def predict_test_labels(classifier, std_scale, pca_std):
"""
This function predicts labels for test data using the trained classifier and writes output to file
:param classifier: classifier trained on train data
:param std_scale
:param pca_std
"""
top_level_test_dirs = os.listdir(TEST_DATA_DIR)
top_level_test_dirs = [x for x in top_level_test_dirs if not x.startswith('.')]
predictions_list = [['timestamp', 'label']]
# Remove prediction data file if exists
try:
os.remove(FINAL_PREDICTIONS)
except OSError:
pass
# Walks through directories in test directory and reads touch.csv, audio.wav files
# Extracts timestamp and mode from directory names
for dir_name in top_level_test_dirs:
mode = dir_name.split('-')[0]
timestamped_dirs = os.listdir(os.path.join(TEST_DATA_DIR, dir_name))
timestamped_dirs = [x for x in timestamped_dirs if not x.startswith('.')]
for folder_name in timestamped_dirs:
timestamp = folder_name
audio_file = os.path.join(TEST_DATA_DIR, dir_name, folder_name, 'audio.wav')
touch_file = os.path.join(TEST_DATA_DIR, dir_name, folder_name, 'touch.csv')
touch_features = pd.read_csv(touch_file, sep=',', skiprows=1, header=None)
(fs, frame) = sciw.read(audio_file, mmap=False)
# Creating test feature matrix
feature_matrix = create_feature_vector(touch_features, frame, fs, mode)
# Transform each test feature into the same space as training data
test_feature = pca_std.transform(std_scale.transform(feature_matrix))
# Predict labels for each test feature and write string mappings of labels
label = 'knuckle' if classifier.predict(test_feature) == np.array([1]) else 'pad'
predictions_list.append([timestamp, label])
# Write predictions to the output file
with open(FINAL_PREDICTIONS, 'w') as pred_fh:
writer = csv.writer(pred_fh, delimiter=',')
writer.writerows(predictions_list)
def prepare_training_data():
"""
This function walks through directories in train, and reads touch.csv and audio.wav files.
It invokes create_feature_vector function to extract features, extracts labels and writes them to
corresponding csv files.
:return:
"""
top_level_train_dirs = os.listdir(TRAIN_DATA_DIR)
top_level_train_dirs = [x for x in top_level_train_dirs if not x.startswith('.')]
# Remove prep data files if exist
try:
os.remove(TRAIN_FEATURES_FILE)
os.remove(TRAIN_LABELS_FILE)
except OSError:
pass
# Write header to the csv file that should contain feature matrix
with open(TRAIN_FEATURES_FILE, 'wb') as write_header:
writer = csv.writer(write_header)
writer.writerow(['x', 'y', 'major', 'minor', 'pressure', 'orientation', 'signal energy',
'signal energy entropy', 'spectral centroid', 'spectral spread', 'spectral entropy',
'spectral roll off', 'mode'])
# Walk through directories in train directory and extract features from files,
# along with label from directory names
for dir_name in top_level_train_dirs:
mode = dir_name.split('-')[0]
timestamped_dirs = os.listdir(os.path.join(TRAIN_DATA_DIR, dir_name))
timestamped_dirs = [x for x in timestamped_dirs if not x.startswith('.')]
for folder_name in timestamped_dirs:
split_details = folder_name.split('-')
label = split_details[1]
# timestamp = split_details[0]
audio_file = os.path.join(TRAIN_DATA_DIR, dir_name, folder_name, 'audio.wav')
touch_file = os.path.join(TRAIN_DATA_DIR, dir_name, folder_name, 'touch.csv')
touch_features = pd.read_csv(touch_file, sep=',', skiprows=1, header=None)
(fs, frame) = sciw.read(audio_file, mmap=False)
feature_matrix = create_feature_vector(touch_features, frame, fs, mode)
with open(TRAIN_FEATURES_FILE, 'a') as f_handle:
np.savetxt(f_handle, feature_matrix, delimiter=',')
with open(TRAIN_LABELS_FILE, 'a') as f_handle:
np.savetxt(f_handle, [1] if label == 'knuckle' else [-1], delimiter=',')
# ASSUMING feature_extraction.py is in same directory
import feature_extraction as fe
# IMPORT other necessities
from sklearn import linear_model
from sklearn import tree
from sklearn import svm
# GET entire dataset
data = fe.extract_from_tsv()
# GET feature vectors with supplied extraction functions
extraction_functions = [fe.basic_numerical_feature_extractor,
fe.filter_selection,
fe.filter_rarity]
x_data, y_data = fe.create_feature_vector(data, extractor_funcs=extraction_functions)
# VISUALIZE pca graph of dataset
fe.apply_machine_learning_algorithm(x_data, y_data, graph_pca=True)
# TOGGLE pca preprocessing
print "|======================================|"
print "Printing w/ PCA PREPROCESS toggled off and on:"
print fe.apply_machine_learning_algorithm(x_data, y_data)
print fe.apply_machine_learning_algorithm(x_data, y_data, pca_preprocess=True)
print "|======================================|"
# INPUT pca dimensionality reduction
print "|======================================|"
print "Printing w/ PCA REDUCTION at normal and reduced dimension 2:"
print fe.apply_machine_learning_algorithm(x_data, y_data)