def run(limit=None): outDir = "./DataCache/4_EvalSweeps/" # get where the raw data and pre-processed data are obj, Labels = Cacher.ReadProcessedFiles(baseDir, limit=limit) evalObj = pCheckUtil.getCheckpoint(outDir + "svm.pkl", GetEvaluation, True, obj, Labels, SVM_Learner) MakeEvalutionPlot(evalObj, outName=outDir + "SVM_plot.png")
def GetOrCreatedPreProcessed(BaseDirIn, SourceName, BaseDirOut, Opt, Labels=None, ForceUpdate=False, UseLowOnly=False): """ Given a source name to read, reads from the pre-processed cache, it if exists. Otherwise, creates the data object and pre-processes Args: BaseDirIn: Base directory of where to look for the SourceFiles BaseDirOut: Base directory of where to look for the saved files SourceName: the name of the source Opt: Pre-processing options Labels: the labels of the data object. ForceUpdate: if true, forces an update of the pre-processed data UseLowOnly: see GetPreProcessed Returns: the Pre Processed Object """ outPath = BaseDirOut + SourceName + ".pkl" return pCheckUtil.getCheckpoint(outPath, ReadAndProcess, ForceUpdate, BaseDirIn, SourceName, BaseDirOut, Opt, Labels=Labels, UseLowOnly=UseLowOnly)
def run(limit=None): outDir = "./DataCache/4_EvalSweeps/" # get where the raw data and pre-processed data are obj,Labels = Cacher.ReadProcessedFiles(baseDir,limit=limit) evalObj = pCheckUtil.getCheckpoint(outDir + "forests.pkl", GetEvaluation,True, obj,Labels, RandomForest_Learner) MakeEvalutionPlot(evalObj,outName=outDir + "forests.png")
def run(limit=5): outDir = "./DataCache/4_EvalSweeps/" # get where the raw data and pre-processed data are obj,Labels = Cacher.ReadProcessedFiles(baseDir,limit=limit) evalObj = pCheckUtil.getCheckpoint(outDir + "eval_GMM.pkl", GetEvaluation,True, obj,Labels,GaussianMixtureLearner) MakeEvalutionPlot(evalObj,outName=outDir + "GMMPlot.png")
def run(limit=5): outDir = "./DataCache/4_EvalSweeps/" # get where the raw data and pre-processed data are obj, Labels = Cacher.ReadProcessedFiles(baseDir, limit=limit) evalObj = pCheckUtil.getCheckpoint(outDir + "eval_GMM.pkl", GetEvaluation, True, obj, Labels, GaussianMixtureLearner) MakeEvalutionPlot(evalObj, outName=outDir + "GMMPlot.png")
def ReadProcessedFileFromDirectory(BaseDir, DirectoryPath): """ Given a single element from the output of GetListOfCacheFilesDirectory, returns the pre-processed data Args: BaseDir: the base data directory DirectoryPath: single element of output from GetListOfProcessedFiles Returns: PreProcessedObject corresponding to the file """ filePath = BaseDir + DirectoryPath + "/" + DirectoryPath + ".pkl" return pCheckUtil.loadFile(filePath, useNpy=False)
def ReadProcessedFileFromDirectory(BaseDir,DirectoryPath): """ Given a single element from the output of GetListOfCacheFilesDirectory, returns the pre-processed data Args: BaseDir: the base data directory DirectoryPath: single element of output from GetListOfProcessedFiles Returns: PreProcessedObject corresponding to the file """ filePath = BaseDir + DirectoryPath + "/" + DirectoryPath + ".pkl" return pCheckUtil.loadFile(filePath,useNpy=False)
def run(limit=1): """ Runs the main algorithm Args: limit: the number of files we limit ourselves to """ # get where the raw data and pre-processed data are dataBase = "./DataCache/" cacheSub = dataBase + "2_ProcessedData/" # how many pre-processed objects to use limit = 1 # where the (cached) feature maks should go featureCache = dataBase + "3_FeatureMask/FeatureMask.pkl" # get the feature mask, False means dont force regeneration matr = pCheckUtil.getCheckpoint(featureCache, Caching.GetFeatureMask, True, cacheSub, limit=limit) # create the learner mLearner = NeuralLearner(matr) # get the predictions (binary array for each point) predictIdx = mLearner.FitAndPredict() predEval = mLearner.Evaluate(predictIdx) print(predEval.__dict__) # get the *actual* 'gold standard' event labels. eventIdx = mLearner.IdxWhereEvent toPlot = mLearner.FeatureMask.SepStd # find where we predict an event eventPredicted = np.where(predictIdx == 1)[0] plt.plot(toPlot, alpha=0.3, label="Feature") plt.plot(eventPredicted, toPlot[eventPredicted], 'b.', label="Predicted (Neural Network)") plt.plot(eventIdx, toPlot[eventIdx], 'r.', linewidth=3.0, label="Labelled Events") plt.legend() plt.show()
def GetOrCreatedPreProcessed(BaseDirIn,SourceName,BaseDirOut,Opt,Labels=None, ForceUpdate=False,UseLowOnly=False): """ Given a source name to read, reads from the pre-processed cache, it if exists. Otherwise, creates the data object and pre-processes Args: BaseDirIn: Base directory of where to look for the SourceFiles BaseDirOut: Base directory of where to look for the saved files SourceName: the name of the source Opt: Pre-processing options Labels: the labels of the data object. ForceUpdate: if true, forces an update of the pre-processed data UseLowOnly: see GetPreProcessed Returns: the Pre Processed Object """ outPath = BaseDirOut + SourceName + ".pkl" return pCheckUtil.getCheckpoint(outPath,ReadAndProcess,ForceUpdate, BaseDirIn,SourceName,BaseDirOut,Opt, Labels=Labels,UseLowOnly=UseLowOnly)
def run(limit=1): """ Runs the main algorithm Args: limit: the number of files we limit ourselves to """ # get where the raw data and pre-processed data are dataBase = "./DataCache/" cacheSub = dataBase + "2_ProcessedData/" # how many pre-processed objects to use limit=3 # where the (cached) feature maks should go featureCache = dataBase + "3_FeatureMask/FeatureMask.pkl" # get the feature mask, False means dont force regeneration matr = pCheckUtil.getCheckpoint(featureCache,Caching.GetFeatureMask,True, cacheSub,limit=limit) # create the learner mLearner = LogisticLearner(matr) # get the predictions (binary array for each point) # predictIdx = mLearner.FitAndPredict() predictIdx = mLearner.FitAndPredict() predEval = mLearner.Evaluate(predictIdx) print(predEval.__dict__) # get the *actual* 'gold standard' event labels. eventIdx = mLearner.IdxWhereEvent toPlot = mLearner.FeatureMask.SepStd # find where we predict an event eventPredicted = np.where(predictIdx==1)[0] plt.plot(toPlot,alpha=0.3,label="Feature") plt.plot(eventPredicted,toPlot[eventPredicted],'b.', label="Predicted (Regression)") plt.plot(eventIdx,toPlot[eventIdx],'r.', linewidth=3.0,label="Labelled Events") plt.legend() plt.show()
def CachedLowRes(base="../../../", **kwargs): return pCheckUtil.getCheckpoint("./lowCache.pkl", GetLowResData, False, base, **kwargs)
def CachedLowRes(base="../../../",**kwargs): return pCheckUtil.getCheckpoint("./lowCache.pkl",GetLowResData,False,base, **kwargs)