def __init__(self, testData, model, ytrue=[]):
N=10
print model.rng
data = ExtraFeatures()
data.fit_transform(testData.X)
self.predictions=[]
self.mainModelPredictions=self.evaluateMainModel(data, model)
#self.invIdxModelPredictions=self.lookupIdx(testData, model, N)
#self.distanceBasedClassifier=self.distanceBasedClassifier(data,model,0)
for i, vector in enumerate(data.features):
label = -1
k=0 #To track which classifier was used in prediction
if self.mainModelPredictions[i] >= 1:
label = 1
k = 5
#elif data[0]>0 and len(data[-1]) <= 3:
# for word in data[-1]:
# if word in model.plist:
# label = 1
# k=1
# break
#elif len(data[-1]) == 1 and data[-1][0] in model.plist:
# k=2
# label = 1
#elif vector[2]>0:
# k=3
# label=1
#elif self.invIdxModelPredictions[i]==1:
# label= 1
# k=4
self.predictions.append(label)
def __init__(self, trainingData):
comments = trainingData.X
yTrain = trainingData.y
# print yTrain
# this model is no longer useful
self.invIdx = {}
data = ExtraFeatures()
data.fit_transform(comments, yTrain)
lf = np.asmatrix(np.asarray(data.features))
print lf[0]
mins = np.min(lf, axis=0)
maxs = np.max(lf, axis=0)
self.rng = copy.deepcopy(maxs - mins)
print self.rng
print self.rng.shape
lf = lf / self.rng
# print lf
self.WordFeatures = TfidfVectorizer(
ngram_range=(1, 3), smooth_idf=True, max_features=2500, stop_words=["you you"]
)
self.WordFeatures.fit_transform(data.new_documents)
wf = self.WordFeatures.transform(data.new_documents)
# XTrain = lf
XTrain = scipy.sparse.coo_matrix(np.concatenate((wf.todense(), lf), axis=1))
# XTrain = wf
# Scaling seems to worsen the performance
# Smaller C implies stronger regularization
# mainModel = RandomForestClassifier(n_estimators=10)
mainModel = LogisticRegression(penalty="l1")
wModel = LogisticRegression(penalty="l1")
lModel = LogisticRegression(penalty="l2")
# mainModel = svm.LinearSVC(penalty='l1', loss='l2', dual=False,
# tol=0.0001, fit_intercept=True, random_state=1)
score_func = metrics.roc_auc_score
cv = StratifiedShuffleSplit(yTrain, n_iter=5, test_size=0.20)
param_grid = {"C": [0.1, 0.25, 0.5, 1], "class_weight": [{-1: 1, 1: 2}, {-1: 1, 1: 2.25}, {-1: 1, 1: 1.5}]}
# bs = Bootstrap(nsamples, n_iter=25, test_size=0.20, random_state=1)
self.classifier = GridSearchCV(
mainModel, param_grid, loss_func=None, scoring="roc_auc", n_jobs=3, refit=True, cv=cv, verbose=1
)
self.classifier.fit(XTrain, yTrain)
print "Best %s: %0.3f" % (score_func.__name__, self.classifier.best_score_)
print "Best parameters set:"
best_parameters = self.classifier.best_estimator_.get_params()
for param_name in param_grid.keys():
print "\t%s: %r" % (param_name, best_parameters[param_name])
# newY=[]
# ypred = self.classifier.predict(XTrain)
# print ypred
# for i in xrange(len(yTrain)-1, 0, -1):
# if ypred[i] != yTrain[i]:
# newY.append(yTrain[i])
# else:
# np.delete(lf, i)
#
# newY = np.asarray(newY.reverse())
# print lf.shape, newY.shape
#
# self.classifier2 = GridSearchCV(mainModel, param_grid, loss_func=None,
# scoring='roc_auc', n_jobs=3, refit=True, cv=cv, verbose=1)
#
# self.classifier2.fit(lf, newY)
# print "Best %s: %0.3f" % (score_func.__name__, self.classifier2.best_score_)
# print "Best parameters set:"
# best_parameters = self.classifier2.best_estimator_.get_params()
# for param_name in param_grid.keys():
# print "\t%s: %r" % (param_name, best_parameters[param_name])
self.wclassifier = GridSearchCV(
wModel, param_grid, loss_func=None, scoring="roc_auc", n_jobs=3, refit=True, cv=cv, verbose=1
)
self.wclassifier.fit(wf, yTrain)
print "Best %s: %0.3f" % (score_func.__name__, self.wclassifier.best_score_)
print "Best parameters set:"
best_parameters = self.wclassifier.best_estimator_.get_params()
for param_name in param_grid.keys():
print "\t%s: %r" % (param_name, best_parameters[param_name])
self.lclassifier = GridSearchCV(
lModel, param_grid, loss_func=None, scoring="roc_auc", n_jobs=3, refit=True, cv=cv, verbose=1
)
self.lclassifier.fit(lf, yTrain)
print "Best %s: %0.3f" % (score_func.__name__, self.lclassifier.best_score_)
print "Best parameters set:"
best_parameters = self.lclassifier.best_estimator_.get_params()
for param_name in param_grid.keys():
print "\t%s: %r" % (param_name, best_parameters[param_name])
