def train_weak_classifier_motion(motion_train_set, adjective, feature_dictionary):
'''
Takes the feature_object_train_set and trains the specified
feature.
Will return a single trained SVM
'''
# Store SVM for each feature
svm_store = dict()
scaler_store = dict()
import pdb; pdb.set_trace()
# For each feature set (pdc, pac, etc.)
for feature in feature_dictionary:
# Pull out the list of features
feature_list = feature_dictionary[feature]
# Pull out the features specified as a vector
train_feature_vector, train_label_dict = utilities.feature_obj_2_feature_vector(motion_train_set, feature_list)
# Create scaler
scaler_store[feature] = preprocessing.Scaler().fit(train_feature_vector)
train_feature_vector_scaled = scaler_store[feature].transform(train_feature_vector)
# Train the SVM
svm_store[feature] = train_svm(train_feature_vector_scaled, train_label_dict[1][adjective], train_label_dict[0])
return (svm_store, scaler_store)
def test_weak_classifier_adjective(test_feature_objects, adjective,
classifiers, scalers, file_ptr,
comma_file_ptr):
'''
takes in a dictionary of all features
returns a dictionary of weak classifiers for each feature
'''
# specify feature to be extracted
feature_name_list = [
"pdc_rise_count", "pdc_area", "pdc_max", "pac_energy", "pac_sc",
"pac_sv", "pac_ss", "pac_sk", "tac_area", "tdc_exp_fit", "gripper_min",
"gripper_mean", "transform_distance", "electrode_polyfit"
]
motion_scores = dict()
# for each motion (slide, squeeze, etc.)
for motion in test_feature_objects:
motion_test_set = test_feature_objects[motion]
# pull out the features specified as a vector
test_feature_vector, test_label_dict = utilities.feature_obj_2_feature_vector(
motion_test_set, feature_name_list)
# create scaler
test_feature_vector_scaled = scalers[motion].transform(
test_feature_vector)
clf = classifiers[motion]
results = clf.predict(test_feature_vector_scaled)
print classification_report(test_label_dict[1][adjective], results)
file_ptr.write('Adjective: ' + adjective + ' Motion name: ' +
motion)
file_ptr.write(
'\n' +
classification_report(test_label_dict[1][adjective], results) +
'\n\n')
motion_scores[motion] = f1_score(test_label_dict[1][adjective],
results)
# Pull out the best motion
best_motion, best_score = utilities.get_best_motion(motion_scores)
# Write results to comma split file to load
comma_file_ptr.write(adjective + ',' + str(motion_scores['tap']) + ',' +
str(motion_scores['squeeze']) + ',' +
str(motion_scores['thermal_hold']) + ',' +
str(motion_scores['slide']) + ',' +
str(motion_scores['slide_fast']) + ',' + best_motion +
'\n')
def build_ensemble_feature_vector(train_feature_objects, adjective,
classifiers, scalers, feature_name_list):
'''
Builds the feature vector set for the ensemble training
Returns a dictionary of motion + probabilities
'''
motion_prob = dict()
train_labels = None
object_ids = None
weights = dict()
for motion in train_feature_objects:
motion_train_set = train_feature_objects[motion]
# pull out the features specified as a vector
train_feature_vector, train_label_dict = utilities.feature_obj_2_feature_vector(
motion_train_set, feature_name_list)
# create scaled vector
train_feature_vector_scaled = scalers[motion].transform(
train_feature_vector)
clf = classifiers[motion]
# Get results from classifier
results = clf.predict(train_feature_vector_scaled)
probabilities = clf.predict_proba(train_feature_vector_scaled)[:, 1]
# Store off probabilities and their labels
motion_prob[motion] = probabilities
# Store off real labels
train_labels = train_label_dict[1][adjective]
# Store off the f1 score, which becomes the weight
weights[motion] = f1_score(train_labels, results)
# Store off object ids
object_ids = train_label_dict[0]
motion_vector = np.transpose(
np.vstack((motion_prob['tap'], motion_prob['squeeze'],
motion_prob['thermal_hold'], motion_prob['slide'],
motion_prob['slide_fast'])))
# Weight vector
weight_vector = np.hstack(
(weights['tap'], weights['squeeze'], weights['thermal_hold'],
weights['slide'], weights['slide_fast']))
return (motion_vector, train_labels, object_ids, weight_vector)
def train_weak_classifier_adjective(train_feature_objects, adjective,
feature_dictionary):
'''
takes in a dictionary of all features
returns a dictionary of weak classifiers for each feature
'''
# specify feature to be extracted
feature_name_list = [
"pdc_rise_count", "pdc_area", "pdc_max", "pac_energy", "pac_sc",
"pac_sv", "pac_ss", "pac_sk", "tac_area", "tdc_exp_fit", "gripper_min",
"gripper_mean", "transform_distance", "electrode_polyfit"
]
# store weak svms
svm_motion_store = dict()
# store scalers
scaler_motion_store = dict()
# store scalers
classifiers = dict()
# for each motion (slide, squeeze, etc.)
for motion in train_feature_objects:
motion_train_set = train_feature_objects[motion]
# pull out the features specified as a vector
train_feature_vector, train_label_dict = utilities.feature_obj_2_feature_vector(
motion_train_set, feature_name_list)
# create scaler
scaler_motion_store[motion] = preprocessing.Scaler().fit(
train_feature_vector)
train_feature_vector_scaled = scaler_motion_store[motion].transform(
train_feature_vector)
params = {
'n_estimators': 1000,
'max_depth': 4,
'min_samples_split': 1,
'learn_rate': 0.01,
'loss': 'deviance'
}
#params = {'n_estimators': 1, 'max_depth': 1, 'min_samples_split': 1,'learn_rate': 0.1, 'loss': 'deviance'}
clf = ensemble.GradientBoostingClassifier(**params)
clf.fit(train_feature_vector_scaled, train_label_dict[1][adjective])
#clf = train_gradient_boost(train_feature_vector_scaled, train_label_dict[1][adjective], train_label_dict[0])
classifiers[motion] = clf
return (classifiers, scaler_motion_store)
def test_adj_motion_classifier(test_feature_objects, adjective, classifiers,
scalers, feature_name_list, file_ptr,
comma_file_ptr):
'''
takes in a dictionary of all features
returns a dictionary of weak classifiers for each feature
'''
motion_scores = dict()
# for each motion (slide, squeeze, etc.)
for motion in test_feature_objects:
motion_test_set = test_feature_objects[motion]
# pull out the features specified as a vector
test_feature_vector, test_label_dict = utilities.feature_obj_2_feature_vector(
motion_test_set, feature_name_list)
# create scaler
test_feature_vector_scaled = scalers[motion].transform(
test_feature_vector)
clf = classifiers[motion]
results = clf.predict(test_feature_vector_scaled)
print classification_report(test_label_dict[1][adjective], results)
file_ptr.write('Adjective: ' + adjective + ' Motion name: ' +
motion)
file_ptr.write(
'\n' +
classification_report(test_label_dict[1][adjective], results) +
'\n\n')
motion_scores[motion] = f1_score(test_label_dict[1][adjective],
results)
# Pull out the best motion
best_motion, best_score = utilities.get_best_motion(motion_scores)
# Write results to comma split file to load
comma_file_ptr.write(adjective + ',' + str(motion_scores['tap']) + ',' +
str(motion_scores['squeeze']) + ',' +
str(motion_scores['thermal_hold']) + ',' +
str(motion_scores['slide']) + ',' +
str(motion_scores['slide_fast']) + ',' + best_motion +
'\n')
def build_ensemble_feature_vector(train_feature_objects, adjective, classifiers, scalers, feature_name_list):
'''
Builds the feature vector set for the ensemble training
Returns a dictionary of motion + probabilities
'''
motion_prob = dict()
train_labels = None
object_ids = None
weights = dict()
for motion in train_feature_objects:
motion_train_set = train_feature_objects[motion]
# pull out the features specified as a vector
train_feature_vector, train_label_dict = utilities.feature_obj_2_feature_vector(motion_train_set, feature_name_list)
# create scaled vector
train_feature_vector_scaled = scalers[motion].transform(train_feature_vector)
clf = classifiers[motion]
# Get results from classifier
results = clf.predict(train_feature_vector_scaled)
probabilities = clf.predict_proba(train_feature_vector_scaled)[:,1]
# Store off probabilities and their labels
motion_prob[motion] = probabilities
# Store off real labels
train_labels = train_label_dict[1][adjective]
# Store off the f1 score, which becomes the weight
weights[motion] = f1_score(train_labels, results)
# Store off object ids
object_ids = train_label_dict[0]
motion_vector = np.transpose(np.vstack((motion_prob['tap'], motion_prob['squeeze'], motion_prob['thermal_hold'], motion_prob['slide'], motion_prob['slide_fast'])))
# Weight vector
weight_vector = np.hstack((weights['tap'], weights['squeeze'], weights['thermal_hold'],weights['slide'], weights['slide_fast']))
return (motion_vector, train_labels, object_ids, weight_vector)
def train_weak_classifier_adjective(train_feature_objects, adjective, feature_dictionary):
'''
takes in a dictionary of all features
returns a dictionary of weak classifiers for each feature
'''
# specify feature to be extracted
feature_name_list = ["pdc_rise_count", "pdc_area", "pdc_max", "pac_energy", "pac_sc", "pac_sv", "pac_ss", "pac_sk", "tac_area", "tdc_exp_fit", "gripper_min", "gripper_mean", "transform_distance", "electrode_polyfit"]
# store weak svms
svm_motion_store = dict()
# store scalers
scaler_motion_store = dict()
# store scalers
classifiers = dict()
# for each motion (slide, squeeze, etc.)
for motion in train_feature_objects:
motion_train_set = train_feature_objects[motion]
# pull out the features specified as a vector
train_feature_vector, train_label_dict = utilities.feature_obj_2_feature_vector(motion_train_set, feature_name_list)
# create scaler
scaler_motion_store[motion] = preprocessing.Scaler().fit(train_feature_vector)
train_feature_vector_scaled = scaler_motion_store[motion].transform(train_feature_vector)
params = {'n_estimators': 1000, 'max_depth': 4, 'min_samples_split': 1,'learn_rate': 0.01, 'loss': 'deviance'}
#params = {'n_estimators': 1, 'max_depth': 1, 'min_samples_split': 1,'learn_rate': 0.1, 'loss': 'deviance'}
clf = ensemble.GradientBoostingClassifier(**params)
clf.fit(train_feature_vector_scaled, train_label_dict[1][adjective])
#clf = train_gradient_boost(train_feature_vector_scaled, train_label_dict[1][adjective], train_label_dict[0])
classifiers[motion] = clf
return (classifiers, scaler_motion_store)
def test_weak_classifier_adjective(test_feature_objects, adjective, classifiers, scalers, file_ptr, comma_file_ptr):
'''
takes in a dictionary of all features
returns a dictionary of weak classifiers for each feature
'''
# specify feature to be extracted
feature_name_list = ["pdc_rise_count", "pdc_area", "pdc_max", "pac_energy", "pac_sc", "pac_sv", "pac_ss", "pac_sk", "tac_area", "tdc_exp_fit", "gripper_min", "gripper_mean", "transform_distance", "electrode_polyfit"]
motion_scores = dict()
# for each motion (slide, squeeze, etc.)
for motion in test_feature_objects:
motion_test_set = test_feature_objects[motion]
# pull out the features specified as a vector
test_feature_vector, test_label_dict = utilities.feature_obj_2_feature_vector(motion_test_set, feature_name_list)
# create scaler
test_feature_vector_scaled = scalers[motion].transform(test_feature_vector)
clf = classifiers[motion]
results = clf.predict(test_feature_vector_scaled)
print classification_report(test_label_dict[1][adjective], results)
file_ptr.write('Adjective: ' + adjective + ' Motion name: '+motion)
file_ptr.write('\n'+classification_report(test_label_dict[1][adjective], results)+ '\n\n')
motion_scores[motion] = f1_score(test_label_dict[1][adjective], results)
# Pull out the best motion
best_motion, best_score = utilities.get_best_motion(motion_scores)
# Write results to comma split file to load
comma_file_ptr.write(adjective+','+str(motion_scores['tap'])+',' +str(motion_scores['squeeze'])+','+str(motion_scores['thermal_hold'])+','+str(motion_scores['slide'])+','+str(motion_scores['slide_fast'])+','+best_motion +'\n')
def train_weak_classifier_motion(motion_train_set, adjective,
feature_dictionary):
'''
Takes the feature_object_train_set and trains the specified
feature.
Will return a single trained SVM
'''
# Store SVM for each feature
svm_store = dict()
scaler_store = dict()
import pdb
pdb.set_trace()
# For each feature set (pdc, pac, etc.)
for feature in feature_dictionary:
# Pull out the list of features
feature_list = feature_dictionary[feature]
# Pull out the features specified as a vector
train_feature_vector, train_label_dict = utilities.feature_obj_2_feature_vector(
motion_train_set, feature_list)
# Create scaler
scaler_store[feature] = preprocessing.Scaler().fit(
train_feature_vector)
train_feature_vector_scaled = scaler_store[feature].transform(
train_feature_vector)
# Train the SVM
svm_store[feature] = train_svm(train_feature_vector_scaled,
train_label_dict[1][adjective],
train_label_dict[0])
return (svm_store, scaler_store)
def test_adj_motion_classifier(test_feature_objects, adjective, classifiers, scalers, feature_name_list, file_ptr, comma_file_ptr):
'''
takes in a dictionary of all features
returns a dictionary of weak classifiers for each feature
'''
motion_scores = dict()
# for each motion (slide, squeeze, etc.)
for motion in test_feature_objects:
motion_test_set = test_feature_objects[motion]
# pull out the features specified as a vector
test_feature_vector, test_label_dict = utilities.feature_obj_2_feature_vector(motion_test_set, feature_name_list)
# create scaler
test_feature_vector_scaled = scalers[motion].transform(test_feature_vector)
clf = classifiers[motion]
results = clf.predict(test_feature_vector_scaled)
print classification_report(test_label_dict[1][adjective], results)
file_ptr.write('Adjective: ' + adjective + ' Motion name: '+motion)
file_ptr.write('\n'+classification_report(test_label_dict[1][adjective], results)+ '\n\n')
motion_scores[motion] = f1_score(test_label_dict[1][adjective], results)
# Pull out the best motion
best_motion, best_score = utilities.get_best_motion(motion_scores)
# Write results to comma split file to load
comma_file_ptr.write(adjective+','+str(motion_scores['tap'])+',' +str(motion_scores['squeeze'])+','+str(motion_scores['thermal_hold'])+','+str(motion_scores['slide'])+','+str(motion_scores['slide_fast'])+','+best_motion +'\n')
