def first_test():
from ml_metrics import auc
import random
from sklearn import datasets
b = BasicLogisticRegression(4)
iris = datasets.load_iris()
train_data = iris.data[:75]
train_y = iris.target[:75]
test_x = iris.data[75:100]
tmp = iris.target[:100]
random.shuffle(tmp)
test_y = tmp[:50]
def to_dict(x):
return {i: k for i, k in enumerate(x, start=1)}
for z in xrange(50):
for x, y in random.shuffle(zip(train_data, train_y)):
# print x, y
b.sgd_fit_one(to_dict(x), y)
print "fit done"
rst_y = map(b.predict_raw, map(to_dict, test_x))
print b.weights
print test_y
print rst_y
print auc(test_y, rst_y)
# print len(iris.data)
#
# another implementation
from sgd import log_reg_sgd, h
theta, err = log_reg_sgd(train_data, train_y, 0.001, max_iter=100)
pred = [h(i, theta) for i in test_x]
print "theta,", theta
print auc(test_y, pred)
def test_sgd():
#number of examples
EX = 500
#learning rate
a = 0.001
#create a synthetic data set
x,y = datasets.make_classification(EX)
#append a 1 column at index 0 in x
x = np.hstack((np.ones((x.shape[0],1)),x))
#train on half the data
theta,err = log_reg_sgd(x[:EX/2],y[:EX/2],a,max_iter=100)
#plot the error
plt.plot(err, linewidth=2)
plt.xlabel('Training example', fontsize=20)
plt.ylabel('Error', fontsize=20)
plt.show()
#predict the test set
pred = [h(x[i],theta) for i in xrange(EX/2,EX)]
#plot the error as a function of training examples
fpr, tpr, thresholds = metrics.roc_curve(y[EX/2:], pred)
#plot the ROC curve
plt.plot(fpr,tpr, linewidth=2)
plt.xlabel('False positive rate', fontsize=20)
plt.ylabel('True positive rate', fontsize=20)
plt.show()
#measure the performance using ROC and AUC
auc = metrics.auc(fpr, tpr)
print 'AUC of classifier: ', auc
def test_sgd():
#number of examples
EX = 500
#learning rate
a = 0.001
#create a synthetic data set
x,y = datasets.make_classification(EX)
#append a 1 column at index 0 in x
x = np.hstack((np.ones((x.shape[0],1)),x))
#train on half the data
theta,err = log_reg_sgd(x[:EX/2],y[:EX/2],a,max_iter=100)
#plot the error
plt.plot(err, linewidth=2)
plt.xlabel('Training example', fontsize=20)
plt.ylabel('Error', fontsize=20)
plt.show()
#predict the test set
pred = [h(x[i],theta) for i in xrange(EX/2,EX)]
#plot the error as a function of training examples
fpr, tpr, thresholds = metrics.roc_curve(y[EX/2:], pred)
#plot the ROC curve
plt.plot(fpr,tpr, linewidth=2)
plt.xlabel('False positive rate', fontsize=20)
plt.ylabel('True positive rate', fontsize=20)
plt.show()
#measure the performance using ROC and AUC
auc = metrics.auc(fpr, tpr)
print 'AUC of classifier: ', auc
# learning rate
a = 0.001
max_iter = 10
# create a synthetic data set
x, y = datasets.make_classification(EX)
print "sample", x[251]
print "feature num ", x.shape[1]
# append a 1 column at index 0 in x
x = np.hstack((np.ones((x.shape[0], 1)), x))
print x[251]
from sgd import log_reg_sgd, h
theta = log_reg_sgd(x[:EX / 2], y[:EX / 2], a, max_iter=max_iter)
pred = [h(x[i], theta) for i in xrange(EX / 2, EX)]
print "weights ",theta
# print "err ",err
print auc(y[EX / 2:], pred)
def to_dict(x):
# print x
return {i: k for i, k in enumerate(x[1:], start=1)}
b = BasicLogisticRegression(x.shape[1]-1, a)
for z in xrange(max_iter ):
for i in xrange(EX / 2):
b.sgd_fit_one(to_dict(x[i]), y[i])
def test_parallel_sgd():
#learning rate
a = 0.001
#create a synthetic data set, default features, 1500 examples, 2 classes
x,y = datasets.make_classification(1500)
#append a 1 column at index 0 in x
x = np.hstack((np.ones((x.shape[0],1)),x))
### PARALLEL VERSION ###
#worker pool
pool = Pool(4)
input = [{'x':x[:250],'y':y[:250],'learning_rate':a,'iters':500},
{'x':x[250:500],'y':y[250:500],'learning_rate':a,'iters':500},
{'x':x[500:750],'y':y[500:750],'learning_rate':a,'iters':500},
{'x':x[750:1000],'y':y[750:1000],'learning_rate':a,'iters':500}]
thetas = pool.map(train, input)
#compute the average
theta = np.mean(thetas,axis=0)
#we take the average prediction
b_pred = [h(x[i],theta) for i in xrange(1000,1500)]
#plot the error as a function of training examples
b_fpr, b_tpr, thresholds = metrics.roc_curve(y[1000:], b_pred)
#plot the ROC curve
plt.plot(b_fpr,b_tpr, 'r-', label='Bagged', linewidth=2)
#measure the performance using ROC and AUC
b_auc = metrics.auc(b_fpr, b_tpr)
print 'AUC of parallel classifier: ', b_auc
###
### SEQUENTIAL VERSION ###
#train on half the data
theta = log_reg_sgd(x[:1000],y[:1000],a,max_iter=500,debug=False)
#predict the test set
pred = [h(x[i],theta) for i in xrange(1000,1500)]
#plot the error as a function of training examples
fpr, tpr, thresholds = metrics.roc_curve(y[1000:], pred)
#plot the ROC curve
plt.plot(fpr,tpr, 'b-', label='Non-bagged', linewidth=2)
plt.xlabel('False positive rate', fontsize=20)
plt.ylabel('True positive rate', fontsize=20)
plt.legend(loc=0)
plt.show()
#measure the performance using ROC and AUC
auc = metrics.auc(fpr, tpr)
print 'AUC of sequential classifier: ', auc
#write results to file for later
with open('bag_results.tsv','w') as out:
for i,j in zip(b_fpr,b_tpr):
out.write("\t".join((str(i),str(j)))+"\n")
#write results to file for later
with open('results.tsv','w') as out:
for i,j in zip(fpr,tpr):
out.write("\t".join((str(i),str(j)))+"\n")
def test_parallel_sgd():
#learning rate
a = 0.001
#create a synthetic data set, default features, 1500 examples, 2 classes
x,y = datasets.make_classification(1500)
#append a 1 column at index 0 in x
x = np.hstack((np.ones((x.shape[0],1)),x))
### PARALLEL VERSION ###
#worker pool
pool = Pool(4)
input = [{'x':x[:250],'y':y[:250],'learning_rate':a,'iters':500},
{'x':x[250:500],'y':y[250:500],'learning_rate':a,'iters':500},
{'x':x[500:750],'y':y[500:750],'learning_rate':a,'iters':500},
{'x':x[750:1000],'y':y[750:1000],'learning_rate':a,'iters':500}]
thetas = pool.map(train, input)
#compute the average
theta = np.mean(thetas,axis=0)
#we take the average prediction
b_pred = [h(x[i],theta) for i in xrange(1000,1500)]
#plot the error as a function of training examples
b_fpr, b_tpr, thresholds = metrics.roc_curve(y[1000:], b_pred)
#plot the ROC curve
plt.plot(b_fpr,b_tpr, 'r-', label='Bagged', linewidth=2)
#measure the performance using ROC and AUC
b_auc = metrics.auc(b_fpr, b_tpr)
print 'AUC of parallel classifier: ', b_auc
###
### SEQUENTIAL VERSION ###
#train on half the data
theta = log_reg_sgd(x[:1000],y[:1000],a,max_iter=500,debug=False)
#predict the test set
pred = [h(x[i],theta) for i in xrange(1000,1500)]
#plot the error as a function of training examples
fpr, tpr, thresholds = metrics.roc_curve(y[1000:], pred)
#plot the ROC curve
plt.plot(fpr,tpr, 'b-', label='Non-bagged', linewidth=2)
plt.xlabel('False positive rate', fontsize=20)
plt.ylabel('True positive rate', fontsize=20)
plt.legend(loc=0)
plt.show()
#measure the performance using ROC and AUC
auc = metrics.auc(fpr, tpr)
print 'AUC of sequential classifier: ', auc
#write results to file for later
with open('bag_results.tsv','w') as out:
for i,j in zip(b_fpr,b_tpr):
out.write("\t".join((str(i),str(j)))+"\n")
#write results to file for later
with open('results.tsv','w') as out:
for i,j in zip(fpr,tpr):
out.write("\t".join((str(i),str(j)))+"\n")