def validate(data, model, offset=0.0):
loss = 0.0
count = 0
for k, df in enumerate(data):
for t in df.itertuples():
count += 1
x, y = process_line(t, False)
f = hash_features(x, model.D)
dv = model.predict(f, False)
dv += offset
p = 1.0 / (1.0 + exp(-dv))
loss += logloss(p, y)
return loss / count
def validate(data, model, offset=0.0):
loss = 0.0
count = 0
for k, df in enumerate(data):
for t in df.itertuples():
count += 1
x, y = process_line(t, False)
f = hash_features(x, model.D)
dv = model.predict(f, False)
dv += offset
p = 1.0/(1.0 + exp(-dv))
loss += logloss(p, y)
return loss/count
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 run_val(alpha, l2, l1, maxlines, interact):
val_ids = avito2_io.get_artifact('full_val_set.pkl')
model = ftrl_proximal(alpha, beta, l1, l2, D, interact)
train_path = os.path.join(avito2_io.PROCESSED, TRAIN_INFILE)
with open(train_path) as train_file:
input = csv.DictReader(train_file)
for (k, x) in enumerate(input):
if int(x['SearchID']) not in val_ids:
y = float(x['IsClick'])
del x['IsClick']
del x['SearchDate']
del x['SearchID']
f = hash_features(x, D)
p = model.predict(f)
model.update(f, p, y)
if k == maxlines:
break
if (k + 1) % 1000000 == 0:
print 'processed %d lines' % (k + 1)
print 'finished training'
count = 0
loss = 0.0
with open(train_path) as train_file:
input = csv.DictReader(train_file)
for (k, x) in enumerate(input):
if int(x['SearchID']) in val_ids:
count += 1
y = float(x['IsClick'])
del x['IsClick']
del x['SearchDate']
del x['SearchID']
f = hash_features(x, D)
p = model.predict(f)
loss += logloss(p, y)
if k == maxlines:
break
if (k + 1) % 1000000 == 0:
print 'processed %d lines of raw train on validation pass' % (k + 1)
print 'validation loss: %.5f on %d rows' % (loss/count, count)
p_total = total_y / (k + 1.0)
p_sample = total_y / sample_ct
offset = log(p_total / (1.0 - p_total)) - log(p_sample / (1.0 - p_sample))
print 'offset:' + str(offset)
# validation run
input = avito2_io.join_with_ads(True,
ads,
train_etl,
search_etl,
ads_etl,
do_validation=True,
val_ids=val_ids)
loss = 0.0
count = 0
for (k, (x, y)) in enumerate(input):
f = hash_features(x, D)
dv = model.predict(f, False)
dv += offset
p = 1.0 / (1.0 + exp(-dv))
loss += logloss(p, y)
count += 1
if k == maxlines_val:
break
if (k + 1) % 250000 == 0:
print 'processed %d lines on validation pass' % (k + 1)
print 'validation set log loss: %.5f' % (loss / count)
print 'elapsed time: %s' % (datetime.now() - start)
print 'finished training'
# validation run
input = avito2_io.join_with_ads(True,
ads,
train_etl,
search_etl,
ads_etl,
do_validation=True,
val_ids=val_ids)
loss = 0.0
count = 0
for (k, (x, y)) in enumerate(input):
f = hash_features(x, D)
p = model.predict(f)
loss += logloss(p, y)
count += 1
if k == maxlines_val:
break
if (k + 1) % 250000 == 0:
print 'processed %d lines on validation pass' % (k + 1)
print 'validation set log loss: %.5f' % (loss/count)
print 'elapsed time: %s' % (datetime.now() - start)
from eval import logloss
maxlines_val = None
start = datetime.now()
val_ids = avito2_io.get_artifact('full_val_set.pkl')
print 'validation set ids read'
train_etl = {
'ad': lambda l: l['AdID'],
'pos': lambda l: l['Position'],
'ctr': lambda l: l['HistCTR']
}
search_etl = {'cat': lambda l: l['CategoryID']}
# validation run
input = avito2_io.rolling_join(True,
train_etl,
search_etl,
do_validation=True,
val_ids=val_ids)
loss = 0.0
for (k, (x, y)) in enumerate(input):
#loss += logloss(float(x['ctr']), y)
loss += logloss(0.006, y)
if k == maxlines_val:
break
if (k + 1) % 250000 == 0:
print 'processed %d lines on validation pass' % (k + 1)
print 'validation set log loss: %.5f' % (loss / (k + 1))
print 'elapsed time: %s' % (datetime.now() - start)
val_ids = avito2_io.get_artifact('full_val_set.pkl')
print 'validation set ids read'
train_etl = {'ad' : lambda l : l['AdID'],
'pos' : lambda l : l['Position'],
'ctr' : lambda l : l['HistCTR']}
search_etl = {'cat' : lambda l : l['CategoryID']}
# validation run
input = avito2_io.rolling_join(True,
train_etl,
search_etl,
do_validation=True,
val_ids=val_ids)
loss = 0.0
for (k, (x, y)) in enumerate(input):
#loss += logloss(float(x['ctr']), y)
loss += logloss(0.006, y)
if k == maxlines_val:
break
if (k + 1) % 250000 == 0:
print 'processed %d lines on validation pass' % (k + 1)
print 'validation set log loss: %.5f' % (loss/(k + 1))
print 'elapsed time: %s' % (datetime.now() - start)
