def run(dataset):
n_features = len(meta[dataset]['val_name'])
result_online = Result('%s-%s' %(dataset, 'aws-online'), aws=True)
result_baseline = Result('%s-%s' %(dataset, 'aws-baseline'), aws=True)
result_active = Result('%s-%s' %(dataset, 'aws-active'), aws=True)
for repeat in range(0, n_repeat):
print 'Round %d of %d'% (repeat, n_repeat - 1)
ex = AWSOnline(meta[dataset]['model_id'], 1, 0, n_features, meta[dataset]['val_name'], ftype='uniform', error=.1)
test_x, test_y = load_svmlight_file('/Users/Fan/dev/ML/code/binary-classifiers/targets/%s/test.scale' % dataset, n_features)
test_x = test_x.todense()
test_y = [a if a == 1 else 0 for a in test_y]
train_x, train_y = [], []
for i in result_active.index:
q_by_u = result_active.Q_by_U[i]
print 'Active learning with budget %d / %d' % (q_by_u, q_by_u * (n_features + 1))
main = ActiveLearning(ex, (None, None), (test_x, test_y), n_features,
q_by_u * (n_features + 1), 5)
L_unif, L_test = main.do()
result_active.L_unif[i].append(L_unif)
result_active.L_test[i].append(L_test)
result_active.nquery[i].append(ex.get_n_query())
ex = AWSOnline(meta[dataset]['model_id'], 1, 0, n_features, meta[dataset]['val_name'], ftype='uniform', error=.1)
for i in result_online.index:
q_by_u = result_online.Q_by_U[i]
print 'collecting up to budget %d / %d' % (q_by_u, q_by_u * (n_features + 1))
ex.collect_up_to_budget(q_by_u * (n_features + 1))
train_x.extend(ex.pts_near_b)
train_y.extend(ex.pts_near_b_labels)
print 'retraining with %d points' % len(train_y)
# online
e = RBFKernelRetraining(ex.batch_predict, (train_x, train_y), (test_x, test_y), n_features)
L_unif, L_test = e.grid_retrain_in_x()
result_online.L_unif[i].append(L_unif)
result_online.L_test[i].append(L_test)
result_online.nquery[i].append(ex.get_n_query())
# baseline
e = Baseline(ex.batch_predict, (train_x, train_y), (test_x, test_y), n_features)
L_unif, L_test = e.do()
result_baseline.L_unif[i].append(L_unif)
result_baseline.L_test[i].append(L_test)
result_baseline.nquery[i].append(ex.get_n_query())
print result_online
print result_baseline
print result_active
import sys
import numpy as np
from sklearn.datasets import load_svmlight_file
import sklearn.metrics as sm
from scipy.special import expit
from scipy.special import logit
from algorithms.awsOnline import AWSOnline
online = False
if online:
val_name = map(lambda x: 'v%d' % x, range(1, 11))
print val_name
test = AWSOnline('ml-lkYRYeldcrH', 1, 0, 10, val_name, 'uniform', .1)
# spec = FeatureSpec('norm', (-1, 1), (-.85, -.85, -.20, -.51, -.49, -.58, -.48, -.38, -.44, -.55))
spec = None
test.collect_with_score(20, spec=spec)
sys.exit(-1)
class LRSolver(object):
def __init__(self):
self.w = None
def fit(self, X, s):
_x = np.ones((X.shape[0], X.shape[1] + 1))
_x[:, : - 1] = X
self.w, _, _, _ = np.linalg.lstsq(_x, logit(s))
__author__ = 'Fan'
import numpy as np
from algorithms.awsOnline import AWSOnline
from algorithms.OnlineBase import FeatureSpec
for i in range(0, 1):
val_name = map(lambda x: 'v%d' % x, range(1, 11))
print val_name
test = AWSOnline('ml-lkYRYeldcrH', 1, 0, 10, val_name, 'uniform', .1)
# X, Y = test.collect_pts(2, -1)
spec = FeatureSpec(
'norm', (-1, 1),
(-.85, -.85, -.20, -.51, -.49, -.58, -.48, -.38, -.44, -.55))
X, Y = test.collect_universe(1000, spec=spec)
print np.bincount(Y)
import matplotlib.pyplot as plt
from algorithms.awsOnline import AWSOnline
import numpy as np
from algorithms.RBFTrainer import RBFKernelRetraining
from sklearn.datasets import load_svmlight_file
for i in range(0, 1):
val_name = ['v1', 'v2', 'v3', 'v4', 'v5', 'v6', 'v7', 'v8', 'v9', 'v10']
n_features = 10
ex = AWSOnline(model_id='ml-lkYRYeldcrH',
label_p=1,
label_n=0,
n_features=n_features,
val_name=val_name,
ftype='uniform',
error=.1)
step = 6
train_x, train_y = [], []
val_x, val_y = [], []
test_x, test_y = load_svmlight_file('test.scale', n_features)
test_x = test_x.todense()
test_y = [a if a == 1 else 0 for a in test_y]
try:
while True:
ex.collect_pts(step)
train_x.extend(ex.pts_near_b)
train_y.extend(ex.pts_near_b_labels)
val_x.extend(ex.support_pts)
val_y.extend(ex.support_labels)
__author__ = 'Fan'
import os
from sklearn.datasets import load_svmlight_file
from sklearn.metrics import accuracy_score
from algorithms.awsOnline import AWSOnline
val_name = map(lambda x: 'v%d' % x, range(1, 9))
print val_name
test = AWSOnline('ml-lzYmNFzPh2N', 1, 0, 8, val_name, 'uniform', .1)
Xt, Yt = load_svmlight_file(os.getenv('HOME') + '/Dropbox/Projects/SVM/dataset/cod-rna/cod-rna.test.scaled',
n_features=8)
Xt = Xt.todense().tolist()
import random
z = zip(Xt, Yt)
random.shuffle(z)
Xt, Yt = zip(*z)
start = 0
cutoff = 10
Xt = Xt[start:start + cutoff]
yy = [test.query(x) for x in Xt]
print 'True:', Yt[start:start + cutoff]
print 'Predict:', yy
__author__ = 'Fan'
import numpy as np
from algorithms.awsOnline import AWSOnline
from algorithms.OnlineBase import FeatureSpec
for i in range(0, 1):
val_name = map(lambda x: 'v%d' % x, range(1, 11))
print val_name
test = AWSOnline('ml-lkYRYeldcrH', 1, 0, 10, val_name, 'uniform', .1)
# X, Y = test.collect_pts(2, -1)
spec = FeatureSpec('norm', (-1, 1), (-.85, -.85, -.20, -.51, -.49, -.58, -.48, -.38, -.44, -.55))
X, Y = test.collect_universe(1000, spec=spec)
print np.bincount(Y)
import matplotlib.pyplot as plt
from algorithms.awsOnline import AWSOnline
import numpy as np
from algorithms.RBFTrainer import RBFKernelRetraining
for i in range(0, 1):
val_name = ['x1', 'x2']
ex = AWSOnline('ml-i0GeYZaGQ3f', 1, 0, 2, val_name, 'uniform', .1)
step = 6
train_x, train_y = [], []
val_x, val_y = [], []
try:
while True:
ex.collect_pts(step)
train_x.extend(ex.pts_near_b)
train_y.extend(ex.pts_near_b_labels)
val_x.extend(ex.support_pts)
val_y.extend(ex.support_labels)
e = RBFKernelRetraining('circle', train_x, train_y, val_x, val_y, train_x, train_y, n_features=2)
print ex.get_n_query(), e.grid_retrain_in_x()
except KeyboardInterrupt:
print 'Done'
train_x = np.array(train_x)
plt.figure()
plt.scatter(train_x[:, 0], train_x[:, 1], c=train_y)
plt.xlim((-2, 2))
plt.ylim((-2, 2))
plt.show()