def test_process(self):
iris_mat_train, iris_label_train = dataset.load_iris("sample_data", "training", one_hot=True)
iris_mat_test, iris_label_test = dataset.load_iris("sample_data", "testing", one_hot=True)
linear_reg = LinearRegression(iris_mat_train, iris_label_train)
linear_reg.fit(lr = 0.0001, epoch = 1000, batch_size = 20)
error_rate = autotest.eval_predict(linear_reg, iris_mat_test, iris_label_test, self.logging, one_hot=True)
self.tlog("iris predict (with linear regression) error rate :" + str(error_rate))
def test_process(self):
lense_mat_train, lense_label_train, lense_mat_test, lense_label_test=\
fs.tsv_loader("sample_data/lense/lense.tsv", 0.3)
dtree_lense = DecisionTreeID3(lense_mat_train,lense_label_train)
tree_structure = dtree_lense.build()
self.tlog("Tree structure : " + str(tree_structure))
error_rate = autotest.eval_predict(dtree_lense, lense_mat_test, lense_label_test, self.logging)
self.tlog("lense predict (with decision tree) error rate : " +str(error_rate))
def test_process(self):
iris_mat_train, iris_label_train = dataset.load_iris("sample_data", "training", one_hot=True)
iris_mat_test, iris_label_test = dataset.load_iris("sample_data", "testing", one_hot=True)
fnn = FNN(iris_mat_train, iris_label_train, [2])
fnn.fit(lr = 0.001, epoch = 4000, err_th = 0.00001, batch_size = 30)
error_rate = autotest.eval_predict(fnn, iris_mat_test, iris_label_test, self.logging, one_hot=True)
self.tlog("iris predict (with fnn) error rate :" + str(error_rate))
def test_process(self):
normed_dmat_train = self.get_global_value('normed_iris_mat_train')
normed_dmat_test = self.get_global_value('normed_iris_mat_test')
dlabel_train = self.get_global_value('iris_label_train')
dlabel_test = self.get_global_value('iris_label_test')
knn_date = KNN(normed_dmat_train, dlabel_train, 3, 'euclidean')
error_rate = autotest.eval_predict(knn_date, normed_dmat_test, dlabel_test, self.logging)
self.tlog("date predict (with basic knn) error rate : " + str(error_rate))
def test_process(self):
lense_mat_train, lense_label_train, lense_mat_test, lense_label_test = fs.tsv_loader(
"sample_data/lense/lense.tsv", 0.3
)
dtree_lense = DecisionTreeID3(lense_mat_train, lense_label_train)
tree_structure = dtree_lense.build()
self.tlog("Tree structure : " + str(tree_structure))
error_rate = autotest.eval_predict(dtree_lense, lense_mat_test, lense_label_test, self.logging)
self.tlog("lense predict (with decision tree) error rate : " + str(error_rate))
def test_process(self):
MAJOR_AP_COUNT = 17
BAD_SIGNAL = -100
areaf = open("sample_data/wrm/wrm.json.dat")
area_json_list = areaf.readlines()
areaf.close()
area_set = {}
ap_set = {}
def compare(x, y):
if x['rssi'] < y['rssi']:
return 1
elif x['rssi'] == y['rssi']:
return 0
else:
return -1
for aobj in area_json_list:
area = json.loads(aobj)
label = area["areaID"]
aplist = area["apList"]
aplist.sort(compare)
for ap in aplist[:MAJOR_AP_COUNT]:
ap_set[ap['bssid']] = 1
area_set[label] = area_set.get(label, [])
area_set[label].append(aplist[:MAJOR_AP_COUNT])
ap_vector_column = ap_set.keys()
train_mat = []
train_label = []
test_mat = []
test_label = []
count = 0
for label in area_set:
for aps in area_set[label]:
ap_vector = tile(BAD_SIGNAL, len(ap_vector_column))
for ap in aps:
ap_vector[ap_vector_column.index(ap['bssid'])] = ap['rssi']
count += 1
if count % 10 == 0:
test_label.append(label)
test_mat.append(ap_vector)
else:
train_label.append(label)
train_mat.append(ap_vector)
gnb = GaussianNaiveBayes(train_mat, train_label)
gnb.fit()
error_rate = autotest.eval_predict(gnb, test_mat, test_label,
self.logging)
self.tlog("rssi predict (with GaussianNaiveBayes) error rate : " +
str(error_rate))
def test_process(self):
MAJOR_AP_COUNT = 17
BAD_SIGNAL = -100
areaf = open("sample_data/wrm/wrm.json.dat")
area_json_list = areaf.readlines()
areaf.close()
area_set = {}
ap_set = {}
def compare(x,y):
if x['rssi'] < y['rssi']:
return 1
elif x['rssi'] == y['rssi']:
return 0
else:
return -1
for aobj in area_json_list:
area = json.loads(aobj)
label = area["areaID"]
aplist = area["apList"]
aplist.sort(compare)
for ap in aplist[:MAJOR_AP_COUNT]:
ap_set[ap['bssid']] = 1
area_set[label] = area_set.get(label,[])
area_set[label].append(aplist[:MAJOR_AP_COUNT])
ap_vector_column = ap_set.keys()
train_mat = []
train_label = []
test_mat = []
test_label = []
count = 0;
for label in area_set:
for aps in area_set[label]:
ap_vector = tile(BAD_SIGNAL, len(ap_vector_column))
for ap in aps:
ap_vector[ap_vector_column.index(ap['bssid'])] = ap['rssi']
count += 1
if count % 10 == 0:
test_label.append(label)
test_mat.append(ap_vector)
else :
train_label.append(label)
train_mat.append(ap_vector)
gnb = GaussianNaiveBayes(train_mat,train_label)
gnb.fit()
error_rate = autotest.eval_predict(gnb, test_mat, test_label, self.logging)
self.tlog("rssi predict (with GaussianNaiveBayes) error rate : " + str(error_rate))
def test_process(self):
iris_mat_train, iris_label_train = dataset.load_iris(
"sample_data", "training")
iris_mat_test, iris_label_test = dataset.load_iris(
"sample_data", "testing")
knn = KNN(iris_mat_train, iris_label_train, 3, 'manhattan')
error_rate = autotest.eval_predict(knn, iris_mat_test, iris_label_test,
self.logging)
self.tlog("iris predict (with basic knn) error rate :" +
str(error_rate))
def test_process(self):
dg_mat_train, dg_label_train = dataset.load_mnist(
"sample_data", "training")
dg_mat_test, dg_label_test = dataset.load_mnist(
"sample_data", "testing")
knn_digit = KNN(dg_mat_train, dg_label_train, 10, 'euclidean')
error_rate = autotest.eval_predict(knn_digit, dg_mat_test,
dg_label_test, self.logging)
self.tlog("digit predict (with basic knn) error rate :" +
str(error_rate))
def test_process(self):
dg_mat_train, dg_label_train = dataset.load_mnist("sample_data",
"training",
one_hot=True)
dg_mat_test, dg_label_test = dataset.load_mnist("sample_data",
"testing",
one_hot=True)
fnn = FNN(dg_mat_train, dg_label_train, [400, 100])
fnn.fit(lr=0.01, epoch=1000, err_th=0.00001, batch_size=100)
error_rate = autotest.eval_predict(fnn,
dg_mat_test,
dg_label_test,
self.logging,
one_hot=True)
self.tlog("digit predict (with fnn) error rate :" + str(error_rate))
def test_process(self):
iris_mat_train, iris_label_train = dataset.load_iris("sample_data",
"training",
one_hot=True)
iris_mat_test, iris_label_test = dataset.load_iris("sample_data",
"testing",
one_hot=True)
fnn = FNN(iris_mat_train, iris_label_train, [2])
fnn.fit(lr=0.001, epoch=4000, err_th=0.00001, batch_size=30)
error_rate = autotest.eval_predict(fnn,
iris_mat_test,
iris_label_test,
self.logging,
one_hot=True)
self.tlog("iris predict (with fnn) error rate :" + str(error_rate))
def test_process(self):
iris_mat_train, iris_label_train = dataset.load_iris("sample_data",
"training",
one_hot=True)
iris_mat_test, iris_label_test = dataset.load_iris("sample_data",
"testing",
one_hot=True)
logistic_reg = LogisticRegression(iris_mat_train, iris_label_train)
logistic_reg.fit(lr=0.001, epoch=2000, batch_size=30)
error_rate = autotest.eval_predict(logistic_reg,
iris_mat_test,
iris_label_test,
self.logging,
one_hot=True)
self.tlog("iris predict (with logistic regression) error rate :" +
str(error_rate))
def test_process(self):
dg_mat_train, dg_label_train = dataset.load_mnist("sample_data",
"training",
one_hot=True)
dg_mat_test, dg_label_test = dataset.load_mnist("sample_data",
"testing",
one_hot=True)
logistic_reg = LogisticRegression(dg_mat_train, dg_label_train)
logistic_reg.fit(lr=0.0001, epoch=1000, batch_size=100)
error_rate = autotest.eval_predict(logistic_reg,
dg_mat_test,
dg_label_test,
self.logging,
one_hot=True)
self.tlog("digit predict (with logistic regression) error rate :" +
str(error_rate))
def test_process(self):
nlp_eng = nlp("eng")
email_data_file = "sample_data/email/email.tsv"
emailmat_train, emaillabel_train, voca, emailmat_test, emaillabel_test = fs.tsv_loader_with_nlp(
email_data_file, 0.3, nlp_eng
)
self.tlog(voca)
email_nbayes = NaiveBayes(emailmat_train, emaillabel_train)
email_nbayes.fit()
error_rate = autotest.eval_predict(email_nbayes, emailmat_test, emaillabel_test, self.logging)
self.tlog("spam-mail predict (with NaiveBayes) error rate : " + str(error_rate))
assert error_rate <= 0.1
def test_process(self):
nlp_eng = nlp("eng_lower")
email_data_file = "sample_data/email/email.tsv"
emailmat_train, emaillabel_train, voca, emailmat_test, emaillabel_test \
= fs.tsv_loader_with_nlp(email_data_file, 0.4, nlp_eng)
self.tlog(voca)
email_nbayes = NaiveBayes(emailmat_train, emaillabel_train)
email_nbayes.fit()
error_rate = autotest.eval_predict(email_nbayes, emailmat_test,
emaillabel_test, self.logging)
self.tlog("spam-mail predict (with NaiveBayes) error rate : " +
str(error_rate))
assert error_rate <= 0.1
def test_process(self):
train_mat = [\
[-65,-55,-42],[-20,-59,-71],[-43,-49,-69],\
[-61,-30,-74],[-79,-81,-40],[-71,-57,-24],\
[-67,-19,-58],[-57,-73,-83],[-68,-74,-59],\
[-80,-85,-79]
]
train_label = ['B','A','A','A','B','B','A','C','C','C']
test_mat = [\
[-45,-47,-74],[-77,-69,-25],[-64,-71,-59],\
[-85,-85,-25],[-85,-85,-85]
]
test_label = ['A','B','C','B','C']
gnb = GaussianNaiveBayes(train_mat,train_label)
gnb.fit()
error_rate = autotest.eval_predict(gnb, test_mat, test_label, self.logging)
self.tlog("strength of signal predict error rate : " + str(error_rate))
def test_process(self):
train_mat = [\
[-65,-55,-42],[-20,-59,-71],[-43,-49,-69],\
[-61,-30,-74],[-79,-81,-40],[-71,-57,-24],\
[-67,-19,-58],[-57,-73,-83],[-68,-74,-59],\
[-80,-85,-79]
]
train_label = ['B', 'A', 'A', 'A', 'B', 'B', 'A', 'C', 'C', 'C']
test_mat = [\
[-45,-47,-74],[-77,-69,-25],[-64,-71,-59],\
[-85,-85,-25],[-85,-85,-85]
]
test_label = ['A', 'B', 'C', 'B', 'C']
gnb = GaussianNaiveBayes(train_mat, train_label)
gnb.fit()
error_rate = autotest.eval_predict(gnb, test_mat, test_label,
self.logging)
self.tlog("strength of signal predict error rate : " + str(error_rate))
def test_process(self):
dg_mat_train, dg_label_train = dataset.load_mnist("sample_data",
"training",
one_hot=True)
dg_mat_test, dg_label_test = dataset.load_mnist("sample_data",
"testing",
one_hot=True)
svc = SVC(dg_mat_train, dg_label_train)
svc.fit(C=1.5,
toler=0.0001,
epoch=1000,
kernel="RBF",
kernel_params={"gamma": 0.7})
error_rate = autotest.eval_predict(svc,
dg_mat_test,
dg_label_test,
self.logging,
one_hot=True)
self.tlog("digit predict (with svc) error rate :" + str(error_rate))
def test_process(self):
iris_mat_train, iris_label_train = dataset.load_iris("sample_data",
"training",
one_hot=True)
iris_mat_test, iris_label_test = dataset.load_iris("sample_data",
"testing",
one_hot=True)
svc = SVC(iris_mat_train, iris_label_train)
svc.fit(C=1.5,
toler=0.0001,
epoch=1000,
kernel="Polynomial",
kernel_params={"degree": 3})
error_rate = autotest.eval_predict(svc,
iris_mat_test,
iris_label_test,
self.logging,
one_hot=True)
self.tlog("iris predict (with svc) error rate :" + str(error_rate))