def setUp(self):
for i in range(len(test_cases)):
results.append(
bootstrap(test_cases[i]['sample'], test_cases[i]['predstot'],
test_cases[i]['predsdim']))
resultsInt64.append(
bootstrap(test_cases[i]['sample'], test_cases[i]['predstot'],
test_cases[i]['predsdim'], True))
def main(args):
trees = args.trees
depth = args.depth
train = args.train
test = args.test
test = test.replace('\r','') #Removes the carriage return cuz I use windows
#Load the data in and convert to numpy
with open(train,"r") as read_file:
train = json.load(read_file)
train = json2numpy(train)
with open(test,"r") as read_file:
test = json.load(read_file)
test = json2numpy(test)
bootstrap(trees, depth, train, test, display = True)
def main(args):
method = args.method
trees = args.trees
depth = args.depth
train = args.train
test = args.test
test = test.replace('\r','') #Removes the carriage return cuz I use windows
#Load the data in and convert to numpy
with open(train,"r") as read_file:
train = json.load(read_file)
train = json2numpy(train)
with open(test,"r") as read_file:
test = json.load(read_file)
test = json2numpy(test)
#Pull the true labels
truth = test.labels
#Generate the predictions from the ensemble
if method == 'bag':
predictions = bootstrap(trees, depth, train, test, display = False)
elif method == 'boost':
predictions = adaboost(trees, depth, train, test, display = False)
else:
print('Invalid ensemble method.')
build_confusion_matrix(test, predictions, verbose = True)
msusc = np.zeros(len(sizes))
mbeta = np.zeros(len(sizes))
merr = np.zeros(len(sizes))
start = time.time()
mag = np.zeros((len(sizes), risol))
for L in sizes:
print "Lattice dimension:", L
for j in range(len(beta)):
conf = 2 * np.random.randint(2, size=(L, L, L)) - 1
magn, cc = fx.clusteralg(conf, beta[j], beta[j], T)
print(j)
susc[j] = fx.suscet(magn[cut:], conf)
stsusc[j] = fx.bootstrap(magn[cut:], 500, fx.suscet, conf)
binder[j] = fx.bindercum(magn[cut:], conf)
stbinder[j] = fx.bootstrap(magn[cut:], 500, fx.bindercum, conf)
if (L == 40):
plt.figure(j + 4)
plt.title('beta=' + str(beta[j]))
plt.hist(magn, normed="True")
plt.savefig('histBeta=' + str(beta[j]) + '.pdf')
mag[sizes.index(L), :] = np.mean(magn[cut:])
msusc[sizes.index(L)] = susc.max()
mbeta[sizes.index(L)] = beta[list(susc).index(susc.max())]
merr[sizes.index(L)] = stsusc[list(susc).index(susc.max())]
plt.figure(2)
plt.grid(True)
plt.title("Cumulante di binder")
plt.xlabel("Beta")
def main(args):
method = args.method
trees = args.trees
depth = args.depth
train = args.train
test = args.test
test = test.replace('\r','') #Removes the carriage return cuz I use windows
data_origin = test.replace('_test.json','')
data_origin = data_origin.replace('data/','')
#Load the data in and convert to numpy
with open(train,"r") as read_file:
train = json.load(read_file)
train = json2numpy(train)
with open(test,"r") as read_file:
test = json.load(read_file)
test = json2numpy(test)
#Pull the true labels
truth = test.labels
#Generate the predictions from the ensemble, create list of coordinates
xlist = []
ylist = []
if method == 'bag':
title = 'Decision Tree Bagging: Accuracy vs. Number of trees'
filename = 'bagged_tree_plot.pdf'
caption = ('Dataset: ' + data_origin)
depth1 = depth - 2
depth2 = depth
depth3 = depth + 2
for j in [depth1,depth2,depth3]:
for i in range(1,trees+1):
predictions = bootstrap(i, j, train, test, display = False)
accuracy = sum((truth == predictions).astype(float)) / test.length
xlist.append(i)
ylist.append(accuracy)
plt.plot(xlist,ylist)
xlist = []
ylist = []
elif method == 'boost':
title = 'Decision Tree AdaBoost: Accuracy vs. Number of trees'
filename = 'boosted_tree_plot.pdf'
caption = ('Dataset: ' + data_origin)
depth1 = depth - 1
depth2 = depth
depth3 = depth + 1
for j in [depth1,depth2,depth3]:
for i in range(1,trees+1):
predictions = adaboost(i, j, train, test, display = False)
accuracy = sum((truth == predictions).astype(float)) / test.length
xlist.append(i)
ylist.append(accuracy)
plt.plot(xlist,ylist)
xlist = []
ylist = []
else:
print('Invalid ensemble method.')
#Plot the data
plt.legend([depth1,depth2,depth3], loc = "lower right", title = "Maximum tree depth", fancybox = True)
plt.xlabel('Ensemble size')
plt.ylabel('Accuracy')
plt.ylim([0.0, 1.05])
plt.xlim([1, trees])
plt.title(caption, fontsize = 9, wrap = True)
plt.suptitle(title)
plt.savefig(filename)