def define_segments(QLINK_URLS, UNKNOWN_URLS, QUOTA):
global OH, lr, quota, i, km, part
quota = QUOTA
list_q = []
obj_q = []
for url in QLINK_URLS:
prop = get_prop(url)
list_q += prop
obj_q.append(prop)
params, count = np.unique(list_q, return_counts=True)
params = np.array(params, dtype='object')
count = np.array(count, dtype='object')
feat_q_num = np.hstack((params.reshape(-1,1), count.reshape(-1,1)))
feat_q_num = feat_q_num[np.argsort(feat_q_num[:,1])]
feat_q_num = feat_q_num[::-1]
obj_g = []
for url in UNKNOWN_URLS:
prop = get_prop(url)
obj_g.append(prop)
imp_features = (feat_q_num[:100][:,0]).reshape(-1,1)
OH = OnehotTransactions()
OH.fit(imp_features)
q_matrix = OH.transform(obj_q)
g_matrix = OH.transform(obj_g)
X = np.vstack((q_matrix, g_matrix))
y = [1]*500 + [0]*500
y = np.array(y)
lr = LinearRegression()
lr.fit(X,y)
i = 0
## divide by n clusters set part for each one
n = 15
km = KMeans(n_clusters=n)
a = np.hstack((km.fit_predict(X).reshape(-1,1), y.reshape(-1,1)))
part = np.zeros(n)
for i in range(n):
part[i] = a[a[:,0] == i][:,1].sum()
part /= part.sum()
def define_segments(QLINK_URLS, UNKNOWN_URLS, QUOTA):
global OH, lr, quota, i, km, part
quota = QUOTA
list_q = []
obj_q = []
for url in QLINK_URLS:
prop = get_prop(url)
list_q += prop
obj_q.append(prop)
params, count = np.unique(list_q, return_counts=True)
params = np.array(params, dtype='object')
count = np.array(count, dtype='object')
feat_q_num = np.hstack((params.reshape(-1, 1), count.reshape(-1, 1)))
feat_q_num = feat_q_num[np.argsort(feat_q_num[:, 1])]
feat_q_num = feat_q_num[::-1]
obj_g = []
for url in UNKNOWN_URLS:
prop = get_prop(url)
obj_g.append(prop)
imp_features = (feat_q_num[:100][:, 0]).reshape(-1, 1)
OH = OnehotTransactions()
OH.fit(imp_features)
q_matrix = OH.transform(obj_q)
g_matrix = OH.transform(obj_g)
X = np.vstack((q_matrix, g_matrix))
y = [1] * 500 + [0] * 500
y = np.array(y)
lr = LinearRegression()
lr.fit(X, y)
i = 0
## divide by n clusters set part for each one
n = 15
km = KMeans(n_clusters=n)
a = np.hstack((km.fit_predict(X).reshape(-1, 1), y.reshape(-1, 1)))
part = np.zeros(n)
for i in range(n):
part[i] = a[a[:, 0] == i][:, 1].sum()
part /= part.sum()
def test_transform():
oht = OnehotTransactions()
oht.fit(dataset)
trans = oht.transform(dataset)
np.testing.assert_array_equal(expect, trans)
def test_transform():
oht = OnehotTransactions()
oht.fit(dataset)
trans = oht.transform(dataset)
np.testing.assert_array_equal(expect, trans)
