def run(self, k=3, useOnlyRF=True):
featureGetter = FeatureGetter()
fileNameTrain = data_io.get_savez_name()
fileNameTest = data_io.get_savez_name_test()
print "Merging files..."
(namesObservations, coordinates, dataset) = self.mergeFiles(fileNameTrain, fileNameTest)
dataset = dataset[:,self.filterIndexes(len(dataset[0]))]
print "Shuffling and splitting the data"
indexesChanged = np.arange(len(dataset))
np.random.shuffle(indexesChanged)
splittedNamesObs = self.getShuffledSplits(namesObservations, indexesChanged, k+1)
splittedCoords = self.getShuffledSplits(coordinates, indexesChanged, k+1)
splittedData = self.getShuffledSplits(dataset, indexesChanged, k+1)
"""Leave the last split for testing"""
testNamesObs = splittedNamesObs[k]
testCoords = splittedCoords[k]
testDataset = splittedData[k]
splittedNamesObs = splittedNamesObs[:k]
splittedCoords = splittedCoords[:k]
splittedData = splittedData[:k]
del(dataset)
del(coordinates)
del(namesObservations)
del(indexesChanged)
bestModel = None
bestFmeasure = 0
for i in range(k-1,-1,-1):#i is the index of the validation
print "Doing cross-validation for i=%d" %i
namesObservationsValid = splittedNamesObs[i]
coordinatesValid = splittedCoords[i]
datasetValid = splittedData[i]
namesObservationsValid = np.reshape(namesObservationsValid, namesObservationsValid.shape[0])
namesObservationsTrain = self.getTrainData(splittedNamesObs,i)
coordinatesTrain = self.getTrainData(splittedCoords,i)
datasetTrain = self.getTrainData(splittedData, i)
namesObservationsTrain = np.reshape(namesObservationsTrain, namesObservationsTrain.shape[0])
print "Getting target vector"
(indexes, target, obs) = featureGetter.getTargetVector(coordinatesTrain, namesObservationsTrain, datasetTrain)
print "Selecting features"
classifier = RandomForestClassifier(n_estimators=100, verbose=2, n_jobs=1, min_samples_split=1, random_state=1, compute_importances=True)
model = Pipeline([('scaling', MinMaxScaler()), ('classifying', classifier)])
model.fit(obs[indexes], target[indexes])
if not useOnlyRF:
importances = classifier.feature_importances_
filterImportances = np.where(importances > 0.0001)[0]
print len(filterImportances)
#namesObservationsTrain = np.reshape(namesObservationsTrain, namesObservationsTrain.shape[0])
print "Training model"
#classifier = RandomForestClassifier(n_estimators=500, verbose=2, n_jobs=1, min_samples_split=100, random_state=1, compute_importances=True)
#classifier = KNeighborsClassifier()
classifier = LinearSVC(verbose=1)
#classifier = MLPClassifier(verbose=1)
model = Pipeline([('scaling', MinMaxScaler()), ('classifying', classifier)])
model.fit(obs[indexes][:,filterImportances], target[indexes])
print "Making predictions"
if not useOnlyRF:
predictions = model.predict(datasetValid[:,filterImportances])
else:
predictions = model.predict(datasetValid)
predictions = predictions.reshape(len(predictions), 1)
print "Calculating validation results"
[_, _, _, _, _, fmeasure, _] = Predictor.finalResults(namesObservationsValid, predictions, coordinatesValid)
if fmeasure > bestFmeasure:
bestFmeasure = fmeasure
bestModel = model
del(datasetTrain)
del(datasetValid)
del(coordinatesTrain)
del(coordinatesValid)
del(namesObservationsTrain)
del(namesObservationsValid)
print "Calculating final results"
predictions = bestModel.predict(testDataset)
print "The final score is: "
testNamesObs = np.reshape(testNamesObs, testNamesObs.shape[0])
Predictor.finalResults(testNamesObs, predictions, testCoords)
def run(self, k=3, patientSplit=True, useOnlyRF=True, breakin2=True):
featureGetter = FeatureGetter()
overallTP = 0
overallFP = 0
overallFN = 0
fileNameTrain = data_io.get_savez_name()
fileNameTest = data_io.get_savez_name_test()
print "Merging files..."
(namesObservations, coordinates, dataset) = self.mergeFiles(fileNameTrain, fileNameTest)
dataset = dataset[:,self.filterIndexes(len(dataset[0]))]
print "Shuffling and splitting the data"
indexesChanged = np.arange(len(dataset))
np.random.shuffle(indexesChanged)
if patientSplit:
k = 12
(splittedNamesObs, splittedCoords, splittedData) = self.getSplits(namesObservations, coordinates, dataset)
if breakin2:
k = 2
(splittedNamesObs, splittedCoords, splittedData) = self.getNewSplits(splittedNamesObs, splittedCoords, splittedData)
else:
splittedNamesObs = self.getShuffledSplits(namesObservations, indexesChanged, k)
splittedCoords = self.getShuffledSplits(coordinates, indexesChanged, k)
splittedData = self.getShuffledSplits(dataset, indexesChanged, k)
del(dataset)
del(coordinates)
del(namesObservations)
del(indexesChanged)
overallArrayTP = np.zeros(12)
overallArrayFP = np.zeros(12)
overallArrayFN = np.zeros(12)
for i in range(k-1,-1,-1):#i is the index of the validation
print "Doing cross-validation for i=%d" %i
namesObservationsTest = splittedNamesObs[i]
coordinatesTest = splittedCoords[i]
datasetTest = splittedData[i]
namesObservationsTest = np.reshape(namesObservationsTest, namesObservationsTest.shape[0])
namesObservationsTrain = self.getTrainData(splittedNamesObs,i)
coordinatesTrain = self.getTrainData(splittedCoords,i)
datasetTrain = self.getTrainData(splittedData, i)
namesObservationsTrain = np.reshape(namesObservationsTrain, namesObservationsTrain.shape[0])
print "Getting target vector"
(indexes, target, obs) = featureGetter.getTargetVector(coordinatesTrain, namesObservationsTrain, datasetTrain)
print "Selecting features"
classifier = RandomForestClassifier(n_estimators=100, verbose=2, n_jobs=1, min_samples_split=1, random_state=1, compute_importances=True)
model = Pipeline([('scaling', MinMaxScaler()), ('classifying', classifier)])
model.fit(obs[indexes], target[indexes])
if not useOnlyRF:
importances = classifier.feature_importances_
filterImportances = np.where(importances > 0.0001)[0]
print len(filterImportances)
#namesObservationsTrain = np.reshape(namesObservationsTrain, namesObservationsTrain.shape[0])
print "Training model"
#classifier = RandomForestClassifier(n_estimators=500, verbose=2, n_jobs=1, min_samples_split=100, random_state=1, compute_importances=True)
#classifier = KNeighborsClassifier()
classifier = LinearSVC(verbose=1)
#classifier = MLPClassifier(verbose=1)
model = Pipeline([('scaling', MinMaxScaler()), ('classifying', classifier)])
model.fit(obs[indexes][:,filterImportances], target[indexes])
print "Making predictions"
if not useOnlyRF:
predictions = model.predict(datasetTest[:,filterImportances])
else:
predictions = model.predict(datasetTest)
predictions = predictions.reshape(len(predictions), 1)
print "Calculating final results"
[truePositives, falsePositives, falseNegatives, _, _, _, (arrayTP, arrayFP, arrayFN)] = Predictor.finalResults(namesObservationsTest, predictions, coordinatesTest)
print arrayTP
print arrayFP
print arrayFN
overallArrayTP += arrayTP
overallArrayFP += arrayFP
overallArrayFN += arrayFN
overallTP += truePositives
overallFP += falsePositives
overallFN += falseNegatives
del(datasetTrain)
del(datasetTest)
del(coordinatesTrain)
del(coordinatesTest)
del(namesObservationsTrain)
del(namesObservationsTest)
precision = 0 if overallTP+overallFP == 0 else (overallTP+0.0)/(overallTP+overallFP+0.0)
recall = 0 if overallTP+overallFN == 0 else (overallTP+0.0)/(overallTP+overallFN+0.0)
fmeasure = 0 if recall+precision == 0 else 2*(precision*recall)/(recall+precision)
print "Overall results for k=%d" %k
print overallTP
print overallFP
print overallFN
print precision
print recall
print fmeasure
for i in range(len(overallArrayTP)):
"Results for patient number %d:"% (i+1)
overallTP = overallArrayTP[i]
overallFP = overallArrayFP[i]
overallFN = overallArrayFN[i]
precision = 0 if overallTP+overallFP == 0 else (overallTP+0.0)/(overallTP+overallFP+0.0)
recall = 0 if overallTP+overallFN == 0 else (overallTP+0.0)/(overallTP+overallFN+0.0)
fmeasure = 0 if recall+precision == 0 else 2*(precision*recall)/(recall+precision)
print precision
print recall
print fmeasure