight;
}
// node is an input
else
{
dag.setWeight(node, 1);
return 1;
}
}
// Propagate weights
private static void PropagateWeights(DAG dag)
{
if (dag.containsLoop())
{
throw new ContainsLoopException();
}
// starting set of functions; roots in the forest
var formulas = dag.terminalFormulaNodes(false);
// for each forest
foreach (AST.Address f in formulas)
{
dag.setWeight(f, PropagateNodeWeight(f, dag));
}
}
// save all of the values of the spreadsheet that
// participate in any computation
public static CellDict SaveInputs(DAG dag)
{
try
{
var cd = new CellDict();
foreach (var addr in dag.allComputationCells())
{
cd.Add(addr, dag.readCOMValueAtAddress(addr));
}
return cd;
}
catch (Exception e)
{
throw new Exception(String.Format("Failed in SaveInputs: {0}", e.Message));
}
}
public DataDebugJob(
DAG dag,
FunctionOutput<String>[][] bs,
Dictionary<AST.Address, string> initial_outputs,
AST.Range input,
AST.Address[] output_arr,
bool weighted,
double significance,
ManualResetEvent mre)
{
_dag = dag;
_bs = bs;
_initial_outputs = initial_outputs;
_input = input;
_outputs = output_arr;
_weighted = weighted;
_significance = significance;
_mre = mre;
_score = new TreeScore();
}
// Get dictionary of inputs and the error they produce
public static CellDict GenImportantErrors(AST.Address[] output_nodes,
CellDict inputs,
int k, // number of alternatives to consider
CellDict correct_outputs,
Excel.Application app,
Excel.Workbook wb,
Classification c,
DAG dag)
{
var eg = new ErrorGenerator();
var max_error_produced_dictionary = new Dictionary<AST.Address, Tuple<string, double>>();
foreach (KeyValuePair<AST.Address, string> pair in inputs)
{
AST.Address addr = pair.Key;
string orig_value = pair.Value;
//Load in the classification's dictionaries
double max_error_produced = 0.0;
string max_error_string = "";
// get k strings
string[] errorstrings = eg.GenerateErrorStrings(orig_value, c, k);
for (int i = 0; i < k; i++)
{
CellDict cd = new CellDict();
cd.Add(addr, errorstrings[i]);
//inject the typo
InjectValues(app, wb, cd);
// save function outputs
CellDict incorrect_outputs = SaveOutputs(output_nodes, dag);
//remove the typo that was introduced
cd.Clear();
cd.Add(addr, orig_value);
InjectValues(app, wb, cd);
double total_error = Utility.CalculateTotalError(correct_outputs, incorrect_outputs);
//keep track of the largest observed max error
if (total_error > max_error_produced)
{
max_error_produced = total_error;
max_error_string = errorstrings[i];
}
}
//Add entry for this TreeNode in our dictionary with its max_error_produced
max_error_produced_dictionary.Add(addr, new Tuple<string, double>(max_error_string, max_error_produced));
}
// sort by max_error_produced
var maxen = max_error_produced_dictionary.OrderByDescending(pair => pair.Value.Item2).Select(pair => new Tuple<AST.Address, string>(pair.Key, pair.Value.Item1)).ToList();
return maxen.Take((int)Math.Ceiling(0.05 * inputs.Count)).ToDictionary(tup => tup.Item1, tup => tup.Item2);
}
// returns the number of cells inspected
public int Run(int nboots, // number of bootstraps
string xlfile, // name of the workbook
double significance, // significance threshold for test
CutoffKind ck, // kind of threshold function to use
Excel.Application app, // reference to Excel app
Classification c, // data from which to generate errors
Random r, // a random number generator
AnalysisType analysisType, // the type of analysis to run
bool weighted, // should we weigh things?
bool all_outputs, // if !all_outputs, we only consider terminal outputs
DAG dag,
Excel.Workbook wb,
AST.Address[] terminal_formula_cells,
AST.Range[] terminal_input_vectors,
CellDict original_inputs,
CellDict correct_outputs,
long max_duration_in_ms,
String logfile, //filename for the output log
ProgBar pb
)
{
//set wbname and path
_wb_name = xlfile;
_wb_path = wb.Path;
_analysis_type = analysisType;
_significance = significance;
_all_outputs = all_outputs;
_weighted = weighted;
//Now we want to inject the errors from _errors
Utility.InjectValues(app, wb, _errors);
// save function outputs
CellDict incorrect_outputs = Utility.SaveOutputs(terminal_formula_cells, dag);
//Time the removal of errors
Stopwatch sw = new Stopwatch();
sw.Start();
// remove errors until none remain; MODIFIES WORKBOOK
_user = SimulateUser(nboots, significance, ck, dag, original_inputs, _errors, correct_outputs, wb, app, analysisType, weighted, all_outputs, max_duration_in_ms, sw, logfile, pb);
sw.Stop();
TimeSpan elapsed = sw.Elapsed;
_analysis_time = elapsed.TotalSeconds;
// save partially-corrected outputs
var partially_corrected_outputs = Utility.SaveOutputs(terminal_formula_cells, dag);
// compute total relative error
_error = Utility.CalculateNormalizedError(correct_outputs, partially_corrected_outputs, _user.max_errors);
_total_relative_error = Utility.TotalRelativeError(_error);
// compute starting total relative error (normalized by max_errors)
ErrorDict starting_error = Utility.CalculateNormalizedError(correct_outputs, incorrect_outputs, _user.max_errors);
_initial_total_relative_error = Utility.TotalRelativeError(starting_error);
// effort
_max_effort = dag.allCells().Length;
_effort = (_user.true_positives.Count + _user.false_positives.Count);
_expended_effort = (double)_effort / (double)_max_effort;
// compute average precision
// AveP = (\sum_{k=1}^n (P(k) * rel(k))) / |total positives|
// where P(k) is the precision at threshold k,
// rel(k) = \{ 1 if item at k is a true positive, 0 otherwise
_average_precision = _user.PrecRel_at_k.Sum() / (double)_errors.Count;
// restore original values
Utility.InjectValues(app, wb, original_inputs);
_tree_construct_time = dag.AnalysisMilliseconds / 1000.0;
// flag that we're done; safe to print output results
_simulation_run = true;
// return the number of cells inspected
return _effort;
}
public static AST.Address NormalPerRange_Step(DAG dag,
Excel.Workbook wb,
HashSet<AST.Address> known_good,
long max_duration_in_ms,
Stopwatch sw)
{
AST.Address flagged_cell = null;
//Generate normal distributions for every input range until an error is found
//Then break out of the loop and report it.
foreach (var vect_addr in dag.allVectors())
{
var normal_dist = new DataDebugMethods.NormalDistribution(dag.getCOMRefForRange(vect_addr).Range);
// Get top outlier which has not been inspected already
if (normal_dist.getErrorsCount() > 0)
{
for (int i = 0; i < normal_dist.getErrorsCount(); i++)
{
// check for timeout
if (sw.ElapsedMilliseconds > max_duration_in_ms)
{
throw new TimeoutException("Timeout exception in NormalPerRange_Step.");
}
var flagged_com = normal_dist.getErrorAtPosition(i);
flagged_cell = AST.Address.AddressFromCOMObject(flagged_com, wb);
if (known_good.Contains(flagged_cell))
{
flagged_cell = null;
}
else
{
break;
}
}
}
//If a cell is flagged, do not move on to the next range (if you do, you'll overwrite the flagged_cell
if (flagged_cell != null)
{
break;
}
}
return flagged_cell;
}
// save spreadsheet outputs to a CellDict
public static CellDict SaveOutputs(AST.Address[] formula_nodes, DAG dag)
{
var cd = new CellDict();
foreach (AST.Address formula_addr in formula_nodes)
{
// throw an exception in debug mode, because this should never happen
#if DEBUG
if (!(bool)(dag.getCOMRefForAddress(formula_addr).Range.HasFormula))
{
String fstring = dag.getFormulaAtAddress(formula_addr);
throw new Exception("Formula address is not a formula.");
}
#endif
// save value
if (cd.ContainsKey(formula_addr))
{
throw new Exception(String.Format("Failed in SaveOutputs."));
}
else
{
cd.Add(formula_addr, dag.readCOMValueAtAddress(formula_addr));
}
}
return cd;
}
// For running a simulation from the batch runner
// returns the number of cells inspected
public int RunFromBatch(int nboots, // number of bootstraps
string xlfile, // name of the workbook
double significance, // significance threshold for test
Excel.Application app, // reference to Excel app
CutoffKind ck,
Classification c, // data from which to generate errors
Random r, // a random number generator
AnalysisType analysisType, // the type of analysis to run
bool weighted, // should we weigh things?
bool all_outputs, // if !all_outputs, we only consider terminal outputs
DAG dag, // the computation tree of the spreadsheet
Excel.Workbook wb, // the workbook being analyzed
CellDict errors, // the errors that will be introduced in the spreadsheet
AST.Range[] terminal_input_vectors, // the inputs
AST.Address[] terminal_formula_cells, // the outputs
CellDict original_inputs, // original values of the inputs
CellDict correct_outputs, // the correct outputs
long max_duration_in_ms,
String logfile //filename for the output log
)
{
if (terminal_input_vectors.Length == 0)
{
throw new NoRangeInputs();
}
if (original_inputs.Count() == 0)
{
throw new NoFormulas();
}
_errors = errors;
// find the error with the largest magnitude
// this is mostly useful for the single-perturbation experiments
var num_errs = _errors.Where(pair => Utility.BothNumbers(pair.Value, original_inputs[pair.Key]));
var str_errs = _errors.Where(pair => !Utility.BothNumbers(pair.Value, original_inputs[pair.Key]));
_num_max_err_diff_mag = num_errs.Count() != 0 ? num_errs.Select(
(KeyValuePair<AST.Address, string> pair) =>
Utility.NumericalMagnitudeChange(Double.Parse(pair.Value), Double.Parse(original_inputs[pair.Key]))
).Max() : 0;
_str_max_err_diff_mag = str_errs.Count() != 0 ? str_errs.Select(
(KeyValuePair<AST.Address, string> pair) =>
Utility.StringMagnitudeChange(pair.Value, original_inputs[pair.Key])
).Max() : 0;
// find the output with the largest magnitude
var num_outs = correct_outputs.Where(pair => Utility.IsNumber(pair.Value));
var str_outs = correct_outputs.Where(pair => !Utility.IsNumber(pair.Value));
_num_max_output_diff_mag = num_outs.Count() != 0 ? num_outs.Select(
(KeyValuePair<AST.Address, string> pair) =>
Utility.NumericalMagnitudeChange(Double.Parse(pair.Value), Double.Parse(correct_outputs[pair.Key]))
).Max() : 0;
_str_max_output_diff_mag = str_outs.Count() != 0 ? str_outs.Select(
(KeyValuePair<AST.Address, string> pair) =>
Utility.StringMagnitudeChange(pair.Value, correct_outputs[pair.Key])
).Max() : 0;
return Run(nboots, xlfile, significance, ck, app, c, r, analysisType, weighted, all_outputs, dag, wb, terminal_formula_cells, terminal_input_vectors, original_inputs, correct_outputs, max_duration_in_ms, logfile, null);
}
public void TestGetFormulaRanges()
{
var mwb = new MockWorkbook();
// rnd, for random formulae assignment
Random rand = new Random();
// gin up some formulae
Tuple<string, string>[] fs = {new Tuple<string,string>("B4", "=COUNT(A1:A5)"),
new Tuple<string,string>("A6", "=SUM(B5:B40)"),
new Tuple<string,string>("Z2", "=AVERAGE(A1:E1)"),
new Tuple<string,string>("B44", "=MEDIAN(D4:D9)")};
// to keep track of what we did
var d = new System.Collections.Generic.Dictionary<Excel.Worksheet, System.Collections.Generic.List<Tuple<string, string>>>();
// add the formulae to the worksheets, randomly
foreach (Excel.Worksheet w in mwb.GetWorksheets())
{
// init list for each worksheet
d[w] = new System.Collections.Generic.List<Tuple<string, string>>();
// add the formulae, randomly
foreach (var f in fs)
{
if (rand.Next(0, 2) == 0)
{
w.Range[f.Item1, f.Item1].Formula = f.Item2;
// keep track of what we did
d[w].Add(f);
}
}
// we need at least one formula, so add one if the above procedure did not
if (d[w].Count() == 0)
{
w.Range[fs[0].Item1, fs[0].Item1].Formula = fs[0].Item2;
d[w].Add(fs[0]);
}
}
// init DAG
var dag = new DAG(mwb.GetWorkbook(), mwb.GetApplication(), false);
// get the formulas; 1 formula per worksheet
var formulas = dag.getAllFormulaAddrs();
// there should be e.Count + 3 entries
// don't forget: workbooks have 3 blank worksheets by default
var expected = d.Values.Select(v => v.Count).Aggregate((acc, c) => acc + c);
if (formulas.Length != expected)
{
throw new Exception("DAG.getAllFormulaAddrs() should return " + expected + " elements but instead returns " + formulas.Length + ".");
}
bool all_ok = true;
// make sure that each worksheet's range has the formulas that it should
var f_wsgroups = formulas.GroupBy(f => f.GetCOMObject(mwb.GetApplication()).Worksheet);
foreach (var pair in f_wsgroups)
{
// get formulas in this worksheet
var r = pair.Key.UsedRange.SpecialCells(Excel.XlCellType.xlCellTypeFormulas);
// check that all formulae for this worksheet are accounted for
bool r_ok = d[r.Worksheet].Aggregate(true, (bool acc, Tuple<string, string> f) =>
{
bool found = false;
foreach (Excel.Range cell in r)
{
if (String.Equals((string)cell.Formula, f.Item2))
{
found = true;
}
}
return acc && found;
});
all_ok = all_ok && r_ok;
}
if (!all_ok)
{
throw new Exception("ConstructTree.GetFormulaRanges() failed to return all of the formulae that were added.");
}
}
// remove errors until none remain
private UserResults SimulateUser(int nboots,
double significance,
CutoffKind ck,
DAG dag,
CellDict original_inputs,
CellDict errord,
CellDict correct_outputs,
Excel.Workbook wb,
Excel.Application app,
AnalysisType analysis_type,
bool weighted,
bool all_outputs,
long max_duration_in_ms,
Stopwatch sw,
String logfile,
ProgBar pb
)
{
// init user results data structure
var o = new UserResults();
HashSet<AST.Address> known_good = new HashSet<AST.Address>();
// initialize procedure
var errors_remain = true;
var max_errors = new ErrorDict();
var incorrect_outputs = Utility.SaveOutputs(dag.terminalFormulaNodes(all_outputs), dag);
var errors_found = 0;
var number_of_true_errors = errord.Count;
Utility.UpdatePerFunctionMaxError(correct_outputs, incorrect_outputs, max_errors);
// the corrected state of the spreadsheet
CellDict partially_corrected_outputs = correct_outputs.ToDictionary(p => p.Key, p => p.Value);
// remove errors loop
var cells_inspected = 0;
List<KeyValuePair<AST.Address, int>> filtered_high_scores = null;
bool correction_made = true;
while (errors_remain)
{
Console.Write(".");
AST.Address flagged_cell = null;
// choose the appropriate test
if (analysis_type == AnalysisType.CheckCell5 ||
analysis_type == AnalysisType.CheckCell10
)
{
flagged_cell = SimulationStep.CheckCell_Step(o,
significance,
ck,
nboots,
dag,
app,
weighted,
all_outputs,
correction_made,
known_good,
ref filtered_high_scores,
max_duration_in_ms,
sw,
pb);
} else if (analysis_type == AnalysisType.NormalPerRange)
{
flagged_cell = SimulationStep.NormalPerRange_Step(dag, wb, known_good, max_duration_in_ms, sw);
}
else if (analysis_type == AnalysisType.NormalAllInputs)
{
flagged_cell = SimulationStep.NormalAllOutputs_Step(dag, app, wb, known_good, max_duration_in_ms, sw);
}
// stop if the test no longer returns anything or if
// the test is simply done inspecting based on a fixed threshold
if (flagged_cell == null || (ck.isCountBased && ck.Threshold == cells_inspected))
{
errors_remain = false;
}
else // a cell was flagged
{
//cells_inspected should only be incremented when a cell is actually flagged. If nothing is flagged,
//then nothing is inspected, so cells_inspected doesn't increase.
cells_inspected += 1;
// check to see if the flagged value is actually an error
if (errord.ContainsKey(flagged_cell))
{
correction_made = true;
errors_found += 1;
// P(k) * rel(k)
o.PrecRel_at_k.Add(errors_found / (double)cells_inspected);
o.true_positives.Add(flagged_cell);
// correct flagged cell
flagged_cell.GetCOMObject(app).Value2 = original_inputs[flagged_cell];
Utility.UpdatePerFunctionMaxError(correct_outputs, partially_corrected_outputs, max_errors);
// compute total error after applying this correction
var current_total_error = Utility.CalculateTotalError(correct_outputs, partially_corrected_outputs);
o.current_total_error.Add(current_total_error);
// save outputs
partially_corrected_outputs = Utility.SaveOutputs(dag.terminalFormulaNodes(all_outputs), dag);
}
else
{
correction_made = false;
// numerator is 0 here because rel(k) = 0 when no error was found
o.PrecRel_at_k.Add(0.0);
o.false_positives.Add(flagged_cell);
}
// mark it as known good -- at this point the cell has been
// 'inspected' regardless of whether it was an error
// It was either corrected or marked as OK
known_good.Add(flagged_cell);
// compute output error magnitudes
var output_error_magnitude = Utility.MeanErrorMagnitude(partially_corrected_outputs, correct_outputs);
// compute input error magnitude
double num_input_error_magnitude;
double str_input_error_magnitude;
if (errord.ContainsKey(flagged_cell))
{
if (Utility.BothNumbers(errord[flagged_cell], original_inputs[flagged_cell]))
{
num_input_error_magnitude = Utility.NumericalMagnitudeChange(Double.Parse(errord[flagged_cell]), Double.Parse(original_inputs[flagged_cell]));
str_input_error_magnitude = 0;
}
else
{
num_input_error_magnitude = 0;
str_input_error_magnitude = Utility.StringMagnitudeChange(errord[flagged_cell], original_inputs[flagged_cell]);
}
}
else
{
num_input_error_magnitude = 0;
str_input_error_magnitude = 0;
}
// write error log
var logentry = new LogEntry(analysis_type,
wb.Name,
flagged_cell,
original_inputs[flagged_cell],
errord.ContainsKey(flagged_cell) ? errord[flagged_cell] : original_inputs[flagged_cell],
output_error_magnitude,
num_input_error_magnitude,
str_input_error_magnitude,
true,
correction_made,
significance,
ck.Threshold);
logentry.WriteLog(logfile);
_error_log.Add(logentry);
}
}
// find all of the false negatives
o.false_negatives = Utility.GetFalseNegatives(o.true_positives, o.false_positives, errord);
o.max_errors = max_errors;
var last_out_err_mag = Utility.MeanErrorMagnitude(partially_corrected_outputs, correct_outputs);
// write out all false negative information
foreach (AST.Address fn in o.false_negatives)
{
double num_input_error_magnitude;
double str_input_error_magnitude;
if (Utility.BothNumbers(errord[fn], original_inputs[fn]))
{
num_input_error_magnitude = Utility.NumericalMagnitudeChange(Double.Parse(errord[fn]), Double.Parse(original_inputs[fn]));
str_input_error_magnitude = 0;
}
else
{
num_input_error_magnitude = 0;
str_input_error_magnitude = Utility.StringMagnitudeChange(errord[fn], original_inputs[fn]);
}
// write error log
_error_log.Add(new LogEntry(analysis_type,
wb.Name,
fn,
original_inputs[fn],
errord[fn],
last_out_err_mag,
num_input_error_magnitude,
str_input_error_magnitude,
false,
true,
significance,
ck.Threshold));
}
return o;
}
