public static IList <float?> checkStability(LangDescriptor language)
{
IList <float?> errorRates = new List <float?>();
// format the corpus into tmp dir
LeaveOneOutValidator validator0 = new LeaveOneOutValidator(language.corpusDir, language);
Triple <IList <Formatter>, IList <float>, IList <float> > results0 = validator0.validateDocuments(false, "/tmp/stability/1");
errorRates.Add(BuffUtils.median(results0.c));
IList <Formatter> formatters0 = results0.a;
// now try formatting it over and over
for (int i = 1; i <= STAGES; i++)
{
string inputDir = "/tmp/stability/" + i;
string outputDir = "/tmp/stability/" + (i + 1);
LeaveOneOutValidator validator = new LeaveOneOutValidator(inputDir, language);
Triple <IList <Formatter>, IList <float>, IList <float> > results = validator.validateDocuments(false, outputDir);
IList <Formatter> formatters = results.a;
IList <float?> distances = new List <float?>();
for (int j = 0; j < formatters.Count; j++)
{
Formatter f0 = formatters0[j];
Formatter f = formatters[j];
float editDistance = Dbg.normalizedLevenshteinDistance(f.Output, f0.Output);
distances.Add(editDistance);
}
errorRates.Add(BuffUtils.median(distances));
}
return(errorRates);
}
public static Triple <Formatter, float, float> validate(LangDescriptor language, IList <InputDocument> documents, InputDocument testDoc, bool saveOutput, bool computeEditDistance)
{
// kNNClassifier.resetCache();
Corpus corpus = new Corpus(documents, language);
corpus.train();
// System.out.printf("%d feature vectors\n", corpus.featureVectors.size());
Formatter formatter = new Formatter(corpus, language.indentSize);
string output = formatter.format(testDoc, false);
float editDistance = 0;
if (computeEditDistance)
{
editDistance = Dbg.normalizedLevenshteinDistance(testDoc.content, output);
}
ClassificationAnalysis analysis = new ClassificationAnalysis(testDoc, formatter.AnalysisPerToken);
// System.out.println(testDoc.fileName+": edit distance = "+editDistance+", error rate = "+analysis.getErrorRate());
if (saveOutput)
{
File dir = new File(outputDir + "/" + language.name);
if (saveOutput)
{
dir = new File(outputDir + "/" + language.name);
dir.mkdir();
}
org.antlr.codebuff.misc.Utils.writeFile(dir.Path + "/" + System.IO.Path.GetFileName(testDoc.fileName), output);
}
return(new Triple <Formatter, float?, float?>(formatter, editDistance, analysis.ErrorRate));
}
public static void Main(string[] args)
{
LangDescriptor[] languages = new LangDescriptor[] { Tool.ANTLR4_DESCR };
int maxNumFiles = 30;
int trials = 50;
IDictionary <string, float[]> results = new Dictionary <string, float[]>();
foreach (LangDescriptor language in languages)
{
float[] medians = getMedianErrorRates(language, maxNumFiles, trials);
results[language.name] = medians;
}
string python = "#\n" + "# AUTO-GENERATED FILE. DO NOT EDIT\n" + "# CodeBuff <version> '<date>'\n" + "#\n" + "import numpy as np\n" + "import matplotlib.pyplot as plt\n\n" + "fig = plt.figure()\n" + "ax = plt.subplot(111)\n" + "N = <maxNumFiles>\n" + "sizes = range(1,N+1)\n" + "<results:{r |\n" + "<r> = [<rest(results.(r)); separator={,}>]\n" + "ax.plot(range(1,len(<r>)+1), <r>, label=\"<r>\", marker='<markers.(r)>', color='<colors.(r)>')\n" + "}>\n" + "ax.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)\n" + "ax.set_xlabel(\"Number of training files in sample corpus subset\", fontsize=14)\n" + "ax.set_ylabel(\"Median Error rate for <trials> trials\", fontsize=14)\n" + "ax.set_title(\"Effect of Corpus size on Median Leave-one-out Validation Error Rate\")\n" + "plt.legend()\n" + "plt.tight_layout()\n" + "fig.savefig('images/subset_validator.pdf', format='pdf')\n" + "plt.show()\n";
ST pythonST = new ST(python);
pythonST.add("results", results);
pythonST.add("markers", LeaveOneOutValidator.nameToGraphMarker);
pythonST.add("colors", LeaveOneOutValidator.nameToGraphColor);
pythonST.add("version", version);
pythonST.add("date", DateTime.Now);
pythonST.add("trials", trials);
pythonST.add("maxNumFiles", maxNumFiles);
IList <string> corpusDirs = map(languages, l => l.corpusDir);
string[] dirs = corpusDirs.ToArray();
string fileName = "python/src/subset_validator.py";
org.antlr.codebuff.misc.Utils.writeFile(fileName, pythonST.render());
Console.WriteLine("wrote python code to " + fileName);
}
public static void Main(string[] args)
{
LeaveOneOutValidator.FORCE_SINGLE_THREADED = true; // need this when we compare results file by file
LangDescriptor[] languages = new LangDescriptor[] { QUORUM_DESCR };
IDictionary <string, IList <float?> > results = new Dictionary <string, IList <float?> >();
foreach (LangDescriptor language in languages)
{
IList <float?> errorRates = checkStability(language);
Log.WriteLine(language.name + " " + errorRates);
results[language.name] = errorRates;
}
foreach (string name in results.Keys)
{
Log.WriteLine(name + " = " + results[name]);
}
string python = "#\n" + "# AUTO-GENERATED FILE. DO NOT EDIT\n" + "# CodeBuff <version> '<date>'\n" + "#\n" + "import numpy as np\n" + "import matplotlib.pyplot as plt\n\n" + "import matplotlib\n" + "fig = plt.figure()\n" + "ax = plt.subplot(111)\n" + "N = <N>\n" + "sizes = range(0,N)\n" + "<results:{r |\n" + "<r> = [<results.(r); separator={,}>]\n" + "ax.plot(sizes, <r>, label=\"<r>\", marker='o')\n" + "}>\n" + "ax.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)\n" + "xa = ax.get_xaxis()\n" + "xa.set_major_locator(matplotlib.ticker.MaxNLocator(integer=True))\n" + "ax.set_xlabel(\"Formatting Stage; stage 0 is first formatting pass\")\n" + "ax.set_ylabel(\"Median Leave-one-out Validation Error Rate\")\n" + "ax.set_title(\"<N>-Stage Formatting Stability\\nStage $n$ is formatted output of stage $n-1$\")\n" + "plt.legend()\n" + "plt.tight_layout()\n" + "fig.savefig('images/stability.pdf', format='pdf')\n" + "plt.show()\n";
ST pythonST = new ST(python);
pythonST.add("results", results);
pythonST.add("version", version);
pythonST.add("date", DateTime.Now);
pythonST.add("N", STAGES + 1);
string fileName = "python/src/stability.py";
org.antlr.codebuff.misc.Utils.writeFile(fileName, pythonST.render());
Log.WriteLine("wrote python code to " + fileName);
}
public static string testAllLanguages(LangDescriptor[] languages, string[] corpusDirs, string imageFileName)
{
IList <string> languageNames = BuffUtils.map(languages, l => l.name + "_err");
// Collections.sort(languageNames);
IDictionary <string, int?> corpusSizes = new Dictionary <string, int?>();
for (int i = 0; i < languages.Length; i++)
{
LangDescriptor language = languages[i];
IList <string> filenames = Tool.getFilenames(corpusDirs[i], language.fileRegex);
corpusSizes[language.name] = filenames.Count;
}
IList <string> languageNamesAsStr = BuffUtils.map(languages, l => '"' + l.name + "\\nn=" + corpusSizes[l.name] + '"');
// Collections.sort(languageNamesAsStr);
StringBuilder data = new StringBuilder();
for (int i = 0; i < languages.Length; i++)
{
LangDescriptor language = languages[i];
string corpus = corpusDirs[i];
LeaveOneOutValidator validator = new LeaveOneOutValidator(corpus, language);
Triple <IList <Formatter>, IList <float>, IList <float> > results = validator.validateDocuments(true, "/tmp");
IList <Formatter> formatters = results.a;
IList <float> distances = results.b;
IList <float> errors = results.c;
// data.append(language.name+"_dist = "+distances+"\n");
data.Append(language.name + "_err = " + errors + "\n");
}
string python = "#\n" + "# AUTO-GENERATED FILE. DO NOT EDIT\n" + "# CodeBuff %s '%s'\n" + "#\n" + "import numpy as np\n" + "import pylab\n" + "import matplotlib.pyplot as plt\n\n" + "%s\n" + "language_data = %s\n" + "labels = %s\n" + "fig = plt.figure()\n" + "ax = plt.subplot(111)\n" + "ax.boxplot(language_data,\n" + " whis=[10, 90], # 10 and 90 %% whiskers\n" + " widths=.35,\n" + " labels=labels,\n" + " showfliers=False)\n" + "ax.set_xticklabels(labels, rotation=60, fontsize=18)\n" + "ax.tick_params(axis='both', which='major', labelsize=18)\n" + "plt.xticks(range(1,len(labels)+1), labels, rotation=60, fontsize=18)\n" + "pylab.ylim([0,.28])\n" + "ax.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)\n" + "ax.set_xlabel(\"Grammar and corpus size\", fontsize=20)\n" + "ax.set_ylabel(\"Misclassification Error Rate\", fontsize=20)\n" + "# ax.set_title(\"Leave-one-out Validation Using Error Rate\\nBetween Formatted and Original File\")\n" + "plt.tight_layout()\n" + "fig.savefig('images/%s', format='pdf')\n" + "plt.show()\n";
return(string.Format(python, Tool.version, DateTime.Now, data, languageNames, languageNamesAsStr, imageFileName));
}
public virtual Triple <Formatter, float, float> validate(LangDescriptor language, IList <InputDocument> documents, string fileToExclude, int k, FeatureMetaData[] injectWSFeatures, FeatureMetaData[] alignmentFeatures, string outputDir, bool computeEditDistance, bool collectAnalysis)
{
string path = System.IO.Path.GetFullPath(fileToExclude);
IList <InputDocument> others = BuffUtils.filter(documents, d => !d.fileName.Equals(path));
IList <InputDocument> excluded = BuffUtils.filter(documents, d => d.fileName.Equals(path));
Debug.Assert(others.Count == documents.Count - 1);
// kNNClassifier.resetCache();
if (excluded.Count == 0)
{
Console.Error.WriteLine("Doc not in corpus: " + path);
return(null);
}
InputDocument testDoc = excluded[0];
DateTime start = System.DateTime.Now;
Corpus corpus = new Corpus(others, language);
corpus.train();
DateTime stop = System.DateTime.Now;
Formatter formatter = new Formatter(corpus, language.indentSize, k, injectWSFeatures, alignmentFeatures);
InputDocument originalDoc = testDoc;
DateTime format_start = System.DateTime.Now;
string output = formatter.format(testDoc, collectAnalysis);
DateTime format_stop = System.DateTime.Now;
float editDistance = 0;
if (computeEditDistance)
{
editDistance = Dbg.normalizedLevenshteinDistance(testDoc.content, output);
}
ClassificationAnalysis analysis = new ClassificationAnalysis(originalDoc, formatter.AnalysisPerToken);
Console.WriteLine(testDoc.fileName + ": edit distance = " + editDistance + ", error rate = " + analysis.ErrorRate);
if (!string.ReferenceEquals(outputDir, null))
{
string dir = outputDir + "/" + language.name + "/" + Tool.version;
if (!System.IO.Directory.Exists(dir))
{
System.IO.Directory.CreateDirectory(dir);
}
org.antlr.codebuff.misc.Utils.writeFile(dir + "/" + System.IO.Path.GetFileName(testDoc.fileName), output);
}
var tms = (stop - start);
var fms = format_stop - format_start;
trainingTimes.Add((double)tms.Milliseconds);
float tokensPerMS = testDoc.tokens.Size / (float)fms.TotalMilliseconds;
formattingTokensPerMS.Add((double)tokensPerMS);
Console.Write("Training time = {0:D} ms, formatting {1:D} ms, {2,5:F3} tokens/ms ({3:D} tokens)\n", tms, fms, tokensPerMS, testDoc.tokens.Size);
// System.out.printf("classify calls %d, hits %d rate %f\n",
// kNNClassifier.nClassifyCalls, kNNClassifier.nClassifyCacheHits,
// kNNClassifier.nClassifyCacheHits/(float) kNNClassifier.nClassifyCalls);
// System.out.printf("kNN calls %d, hits %d rate %f\n",
// kNNClassifier.nNNCalls, kNNClassifier.nNNCacheHits,
// kNNClassifier.nNNCacheHits/(float) kNNClassifier.nNNCalls);
return(new Triple <Formatter, float, float>(formatter, editDistance, analysis.ErrorRate));
}
public static void Main(string[] args)
{
LangDescriptor[] languages = new LangDescriptor[] { QUORUM_DESCR, JAVA_DESCR, JAVA8_DESCR, ANTLR4_DESCR, SQLITE_NOISY_DESCR, SQLITE_CLEAN_DESCR, TSQL_NOISY_DESCR, TSQL_CLEAN_DESCR };
for (int i = 0; i < languages.Length; i++)
{
LangDescriptor language = languages[i];
runCaptureForOneLanguage(language);
}
}
public static void Main(string[] args)
{
string langname = args[0].Substring(1);
string testFilename = args[1];
LangDescriptor language = null;
for (int i = 0; i < languages.length; i++)
{
if (languages[i].name.Equals(langname))
{
language = languages[i];
break;
}
}
if (language == null)
{
Log.WriteLine("Language " + langname + " unknown");
return;
}
// load all files up front
DateTime load_start = System.DateTime.Now;
IList <string> allFiles = Tool.getFilenames(language.corpusDir, language.fileRegex);
IList <InputDocument> documents = Tool.load(allFiles, language);
DateTime load_stop = System.DateTime.Now;
DateTime load_time = (load_stop - load_start) / 1000000;
Log.Write("Loaded {0:D} files in {1:D}ms\n", documents.Count, load_time);
string path = System.IO.Path.GetFullPath(testFilename);
IList <InputDocument> others = BuffUtils.filter(documents, d => !d.fileName.Equals(path));
IList <InputDocument> excluded = BuffUtils.filter(documents, d => d.fileName.Equals(path));
Debug.Assert(others.Count == documents.Count - 1);
if (excluded.Count == 0)
{
Log.WriteLine("Doc not in corpus: " + path);
return;
}
InputDocument testDoc = excluded[0];
IList <int> training = new List <int>();
IList <int> formatting = new List <int>();
for (int i = 1; i <= TRIALS; i++)
{
org.antlr.codebuff.misc.Pair <int, int> timing = test(language, others, testDoc);
training.Add(timing.a);
formatting.Add(timing.b);
}
// drop first four
training = training.subList(5, training.Count);
formatting = formatting.subList(5, formatting.Count);
Log.Write("median of [5:{0:D}] training {1:D}ms\n", TRIALS - 1, BuffUtils.median(training));
Log.Write("median of [5:{0:D}] formatting {1:D}ms\n", TRIALS - 1, BuffUtils.median(formatting));
}
public Corpus(string rootDir, LangDescriptor language)
{
this.rootDir = rootDir;
this.language = language;
if (documents == null)
{
IList <string> allFiles = Tool.getFilenames(rootDir, language.fileRegex);
documents = Tool.load(allFiles, language);
}
}
public static float[] getMedianErrorRates(LangDescriptor language, int maxNumFiles, int trials)
{
SubsetValidator validator = new SubsetValidator(language.corpusDir, language);
IList <InputDocument> documents = Tool.load(validator.allFiles, language);
float[] medians = new float[Math.Min(documents.Count, maxNumFiles) + 1];
int ncpu = Runtime.Runtime.availableProcessors();
if (FORCE_SINGLE_THREADED)
{
ncpu = 2;
}
ExecutorService pool = Executors.newFixedThreadPool(ncpu - 1);
IList <Callable <Void> > jobs = new List <Callable <Void> >();
for (int i = 1; i <= Math.Min(validator.allFiles.Count, maxNumFiles); i++)
{ // i is corpus subset size
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int corpusSubsetSize = i;
int corpusSubsetSize = i;
Callable <Void> job = () =>
{
try
{
IList <float?> errorRates = new List <float?>();
for (int trial = 1; trial <= trials; trial++)
{ // multiple trials per subset size
org.antlr.codebuff.misc.Pair <InputDocument, IList <InputDocument> > sample = validator.selectSample(documents, corpusSubsetSize);
Triple <Formatter, float?, float?> results = validate(language, sample.b, sample.a, true, false);
// System.out.println(sample.a.fileName+" n="+corpusSubsetSize+": error="+results.c);
// System.out.println("\tcorpus =\n\t\t"+Utils.join(sample.b.iterator(), "\n\t\t"));
errorRates.Add(results.c);
}
errorRates.Sort();
int n = errorRates.Count;
float median = errorRates[n / 2].Value;
Console.WriteLine("median " + language.name + " error rate for n=" + corpusSubsetSize + " is " + median);
medians[corpusSubsetSize] = median;
}
catch (Exception t)
{
t.printStackTrace(System.err);
}
return(null);
};
jobs.Add(job);
}
pool.invokeAll(jobs);
pool.shutdown();
bool terminated = pool.awaitTermination(60, TimeUnit.MINUTES);
return(medians);
}
public static void Main(string[] args)
{
LangDescriptor[] languages = new LangDescriptor[] { JAVA_DESCR, JAVA8_DESCR, JAVA_GUAVA_DESCR };
IList <string> corpusDirs = BuffUtils.map(languages, l => l.corpusDir);
string[] dirs = corpusDirs.ToArray();
string python = LeaveOneOutValidator.testAllLanguages(languages, dirs, "all_java_leave_one_out.pdf");
string fileName = "python/src/all_java_leave_one_out.py";
org.antlr.codebuff.misc.Utils.writeFile(fileName, python);
Log.WriteLine("wrote python code to " + fileName);
}
public static void Main(string[] args)
{
LangDescriptor[] languages = new LangDescriptor[] { Tool.ANTLR4_DESCR };
IList <string> corpusDirs = BuffUtils.map(languages, l => l.corpusDir);
string[] dirs = corpusDirs.ToArray();
string python = testAllLanguages(languages, dirs, "leave_one_out.pdf");
string fileName = "python/src/leave_one_out.py";
org.antlr.codebuff.misc.Utils.writeFile(fileName, python);
Console.WriteLine("wrote python code to " + fileName);
}
/// <summary>
/// Get all file contents into input doc list </summary>
public static IList <InputDocument> load(IList <string> fileNames, LangDescriptor language)
{
IList <InputDocument> documents = new List <InputDocument>();
foreach (string fileName in fileNames)
{
documents.Add(parse(fileName, language));
}
if (documents.Count > 0)
{
documents[0].parser.Interpreter.ClearDFA(); // free up memory
}
return(documents);
}
public static IList <float> getAlignmentErrorRates(LangDescriptor language, FeatureMetaData[] injectWSFeatures, FeatureMetaData[] alignmentFeatures)
{
LeaveOneOutValidator validator = new LeaveOneOutValidator(language.corpusDir, language);
Triple <IList <Formatter>, IList <float>, IList <float> > results = validator.validateDocuments(injectWSFeatures, alignmentFeatures, false, null);
IList <Formatter> formatters = results.a;
IList <float> alignErrorRates = new List <float>(); // don't include align errors
foreach (Formatter formatter in formatters)
{
ClassificationAnalysis analysis = new ClassificationAnalysis(formatter.testDoc, formatter.AnalysisPerToken);
alignErrorRates.Add(analysis.AlignmentErrorRate);
}
// System.out.println(results.c);
// System.out.println("vs");
// System.out.println(alignErrorRates);
return(alignErrorRates);
}
public static InputDocument parse(string fileName, string content, LangDescriptor language)
{
ANTLRInputStream input = new ANTLRInputStream(content);
Lexer lexer = getLexer(language.lexerClass, input);
input.name = fileName;
InputDocument doc = new InputDocument(fileName, content, language);
doc.tokens = new CodeBuffTokenStream(lexer);
doc.parser = getParser(language.parserClass, doc.tokens);
doc.parser.BuildParseTree = true;
// two-stage parsing. Try with SLL first
doc.parser.Interpreter.PredictionMode = Antlr4.Runtime.Atn.PredictionMode.SLL;
doc.parser.ErrorHandler = new BailErrorStrategy();
doc.parser.RemoveErrorListeners();
MethodInfo startRule = language.parserClass.GetMethod(language.startRuleName);
try
{
doc.Tree = (ParserRuleContext)startRule.Invoke(doc.parser, (object[])null);
}
catch (Exception ex)
{
if (ex.InnerException is ParseCanceledException)
{
doc.parser.Reset();
doc.tokens.Reset(); // rewind input stream
// back to standard listeners/handlers
doc.parser.AddErrorListener(new ANTLRErrorListenerAnonymousInnerClass());
doc.parser.ErrorHandler = new DefaultErrorStrategy();
doc.parser.Interpreter.PredictionMode = PredictionMode.LL;
doc.Tree = (ParserRuleContext)startRule.Invoke(doc.parser, (object[])null);
if (doc.parser.NumberOfSyntaxErrors > 0)
{
doc.Tree = null;
}
}
}
return(doc);
}
public static void runCaptureForOneLanguage(LangDescriptor language)
{
IList <string> filenames = Tool.getFilenames(language.corpusDir, language.fileRegex);
IList <InputDocument> documents = Tool.load(filenames, language);
foreach (string fileName in filenames)
{
// Examine info for this file in isolation
Corpus fileCorpus = new Corpus(fileName, language);
fileCorpus.train();
Console.WriteLine(fileName);
// examineCorpus(corpus);
ArrayListMultiMap <FeatureVectorAsObject, int> ws = getWSContextCategoryMap(fileCorpus);
ArrayListMultiMap <FeatureVectorAsObject, int> hpos = getHPosContextCategoryMap(fileCorpus);
// Compare with corpus minus this file
string path = fileName;
IList <InputDocument> others = BuffUtils.filter(documents, d => !d.fileName.Equals(path));
Corpus corpus = new Corpus(others, language);
corpus.train();
// examineCorpus(corpus);
ArrayListMultiMap <FeatureVectorAsObject, int> corpus_ws = getWSContextCategoryMap(corpus);
ArrayListMultiMap <FeatureVectorAsObject, int> corpus_hpos = getHPosContextCategoryMap(corpus);
foreach (FeatureVectorAsObject x in ws.Keys)
{
HashBag <int> fwsCats = getCategoriesBag(ws[x]);
IList <float> fwsRatios = getCategoryRatios(fwsCats.Values);
HashBag <int> wsCats = getCategoriesBag(corpus_ws[x]);
IList <float> wsRatios = getCategoryRatios(wsCats.Values);
// compare file predictions with corpus predictions
if (!fwsRatios.SequenceEqual(wsRatios))
{
Console.WriteLine(fwsRatios + " vs " + wsRatios);
}
HashBag <int> fhposCats = getCategoriesBag(hpos[x]);
HashBag <int> hposCats = getCategoriesBag(corpus_hpos[x]);
}
break;
}
}
public static org.antlr.codebuff.misc.Pair <int, int> test(LangDescriptor language, IList <InputDocument> others, InputDocument testDoc)
{
var train_start = System.DateTime.Now;
Corpus corpus = new Corpus(others, language);
corpus.train();
var train_stop = System.DateTime.Now;
var format_start = System.DateTime.Now;
Formatter formatter = new Formatter(corpus, language.indentSize, Formatter.DEFAULT_K, FEATURES_INJECT_WS, FEATURES_HPOS);
formatter.format(testDoc, false);
var format_stop = System.DateTime.Now;
var train_time = (train_stop - train_start) / 1000000;
var format_time = (format_stop - format_start) / 1000000;
Log.Write("{0} training of {1} = {2:D}ms formatting = {3:D}ms\n", language.name, testDoc.fileName, train_time, format_time);
return(new org.antlr.codebuff.misc.Pair <int, int>((int)train_time, (int)format_time));
}
public static void writePython(LangDescriptor[] languages, IList <int?> ks, float[][] medians)
{
StringBuilder data = new StringBuilder();
StringBuilder plot = new StringBuilder();
for (int i = 0; i < languages.Length; i++)
{
LangDescriptor language = languages[i];
IList <float?> filteredMedians = BuffUtils.filter(Arrays.asList(medians[i]), m => m != null);
data.Append(language.name + '=' + filteredMedians + '\n');
plot.Append(string.Format("ax.plot(ks, {0}, label=\"{1}\", marker='{2}', color='{3}')\n", language.name, language.name, nameToGraphMarker.get(language.name), nameToGraphColor.get(language.name)));
}
string python = "#\n" + "# AUTO-GENERATED FILE. DO NOT EDIT\n" + "# CodeBuff %s '%s'\n" + "#\n" + "import numpy as np\n" + "import matplotlib.pyplot as plt\n\n" + "%s\n" + "ks = %s\n" + "fig = plt.figure()\n" + "ax = plt.subplot(111)\n" + "%s" + "ax.tick_params(axis='both', which='major', labelsize=18)\n" + "ax.set_xlabel(\"$k$ nearest neighbors\", fontsize=20)\n" + "ax.set_ylabel(\"Median error rate\", fontsize=20)\n" + "#ax.set_title(\"k Nearest Neighbors vs\\nLeave-one-out Validation Error Rate\")\n" + "plt.legend(fontsize=18)\n\n" + "fig.savefig('images/vary_k.pdf', format='pdf')\n" + "plt.show()\n";
string code = string.format(python, Tool.version, DateTime.Now, data, ks, plot);
string fileName = "python/src/vary_k.py";
org.antlr.codebuff.misc.Utils.writeFile(fileName, code);
Log.WriteLine("wrote python code to " + fileName);
}
public Corpus(IList <InputDocument> documents, LangDescriptor language)
{
this.documents = documents;
this.language = language;
}
public SubsetValidator(string rootDir, LangDescriptor language)
{
this.rootDir = rootDir;
this.language = language;
allFiles = Tool.getFilenames(rootDir, language.fileRegex);
}
public virtual Triple <Formatter, float, float> validate(LangDescriptor language, IList <InputDocument> documents, string fileToExclude, int k, string outputDir, bool computeEditDistance, bool collectAnalysis)
{
return(validate(language, documents, fileToExclude, k, Trainer.FEATURES_INJECT_WS, Trainer.FEATURES_HPOS, outputDir, computeEditDistance, collectAnalysis));
}
public static void computeConsistency(LangDescriptor language, bool report)
{
if (report)
{
Console.WriteLine("-----------------------------------");
Console.WriteLine(language.name);
Console.WriteLine("-----------------------------------");
}
Corpus corpus = new Corpus(language.corpusDir, language);
corpus.train();
// a map of feature vector to list of exemplar indexes of that feature
MyMultiMap <FeatureVectorAsObject, int> wsContextToIndex = new MyMultiMap <FeatureVectorAsObject, int>();
MyMultiMap <FeatureVectorAsObject, int> hposContextToIndex = new MyMultiMap <FeatureVectorAsObject, int>();
int n = corpus.featureVectors.Count;
for (int i = 0; i < n; i++)
{
int[] features = corpus.featureVectors[i];
wsContextToIndex.Map(new FeatureVectorAsObject(features, Trainer.FEATURES_INJECT_WS), i);
hposContextToIndex.Map(new FeatureVectorAsObject(features, Trainer.FEATURES_HPOS), i);
}
int num_ambiguous_ws_vectors = 0;
int num_ambiguous_hpos_vectors = 0;
// Dump output grouped by ws vs hpos then feature vector then category
if (report)
{
Console.WriteLine(" --- INJECT WS ---");
}
IList <double> ws_entropies = new List <double>();
foreach (FeatureVectorAsObject fo in wsContextToIndex.Keys)
{
var exemplarIndexes = wsContextToIndex[fo];
// we have group by feature vector, now group by cat with that set for ws
MyMultiMap <int, int> wsCatToIndexes = new MyMultiMap <int, int>();
foreach (int i in exemplarIndexes)
{
wsCatToIndexes.Map(corpus.injectWhitespace[i], i);
}
if (wsCatToIndexes.Count == 1)
{
continue;
}
if (report)
{
Console.WriteLine("Feature vector has " + exemplarIndexes.size() + " exemplars");
}
IList <int> catCounts = BuffUtils.map(wsCatToIndexes.Values, (x) => x.size());
double wsEntropy = Entropy.getNormalizedCategoryEntropy(Entropy.getCategoryRatios(catCounts));
if (report)
{
Console.Write("entropy={0,5:F4}\n", wsEntropy);
}
wsEntropy *= exemplarIndexes.size();
ws_entropies.Add(wsEntropy);
num_ambiguous_ws_vectors += exemplarIndexes.size();
if (report)
{
Console.Write(Trainer.featureNameHeader(Trainer.FEATURES_INJECT_WS));
}
if (report)
{
foreach (int cat in wsCatToIndexes.Keys)
{
var indexes = wsCatToIndexes[cat];
foreach (int i in indexes)
{
string display = getExemplarDisplay(Trainer.FEATURES_INJECT_WS, corpus, corpus.injectWhitespace, i);
Console.WriteLine(display);
}
Console.WriteLine();
}
}
}
if (report)
{
Console.WriteLine(" --- HPOS ---");
}
IList <double> hpos_entropies = new List <double>();
foreach (FeatureVectorAsObject fo in hposContextToIndex.Keys)
{
MyHashSet <int> exemplarIndexes = hposContextToIndex[fo];
// we have group by feature vector, now group by cat with that set for hpos
MyMultiMap <int, int> hposCatToIndexes = new MyMultiMap <int, int>();
foreach (int i in exemplarIndexes)
{
hposCatToIndexes.Map(corpus.hpos[i], i);
}
if (hposCatToIndexes.Count == 1)
{
continue;
}
if (report)
{
Console.WriteLine("Feature vector has " + exemplarIndexes.size() + " exemplars");
}
IList <int> catCounts = BuffUtils.map(hposCatToIndexes.Values, (x) => x.size());
double hposEntropy = Entropy.getNormalizedCategoryEntropy(Entropy.getCategoryRatios(catCounts));
if (report)
{
Console.Write("entropy={0,5:F4}\n", hposEntropy);
}
hposEntropy *= exemplarIndexes.size();
hpos_entropies.Add(hposEntropy);
num_ambiguous_hpos_vectors += exemplarIndexes.size();
if (report)
{
Console.Write(Trainer.featureNameHeader(Trainer.FEATURES_HPOS));
}
if (report)
{
foreach (int cat in hposCatToIndexes.Keys)
{
var indexes = hposCatToIndexes[cat];
foreach (int?i in indexes)
{
string display = getExemplarDisplay(Trainer.FEATURES_HPOS, corpus, corpus.hpos, i.Value);
Console.WriteLine(display);
}
Console.WriteLine();
}
}
}
Console.WriteLine();
Console.WriteLine(language.name);
Console.WriteLine("There are " + wsContextToIndex.Count + " unique ws feature vectors out of " + n + " = " + string.Format("{0,3:F1}%", 100.0 * wsContextToIndex.Count / n));
Console.WriteLine("There are " + hposContextToIndex.Count + " unique hpos feature vectors out of " + n + " = " + string.Format("{0,3:F1}%", 100.0 * hposContextToIndex.Count / n));
float prob_ws_ambiguous = num_ambiguous_ws_vectors / (float)n;
Console.Write("num_ambiguous_ws_vectors = {0,5:D}/{1,5:D} = {2,5:F3}\n", num_ambiguous_ws_vectors, n, prob_ws_ambiguous);
float prob_hpos_ambiguous = num_ambiguous_hpos_vectors / (float)n;
Console.Write("num_ambiguous_hpos_vectors = {0,5:D}/{1,5:D} = {2,5:F3}\n", num_ambiguous_hpos_vectors, n, prob_hpos_ambiguous);
// Collections.sort(ws_entropies);
// System.out.println("ws_entropies="+ws_entropies);
Console.WriteLine("ws median,mean = " + BuffUtils.median(ws_entropies) + "," + BuffUtils.mean(ws_entropies));
double expected_ws_entropy = (BuffUtils.sumDoubles(ws_entropies) / num_ambiguous_ws_vectors) * prob_ws_ambiguous;
Console.WriteLine("expected_ws_entropy=" + expected_ws_entropy);
Console.WriteLine("hpos median,mean = " + BuffUtils.median(hpos_entropies) + "," + BuffUtils.mean(hpos_entropies));
double expected_hpos_entropy = (BuffUtils.sumDoubles(hpos_entropies) / num_ambiguous_hpos_vectors) * prob_hpos_ambiguous;
Console.WriteLine("expected_hpos_entropy=" + expected_hpos_entropy);
}
public static void Main(string[] args)
{
if (args.Length < 2)
{
Console.Error.WriteLine("Dbg [-leave-one-out] [-java|-java8|-antlr|-sqlite|-tsql] test-file");
}
int arg = 0;
bool leaveOneOut = true;
bool collectAnalysis = true;
string language = args[arg++];
language = language.Substring(1);
string testFilename = args[arg];
string output = "???";
InputDocument testDoc = null;
IList <TokenPositionAnalysis> analysisPerToken = null;
org.antlr.codebuff.misc.Pair <string, IList <TokenPositionAnalysis> > results;
LangDescriptor lang = null;
System.DateTime start, stop;
for (int i = 0; i < Tool.languages.Length; i++)
{
if (Tool.languages[i].name.Equals(language))
{
lang = Tool.languages[i];
break;
}
}
if (lang != null)
{
start = System.DateTime.Now;
LeaveOneOutValidator validator = new LeaveOneOutValidator(lang.corpusDir, lang);
Triple <Formatter, float, float> val = validator.validateOneDocument(testFilename, null, collectAnalysis);
testDoc = Tool.parse(testFilename, lang);
stop = System.DateTime.Now;
Formatter formatter = val.a;
output = formatter.Output;
Console.WriteLine("output len = " + output.Length);
float editDistance = normalizedLevenshteinDistance(testDoc.content, output);
Console.WriteLine("normalized Levenshtein distance: " + editDistance);
analysisPerToken = formatter.AnalysisPerToken;
Regex rex = new Regex("^\\s+$");
CommonTokenStream original_tokens = Tool.tokenize(testDoc.content, lang.lexerClass);
IList <Token> wsTokens = BuffUtils.filter(original_tokens.GetTokens(), t => rex.IsMatch(t.Text));
string originalWS = tokenText(wsTokens);
Console.WriteLine("origin ws tokens len: " + originalWS.Length);
CommonTokenStream formatted_tokens = Tool.tokenize(output, lang.lexerClass);
wsTokens = BuffUtils.filter(formatted_tokens.GetTokens(), t => rex.IsMatch(t.Text));
string formattedWS = tokenText(wsTokens);
Console.WriteLine("formatted ws tokens len: " + formattedWS.Length);
editDistance = levenshteinDistance(originalWS, formattedWS);
editDistance /= Math.Max(testDoc.content.Length, output.Length);
Console.WriteLine("Levenshtein distance of ws normalized to output len: " + editDistance);
ClassificationAnalysis analysis = new ClassificationAnalysis(testDoc, analysisPerToken);
Console.WriteLine(analysis);
}
if (lang != null)
{
// GUIController controller;
// controller = new GUIController(analysisPerToken, testDoc, output, lang.lexerClass);
//controller.show();
// System.out.println(output);
//Console.Write("formatting time {0:D}s\n", (stop - start) / 1000000);
Console.Write("classify calls {0:D}, hits {1:D} rate {2:F}\n", kNNClassifier.nClassifyCalls, kNNClassifier.nClassifyCacheHits, kNNClassifier.nClassifyCacheHits / (float)kNNClassifier.nClassifyCalls);
Console.Write("kNN calls {0:D}, hits {1:D} rate {2:F}\n", kNNClassifier.nNNCalls, kNNClassifier.nNNCacheHits, kNNClassifier.nNNCacheHits / (float)kNNClassifier.nNNCalls);
}
}
public static void Main(string[] args)
{
LangDescriptor[] languages = new LangDescriptor[] { Tool.ANTLR4_DESCR };
testFeatures(languages, false);
}
/// <summary>
/// Parse doc and fill tree and tokens fields
/// </summary>
public static InputDocument parse(string fileName, LangDescriptor language)
{
string content = load(fileName, language.indentSize);
return(parse(fileName, content, language));
}
public static string Main(object[] args)
{
Log.Reset();
try
{
if (args.Length < 7)
{
Log.WriteLine("org.antlr.codebuff.Tool -g grammar-name -rule start-rule -corpus root-dir-of-samples \\\n" + " [-files file-extension] [-indent num-spaces] \\" + " [-comment line-comment-name] [-o output-file] file-to-format");
return(Log.Message());
}
formatted_output = null;
string outputFileName = "";
string grammarName = null;
string startRule = null;
string corpusDir = null;
string indentS = "4";
string commentS = null;
string input_file_name = null;
string fileExtension = null;
int i = 0;
Type parserClass = null;
Type lexerClass = null;
while (i < args.Length && ((string)args[i]).StartsWith("-", StringComparison.Ordinal))
{
switch (args[i])
{
case "-g":
i++;
grammarName = (string)args[i++];
break;
case "-lexer":
i++;
lexerClass = (Type)args[i++];
break;
case "-parser":
i++;
parserClass = (Type)args[i++];
break;
case "-rule":
i++;
startRule = (string)args[i++];
break;
case "-corpus":
i++;
corpusDir = (string)args[i++];
break;
case "-files":
i++;
fileExtension = (string)args[i++];
break;
case "-indent":
i++;
indentS = (string)args[i++];
break;
case "-comment":
i++;
commentS = (string)args[i++];
break;
case "-o":
i++;
outputFileName = (string)args[i++];
break;
case "-inoutstring":
i++;
formatted_output = "";
outputFileName = null;
break;
}
}
input_file_name = (string)args[i]; // must be last
Log.WriteLine("gramm: " + grammarName);
string parserClassName = grammarName + "Parser";
string lexerClassName = grammarName + "Lexer";
Lexer lexer = null;
if (lexerClass == null || parserClass == null)
{
Log.WriteLine("You must specify a lexer and parser.");
}
if (parserClass == null | lexerClass == null)
{
return(Log.Message());
}
int indentSize = int.Parse(indentS);
int singleLineCommentType = -1;
if (!string.ReferenceEquals(commentS, null))
{
try
{
lexer = getLexer(lexerClass, null);
}
catch (Exception e)
{
Log.WriteLine("Can't instantiate lexer " + lexerClassName);
Log.WriteLine(e.StackTrace);
}
if (lexer == null)
{
return(Log.Message());
}
IDictionary <string, int> tokenTypeMap = lexer.TokenTypeMap;
if (tokenTypeMap.ContainsKey(commentS))
{
singleLineCommentType = tokenTypeMap[commentS];
}
}
string fileRegex = null;
if (!string.ReferenceEquals(fileExtension, null))
{
var pattern = "";
var allowable_suffices = fileExtension.Split(';').ToList <string>();
foreach (var s in allowable_suffices)
{
var no_dot = s.Substring(s.IndexOf('.') + 1);
pattern = pattern == "" ? ("(" + no_dot) : (pattern + "|" + no_dot);
}
pattern = pattern + ")";
fileRegex = ".*\\." + pattern;
}
LangDescriptor language = new LangDescriptor(grammarName, corpusDir, fileRegex, lexerClass, parserClass, startRule, indentSize, singleLineCommentType);
////////
// load all corpus files up front
IList <string> allFiles = getFilenames(language.corpusDir, language.fileRegex);
IList <InputDocument> documents = load(allFiles, language);
// Handle formatting of document if it's passed as a string or not.
if (unformatted_input == null)
{
// Don't include file to format in corpus itself.
string path = System.IO.Path.GetFullPath(input_file_name);
IList <InputDocument> others = BuffUtils.filter(documents, d => !d.fileName.Equals(path));
// Perform training of formatter.
Corpus corpus = new Corpus(others, language);
corpus.train();
// Parse code contained in file.
InputDocument unformatted_document = parse(input_file_name, language);
// Format document.
Formatter formatter = new Formatter(corpus, language.indentSize, Formatter.DEFAULT_K, Trainer.FEATURES_INJECT_WS, Trainer.FEATURES_HPOS);
formatted_output = formatter.format(unformatted_document, false);
}
else
{
// Perform training of formatter.
Corpus corpus = new Corpus(documents, language);
corpus.train();
// Parse code that was represented as a string.
InputDocument unformatted_document = parse(input_file_name, unformatted_input, language);
// Format document.
Formatter formatter = new Formatter(corpus, language.indentSize, Formatter.DEFAULT_K, Trainer.FEATURES_INJECT_WS, Trainer.FEATURES_HPOS);
formatted_output = formatter.format(unformatted_document, false);
}
///////
if (outputFileName != null && outputFileName == "")
{
Log.WriteLine(formatted_output);
}
else if (!string.IsNullOrEmpty(outputFileName))
{
org.antlr.codebuff.misc.Utils.writeFile(outputFileName, formatted_output);
}
}
catch (Exception e)
{
throw e;
}
return(formatted_output);
}
public static void Main(string[] args)
{
LangDescriptor[] languages = new LangDescriptor[] { Tool.ANTLR4_DESCR };
int MAX_K = 98; // should be odd
int OUTLIER_K = 99;
IList <int?> ks = new List <int?>();
for (int i = 1; i <= MAX_K; i += 2)
{
ks.Add(i);
}
ks.Add(OUTLIER_K);
// track medians[language][k]
float[][] medians = new float[languages.Length + 1][];
int ncpu = 1;
if (FORCE_SINGLE_THREADED)
{
ncpu = 2;
}
ExecutorService pool = Executors.newFixedThreadPool(ncpu - 1);
IList <Callable <Void> > jobs = new List <Callable <Void> >();
for (int i = 0; i < languages.Length; i++)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.antlr.codebuff.misc.LangDescriptor language = languages[i];
LangDescriptor language = languages[i];
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int langIndex = i;
int langIndex = i;
Log.WriteLine(language.name);
foreach (int k in ks)
{
medians[langIndex] = new float?[OUTLIER_K + 1];
Callable <Void> job = () =>
{
try
{
TestK tester = new TestK(language.corpusDir, language, k);
IList <float?> errorRates = tester.scoreDocuments();
errorRates.Sort();
int n = errorRates.Count;
float median = errorRates[n / 2].Value;
// double var = BuffUtils.varianceFloats(errorRates);
// String display = String.format("%5.4f, %5.4f, %5.4f, %5.4f, %5.4f", min, quart, median, quart3, max);
medians[langIndex][k] = median;
}
catch (Exception t)
{
t.printStackTrace(System.err);
}
return(null);
};
jobs.Add(job);
}
}
pool.invokeAll(jobs);
pool.shutdown();
bool terminated = pool.awaitTermination(60, TimeUnit.MINUTES);
writePython(languages, ks, medians);
}
public static void runCaptureForOneLanguage(LangDescriptor language)
{
IList <string> filenames = Tool.getFilenames(language.corpusDir, language.fileRegex);
IList <float> selfEditDistances = new List <float>();
foreach (string fileName in filenames)
{
Corpus corpus = new Corpus(fileName, language);
corpus.train();
InputDocument testDoc = Tool.parse(fileName, corpus.language);
Formatter formatter = new Formatter(corpus, language.indentSize);
string output = formatter.format(testDoc, false);
// System.out.println(output);
float editDistance = Dbg.normalizedLevenshteinDistance(testDoc.content, output);
Log.WriteLine(fileName + " edit distance " + editDistance);
selfEditDistances.Add(editDistance);
}
{
Corpus corpus = new Corpus(language.corpusDir, language);
corpus.train();
IList <float> corpusEditDistances = new List <float>();
foreach (string fileName in filenames)
{
InputDocument testDoc = Tool.parse(fileName, corpus.language);
Formatter formatter = new Formatter(corpus, language.indentSize);
string output = formatter.format(testDoc, false);
// System.out.println(output);
float editDistance = Dbg.normalizedLevenshteinDistance(testDoc.content, output);
Log.WriteLine(fileName + "+corpus edit distance " + editDistance);
corpusEditDistances.Add(editDistance);
}
// heh this gives info on within-corpus variability. i.e., how good/consistent is my corpus?
// those files with big difference are candidates for dropping from corpus or for cleanup.
IList <string> labels = BuffUtils.map(filenames, f => '"' + System.IO.Path.GetFileName(f) + '"');
string python = "#\n" + "# AUTO-GENERATED FILE. DO NOT EDIT\n" + "# CodeBuff <version> '<date>'\n" + "#\n" +
"import numpy as np\n" + "import matplotlib.pyplot as plt\n\n" + "fig = plt.figure()\n" +
"ax = plt.subplot(111)\n" + "labels = <labels>\n" + "N = len(labels)\n\n" +
"featureIndexes = range(0,N)\n" + "<lang>_self = <selfEditDistances>\n" +
"<lang>_corpus = <corpusEditDistances>\n" +
"<lang>_diff = np.abs(np.subtract(<lang>_self, <lang>_corpus))\n\n" +
"all = zip(<lang>_self, <lang>_corpus, <lang>_diff, labels)\n" +
"all = sorted(all, key=lambda x : x[2], reverse=True)\n" +
"<lang>_self, <lang>_corpus, <lang>_diff, labels = zip(*all)\n\n" +
"ax.plot(featureIndexes, <lang>_self, label=\"<lang>_self\")\n" +
"#ax.plot(featureIndexes, <lang>_corpus, label=\"<lang>_corpus\")\n" +
"ax.plot(featureIndexes, <lang>_diff, label=\"<lang>_diff\")\n" +
"ax.set_xticklabels(labels, rotation=60, fontsize=8)\n" +
"plt.xticks(featureIndexes, labels, rotation=60)\n" +
"ax.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)\n\n" +
"ax.text(1, .25, 'median $f$ self distance = %5.3f, corpus+$f$ distance = %5.3f' %" +
" (np.median(<lang>_self),np.median(<lang>_corpus)))\n" + "ax.set_xlabel(\"File Name\")\n" +
"ax.set_ylabel(\"Edit Distance\")\n" +
"ax.set_title(\"Difference between Formatting File <lang> $f$\\nwith Training=$f$ and Training=$f$+Corpus\")\n" +
"plt.legend()\n" + "plt.tight_layout()\n" + "fig.savefig(\"images/" + language.name +
"_one_file_capture.pdf\", format='pdf')\n" + "plt.show()\n";
ST pythonST = new ST(python);
pythonST.add("lang", language.name);
pythonST.add("version", version);
pythonST.add("date", DateTime.Now);
pythonST.add("labels", labels.ToString());
pythonST.add("selfEditDistances", selfEditDistances.ToString());
pythonST.add("corpusEditDistances", corpusEditDistances.ToString());
string code = pythonST.render();
{
string fileName = "python/src/" + language.name + "_one_file_capture.py";
org.antlr.codebuff.misc.Utils.writeFile(fileName, code);
Log.WriteLine("wrote python code to " + fileName);
}
}
}
public LeaveOneOutValidator(string rootDir, LangDescriptor language)
{
this.rootDir = rootDir;
this.language = language;
random = new Random(DOCLIST_RANDOM_SEED);
}
public TestK(string rootDir, LangDescriptor language, int k) : base(rootDir, language)
{
this.k = k;
}