def mad_matrix(examples,
clf,
featuredataset,
examplegenerator,
attribute_name='car'):
"""
run examples experiments to see how cars are declaired
the same or different by the clf classifier.abs
examples(int): number of trials
clf(classifier): classifier to make same/different distinciton
fd(featureDataset) : allows joining of chip to features
eg(experimentGenerator): makes expermients for testing
"""
ddg = defaultdict(int)
ddb = defaultdict(int)
for _ in tnrange(examples):
cameras_test = examplegenerator.generate()
match_id = get_match_id(cameras_test)
goods, bads = make_good_bad(cameras_test, match_id)
good0 = goods[0]
good1 = goods[1]
bad0 = bads[0]
bad1 = bads[1]
eval_good_bad(good0, good1, clf, featuredataset, ddg, ddb,
attribute_name)
eval_good_bad(bad0, bad1, clf, featuredataset, ddb, ddg,
attribute_name)
return (ddg, ddb)
def test_svm(examples, clf_train, fd_test, eg_test):
"""
score the trained SVM against test features
examples(int): number of examples to run
clf_train(modle): model for evaluating testing data
fd_test(featureDataset): testing dataset
eg_test(experimentGenerator): generated experiments from testing dataset
out(int): score from the model
"""
lessons_test = list()
outcomes_test = list()
for _ in tnrange(examples):
cameras_test = eg_test.generate()
match_id = get_match_id(cameras_test)
goods, bads = make_good_bad(cameras_test, match_id)
make_work(fd_test, lessons_test, outcomes_test, goods, 1)
make_work(fd_test, lessons_test, outcomes_test, bads, 0)
print('scoring')
start = time.time()
out = clf_train.score(lessons_test, outcomes_test)
end = time.time()
print('scoring took {} seconds'.format(end - start))
return out
def train_svm(examples, fd_train, eg_train):
"""
train a support vector machine
examples(int): number of examples to generate
fd_train(featureDataset): where to join features to chips
eg_train(experimentGenerator): makes experiments
clf(SVM): scm classifier trainined on the input examples
"""
lessons_train = list()
outcomes_train = list()
for _ in tnrange(examples):
cameras_train = eg_train.generate()
match_id = get_match_id(cameras_train)
goods, bads = make_good_bad(cameras_train, match_id)
make_work(fd_train, lessons_train, outcomes_train, goods, 1)
make_work(fd_train, lessons_train, outcomes_train, bads, 0)
clf = svm.SVC()
print('fitting')
start = time.time()
clf.fit(lessons_train, outcomes_train)
end = time.time()
print('fitting took {} seconds'.format(end - start))
return clf
def make_examples(gen, examples):
workitems = []
for _ in range(examples):
cameras = gen.generate()
match_id = get_match_id(cameras)
goods, bads = make_good_bad(cameras, match_id)
makework(workitems, goods)
makework(workitems, bads)
print('made', len(workitems))
return workitems
def search(examples, fd_train, eg_train, iterations):
"""
beginnnings of hyperparameter search for svm
"""
param_grid = {'C': sp_rand()}
lessons_train = list()
outcomes_train = list()
for _ in tnrange(examples):
cameras_train = eg_train.generate()
match_id = get_match_id(cameras_train)
goods, bads = make_good_bad(cameras_train, match_id)
make_work(fd_train, lessons_train, outcomes_train, goods, 1)
make_work(fd_train, lessons_train, outcomes_train, bads, 0)
clf = svm.SVC()
print('searching')
start = time.time()
rsearch = RandomizedSearchCV(
estimator=clf, param_distributions=param_grid, n_iter=iterations)
rsearch.fit(lessons_train, outcomes_train)
end = time.time()
print('searching took {} seconds'.format(end - start))
print(rsearch.best_score_)
print(rsearch.best_estimator_.C)