def begin_train(dynamic_path, static_path, out_path):
dynamic_features = utilities.load_adjective_phase(dynamic_path)
static_features = utilities.load_adjective_phase(static_path)
adjective_list = utilities.adjectives
for adjective in adjective_list:
# File name
dataset_file_name = "_".join(("trained", adjective))+".pkl"
newpath = os.path.join(out_path, "trained_adjectives")
path_name = os.path.join(newpath, dataset_file_name)
if os.path.exists(path_name):
print "File %s already exists, skipping it." % path_name
continue
overall_best_score = 0.0
dataset = defaultdict()
dataset['classifier'] = None
dataset['training_score'] = overall_best_score
dynamic_train = utilities.get_all_train_test_features(adjective, dynamic_features)
y_labels = dynamic_train[1]
object_ids = dynamic_train[2]
dynamic_scaler = preprocessing.StandardScaler().fit(dynamic_train[0])
dynamic_X = dynamic_scaler.transform(dynamic_train[0])
dynamic_kernel = linear_kernel(dynamic_X, -2)
#dynamic_kernel = standardize(dynamic_kernel)
static_train = utilities.get_all_train_test_features(adjective, static_features)
static_scaler = preprocessing.StandardScaler().fit(static_train[0])
static_X = static_scaler.transform(static_train[0])
static_kernel = linear_kernel(static_X, -2)
#static_kernel = standardize(static_kernel)
alpha_range = [0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]
#alpha_range = [0.5]
for alpha in alpha_range:
print "Beginning %s, alpha %1.1f at %s" % (adjective,alpha, time.asctime())
combined_kernel = (alpha)*static_kernel + (1-alpha)*dynamic_kernel;
trained_clf, best_score = gram_grid_search(combined_kernel, labels=y_labels, object_ids=object_ids, refined_range = adjective)
print "F1: %1.5f at %s" % (best_score, time.asctime())
if best_score > overall_best_score:
overall_best_score = best_score
dataset['classifier'] = trained_clf
dataset['training_score'] = best_score
dataset['alpha'] = alpha
dataset['dynamic_features'] = dynamic_features[adjective]
dataset['static_features'] = static_features[adjective]
dataset['adjective'] = adjective
dataset['dynamic_scaler'] = dynamic_scaler
dataset['dynamic_train_scaled'] = dynamic_X;
dataset['dynamic_kernel_mean'] = np.mean(dynamic_kernel)
dataset['dynamic_kernel_std'] = np.std(dynamic_kernel)
dataset['static_scaler'] = static_scaler
dataset['static_train_scaled'] = static_X;
dataset['static_kernel_mean'] = np.mean(static_kernel)
dataset['static_kernel_std'] = np.std(static_kernel)
print "Saving trained_classifier"
# Save the results in the folder
with open(path_name, "w") as f:
print "Saving file: ", path_name
cPickle.dump(dataset, f, protocol=cPickle.HIGHEST_PROTOCOL)
def begin_train(dynamic_path, static_path, out_path):
dynamic_features = utilities.load_adjective_phase(dynamic_path)
static_features = utilities.load_adjective_phase(static_path)
adjective_list = utilities.adjectives
for adjective in adjective_list:
# File name
dataset_file_name = "_".join(("trained", adjective)) + ".pkl"
newpath = os.path.join(out_path, "trained_adjectives")
path_name = os.path.join(newpath, dataset_file_name)
if os.path.exists(path_name):
print "File %s already exists, skipping it." % path_name
continue
overall_best_score = 0.0
dataset = defaultdict()
dataset['classifier'] = None
dataset['training_score'] = overall_best_score
dynamic_train = utilities.get_all_train_test_features(
adjective, dynamic_features)
y_labels = dynamic_train[1]
object_ids = dynamic_train[2]
dynamic_scaler = preprocessing.StandardScaler().fit(dynamic_train[0])
dynamic_X = dynamic_scaler.transform(dynamic_train[0])
dynamic_kernel = linear_kernel(dynamic_X, -2)
#dynamic_kernel = standardize(dynamic_kernel)
static_train = utilities.get_all_train_test_features(
adjective, static_features)
static_scaler = preprocessing.StandardScaler().fit(static_train[0])
static_X = static_scaler.transform(static_train[0])
static_kernel = linear_kernel(static_X, -2)
#static_kernel = standardize(static_kernel)
alpha_range = [0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]
#alpha_range = [0.5]
for alpha in alpha_range:
print "Beginning %s, alpha %1.1f at %s" % (adjective, alpha,
time.asctime())
combined_kernel = (alpha) * static_kernel + (
1 - alpha) * dynamic_kernel
trained_clf, best_score = gram_grid_search(combined_kernel,
labels=y_labels,
object_ids=object_ids,
refined_range=adjective)
print "F1: %1.5f at %s" % (best_score, time.asctime())
if best_score > overall_best_score:
overall_best_score = best_score
dataset['classifier'] = trained_clf
dataset['training_score'] = best_score
dataset['alpha'] = alpha
dataset['dynamic_features'] = dynamic_features[adjective]
dataset['static_features'] = static_features[adjective]
dataset['adjective'] = adjective
dataset['dynamic_scaler'] = dynamic_scaler
dataset['dynamic_train_scaled'] = dynamic_X
dataset['dynamic_kernel_mean'] = np.mean(dynamic_kernel)
dataset['dynamic_kernel_std'] = np.std(dynamic_kernel)
dataset['static_scaler'] = static_scaler
dataset['static_train_scaled'] = static_X
dataset['static_kernel_mean'] = np.mean(static_kernel)
dataset['static_kernel_std'] = np.std(static_kernel)
print "Saving trained_classifier"
# Save the results in the folder
with open(path_name, "w") as f:
print "Saving file: ", path_name
cPickle.dump(dataset, f, protocol=cPickle.HIGHEST_PROTOCOL)
def compute_probability_vector(self, bolt_obj):
# First object - initialize variables to store
# Also clears out the vectors for new run
if bolt_obj.state == bolt_obj.TAP:
# Store results as they come in
self.adjective_vectors_static = dict()
self.adjective_vectors_dynamic = dict()
self.all_motion_results = dict()
self.mkl_results = dict()
# Store dictionary of strings
self.state_string = {
bolt_obj.DISABLED: 'disabled',
bolt_obj.THERMAL_HOLD: 'thermal_hold',
bolt_obj.SLIDE: 'slide',
bolt_obj.SQUEEZE: 'squeeze',
bolt_obj.TAP: 'tap',
bolt_obj.DONE: 'done',
bolt_obj.SLIDE_FAST: 'slide_fast',
bolt_obj.CENTER_GRIPPER: 'center_gripper'
}
# store dictionary for detailed states
self.detailed_states = {
bolt_obj.DISABLED: 'MOVE_ARM_START_POSITION',
bolt_obj.SQUEEZE: 'SQUEEZE_SET_PRESSURE_SLOW',
bolt_obj.THERMAL_HOLD: 'HOLD_FOR_10_SECONDS',
bolt_obj.SLIDE: 'SLIDE_5CM',
bolt_obj.SLIDE_FAST: 'MOVE_DOWN_5CM'
}
# Get the current motion
current_motion = self.state_string[bolt_obj.state]
# Check if state passed in should be processed
if bolt_obj.state not in self.detailed_states:
return
else:
# Get detailed state if exists
current_detailed_state = self.detailed_states[bolt_obj.state]
# Check if the state is a the disabled state
if bolt_obj.state == bolt_obj.DISABLED:
self.norm_bolt_obj = upenn_features.pull_detailed_state(
bolt_obj, current_detailed_state)
return
else:
self.bolt_object = upenn_features.pull_detailed_state(
bolt_obj, current_detailed_state)
# Checks to make sure that the norm obj has been created
if not self.norm_bolt_obj:
print "Warning: there is no normalization data"
# Build the static features
static_feature_object, self.static_features_array = upenn_features.extract_static_features(
self.bolt_object, self.norm_bolt_obj)
static_feats = upenn_features.createFeatureVector(
static_feature_object)
# Store all feature vectors into one large vector array
# Technically we don't need to store the static
# features by adjective - but it's cleaner this way
for classifier in self.all_classifiers:
adj = classifier['adjective']
# need to add pkl to the name b/c the hmm chain dictionary
# takes adjective.pkl as its key
hmm_adj_name = '.'.join((adj, 'pkl'))
# Initialize the dictionary with adjective
if adj in self.adjective_vectors_static:
pass
else:
self.adjective_vectors_static[adj] = list()
self.adjective_vectors_dynamic[adj] = list()
# Pull out chain associated with adjective
# ordering of sensors - [pac, pdc, electrodes, tac]
sensor_hmm = ['pac', 'pdc', 'electrodes', 'tac']
hmm_features_phase = []
for sensor in sensor_hmm:
hmm_chain = self.hmm_chains[hmm_adj_name].chains[
current_detailed_state][sensor]
hmm_data = self.bolt_object.hmm[sensor]
# fill in dyanmic features
hmm_features_phase.append(hmm_chain.score(hmm_data))
# Store the feature vector by adjective away
self.adjective_vectors_static[adj].append(static_feats)
self.adjective_vectors_dynamic[adj].append(hmm_features_phase)
# Check if all motions have been performed
# If so - feed into classifier
if len(self.adjective_vectors_dynamic[adj]) == 4:
print 'All motions received! Computing adjective scores'
for classifier in self.all_classifiers:
# Pull out which adjective we are working on
adj = classifier['adjective']
# Load training vectors for kernel creation
train_dynamic = utilities.get_all_train_test_features(
adj, self.training_dynamic, train=True)
train_static = utilities.get_all_train_test_features(
adj, self.training_static, train=True)
# Scale the training data
d_scaler = preprocessing.StandardScaler().fit(
train_dynamic[0])
s_scaler = preprocessing.StandardScaler().fit(
train_static[0])
train_dynamic_scaled = d_scaler.transform(train_dynamic[0])
train_static_scaled = s_scaler.transform(train_static[0])
# Pull out the feature vectors for static/dynamic
all_static_feats = np.hstack(
self.adjective_vectors_static[adj])
all_dynamic_feats = np.hstack(
self.adjective_vectors_dynamic[adj])
# Normalize the features using scaler
all_static_feats_scaled = classifier[
'static_scaler'].transform(all_static_feats)
all_dynamic_feats_scaled = classifier[
'dynamic_scaler'].transform(all_dynamic_feats)
# Create kernels for both static and dynamic
static_kernel = self.linear_kernel_test(
all_static_feats_scaled, train_static_scaled, 1)
dynamic_kernel = self.linear_kernel_test(
all_dynamic_feats_scaled, train_dynamic_scaled, 1)
# Merge the two kernels
alpha = classifier['alpha']
merged_kernel = (alpha) * static_kernel + (
1 - alpha) * dynamic_kernel
# Predict adjective with computed kernel
clf = classifier['classifier']
self.mkl_results[adj] = clf.predict(merged_kernel)
# Store off the adjectives that returned true
adjectives_found = []
for adj in self.mkl_results:
if self.mkl_results[adj] == 1:
adjectives_found.append(Adj(adj))
publish_string = AdjList()
publish_string = adjectives_found
# Print and publish results!
print "Results from MKL classification"
#print self.mkl_results
print str(adjectives_found)
self.adjectives_pub.publish(publish_string)
def test_adjective(classifier, adjective_report ):
true_positives = 0.0
true_negatives = 0.0
false_positives = 0.0
false_negatives = 0.0
false_positive_list = []
false_negative_list = []
true_positive_list = []
true_negative_list = []
adjective = classifier['adjective']
dynamic_features = utilities.load_adjective_phase('/home/imcmahon/Desktop/mkl/dynamic/adjective_phase_set')
static_features = utilities.load_adjective_phase('/home/imcmahon/Desktop/mkl/static/adjective_phase_set')
#dynamic_features = utilities.load_adjective_phase(dynamic_path)
#static_features = utilities.load_adjective_phase(static_path)
#import pdb; pdb.set_trace()
#Dynamic Train
dynamic_train = utilities.get_all_train_test_features(adjective, dynamic_features, train=True)
dynamic_train_scaler = preprocessing.StandardScaler().fit(dynamic_train[0])
dynamic_train_scaled_X = dynamic_train_scaler.transform(dynamic_train[0])
dynamic_train_kernel = linear_kernel(dynamic_train_scaled_X, -2)
#dynamic_train_kernel = standardize(dynamic_train_kernel)
#Static Train
static_train = utilities.get_all_train_test_features(adjective, static_features, train=True)
static_train_scaler = preprocessing.StandardScaler().fit(static_train[0])
static_train_scaled_X = static_train_scaler.transform(static_train[0])
static_train_kernel = linear_kernel(static_train_scaled_X, -2)
#static_train_kernel = standardize(static_train_kernel)
#Recompute the GRAM matrix
#alpha = classifier['alpha'];
#train_X = (alpha)*static_train_kernel + (1-alpha)*dynamic_train_kernel
#import pdb; pdb.set_trace()
dynamic_test = utilities.get_all_train_test_features(adjective, dynamic_features, train=False)
dynamic_test_scaled_X = classifier['dynamic_scaler'].transform(dynamic_test[0])
dynamic_kernel = linear_kernel_test(dynamic_test_scaled_X, dynamic_train_scaled_X, -2)
#dynamic_kernel = (dynamic_kernel - classifier['dynamic_kernel_mean']) / classifier['dynamic_kernel_std']
static_test = utilities.get_all_train_test_features(adjective, static_features, train=False)
static_test_scaled_X = classifier['static_scaler'].transform(static_test[0])
static_kernel = linear_kernel_test(static_test_scaled_X, static_train_scaled_X, -2)
#static_kernel = (static_kernel - classifier['static_kernel_mean']) / classifier['static_kernel_std']
alpha = classifier['alpha'];
test_X = (alpha)*static_kernel + (1-alpha)*dynamic_kernel
print '\n \nTesting Adjective: %s' % classifier['adjective']
#Pull out test features/labels
#for phase in phases:
#import pdb; pdb.set_trace()
#test_set = classifier['test']
#test_X.append(test_set['features'])
#test_X.append(test_set['features'])
test_Y = dynamic_test[1]
object_ids = dynamic_test[2]
#object_names = test_set['object_names']
# Pull out the classifier and merge features
#test_X = np.concatenate(test_X, axis=1)
#import pdb; pdb.set_trace()
clf = classifier['classifier']
c_dict[classifier['adjective']] = clf.C
#import pdb; pdb.set_trace()
print clf
# Predict the labels!
#if 'scaler' in classifier:
# if type(classifier['scaler']) == preprocessing.Scaler:
# test_X = classifier['scaler'].transform(test_X)
#import pdb; pdb.set_trace()
output = clf.predict(test_X)
# Determine if the true label and classifier prediction match
for val in xrange(len(test_Y)):
true_label = test_Y[val]
predict_label = output[val]
if true_label == 1:
if predict_label == 1:
true_positives += 1.0
#true_positive_list.append(object_names[val])
else:
false_negatives += 1.0
#false_negative_list.append(object_names[val])
else: # label is 0
if predict_label == 1:
false_positives += 1.0
#false_positive_list.append(object_names[val])
else:
true_negatives += 1.0
#true_negative_list.append(object_names[val])
# Compute statistics for the adjective
try:
precision = true_positives / (true_positives + false_positives)
recall = true_positives / (true_positives + false_negatives)
except ZeroDivisionError: # The case when none are found
precision = 0
recall = 0
try:
f1 = 2.0 * precision*recall / (precision + recall)
except ZeroDivisionError:
f1 = 0
print "Precision: %f, Recall: %f, F1: %f \n" % (precision, recall, f1)
print "Alpha = %1.1f" % alpha
adjective_report.write("%s, %1.1f, %f, %f, %f\n" % (classifier['adjective'], alpha, precision, recall, f1))
print "%d False Positive Objects\n" % false_positives
print "%d False Negative Objects\n" % false_negatives
print "%d True Positive Objects\n" % true_positives
print "%d True Negative Objects\n" % true_negatives
return (alpha, precision, recall, f1)
def compute_probability_vector(self, bolt_obj):
if len(self.bolt_object_list) == 0:
self.movement_time = time.time()
# First object - initialize variables to store
# Also clears out the vectors for new run
if bolt_obj.state == bolt_obj.TAP:
# Store results as they come in
self.adjective_vectors_static = dict()
self.adjective_vectors_dynamic = dict()
self.all_motion_results = dict()
self.mkl_results = dict()
# Store dictionary of strings
self.state_string = {bolt_obj.DISABLED:'disabled',
bolt_obj.THERMAL_HOLD:'thermal_hold',
bolt_obj.SLIDE:'slide',
bolt_obj.SQUEEZE:'squeeze',
bolt_obj.TAP:'tap',
bolt_obj.DONE:'done',
bolt_obj.SLIDE_FAST:'slide_fast',
bolt_obj.CENTER_GRIPPER:'center_gripper'
}
# store dictionary for detailed states
self.detailed_states = {bolt_obj.DISABLED:'MOVE_ARM_START_POSITION',
bolt_obj.SQUEEZE:'SQUEEZE_SET_PRESSURE_SLOW',
bolt_obj.THERMAL_HOLD:'HOLD_FOR_10_SECONDS',
bolt_obj.SLIDE:'SLIDE_5CM',
bolt_obj.SLIDE_FAST:'MOVE_DOWN_5CM'
}
if (len(self.bolt_object_list) < 5):
print len(self.bolt_object_list)
self.bolt_object_list.append(bolt_obj)
return
else:
self.bolt_object_list.append(bolt_obj)
motion_end_time = time.time()
print("Elapsed time was %g seconds" % (motion_end_time - self.movement_time))
start_time = time.time()
for bolt_obj_v in self.bolt_object_list:
# Get the current motion
current_motion = self.state_string[bolt_obj_v.state]
# Check if state passed in should be processed
if bolt_obj_v.state not in self.detailed_states:
print "Skipping state: %s" % current_motion
continue
else:
# Get detailed state if exists
current_detailed_state = self.detailed_states[bolt_obj_v.state]
# Check if the state is a the disabled state
if bolt_obj_v.state == bolt_obj_v.DISABLED:
self.norm_bolt_obj = upenn_features.pull_detailed_state(bolt_obj_v,current_detailed_state)
continue
else:
cur_bolt_object = upenn_features.pull_detailed_state(bolt_obj_v, current_detailed_state)
# Checks to make sure that the norm obj has been created
if not self.norm_bolt_obj:
print "Warning: there is no normalization data"
#Start storing the bolt objects
# Build the static features
static_feature_object, self.static_features_array = upenn_features.extract_static_features(cur_bolt_object, self.norm_bolt_obj)
static_feats = upenn_features.createFeatureVector(static_feature_object)
# Store all feature vectors into one large vector array
# Technically we don't need to store the static
# features by adjective - but it's cleaner this way
for classifier in self.all_classifiers:
adj = classifier['adjective']
# need to add pkl to the name b/c the hmm chain dictionary
# takes adjective.pkl as its key
hmm_adj_name = '.'.join((adj,'pkl'))
# Initialize the dictionary with adjective
if adj in self.adjective_vectors_static:
pass
else:
self.adjective_vectors_static[adj] = list()
self.adjective_vectors_dynamic[adj] = list()
# Pull out chain associated with adjective
# ordering of sensors - [pac, pdc, electrodes, tac]
sensor_hmm = ['pac', 'pdc', 'electrodes', 'tac']
hmm_features_phase = [];
for sensor in sensor_hmm:
hmm_chain = self.hmm_chains[hmm_adj_name].chains[current_detailed_state][sensor]
hmm_data = cur_bolt_object.hmm[sensor]
# fill in dyanmic features
hmm_features_phase.append(hmm_chain.score(hmm_data))
# Store the feature vector by adjective away
self.adjective_vectors_static[adj].append(static_feats)
self.adjective_vectors_dynamic[adj].append(hmm_features_phase)
# Check if all motions have been performed
# If so - feed into classifier
if len(self.adjective_vectors_dynamic[adj]) == 4:
print 'All motions received! Computing adjective scores'
for classifier in self.all_classifiers:
# Pull out which adjective we are working on
adj = classifier['adjective']
# Load training vectors for kernel creation
train_dynamic = utilities.get_all_train_test_features(adj, self.training_dynamic, train=True)
train_static = utilities.get_all_train_test_features(adj, self.training_static, train=True)
# Scale the training data
d_scaler = preprocessing.StandardScaler().fit(train_dynamic[0])
s_scaler = preprocessing.StandardScaler().fit(train_static[0])
train_dynamic_scaled = d_scaler.transform(train_dynamic[0])
train_static_scaled = s_scaler.transform(train_static[0])
# Pull out the feature vectors for static/dynamic
all_static_feats = np.hstack(self.adjective_vectors_static[adj])
all_dynamic_feats = np.hstack(self.adjective_vectors_dynamic[adj])
# Normalize the features using scaler
all_static_feats_scaled = classifier['static_scaler'].transform(all_static_feats)
all_dynamic_feats_scaled = classifier['dynamic_scaler'].transform(all_dynamic_feats)
# Create kernels for both static and dynamic
static_kernel = self.linear_kernel_test(all_static_feats_scaled, train_static_scaled, 1)
dynamic_kernel = self.linear_kernel_test(all_dynamic_feats_scaled, train_dynamic_scaled, 1)
# Merge the two kernels
alpha = classifier['alpha']
merged_kernel = (alpha)*static_kernel + (1-alpha)*dynamic_kernel
# Predict adjective with computed kernel
clf = classifier['classifier']
self.mkl_results[adj] = clf.predict(merged_kernel)
# Store off the adjectives that returned true
adjectives_found = []
for adj in self.mkl_results:
if self.mkl_results[adj] == 1:
adjectives_found.append(Adj(adj))
hardcode_adj = [Adj('hard'), Adj('metallic'), Adj('cool')]
publish_string = AdjList()
#publish_string = adjectives_found
publish_string = hardcode_adj;
# Print and publish results!
print "Results from MKL classification"
#print self.mkl_results
print str(adjectives_found)
end_time = time.time()
print("Elapsed time was %g seconds" % (end_time - start_time))
self.adjectives_pub.publish(publish_string)
def test_adjective(classifier, adjective_report):
true_positives = 0.0
true_negatives = 0.0
false_positives = 0.0
false_negatives = 0.0
false_positive_list = []
false_negative_list = []
true_positive_list = []
true_negative_list = []
adjective = classifier['adjective']
dynamic_features = utilities.load_adjective_phase(
'/home/imcmahon/Desktop/mkl/dynamic/adjective_phase_set')
static_features = utilities.load_adjective_phase(
'/home/imcmahon/Desktop/mkl/static/adjective_phase_set')
#dynamic_features = utilities.load_adjective_phase(dynamic_path)
#static_features = utilities.load_adjective_phase(static_path)
#import pdb; pdb.set_trace()
#Dynamic Train
dynamic_train = utilities.get_all_train_test_features(adjective,
dynamic_features,
train=True)
dynamic_train_scaler = preprocessing.StandardScaler().fit(dynamic_train[0])
dynamic_train_scaled_X = dynamic_train_scaler.transform(dynamic_train[0])
dynamic_train_kernel = linear_kernel(dynamic_train_scaled_X, -2)
#dynamic_train_kernel = standardize(dynamic_train_kernel)
#Static Train
static_train = utilities.get_all_train_test_features(adjective,
static_features,
train=True)
static_train_scaler = preprocessing.StandardScaler().fit(static_train[0])
static_train_scaled_X = static_train_scaler.transform(static_train[0])
static_train_kernel = linear_kernel(static_train_scaled_X, -2)
#static_train_kernel = standardize(static_train_kernel)
#Recompute the GRAM matrix
#alpha = classifier['alpha'];
#train_X = (alpha)*static_train_kernel + (1-alpha)*dynamic_train_kernel
#import pdb; pdb.set_trace()
dynamic_test = utilities.get_all_train_test_features(adjective,
dynamic_features,
train=False)
dynamic_test_scaled_X = classifier['dynamic_scaler'].transform(
dynamic_test[0])
dynamic_kernel = linear_kernel_test(dynamic_test_scaled_X,
dynamic_train_scaled_X, -2)
#dynamic_kernel = (dynamic_kernel - classifier['dynamic_kernel_mean']) / classifier['dynamic_kernel_std']
static_test = utilities.get_all_train_test_features(adjective,
static_features,
train=False)
static_test_scaled_X = classifier['static_scaler'].transform(
static_test[0])
static_kernel = linear_kernel_test(static_test_scaled_X,
static_train_scaled_X, -2)
#static_kernel = (static_kernel - classifier['static_kernel_mean']) / classifier['static_kernel_std']
alpha = classifier['alpha']
test_X = (alpha) * static_kernel + (1 - alpha) * dynamic_kernel
print '\n \nTesting Adjective: %s' % classifier['adjective']
#Pull out test features/labels
#for phase in phases:
#import pdb; pdb.set_trace()
#test_set = classifier['test']
#test_X.append(test_set['features'])
#test_X.append(test_set['features'])
test_Y = dynamic_test[1]
object_ids = dynamic_test[2]
#object_names = test_set['object_names']
# Pull out the classifier and merge features
#test_X = np.concatenate(test_X, axis=1)
#import pdb; pdb.set_trace()
clf = classifier['classifier']
c_dict[classifier['adjective']] = clf.C
#import pdb; pdb.set_trace()
print clf
# Predict the labels!
#if 'scaler' in classifier:
# if type(classifier['scaler']) == preprocessing.Scaler:
# test_X = classifier['scaler'].transform(test_X)
#import pdb; pdb.set_trace()
output = clf.predict(test_X)
# Determine if the true label and classifier prediction match
for val in xrange(len(test_Y)):
true_label = test_Y[val]
predict_label = output[val]
if true_label == 1:
if predict_label == 1:
true_positives += 1.0
#true_positive_list.append(object_names[val])
else:
false_negatives += 1.0
#false_negative_list.append(object_names[val])
else: # label is 0
if predict_label == 1:
false_positives += 1.0
#false_positive_list.append(object_names[val])
else:
true_negatives += 1.0
#true_negative_list.append(object_names[val])
# Compute statistics for the adjective
try:
precision = true_positives / (true_positives + false_positives)
recall = true_positives / (true_positives + false_negatives)
except ZeroDivisionError: # The case when none are found
precision = 0
recall = 0
try:
f1 = 2.0 * precision * recall / (precision + recall)
except ZeroDivisionError:
f1 = 0
print "Precision: %f, Recall: %f, F1: %f \n" % (precision, recall, f1)
print "Alpha = %1.1f" % alpha
adjective_report.write(
"%s, %1.1f, %f, %f, %f\n" %
(classifier['adjective'], alpha, precision, recall, f1))
print "%d False Positive Objects\n" % false_positives
print "%d False Negative Objects\n" % false_negatives
print "%d True Positive Objects\n" % true_positives
print "%d True Negative Objects\n" % true_negatives
return (alpha, precision, recall, f1)