def command_line_run(args):
args_dict = {}
for i in range(1, len(args)):
if '-' in args[i]:
args_dict[args[i]] = []
args_dict[-1] = args_dict[args[i]]
else:
args_dict[-1].append(float(args[i]))
del args_dict[-1]
num_classes = 10
random.seed(1917)
if '-debug' in args_dict:
train_outputs = import_csv(TRAIN_OUTPUTS_SUBSET_PATH).astype(int)
train_inputs = import_csv(TRAIN_INPUTS_SUBSET_PATH)
else:
train_outputs = import_csv(TRAIN_OUTPUTS_PATH).astype(int)
train_inputs = import_csv(TRAIN_INPUTS_PATH)
if '-t' in args_dict:
print len(train_inputs)
train_inputs = np.array(transform_features(train_inputs))
print len(train_inputs)
# Default values.
hnh = []
num_features = 300
dropout = None
lr = 1.0
epochs = 50
if '-f' in args_dict:
num_features = map(int, args_dict['-f'])[0]
if '-test' in args_dict:
test_inputs = import_csv(TEST_INPUTS_PATH)
if '-t' in args_dict:
test_inputs = transform_features(test_inputs)
if not num_features == len(train_inputs[0]):
alll = feature_reduce(
np.array(list(train_inputs) + list(test_inputs)), num_features)
train_inputs = alll[:len(train_inputs)]
test_inputs = alll[len(train_inputs):]
if '-validate' in args_dict:
validation_size = (4 * len(train_inputs)) / 5
# Randomize the train and validation set.
rand_idxs = random.sample(range(0, len(train_inputs)),
len(train_inputs))
test_inputs = train_inputs[rand_idxs[validation_size:]]
test_outputs = train_outputs[rand_idxs[validation_size:]]
train_inputs = train_inputs[rand_idxs[0:validation_size]]
train_outputs = train_outputs[rand_idxs[0:validation_size]]
# We have to reduce the features all at the same time because it is unsupervised learning and
# we want the same features to be picked by PCA for both of the train and test sets.
if not num_features == len(train_inputs[0]):
alll = feature_reduce(
np.array(list(train_inputs) + list(test_inputs)), num_features)
train_inputs = alll[:len(train_inputs)]
test_inputs = alll[len(train_inputs):]
if '-hn' in args_dict:
hnh = map(int, args_dict['-hn'])
if '-d' in args_dict:
if not (0.0 <= args_dict['-d'][0] <= 1.0):
print 'Please input a dropout rate between 0 and 1!'
exit(0)
dropout = args_dict['-d'][0]
if '-lr' in args_dict:
lr = args_dict['-lr'][0]
if '-e' in args_dict:
epochs = int(args_dict['-e'][0])
nn = NeuralNetwork(len(train_inputs[0]),
hnh,
num_classes,
learning_rate=lr,
dropout=dropout)
nn.fit(train_inputs, train_outputs, training_horizon=epochs, verbose=True)
p = nn.predict(test_inputs)
fname = data_files_path + 'predictions_with_%depochs_%dfeatures_%0.2flf' % (
epochs, num_features, lr)
if '-test' in args_dict:
with open(fname + '.csv', 'w') as f:
f.write('Id,Prediction\n')
for i in range(len(p)):
f.write('%d,%d\n' % (i + 1, p[i]))
else:
print accuracy(p, test_outputs)
if '-record' in args_dict:
heatmap(p, test_outputs, fname)
def command_line_run(args):
args_dict = {}
for i in range(1,len(args)):
if '-' in args[i]:
args_dict[args[i]] = []
args_dict[-1] = args_dict[args[i]]
else:
args_dict[-1].append(float(args[i]))
del args_dict[-1]
num_classes = 10
random.seed(1917)
if '-debug' in args_dict:
train_outputs = import_csv(TRAIN_OUTPUTS_SUBSET_PATH).astype(int)
train_inputs = import_csv(TRAIN_INPUTS_SUBSET_PATH)
else:
train_outputs = import_csv(TRAIN_OUTPUTS_PATH).astype(int)
train_inputs = import_csv(TRAIN_INPUTS_PATH)
if '-t' in args_dict:
print len(train_inputs)
train_inputs = np.array(transform_features(train_inputs))
print len(train_inputs)
# Default values.
hnh = []
num_features = 300
dropout = None
lr = 1.0
epochs = 50
if '-f' in args_dict:
num_features = map(int, args_dict['-f'])[0]
if '-test' in args_dict:
test_inputs = import_csv(TEST_INPUTS_PATH)
if '-t' in args_dict:
test_inputs = transform_features(test_inputs)
if not num_features == len(train_inputs[0]):
alll = feature_reduce(np.array(list(train_inputs)+list(test_inputs)), num_features)
train_inputs = alll[: len(train_inputs)]
test_inputs = alll[len(train_inputs) :]
if '-validate' in args_dict:
validation_size = (4 * len(train_inputs)) / 5
# Randomize the train and validation set.
rand_idxs = random.sample(range(0, len(train_inputs)), len(train_inputs))
test_inputs = train_inputs[rand_idxs[validation_size : ]]
test_outputs = train_outputs[rand_idxs[validation_size : ]]
train_inputs = train_inputs[rand_idxs[0 : validation_size]]
train_outputs = train_outputs[rand_idxs[0 : validation_size]]
# We have to reduce the features all at the same time because it is unsupervised learning and
# we want the same features to be picked by PCA for both of the train and test sets.
if not num_features == len(train_inputs[0]):
alll = feature_reduce(np.array(list(train_inputs)+list(test_inputs)), num_features)
train_inputs = alll[: len(train_inputs)]
test_inputs = alll[len(train_inputs) :]
if '-hn' in args_dict:
hnh = map(int, args_dict['-hn'])
if '-d' in args_dict:
if not (0.0 <= args_dict['-d'][0] <= 1.0):
print 'Please input a dropout rate between 0 and 1!'
exit(0)
dropout = args_dict['-d'][0]
if '-lr' in args_dict:
lr = args_dict['-lr'][0]
if '-e' in args_dict:
epochs = int(args_dict['-e'][0])
nn = NeuralNetwork(len(train_inputs[0]), hnh, num_classes, learning_rate=lr, dropout=dropout)
nn.fit(train_inputs, train_outputs, training_horizon=epochs, verbose=True)
p = nn.predict(test_inputs)
fname = data_files_path+'predictions_with_%depochs_%dfeatures_%0.2flf'%(epochs,num_features,lr)
if '-test' in args_dict:
with open(fname+'.csv','w') as f:
f.write('Id,Prediction\n')
for i in range(len(p)):
f.write('%d,%d\n'%(i+1,p[i]))
else:
print accuracy(p, test_outputs)
if '-record' in args_dict:
heatmap(p, test_outputs, fname)
# grid score
print ("Grid scores on development set:")
print ()
for params, mean_score, scores in clf.grid_scores_:
print ("%0.3f (+/-%0.03f) for %r" % (mean_score, scores.std() * 2, params))
print ()
# validation
print ("Performance of optimal learner on validation set")
print ()
expected, predicted = test_y, clf.predict(test_x)
print (classification_report(expected, predicted))
print (confusion_matrix(expected, predicted))
print ()
accuracy(predicted, expected)
heatmap(predicted, expected, "LinSVM/testAccuracy")
# training accuracy
print ("Performance of optimal learner on training set")
print ()
expected, predicted = train_y, clf.predict(train_x)
print (classification_report(expected, predicted))
print (confusion_matrix(expected, predicted))
print ()
accuracy(predicted, expected)
heatmap(predicted, expected, "LinSVM/trainAccuracy")
# training on the whole dataset
print ("fitting the best estimator on the complete training set")
learner = clf.best_estimator_
learner.fit(train_inputs, train_outputs)
print("Grid scores on development set:")
print()
for params, mean_score, scores in clf.grid_scores_:
print("%0.3f (+/-%0.03f) for %r" %
(mean_score, scores.std() * 2, params))
print()
#validation
print("Performance of optimal learner on validation set")
print()
expected, predicted = test_y, clf.predict(test_x)
print(classification_report(expected, predicted))
print(confusion_matrix(expected, predicted))
print()
accuracy(predicted, expected)
heatmap(predicted, expected, 'LogReg/testAccuracy')
#training accuracy
print("Performance of optimal learner on training set")
print()
expected, predicted = train_y, clf.predict(train_x)
print(classification_report(expected, predicted))
print(confusion_matrix(expected, predicted))
print()
accuracy(predicted, expected)
heatmap(predicted, expected, 'LogReg/trainAccuracy')
#training on the whole dataset
print("fitting the best estimator on the complete training set")
learner = clf.best_estimator_
learner.fit(train_inputs, train_outputs)
#grid score
print("Grid scores on development set:")
print()
for params, mean_score, scores in clf.grid_scores_:
print("%0.3f (+/-%0.03f) for %r" % (mean_score, scores.std() * 2, params))
print()
#validation
print("Performance of optimal learner on validation set")
print()
expected, predicted = test_y, clf.predict(test_x)
print(classification_report(expected, predicted))
print(confusion_matrix(expected, predicted))
print()
accuracy(predicted,expected)
heatmap(predicted,expected,'LogReg/testAccuracy')
#training accuracy
print("Performance of optimal learner on training set")
print()
expected, predicted = train_y, clf.predict(train_x)
print(classification_report(expected, predicted))
print(confusion_matrix(expected, predicted))
print()
accuracy(predicted,expected)
heatmap(predicted,expected,'LogReg/trainAccuracy')
#training on the whole dataset
print("fitting the best estimator on the complete training set")
learner=clf.best_estimator_
learner.fit(train_inputs,train_outputs)