def compute_probability_vector(self, bolt_obj):
if bolt_obj.state == bolt_obj.TAP:
# Store results as they come in
self.adjective_vectors = dict()
self.all_motion_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'
}
current_motion = self.state_string[bolt_obj.state]
# Create feature vector
self.bolt_object = bolt_obj
utilities.normalize_data(self.bolt_object)
self.bolt_feature_object = extract_features.extract_features(self.bolt_object, self.pca_model[current_motion])
# Create a dictionary to store the results in
for adj in self.all_classifiers:
results, prob = utilities.compute_adjective_probability_score(self.all_classifiers[adj], self.bolt_feature_object, self.feature_list, adj, self.scaler_dict)
# Store off adjective probabilities for ensemble
if adj in self.adjective_vectors:
pass
else:
self.adjective_vectors[adj] = list()
self.adjective_vectors[adj].append(prob)
# Store classifier score based on best motion
best_motion = self.best_motion_dict[adj][1]
if current_motion == best_motion:
rospy.loginfo("Best Motion is: %s" % best_motion)
self.all_motion_results[adj] = results
print len(self.adjective_vectors[adj])
if len(self.adjective_vectors[adj]) == 5:
ensembled_results = dict()
print self.adjective_vectors
#for adj in self.adjective_vectors:
# ensembled_results[adj] = self.ensemble_classifiers[adj].predict(self.adjective_vectors[adj])
# Store off the adjectives that returned true
adjectives_found = []
for adj in self.all_motion_results:
if self.all_motion_results[adj] == 1:
adjectives_found.append(adj)
print "Results from max classification"
print self.all_motion_results
print str(adjectives_found)
self.adjectives_pub.publish(str(adjectives_found))
def compute_probability_vector(self, bolt_obj):
if bolt_obj.state == bolt_obj.TAP:
# Store results as they come in
self.adjective_vectors = dict()
self.all_motion_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'
}
# Get the current motion
current_motion = self.state_string[bolt_obj.state]
# Build the feature vector
self.bolt_object = bolt_obj
utilities.normalize_data(self.bolt_object)
if self.bolt_object.state == bolt_obj.DISABLED:
return
else:
self.bolt_feature_object = extract_features.extract_features(self.bolt_object, self.pca_model[current_motion])
# Create a dictionary to store the results in
for adj in self.all_classifiers:
results, prob = utilities.compute_adjective_probability_score(self.all_classifiers[adj], self.bolt_feature_object, self.feature_list, adj, self.scaler_dict)
# Store off adjective probabilities for ensemble
if adj in self.adjective_vectors:
pass
else:
self.adjective_vectors[adj] = list()
self.adjective_vectors[adj].append(prob)
# Store classifier score based on best motion
best_motion = self.best_motion_dict[adj][1]
if current_motion == best_motion:
rospy.loginfo("Best Motion is: %s"% best_motion)
self.all_motion_results[adj] = results
print len(self.adjective_vectors[adj])
if len(self.adjective_vectors[adj]) == 5:
ensembled_results = dict()
#print self.adjective_vectors
for adj in self.ensemble_classifiers:
ensembled_results[adj] = self.ensemble_classifiers[adj].predict(self.adjective_vectors[adj])[0]
# Store off the adjectives that returned true
adjectives_found = []
for adj in self.all_motion_results:
if self.all_motion_results[adj] == 1:
adjectives_found.append(adj)
# Store off the adjectives that returns true for ensemble
adjectives_ensemble = []
for adj in ensembled_results:
if ensembled_results[adj] == 1:
adjectives_ensemble.append(adj)
publish_string = AdjList()
publish_string = adjective_found
print "Results from max classification"
print self.all_motion_results
print str(adjectives_found)
self.adjectives_pub.publish(str(adjectives_found))
print "Results from ensemble"
print ensembled_results
print adjectives_ensemble
def load_data(input_filename, output_filename, save_to_file):
if not input_filename.endswith(".h5"):
raise Exception("Input file is %s \nPlease pass in a hdf5 data file" % input_filename)
if save_to_file:
if not output_filename.endswith(".pkl"):
output_filename = output_filename + '.pkl'
# Load the data from an h5 file
all_data = tables.openFile(input_filename)
# Flag to indicate if raw values are stored when normalizing
discard_raw_flag = True
# Create a storage container for data
tap_runs = list()
squeeze_runs = list()
hold_runs = list()
slow_slide_runs = list()
fast_slide_runs = list()
# Create dictonary to store the final lists
segmented_data = dict()
# Keep counter of the number of runs done
num_runs = 0
# Pull pointers to only the file heads of the data structure
all_runs_root = [_g for _g in all_data.walkGroups("/") if _g._v_depth == 1]
# For each file extract the segments and data
for _objectRun in all_runs_root:
num_runs += 1
print num_runs
# Pull out tap information
tap_object = PullDataFromRun(_objectRun, BoltPR2MotionObj.TAP)
utilities.normalize_data(tap_object, discard_raw_flag)
tap_runs.append(tap_object)
# Pull out squeeze information
squeeze_object = PullDataFromRun(_objectRun, BoltPR2MotionObj.SQUEEZE)
utilities.normalize_data(squeeze_object, discard_raw_flag)
squeeze_runs.append(squeeze_object)
# Pull out hold information
hold_object = PullDataFromRun(_objectRun, BoltPR2MotionObj.THERMAL_HOLD)
utilities.normalize_data(hold_object, discard_raw_flag)
hold_runs.append(hold_object)
# Pull out slide fast information
slide_fast_object = PullDataFromRun(_objectRun, BoltPR2MotionObj.SLIDE_FAST)
utilities.normalize_data(slide_fast_object, discard_raw_flag)
fast_slide_runs.append(slide_fast_object)
# Pull out slide slow information
slide_slow_object = PullDataFromRun(_objectRun, BoltPR2MotionObj.SLIDE)
utilities.normalize_data(slide_slow_object, discard_raw_flag)
slow_slide_runs.append(slide_slow_object)
# Store all of the lists into the dictionary
segmented_data['tap'] = tap_runs
segmented_data['squeeze'] = squeeze_runs
segmented_data['thermal_hold'] = hold_runs
segmented_data['slide'] = slow_slide_runs
segmented_data['slide_fast'] = fast_slide_runs
# if we want to save to file
if (save_to_file):
file_ptr = open(output_filename, "w")
cPickle.dump(segmented_data, file_ptr, cPickle.HIGHEST_PROTOCOL)
file_ptr.close()
return segmented_data
def load_data(input_filename, output_filename, save_to_file):
if not input_filename.endswith(".h5"):
raise Exception("Input file is %s \nPlease pass in a hdf5 data file" %
input_filename)
if save_to_file:
if not output_filename.endswith(".pkl"):
output_filename = output_filename + '.pkl'
# Load the data from an h5 file
all_data = tables.openFile(input_filename)
# Flag to indicate if raw values are stored when normalizing
discard_raw_flag = True
# Create a storage container for data
tap_runs = list()
squeeze_runs = list()
hold_runs = list()
slow_slide_runs = list()
fast_slide_runs = list()
# Create dictonary to store the final lists
segmented_data = dict()
# Keep counter of the number of runs done
num_runs = 0
# Pull pointers to only the file heads of the data structure
all_runs_root = [_g for _g in all_data.walkGroups("/") if _g._v_depth == 1]
# For each file extract the segments and data
for _objectRun in all_runs_root:
num_runs += 1
print num_runs
# Pull out tap information
tap_object = PullDataFromRun(_objectRun, BoltPR2MotionObj.TAP)
utilities.normalize_data(tap_object, discard_raw_flag)
tap_runs.append(tap_object)
# Pull out squeeze information
squeeze_object = PullDataFromRun(_objectRun, BoltPR2MotionObj.SQUEEZE)
utilities.normalize_data(squeeze_object, discard_raw_flag)
squeeze_runs.append(squeeze_object)
# Pull out hold information
hold_object = PullDataFromRun(_objectRun,
BoltPR2MotionObj.THERMAL_HOLD)
utilities.normalize_data(hold_object, discard_raw_flag)
hold_runs.append(hold_object)
# Pull out slide fast information
slide_fast_object = PullDataFromRun(_objectRun,
BoltPR2MotionObj.SLIDE_FAST)
utilities.normalize_data(slide_fast_object, discard_raw_flag)
fast_slide_runs.append(slide_fast_object)
# Pull out slide slow information
slide_slow_object = PullDataFromRun(_objectRun, BoltPR2MotionObj.SLIDE)
utilities.normalize_data(slide_slow_object, discard_raw_flag)
slow_slide_runs.append(slide_slow_object)
# Store all of the lists into the dictionary
segmented_data['tap'] = tap_runs
segmented_data['squeeze'] = squeeze_runs
segmented_data['thermal_hold'] = hold_runs
segmented_data['slide'] = slow_slide_runs
segmented_data['slide_fast'] = fast_slide_runs
# if we want to save to file
if (save_to_file):
file_ptr = open(output_filename, "w")
cPickle.dump(segmented_data, file_ptr, cPickle.HIGHEST_PROTOCOL)
file_ptr.close()
return segmented_data
