def main():
print("Gill Bates vs Beff Jezos")
print("Who's going to win?")
#subtitle_file = input("Subtitles SRT: ")
#transcript_file = input("Google Protobuf transcript: ")
#amazon_file = input("Amazon JSON transcript: ")
subtitle_file = "500_days.srt"
transcript_file = "500_days_transcribed_audio.pb"
amazon_file = "500_days_amazon.json"
# load the data
transcript_collection = load_proto_file(transcript_file)
subs = parse_subs(subtitle_file)
amazon_text, amazon_timings = amazon_transcript(amazon_file)
google_timings = get_time_transcript(transcript_collection.audiobits)
# get text data ready for processing
subs_align = get_text_ready(subs, False)
tran_google = get_text_ready(transcript_collection.audiobits, False)
tran_amazon = get_text_ready(amazon_text, True)
print("Starting the alignment...")
dist, cost, acc, path = fastdtw(np.array(subs_align), np.array(tran_google), edit_distance)
print("Finished warping ONE")
dist2, cost2, acc2, path2 = fastdtw(np.array(subs_align), np.array(tran_amazon), edit_distance)
print("Finished warping TWO. Starting aligning...")
# find the path from 0,0 to the end to get the timings
google_path_pairs = find_timings_for_words(path)
amazon_path_pairs = find_timings_for_words(path2)
output_timings("google", google_path_pairs, subs_align, tran_google, google_timings)
output_timings("amazon", amazon_path_pairs, subs_align, tran_amazon, amazon_timings)
def cluster(self,
res,
n_cluster,
by_feature,
method='kmeans',
normalized=False,
**kwargs):
stations = list(set(res.index.get_level_values(0)))
series, names = [], []
def transform(x):
return x / np.max(np.abs(x)) if normalized else x
def feature(data):
if by_feature == "Combined":
return data[["Checkout", "Return"]].values.flatten()
else:
return data[by_feature]
for st in stations:
data = res.loc[st]
if len(data) < 24:
data = self.clean_record(data)
if res.loc[st].Factor.iloc[0] < 30 or np.isnan(feature(data)).any()\
or (feature(data) == 0).all():
continue
series.append(transform(feature(data)))
names.append(st)
if method == 'kmeans':
km = KMeans(init='k-means++', n_clusters=n_cluster)
labels = km.fit_predict(np.array(series))
elif method == 'agglomerative':
n = len(series)
simmat = np.zeros((n, n))
for i in range(n):
simmat[i, i] = 0
for j in range(i + 1, n):
simmat[i, j], _, _, _ = fastdtw(
series[i], series[j], dist=lambda x, y: np.abs(x - y))
simmat[j, i] = simmat[i, j]
labels = agg_cluster(simmat,
n_cluster,
linkage=kwargs.get('linkage', 'average'))
path_name = '{}_{}_{}'.format(method, self.bikesystem.city, n_cluster)
path_name = path_name + "_normalized" if normalized else path_name
base_dir = os.path.join('clusters', path_name)
if os.path.exists(base_dir):
rmtree(base_dir)
from_dir = os.path.join('temporal_deltas',
'{}_Hourly'.format(self.bikesystem.city))
for i in range(n_cluster):
path_name = os.path.join(base_dir, str(i))
os.makedirs(path_name)
for name, label in zip(names, labels):
file_name = fname(name) + ".pdf"
copyfile(os.path.join(from_dir, file_name),
os.path.join(base_dir, str(label), file_name))
return names, labels
def predict(self, x_test):
pred = []
err = []
for id_test in range(len(x_test)):
result = np.zeros(len(self.y))
for id_train in range(len(self.X)):
try:
min_dist = fastdtw(self.X[id_train], x_test[id_test],
self.dist)
result[id_train] = min_dist
except Exception as e:
print(self.y[id_train])
print(self.X[id_train])
print(x_test[id_test])
print(e)
if (self.normalize):
result = self.norm(result)
res_indx = result.argsort()[:self.neighbours]
pred.append((self.y[res_indx], result[res_indx]))
return pred
np.maximum(x, softphoc_query)) / len(qword)
for x in resized_preds
])
elif similarity_type == 4: #dtw
resized_preds = [
(cv2.resize(x, (target_size[0], target_size[1])))
for x in softphoc_proposal_preds
] ## for axes oriented boxes
# resized_preds = [warped_logits] ## for warped non axes oriented boxes
# chars = [char2int[x] for x in qword]
# similarities = -np.mean([fastdtw(softphoc_query[:, :, x].transpose(), resized_preds[0][:, :, x].transpose(), 'euclidean')[0] for x in chars])
similarities = -np.mean([
fastdtw(softphoc_query[:, :, x].transpose(),
resized_preds[0][:, :, x].transpose(),
'euclidean')[0] for x in range(38)
])
else:
raise Exception('Unknown similarity type')
sorted_idx = np.argsort(similarities)
if take_always_argmax:
idx = sorted_idx[-1]
else:
# idx = sorted_idx[-query_dict[qword]]
idx = sorted_idx[np.maximum(-query_dict[qword],
-len(sorted_idx))]
np.maximum(x, softphoc_query)) / len(qword)
for x in resized_preds
])
elif similarity_type == 4: #dtw
similarities = []
im = np.copy(img)
for line in houghTransform_proposals:
cv2.line(im, (line[0], line[1]),
(line[2], line[3]), (0, 255, 0), 2)
pred_points_array = get_points_lines(
line, probabilities_np)
# resized_preds = [(cv2.resize(x, (target_size[0]))) for x in pred_points_array]
# similarities = -np.mean([fastdtw(softphoc_query[:, :, x].transpose(), resized_preds[0][:, :, x].transpose(), 'euclidean')[0] for x in range(38)])
dist, cost, acc, path = fastdtw(
np.squeeze(softphoc_query), pred_points_array,
'euclidean')
similarities.append(-dist)
plt.imshow(im)
plt.title(qword)
plt.show()
else:
raise Exception('Unknown similarity type')
sorted_idx = np.argsort(similarities)
if take_always_argmax:
idx = sorted_idx[-1]
else:
# idx = sorted_idx[-query_dict[qword]]
def dtw_metric(x, y):
x = x.reshape(-1,1)
y = y.reshape(-1,1)
dist, cost, acc, path = fastdtw(x, y, dist = lambda x, y: norm(x - y, ord=1))
return dist
priceLow = sortedSmoothedSample[0][1]
for j in range(arcLength):
normalizedSmoothedSample[j][1] = (
smoothedSample[j][1] -
priceLow) / priceRange * circleRadius
midpoint = int(arcLength / 2)
diff = abs(normalizedSmoothedSample[midpoint][1] -
template[midpoint][1])
for j in range(arcLength):
normalizedSmoothedSample[j][
1] = normalizedSmoothedSample[j][1] - diff
normalizedSmoothedSample[j][0] = j
acc = fastdtw(normalizedSmoothedSample, template)
similarity_distance = acc[arcLength - 1][arcLength - 1]
sim_list.append(similarity_distance)
if similarity_distance < similarity_threshold * arcLength:
left = smoothedSample[0][1]
right = smoothedSample[-1][1]
slope = abs(left - right) / min(left, right)
if slope <= horizon_threshold:
dateIndex.append(i)
# record the pattern found under current time span
startday = i
endday = i + arcLength - 1
def dtw_worker(i, t_row, df, df_test):
# print 'Worker:', i
test_list = []
neighbours = []
tlat = []
tlong = []
t_trajectories = ast.literal_eval(t_row[0])
# Collect in list all the trajectories for this trip
for j in range(0, len(t_trajectories)):
test_list.append(
[float(t_trajectories[j][1]),
float(t_trajectories[j][2])])
tlong.append(float(t_trajectories[j][1]))
tlat.append(float(t_trajectories[j][2]))
# Iterate over all trips in tripsClean
start = time.time()
for k, row in df.iterrows():
clean_list = []
trajectories = ast.literal_eval(row[2])
for l in range(0, len(trajectories)):
clean_list.append(
[float(trajectories[l][1]),
float(trajectories[l][2])])
# Compute DTW for these trips using Haversine as distance metric
dist, cost, acc, path = dtw.fastdtw(
test_list,
clean_list,
dist=lambda c1, c2: prep.haversine_dist(c1[0], c1[1], c2[0], c2[1]
))
# dist, path = fdtw.fastdtw(test_list, clean_list, dist=lambda c1, c2: prep.haversine_dist(c1[0], c1[1], c2[0], c2[1]))
neighbours.append([int(row[0]), acc[-1][-1]])
end = time.time()
neighbours = np.asarray(neighbours)
neighbours = neighbours[neighbours[:, 1].argsort()][:5]
# print neighbours
gmap = gmplot.GoogleMapPlotter(tlat[0], tlong[0], 10,
'AIzaSyDf6Dk2_fg0p8XaEhQdFVCXg-AMlm54dAs')
gmap.plot(tlat, tlong, 'green', edge_width=5)
gmap.draw('Maps/dtwMaps/testTrip' + str(i + 1) + '/test-' + str(i + 1) +
'.html')
# print "Test Trip ", i, "\n"
filename = 'Maps/dtwMaps/testTrip' + str(i + 1) + '/data' + str(i +
1) + '.txt'
open(filename, 'w').close()
f = open(filename, "a+")
for n in range(0, 5):
for g, grow in df[df['tripId'] == neighbours[n][0]].iterrows():
gtrajectory = ast.literal_eval(grow[2])
longlist = []
latlist = []
for j in range(0, len(gtrajectory)):
longlist.append(float(gtrajectory[j][1]))
latlist.append(float(gtrajectory[j][2]))
gmap = gmplot.GoogleMapPlotter(
latlist[0], longlist[0], 10,
'AIzaSyDf6Dk2_fg0p8XaEhQdFVCXg-AMlm54dAs')
gmap.plot(latlist, longlist, 'green', edge_width=5)
gmap.draw('Maps/dtwMaps/testTrip' + str(i + 1) + '/neighbour' +
str(n + 1) + '-' + str(grow[1]) + '.html')
f.write("Neighbor %d \nJP_ID: %s \nDTW: %8.5f\n" %
(n, grow[1], float(neighbours[n][1])))
f.write("dt: %8.5f\n\n" % float(end - start))
f.close()
import dtw import numpy as np import matplotlib.pyplot as plt # from numpy.linalg import norm x = np.array(list(range(15, 20))).reshape(-1, 1) y = np.array(list(range(5, 10))).reshape(-1, 1) dist, cost, acc, path = dtw.fastdtw(x, y, dist=lambda x, y: abs(x-y)) dist plt.imshow(acc.T, origin='lower', cmap=plt.cm.gray, interpolation='nearest') plt.plot(path[0], path[1], 'w') plt.xlim((-0.5, acc.shape[0]-0.5)) plt.ylim((-0.5, acc.shape[1]-0.5)) plt.plot(list(range(len(x))), x) plt.plot(y, list(range(len(y)))) plt.show() # 这个dtw距离似乎会随着时间序列的长度改变啊！这个可咋整呢？ # 不过经过实验之后发现，虽然会变，但是还是会收敛的
def dtw_dist(self, other):
x = np.array(self.coords)
y = np.array(other.coords)
#distance, path = fastdtw(x, y,radius=20, dist=lambda x, y: abs(x-y))
distance, C, D1, path = fastdtw(x, y, dist=lambda x, y: abs(x - y))
return distance
key=lambda sortedPeriod: sortedPeriod[1])
periodRange = sortedPeriod[lenPeriod - 1][1] - sortedPeriod[0][1]
for i in range(lenPeriod):
curPeriod[i][1] = (curPeriod[i][1] - sortedPeriod[0][1]
) / periodRange * (lenPeriod / 2.0)
# print(periodRange)
if startDate == 10 and endDate == 41:
print(lenPeriod / 2.0)
midpoint = int(lenPeriod / 2)
diff = abs(curPeriod[midpoint][1] - curTemplate[midpoint][1])
for i in range(lenPeriod):
curPeriod[i][1] = curPeriod[i][1] - diff
curPeriod[i][0] = i
acc = fastdtw(curPeriod, curTemplate)
curSimilarityDist = acc[lenPeriod - 1][lenPeriod - 1]
if curSimilarityDist <= SIM_THRESHOLD * lenPeriod:
left = smoothedData[startDate][1]
right = smoothedData[endDate][1]
slope = abs(left - right) / min(left, right)
# if match
# leftBound = endDate + 1 dateInc = TIMESPAN_MIN save the arc
if slope <= CIRCLE_HORIZONTAL_THRESHOLD:
distList.append(curSimilarityDist / lenPeriod)
dateInc = TIMESPAN_MIN
leftBound = endDate + 1
pricePatternList.append([startDate, endDate])
break
import numpy as np
import matplotlib.pyplot as plt
from dtw import fastdtw
import matplotlib as mpl
from arc import arc_circle_gen
mpl.rcParams['font.sans-serif'] = ['SimHei']
mpl.rcParams['axes.unicode_minus'] = False
import math
from template import template_gen
tem1 = arc_circle_gen(32, 16)
tem2 = template_gen('circle', 32, 16, 1.0)
print(tem1)
print(tem2)
tem1rev = []
for i in range(30):
tem1rev.append([tem1[i][0], 15-tem1[i][1]])
print(fastdtw(tem1, tem2)[29][29])
print(fastdtw(tem1rev, tem2)[29][29])
