def create_random_pipeline():
pipeline_space = {'clf': any_classifier('my_clf'), 'preprocessor': any_preprocessing('my_prep')}
sample = hyperopt.pyll.stochastic.sample(pipeline_space)
classifier = sample['clf']
p = None
try:
preprocessor = sample['preprocessor'][0]
p = Pipeline([('preprocessing', preprocessor), ('classifier', classifier)])
except:
p = Pipeline([('classifier', classifier)])
return p
def main():
# Construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-p", "--path", default='nailgun', help="path to nailgun folder")
ap.add_argument("-m", "--model", required= True, help="name of the model file to save the model")
ap.add_argument("-cs", "--csize", default=80, help="paramter to crop the image around the nailgun")
ap.add_argument("-ex", "--ext", type=str, default='.jpeg', help="extension of the images")
args = vars(ap.parse_args())
# Load paramters
crop_size = args['csize']
path_to_images = args['path']
filename = args['model']
ext = args['ext']
split_factor = 0.75
# List all of the images
paths, labels = list_images(path_to_images, ext)
# Get paths correctly distibuted good/bad
n_paths = distribute_paths(paths)
# Split and generate labels
(x_train_paths, y_train_str), (x_test_paths, y_test_str) = split_and_get_labels(n_paths, split_factor)
print('--- Split ---')
print('Train: '+str(len(x_train_paths))+', Test: '+str(len(x_test_paths)))
# Load object for label binarizer
lb = LabelBinarizer()
lb.fit(y_train_str)
n_feats = crop_size**2 + 2
x_train = np.zeros((len(x_train_paths), n_feats), np.uint8)
y_train = np.zeros((len(y_train_str), 1), np.int32)
print('---- Extracting Train samples ----')
progress = tqdm.tqdm(total=len(x_train_paths))
for idx, path in enumerate(x_train_paths):
x_train[idx, :] = extract_nail(path)
y_train[idx] = lb.transform([path.split("_")[-1].split(".")[0]])
progress.update(1)
y_train = np.ravel(y_train)
print('---- Extracting Test samples ----')
progress = tqdm.tqdm(total=len(x_test_paths))
x_test = np.zeros((len(x_test_paths), n_feats), np.float)
y_test = np.zeros((len(y_test_str), 1), np.int32)
for idx, path in enumerate(x_test_paths):
x_test[idx, :] = extract_nail(path)
y_test[idx] = lb.transform([path.split("_")[-1].split(".")[0]])
progress.update(1)
y_test = np.ravel(y_test)
# Define HyperoptEstimator
estim = HyperoptEstimator(classifier=any_classifier('clf'), preprocessing=any_preprocessing('pp'), algo=tpe.suggest, trial_timeout=30)
estim.fit(x_train, y_train)
print('---- BEST SCORE (acc) ----')
print( estim.score( x_test, y_test ) )
print('---- BEST MODEL ----')
print( estim.best_model() )
pkl_filename = 'model/'+filename+'.pkl'
with open(pkl_filename, 'wb') as file:
pickle.dump(estim.best_model(), file)
print('--- Correctly saved! ---')
'status': STATUS_OK,
'training_time': training_time,
'total_time': total_time
}
except:
total_time = time.time() - start_time
return {
'loss': np.inf,
'status': STATUS_OK,
'training_time': 0,
'total_time': total_time
}
pipeline_space = {
'clf': any_classifier('my_clf'),
'preprocessor': any_preprocessing('my_prep')
}
print(pipeline_space)
trials = Trials()
best = fmin(objective,
space=pipeline_space,
algo=tpe.suggest,
max_evals=200,
trials=trials)
print(trials.best_trial)
pickle.dump(trials, open("/tmp/trials.p", "wb"))
def main(data='newsgroups',
algo='tpe',
seed=1,
evals=100,
clf='any',
loss=None,
pre='any',
text=''):
filename = text + algo + '_' + clf + '_' + pre + '_' + str(seed) + '_' + str(evals) + \
'_' + data
if loss is not None:
if hasattr(metrics, loss):
loss = getattr(metrics, loss)
else:
print('Unknown loss metric specified')
return 1
if algo == 'tpe':
algorithm = tpe.suggest
elif algo == 'anneal':
algorithm = anneal.suggest
elif algo == 'rand':
algorithm = rand.suggest
elif algo == 'tree':
algorithm = hypertree.tree.suggest
elif algo == 'gp_tree':
algorithm = hypertree.gp_tree.suggest
else:
print('Unknown algorithm specified')
return 1
# TODO: impose restrictions on classifiers that do not work on sparse data
if clf == 'any':
if data in ['newsgroups']:
classifier = any_sparse_classifier('clf')
else:
classifier = any_classifier('clf')
elif clf == 'knn':
if data in ['newsgroups']:
classifier = knn('clf', sparse_data=True)
else:
classifier = knn('clf')
elif clf == 'nearest_centroid':
if data in ['newsgroups']:
classifier = nearest_centroid('clf', sparse_data=True)
else:
classifier = nearest_centroid('clf')
elif hasattr(hpsklearn.components, clf):
classifier = getattr(hpsklearn.components, clf)('clf')
else:
print('Unknown classifier specified')
return 1
"""
elif clf == 'svc':
classifier = svc('clf')
elif clf == 'knn':
if data in ['newsgroups']:
classifier = knn('clf', sparse_data=True)
else:
classifier = knn('clf')
elif clf == 'sgd':
classifier = sgd('clf')
elif clf == 'random_forest':
classifier = random_forest('clf')
elif clf == 'extra_trees':
classifier = extra_trees('clf')
elif clf == 'liblinear_svc':
classifier = liblinear_svc('clf')
elif clf == 'multinomial_nb':
classifier = multinomial_nb('clf')
elif clf == 'nearest_centroid':
if data in ['newsgroups']:
classifier = nearest_centroid('clf', sparse_data=True)
else:
classifier = nearest_centroid('clf')
elif clf == 'rbm':
classifier = rbm('clf')
elif clf == 'colkmeans':
classifier = colkmeans('clf')
else:
print( 'Unknown classifier specified' )
return 1
"""
if pre == 'any':
if data in ['newsgroups']:
preproc = any_text_preprocessing('pre')
else:
preproc = any_preprocessing('pre')
elif pre == 'none':
preproc = []
elif hasattr(hpsklearn.components, pre):
preproc = [getattr(hpsklearn.components, pre)('pre')]
else:
print('Unknown preprocessing specified')
return 1
"""
elif pre == 'pca':
preproc = [pca('pre')]
elif pre == 'standard_scaler':
preproc = [standard_scaler('pre')]
elif pre == 'min_max_scaler':
preproc = [min_max_scaler('pre')]
elif pre == 'normalizer':
preproc = [normalizer('pre')]
elif pre == 'tfidf':
preproc = [tfidf('pre')]
"""
if data == 'newsgroups':
sklearn_newsgroups(classifier=classifier,
algorithm=algorithm,
max_evals=evals,
seed=seed,
filename=filename,
preproc=preproc,
loss=loss)
elif data == 'convex':
if CONVEX_EXISTS:
sklearn_convex(classifier=classifier,
algorithm=algorithm,
max_evals=evals,
seed=seed,
filename=filename,
preproc=preproc,
loss=loss)
else:
print(
"Convex dataset not detected on your system, install from MLPython"
)
return 1
elif data == 'mnist':
sklearn_mnist(classifier=classifier,
algorithm=algorithm,
max_evals=evals,
seed=seed,
filename=filename,
preproc=preproc,
loss=loss)
elif data == 'digits':
sklearn_digits(classifier=classifier,
algorithm=algorithm,
max_evals=evals,
seed=seed,
filename=filename,
preproc=preproc,
loss=loss)
else:
print("Unknown dataset specified")
def main( data='newsgroups', algo='tpe', seed=1, evals=100, clf='any',
loss=None, pre='any', text='' ):
filename = text + algo + '_' + clf + '_' + pre + '_' + str(seed) + '_' + str(evals) + \
'_' + data
if loss is not None:
if hasattr( metrics, loss ):
loss = getattr( metrics, loss )
else:
print( 'Unknown loss metric specified' )
return 1
if algo == 'tpe':
algorithm = tpe.suggest
elif algo == 'anneal':
algorithm = anneal.suggest
elif algo == 'rand':
algorithm = rand.suggest
elif algo == 'tree':
algorithm = hypertree.tree.suggest
elif algo == 'gp_tree':
algorithm = hypertree.gp_tree.suggest
else:
print( 'Unknown algorithm specified' )
return 1
# TODO: impose restrictions on classifiers that do not work on sparse data
if clf == 'any':
if data in ['newsgroups']:
classifier = any_sparse_classifier('clf')
else:
classifier = any_classifier('clf')
elif clf == 'knn':
if data in ['newsgroups']:
classifier = knn('clf', sparse_data=True)
else:
classifier = knn('clf')
elif clf == 'nearest_centroid':
if data in ['newsgroups']:
classifier = nearest_centroid('clf', sparse_data=True)
else:
classifier = nearest_centroid('clf')
elif hasattr( hpsklearn.components, clf ):
classifier = getattr( hpsklearn.components, clf )( 'clf' )
else:
print( 'Unknown classifier specified' )
return 1
"""
elif clf == 'svc':
classifier = svc('clf')
elif clf == 'knn':
if data in ['newsgroups']:
classifier = knn('clf', sparse_data=True)
else:
classifier = knn('clf')
elif clf == 'sgd':
classifier = sgd('clf')
elif clf == 'random_forest':
classifier = random_forest('clf')
elif clf == 'extra_trees':
classifier = extra_trees('clf')
elif clf == 'liblinear_svc':
classifier = liblinear_svc('clf')
elif clf == 'multinomial_nb':
classifier = multinomial_nb('clf')
elif clf == 'nearest_centroid':
if data in ['newsgroups']:
classifier = nearest_centroid('clf', sparse_data=True)
else:
classifier = nearest_centroid('clf')
elif clf == 'rbm':
classifier = rbm('clf')
elif clf == 'colkmeans':
classifier = colkmeans('clf')
else:
print( 'Unknown classifier specified' )
return 1
"""
if pre == 'any':
if data in ['newsgroups']:
preproc = any_text_preprocessing('pre')
else:
preproc = any_preprocessing('pre')
elif pre == 'none':
preproc = []
elif hasattr( hpsklearn.components, pre ):
preproc = [getattr( hpsklearn.components, pre)( 'pre' )]
else:
print( 'Unknown preprocessing specified' )
return 1
"""
elif pre == 'pca':
preproc = [pca('pre')]
elif pre == 'standard_scaler':
preproc = [standard_scaler('pre')]
elif pre == 'min_max_scaler':
preproc = [min_max_scaler('pre')]
elif pre == 'normalizer':
preproc = [normalizer('pre')]
elif pre == 'tfidf':
preproc = [tfidf('pre')]
"""
if data == 'newsgroups':
sklearn_newsgroups( classifier=classifier, algorithm=algorithm,
max_evals=evals, seed=seed, filename=filename,
preproc=preproc, loss=loss )
elif data == 'convex':
if CONVEX_EXISTS:
sklearn_convex( classifier=classifier, algorithm=algorithm,
max_evals=evals, seed=seed, filename=filename,
preproc=preproc, loss=loss )
else:
print("Convex dataset not detected on your system, install from MLPython")
return 1
elif data == 'mnist':
sklearn_mnist( classifier=classifier, algorithm=algorithm,
max_evals=evals, seed=seed, filename=filename,
preproc=preproc, loss=loss )
elif data == 'digits':
sklearn_digits( classifier=classifier, algorithm=algorithm,
max_evals=evals, seed=seed, filename=filename,
preproc=preproc, loss=loss )
else:
print( "Unknown dataset specified" )