def heart(dataType):
title = '{0} Ada Boost'.format(dataType)
package = data.createData(dataType)
xTrain = package.xTrain
xTest = package.xTest
yTrain = package.yTrain
yTest = package.yTest
param_range = list(range(1, 160, 10))
param = 'n_estimators'
params = {'algorithm': 'SAMME.R'}
clf = AdaBoostClassifier()
clf.set_params(**params)
plotter.plotValidationCurve(clf,
xTrain,
yTrain,
param,
param_range,
graphTitle=title)
plotter.plotLearningCurve(clf, title=title, xTrain=xTrain, yTrain=yTrain)
title = 'Heart'
clf.fit(xTrain, yTrain)
plotter.plotConfusion(clf, title,
['Diameter narrowing ', 'Diameter not narrowing'],
xTest, yTest)
def heart(dataType):
package = data.createData(dataType)
xTrain = package.xTrain
xTest = package.xTest
yTrain = package.yTrain
yTest = package.yTest
title = '{0} Decision Tree'.format(dataType)
xLabel = 'Depth'
scoreList = util.ScoreList(xLabel)
param_range = list(range(1, 20))
param = 'max_depth'
params = {
'class_weight': None,
'criterion': 'entropy',
'max_features': None,
'min_samples_leaf': 10,
'splitter': 'best'
}
clf_tree = DecisionTreeClassifier(random_state=util.randState)
clf_tree.set_params(**params)
plotter.plotValidationCurve(clf_tree,
xTrain,
yTrain,
param,
param_range,
graphTitle=title + ' Max Depth ')
plotter.plotLearningCurve(clf_tree,
title=title + 'Max Depth',
xTrain=xTrain,
yTrain=yTrain)
clf_tree = DecisionTreeClassifier(random_state=util.randState)
clf_tree.set_params(**params)
clf_tree.max_depth = 8
param_range = [10, 50, 75, 100]
param = 'min_samples_leaf'
plotter.plotValidationCurve(clf_tree,
xTrain,
yTrain,
param,
param_range,
graphTitle=title + ' Min Samples Leaf ')
clf_tree.min_samples_leaf = 10
title = 'Heart'
# plotter.plotLearningCurve(clf_tree, title=title + 'Min Samples Leaf', xTrain=xTrain, yTrain=yTrain)
plotter.plotLearningCurve(clf_tree,
title=title,
xTrain=xTrain,
yTrain=yTrain)
clf_tree.fit(xTrain, yTrain)
plotter.plotConfusion(clf_tree, title,
['Diameter narrowing ', 'Diameter not narrowing'],
xTest, yTest)
def adult(dataType):
package = data.createData(dataType)
xTrain = package.xTrain
xTest = package.xTest
yTrain = package.yTrain
yTest = package.yTest
xLabel = 'Network Layers'
scoreList = util.ScoreList(xLabel)
title = '{0} Neural Network'.format(dataType)
params = {
'activation': 'relu',
'learning_rate': 'adaptive',
'solver': 'sgd'
}
params = {
'activation': 'relu',
'learning_rate': 'invscaling',
'solver': 'lbfgs'
}
# params = searcher.searchNetwork(xTrain, yTrain, xTest, yTest)
clf = MLPClassifier(max_iter=250)
input = package.features.shape[1]
input = int(.7 * input)
# hiddenLayers = (input, 20)
# hiddenLayers = (input,)
# param_range = [(input,1,2), (input,2,2),(input,3,2),(input,4,2),(input,5,2),(input,6,2),(input,7,2),(input,8,2),(input,9,2), (input,10,2)]
# xRange = [1, 2, 3, 4, 5, 6, 7 , 8, 9, 10]
# plotter.plotValidationCurve(clf, xTrain, yTrain, 'hidden_layer_sizes', param_range, title + ' Hidden Layers ', xRange)
# clf = MLPClassifier(hidden_layer_sizes = (input,7,2))
# clf.set_params(**params)
# param_range = [50, 75, 100, 125, 150, 175, 200, 225, 250, 275, 300, 400, 500, 600, 700, 800]
# plotter.plotValidationCurve(clf, xTrain, yTrain, 'max_iter', param_range, graphTitle=title + ' Max Iterations ')
clf = MLPClassifier(hidden_layer_sizes=(input, 7, 2))
clf.max_iter = 150
plotter.plotLearningCurves(clf, title=title, xTrain=xTrain, yTrain=yTrain)
title = 'Adult'
clf.fit(xTrain, yTrain)
plotter.plotConfusion(clf, title, ['>50K', '<=50K'], xTest, yTest)
return
def heart(dataType):
package = data.createData(dataType)
xTrain = package.xTrain
xTest = package.xTest
yTrain = package.yTrain
yTest = package.yTest
xLabel = 'K'
scoreList = util.ScoreList(xLabel)
title = '{0} KNN'.format(dataType)
# searcher.searchKNN(xTrain, yTrain, xTest, yTest)
params = {'algorithm': 'auto', 'p': 1, 'weights': 'uniform'}
params = {'algorithm': 'ball_tree', 'p': 1, 'weights': 'distance'}
# params = searcher.searchKNN(xTrain, yTrain, xTest, yTest)
param = 'n_neighbors'
param_range = list(range(1, 50)) #np.linspace(1, 50, 50)
clf = KNeighborsClassifier()
clf.set_params(**params)
plotter.plotValidationCurve(clf,
xTrain,
yTrain,
param,
param_range,
graphTitle=title)
clf = KNeighborsClassifier()
clf.set_params(**params)
clf.n_neighbors = 12
plotter.plotLearningCurve(clf, title=title, xTrain=xTrain, yTrain=yTrain)
# plotter.plotAll(clf, title, param, param_range, xTrain, yTrain, xTest, yTest)
title = 'Heart'
clf.fit(xTrain, yTrain)
plotter.plotConfusion(clf, title,
['Diameter narrowing ', 'Diameter not narrowing'],
xTest, yTest)
def adult(dataType):
package = data.createData(dataType)
xTrain = package.xTrain
xTest = package.xTest
yTrain = package.yTrain
yTest = package.yTest
xLabel = 'Degrees'
title = '{0} SVM'.format(dataType)
param_range = list(range(1,8))
# polyparams = searcher.searchSVMPoly(xTrain, yTrain, xTest, yTest)
polyparams = {'C': 0.1, 'degree': 1, 'gamma': 50, 'kernel': 'poly'}
clf = createBaseSVC()
clf.set_params(**polyparams)
plotter.plotValidationCurve(clf, xTrain, yTrain, 'degree', param_range, graphTitle=title + ' Poly degree ')
clf.degree = 1
plotter.plotLearningCurve(clf, title=title + ' Poly degree ', xTrain=xTrain, yTrain=yTrain)
# rbfParams = searcher.searchSVMRBF(xTrain, yTrain, xTest, yTest)
rbfParams = {'C': 1000, 'gamma': 0.01, 'kernel': 'rbf'}
clf = createBaseSVC()
clf.set_params(**rbfParams)
param = 'C'
# param_range = [0.01,0.05,1,10,50,100,200,300,500, 1000]
param_range = [0.01,0.05,1,10,15]
plotter.plotValidationCurve(clf, xTrain, yTrain, param, param_range, graphTitle=title+ ' RBF - C ')
clf.C = 10
plotter.plotLearningCurve(clf, title=title + ' RBF', xTrain=xTrain, yTrain=yTrain)
title = 'Adult'
clf.fit(xTrain, yTrain)
plotter.plotConfusion(clf, title, ['>50K', '<=50K'], xTest, yTest)
def heart(dataType):
package = data.createData(dataType)
xTrain = package.xTrain
xTest = package.xTest
yTrain = package.yTrain
yTest = package.yTest
title = '{0} SVM'.format(dataType)
param_range = list(range(1,8))
# polyparams = searcher.searchSVMPoly(xTrain, yTrain, xTest, yTest)
# polyparams = {'kernel': 'poly', 'gamma': 'scale'}
polyparams = {'C': 0.01, 'degree': 3, 'gamma': 10, 'kernel': 'poly'}
clf = createBaseSVC()
clf.set_params(**polyparams)
plotter.plotValidationCurve(clf, xTrain, yTrain, 'degree', param_range, graphTitle=title + ' Poly Degree ')
clf.degree = 3
plotter.plotLearningCurve(clf, title=title + ' Poly degree ', xTrain=xTrain, yTrain=yTrain)
# rbfParams = searcher.searchSVMRBF(xTrain, yTrain, xTest, yTest)
rbfParams = {'C': 1, 'gamma': 1, 'kernel': 'rbf'}
clf = createBaseSVC()
clf.set_params(**rbfParams)
param = 'C'
param_range = [0.01,0.05,0.25, 0.5, 1]
plotter.plotValidationCurve(clf, xTrain, yTrain, param, param_range, graphTitle=title + ' RBF - C ')
clf.C = 0.5
plotter.plotLearningCurve(clf, title=title + ' RBF', xTrain=xTrain, yTrain=yTrain)
title = 'Heart'
clf.fit(xTrain, yTrain)
plotter.plotConfusion(clf, title, ['Diameter narrowing ', 'Diameter not narrowing'], xTest, yTest)