def train(feats, labels, T): ab_labels = transform_labels(labels) ft = feats.transpose() abs = [] for i in range(30): abs.append(AdaBoost(T, ft[i], ab_labels)) abs[-1].train() return abs
def main():
print "Init data"
data = pd.read_csv(sys.argv[1])
columnas = data.columns.tolist()
x = columnas[len(columnas) - 1]
target = data[x]
y = columnas[0:len(columnas) - 1]
dataset = data[y]
AdaBoostObject = AdaBoost.AdaBoost(dataset, target, 3, 'SAMME', 10)
AdaBoostObject.trainingMethod()
#curva roc
#curveRocObject = createRocCurve.curveRoc(dataset, target, AdaBoostObject.model, 10, 'user', 'job', 'path')
#curveRocObject.createCurveROC()
#precision-recall curve
#precisionCurve = createPrecisionRecallCurve.curvePrecision(dataset, target, AdaBoostObject.model, 10, 'user', 'job', 'path')
#precisionCurve.plot_precision_and_recall_curve()
#learning curve
#learningCurveDemo = createLearningCurve.curveLearning(dataset, target, AdaBoostObject.model, 10, 'user', 'job', 'path')
#learningCurveDemo.createLearningCurve()
#confusion matrix data
confusionMatrixDemo = createConfusionMatrix.confusionMatrix(
dataset, target, AdaBoostObject.model, 10, 'user', 'job', 'path',
["Clinical", "No Clinical"])
confusionMatrixDemo.createConfusionMatrix()
#bagginObject = Baggin.Baggin(dataset,target,3,10)
#bagginObject.trainingMethod()
#bernoulliNB = BernoulliNB.Bernoulli(dataset, target, 10)
#bernoulliNB.trainingMethod()
#decisionTreeObject = DecisionTree.DecisionTree(dataset, target, 'entropy', 'best',10)
#decisionTreeObject.trainingMethod()
#gaussianObject = GaussianNB.Gaussian(dataset, target, 10)
#gaussianObject.trainingMethod()
#gradientObject = Gradient.Gradient(dataset,target,3,10)
#gradientObject.trainingMethod()
#knnObect = knn.knn(dataset, target, 2, 'auto', 'minkowski', 10)
#knnObect.trainingMethod()
#MLPObject = MLP.MLP(dataset,target,'relu', 'sgd', 'adaptive', 1,1,1,10)
#MLPObject.trainingMethod()
#nuSVM = NuSVM.NuSVM(dataset,target,'poly',10)
#nuSVM.trainingMethod()
#rf = RandomForest.RandomForest(dataset,target,10,'gini',10)
#rf.trainingMethod()
#svm = SVM.SVM(dataset, target, 'poly', 10)
#svm.trainingMethod()
return 0
def TrainAndTestAdaBoostWeakBinPerceptron():
if len(digits) > 2:
print "digits should be 2 digits in the case of Binary Perceptron"
print "Running the AdaBoost with Weak Binary Perceptron"
print "the digits it shall descriminate between: " + str(
digits[0]) + "," + str(digits[1])
print "the label 1 will be given to the digit " + str(digits[0])
fullimg, lbl = rn.getData(digits, "training")
binlbl = rn.BinaryLabels(lbl, digit)
reducedList = rn.getReductionList(colnum, rownum)
img = rn.ReduceSetDimension(reducedList, fullimg)
adaboost = ab.AdaBoost(pr.Perceptron, img, binlbl, Twl,
int(len(lbl) * alpha))
print "Error on the Training data: " + str(
pr.TestClassifier(img, binlbl, adaboost) * 100.0) + "%"
print "(out of " + str(len(binlbl)) + " samples)"
print "Extracting the Testing Data"
fullimg, lbl = rn.getData(digits, "testing")
img = rn.ReduceSetDimension(reducedList, fullimg)
binlbl = rn.BinaryLabels(lbl, digit)
print "Error on the Testing data: " + str(
pr.TestClassifier(img, binlbl, adaboost) * 100.0) + "%"
print "(out of " + str(len(binlbl)) + " samples)"
def main(number_of_stages, set_pos, set_neg):
trainer = AdaBoost(set_pos, set_neg, number_of_stages)
classifiers = trainer.train_simple()
image = cv2.imread("1.pgm")
print(StrongClassifier(classifiers, pgm_simplifier(image)).get_result())
PP = PreProcess.PreProcess(data, n_buckets=10,
func='boolean') #,swap_labels=True)
data = PP.fit(data)
testset = PP.fit(testset)
# read weights
weights = []
for w in range(6):
tmp = [float(line.rstrip('\n')) for line in open('result/W' + str(w))]
if len(tmp) != len(data[0]):
continue
weights.append(tmp)
ab = AdaBoost.AdaBoost(weightVector=weights)
ab.fit(data, data_labels)
predictTrain = ab.predict(data)
predictTest = ab.predict(testset)
print("Accuracy for training set:")
print(Stat.Accuracy(predictTrain, data_labels))
print("F1 score for training set:")
print(Stat.F1_Score(predictTrain, data_labels))
print("Precision for training set:")
print(Stat.Precision(predictTrain, data_labels))
print("Recall for training set:")
from AdaBoost import *
from sys import argv
x_train = argv[1]
y_train = argv[2]
x_test = argv[3]
y_test = argv[4]
T = int(argv[5])
feats = np.loadtxt(x_train, delimiter=',', dtype=np.float).transpose()
labels = np.loadtxt(y_train, delimiter=',', dtype=np.int)
ab_labels = np.array([1 if i == 1 else -1 for i in labels])
abs = []
for i in range(30):
abs.append(AdaBoost(T, feats[i], ab_labels))
abs[-1].train()
x_test = np.loadtxt(x_test, delimiter=',', dtype=np.float)
y_test = np.loadtxt(y_test, delimiter=',', dtype=np.float)
ab_y_test = np.array([1 if i == 1 else -1 for i in y_test])
predictions = []
for i in range(x_test.shape[0]):
predictions.append(
np.sign(
np.sum([abs[j].eval(x_test[i][j])
for j in range(x_test.shape[1])])))
print("accuracy = {}".format(
len(np.where(predictions == ab_y_test)[0]) / len(ab_y_test)))
