def get_distances(data, data_array, max_warping_window):
a = np.zeros(len(data_array))
for i in range(0,len(data_array)):
dist = dtw_distance(data_array[i], data, max_warping_window)
a[i] = dist
print str(i) + " - " + str(dist)
return a
def get_distances(data, data_array, max_warping_window):
a = np.zeros(len(data_array))
for i in range(0, len(data_array)):
dist = dtw_distance(data_array[i], data, max_warping_window)
a[i] = dist
print(str(i) + " - " + str(dist))
return a
def distance(self, other, entities='characters', constraint='none',
window=0, normalized=True, summed=False, sentiments=False):
if not isinstance(other, Story):
raise ValueError("Can't compare to %s" % type(other))
source = self.to_dataframe(sentiments=sentiments, summed=summed).values
target = other.to_dataframe(
sentiments=sentiments, summed=summed).values
return dtw_distance(source, target, constraint=constraint, window=window, step_pattern=2, normalized=normalized)
def map(self, other, entities='characters', constraint='none', window=0, threshold=0.6):
source, target = (self, other) if len(self.characters) > other.characters else (other, self)
source_df = source.to_dataframe(entities=entities)
target_df = target.to_dataframe(entities=entities)
dm = np.zeros((len(source.characters), len(target.characters)))
for i, character_i in enumerate(source_df.index):
for j, character_j in enumerate(target_df.index):
chars_s, chars_t = source_df.ix[i].values, target_df.ix[j].values
if chars_s.shape[0] < chars_t.shape[0]:
chars_s, chars_t = chars_t, chars_s
d = dtw_distance(chars_s, chars_t, constraint=constraint, window=window, normalized=True)
dm[i, j] = d
return pd.DataFrame(dm, index=source_df.index, columns=target_df.index)
def _distance_matrix(self, x, y):
count = 0
x_shape = np.shape(x)
y_shape = np.shape(y)
distance_matrix = np.zeros((x_shape[0], y_shape[0]))
distance_matrix_size = x_shape[0] * y_shape[0]
for i in xrange(0, x_shape[0]):
for j in xrange(0, y_shape[0]):
# Compute DTW
distance_matrix[i, j] = dtw_distance(x[i], y[j], self.max_warping_window)
# Update progress
count += 1
self._show_progress(distance_matrix_size, count)
print '\r\n'
return distance_matrix
def _distance_matrix(self, x, y, show_progress=True):
count = 0
x_shape = np.shape(x)
y_shape = np.shape(y)
distance_matrix = np.zeros((x_shape[0], y_shape[0]))
distance_matrix_size = x_shape[0] * y_shape[0]
for i in range(0, x_shape[0]):
for j in range(0, y_shape[0]):
# Compute DTW
distance_matrix[i, j] = dtw_distance(x[i], y[j],
self.max_warping_window)
# Update progress
count += 1
if show_progress and count % 50 == 0:
self._show_progress(distance_matrix_size, count)
return distance_matrix
def _distance_matrix(self, x, y):
count = 0
x_shape = np.shape(x)
y_shape = np.shape(y)
distance_matrix = np.zeros((x_shape[0], y_shape[0]))
distance_matrix_size = x_shape[0] * y_shape[0]
for i in xrange(0, x_shape[0]):
for j in xrange(0, y_shape[0]):
# Compute DTW
distance_matrix[i, j] = dtw_distance(x[i], y[j],
self.max_warping_window)
# Update progress
count += 1
self._show_progress(distance_matrix_size, count)
print '\r\n'
return distance_matrix
def compare(spec1, spec2, radius):
return dtw.dtw_distance(spec1, spec2, radius)
def compute_labels(data, dataarray, w, window_size, coordinate, should_plot):
click.echo('--- Compute labels ---')
desired_csv = load_csvs(data, should_preprocess=False)
data_csv = load_csvs(dataarray, should_preprocess=False)
for index, flight_data_number in enumerate(data_csv):
flight_data_number['data']['flight_number'] = index
# For Test
last_second = desired_csv[0]['data']['seconds'].iloc[-1]
#click.echo(' - data : %s ' % data)
click.echo(' - dataarray : %s ' % dataarray)
click.echo(' - w : %d ' % w)
click.echo('\nRunning...')
# For plot-pdfs title
ts = time.time()
st = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d_%H%M%S')
flight_dict = {}
#flight_full_data = pd.DataFrame()
flight_dataframe = pd.DataFrame()
for time_window in range(0, last_second, window_size):
click.echo('Time window is: %d ' % time_window)
desired_window = get_windows(desired_csv, time_window, time_window + window_size - 1)
data_window = get_windows(data_csv, time_window, time_window + window_size - 1)
#print(data_window)
# Compute all DTWs
desired_flight = desired_window[0]['window'][coordinate].tolist()
dtws = []
for index, flight_window in enumerate(data_window):
# Compute DTW of window with desired_window ; window[coordinate].tolist()
pos_data = flight_window['window'][coordinate].tolist()
flight_seconds = flight_window['window']['seconds'].tolist()
dtw = dtw_distance(desired_flight, pos_data, w)
# Add key DTW to window ; window['dtw']
flight_window['dtw'] = dtw
# Track all DTWS ; append dtw value
dtws.append( dtw )
#click.echo('Done. Plots have been saved.')
print(dtw)
if should_plot:
# plotting desired data with each flight for each window
plt.plot(desired_flight, label='Desired')
plt.plot(pos_data, label='Unlabelled')
#plt.xlim(0,15)
plt.ylim(0,2.1)
plt.xlabel('Seconds')
plt.ylabel('Meters')
plt.title('Desired and unlabelled data. DTW = {}'.format(dtw))
plt.legend()
plt.grid(True)
plt.savefig('plots/z/desired_each_flight/dtwValues_{}_{}_{}.jpeg'.format(st, time_window, index))
plt.cla()
print(dtws)
if should_plot:
print(dtws)
dtws = [550 if x==9.223372036854776e+18 else x for x in dtws]
# plotting dtw values of all flights for each window
plt.figure(figsize=(20, 10))
plt.plot(dtws, color='#006600', alpha=.9) # marker='o', linestyle='--',
plt.ylim([0, 600])
flights_x = [i for i in range(0, 53)]
for flight_x, dtw in zip(flights_x, dtws):
plt.text(flight_x, dtw, str(dtw))
plt.grid(True)
#plt.show()
plt.savefig('plots/z/dtw_values/dtwValues_{}_{}.pdf'.format(st, time_window))
plt.cla()
click.echo('Done. Plots have been saved.')
# Loop again and update labels
for flight_window in data_window:
if flight_window['dtw'] < 100:
flight_window['label'] = 1
elif flight_window['dtw'] < 299:
flight_window['label'] = 2
else:
flight_window['label'] = 3
# Save to flight_dict
fn = flight_window['window']['flight_number'].iloc[0]
flight_full_data = flight_window['window']
flight_full_data.is_copy = False
flight_full_data['label'] = flight_window['label']
flight_full_data['dtw'] = flight_window['dtw']
if fn not in flight_dict.keys():
flight_dict[fn] = flight_full_data # flight_window['window']
else:
flight_dict[fn] = pd.concat([flight_dict[fn], flight_full_data]) # flight_window['window']
for flight_index in flight_dict:
flight_dataframe = pd.DataFrame(flight_dict[flight_index])
flight_dataframe.to_csv('data/labelled/z/f_{}.csv'.format(flight_index), sep=';', encoding='utf-8')
print('f_{}.csv saved!'.format(flight_index))
click.echo('\nDone.')