def train(tr,
si,
alpha,
beta,
L1,
L2,
D,
users=None,
interaction=False,
maxlines=None,
iterations=1):
model = ftrl_proximal(alpha, beta, L1, L2, D, interaction)
for j in range(iterations):
it = gl_iter.basic_join(tr, si, users)
for (k, line) in enumerate(it):
y = line.pop('IsClick')
process_line(line)
f = hash_features(line, D)
p = model.predict(f)
model.update(f, p, y)
if k == maxlines:
break
if (k + 1) % 250000 == 0:
print('processed %d lines on training pass %d' %
(k + 1, j + 1))
return model
def run_test(submission_file, test, si, users=None, offset=0):
it = gl_iter.basic_join(test, si, users)
for (k, line) in enumerate(it):
id = line.pop('ID')
process_line(line)
f = hash_features(line, D)
dv = model.predict(f, False)
dv += offset
p = 1.0/(1.0 + exp(-dv))
submission_file.write('%d,%s\n' % (id, str(p)))
if (k + 1) % 250000 == 0:
print 'processed %d lines' % (k + 1)
def run_test(submission_file, test, si, users=None, offset=0):
it = gl_iter.basic_join(test, si, users)
for (k, line) in enumerate(it):
id = line.pop('ID')
process_line(line)
f = hash_features(line, D)
dv = model.predict(f, False)
dv += offset
p = 1.0 / (1.0 + exp(-dv))
submission_file.write('%d,%s\n' % (id, str(p)))
if (k + 1) % 250000 == 0:
print('processed %d lines' % (k + 1))
def validate(val, si, users=None, offset=0, maxlines=None):
it = gl_iter.basic_join(val, si, users)
loss = 0.0
for (k, line) in enumerate(it):
y = line.pop('IsClick')
process_line(line)
f = hash_features(line, D)
dv = model.predict(f, False)
dv += offset
p = 1.0/(1.0 + exp(-dv))
loss += logloss(p, y)
if k == maxlines:
break
if (k + 1) % 250000 == 0:
print 'processed %d lines from validation set' % (k + 1)
return loss/k, k
def validate(val, si, users=None, offset=0, maxlines=None):
it = gl_iter.basic_join(val, si, users)
loss = 0.0
for (k, line) in enumerate(it):
y = line.pop('IsClick')
process_line(line)
f = hash_features(line, D)
dv = model.predict(f, False)
dv += offset
p = 1.0 / (1.0 + exp(-dv))
loss += logloss(p, y)
if k == maxlines:
break
if (k + 1) % 250000 == 0:
print('processed %d lines from validation set' % (k + 1))
return loss / k, k
def train(tr, si, alpha, beta, L1,
L2, D, users=None,
interaction=False, maxlines=None,
iterations=1):
model = ftrl_proximal(alpha, beta, L1, L2, D, interaction)
for j in range(iterations):
it = gl_iter.basic_join(tr, si, users)
for (k, line) in enumerate(it):
y = line.pop('IsClick')
process_line(line)
f = hash_features(line, D)
p = model.predict(f)
model.update(f, p, y)
if k == maxlines:
break
if (k + 1) % 250000 == 0:
print 'processed %d lines on training pass %d' % (k + 1, j + 1)
return model
