def trainLogisticRegressionModel(
featureData, labels, Cvalue, outputClassifierFile, scaleData=True, requireAllClasses=True
):
# See [http://scikit-learn.org/dev/modules/generated/sklearn.linear_model.LogisticRegression.html]
# Features are numPixel x numFeature np arrays, labels are numPixel np array
numTrainDataPoints = np.shape(featureData)[0]
numDataLabels = np.size(labels)
assert ( np.size( np.shape(labels) ) == 1) , ("Labels should be a 1d array. Shape of labels = " + str(np.shape(labels)))
assert ( numTrainDataPoints == numDataLabels) , ("The length of the feature and label data arrays must be equal. Num data points=" + str(numTrainDataPoints) + ", labels=" + str(numDataLabels) )
classLabels = np.unique(labels)
assert not requireAllClasses or \
( np.size(classLabels) == pomio.getNumClasses() or np.size(classLabels) == pomio.getNumLabels() ), \
"Training data does not contains all classes::\n\t" + str(classLabels)
if scaleData == True:
featureData = preprocessing.scale(featureData)
# sklearn.linear_model.LogisticRegression(penalty='l2', dual=False, tol=0.0001, C=1.0, fit_intercept=True, intercept_scaling=1, class_weight=None, random_state=None)
lrc = LogisticRegression(penalty='l1' , dual=False, tol=0.0001, C=Cvalue, fit_intercept=True, intercept_scaling=1)
lrc.fit(featureData, labels)
pickleObject(lrc, outputClassifierFile)
print "LogisticRegression classifier saved to " + str(outputClassifierFile)
return lrc
def trainLogisticRegressionModel(featureData,
labels,
Cvalue,
outputClassifierFile,
scaleData=True,
requireAllClasses=True):
# See [http://scikit-learn.org/dev/modules/generated/sklearn.linear_model.LogisticRegression.html]
# Features are numPixel x numFeature np arrays, labels are numPixel np array
numTrainDataPoints = np.shape(featureData)[0]
numDataLabels = np.size(labels)
assert (np.size(np.shape(labels)) == 1), (
"Labels should be a 1d array. Shape of labels = " +
str(np.shape(labels)))
assert (numTrainDataPoints == numDataLabels), (
"The length of the feature and label data arrays must be equal. Num data points="
+ str(numTrainDataPoints) + ", labels=" + str(numDataLabels))
classLabels = np.unique(labels)
assert not requireAllClasses or \
( np.size(classLabels) == pomio.getNumClasses() or np.size(classLabels) == pomio.getNumLabels() ), \
"Training data does not contains all classes::\n\t" + str(classLabels)
if scaleData == True:
featureData = preprocessing.scale(featureData)
# sklearn.linear_model.LogisticRegression(penalty='l2', dual=False, tol=0.0001, C=1.0, fit_intercept=True, intercept_scaling=1, class_weight=None, random_state=None)
lrc = LogisticRegression(penalty='l1',
dual=False,
tol=0.0001,
C=Cvalue,
fit_intercept=True,
intercept_scaling=1)
lrc.fit(featureData, labels)
pickleObject(lrc, outputClassifierFile)
print "LogisticRegression classifier saved to " + str(outputClassifierFile)
return lrc
else:
labs = pomio.readMatFromCSV(infileLabs).astype(np.int32)
n = len(labs)
assert n == ftrs.shape[0], 'Error: there are %d labels and %d training examples' \
% ( n, ftrs.shape[0] )
assert np.all(np.isfinite(ftrs))
print 'There are %d unique labels in range [%d,%d]' % (len(
np.unique(labs)), np.min(labs), np.max(labs))
if args.verbose:
print 'There are %d training examples' % len(labs)
plt.interactive(True)
plt.hist(labs, bins=range(pomio.getNumLabels()))
plt.waitforbuttonpress()
# Train the classifier, either with CV param search or with default values
if paramSearch:
paramSrc = 'grid search'
# create crossValidation object
stratCV = cross_validation.StratifiedKFold(labs, paramSearchFolds)
print 'Training %s classifier using %d-fold cross-validation parameter search, over %s samples...' % (
clfrType, paramSearchFolds, n)
# empy param values
params = {}
if clfrType == 'logreg':
labs = pomio.unpickleObject( infileLabs )
else:
labs = pomio.readMatFromCSV( infileLabs ).astype(np.int32)
n = len(labs)
assert n == ftrs.shape[0], 'Error: there are %d labels and %d training examples' \
% ( n, ftrs.shape[0] )
assert np.all( np.isfinite( ftrs ) )
print 'There are %d unique labels in range [%d,%d]' % ( len(np.unique(labs)), np.min(labs), np.max(labs) )
if args.verbose:
print 'There are %d training examples' % len(labs)
plt.interactive(True)
plt.hist( labs, bins=range(pomio.getNumLabels()) )
plt.waitforbuttonpress()
# Train the classifier, either with CV param search or with default values
if paramSearch:
paramSrc = 'grid search'
# create crossValidation object
stratCV = cross_validation.StratifiedKFold(labs, paramSearchFolds)
print 'Training %s classifier using %d-fold cross-validation parameter search, over %s samples...' % (clfrType, paramSearchFolds, n)
# empy param values
params = {}
if clfrType == 'logreg':
# create a set of C value and regularisation types for logisitc regression