def generate_inference_data(args):
"""
Generates inference data for the region provided through arguments.
Parameters
----------
reads_path : path to the aligned reads file
ref : reference sequence
region : region for which data is required
Returns
-------
region_name : region name
positions : positions corresponding provided region
examples : examples corresponding provided region
"""
reads_path, ref, region = args
region_string = f'{region.name}:{region.start + 1}-{region.end}'
result = gen.generate_features(reads_path, ref, region_string)
positions = []
examples = []
for P, X in zip(*result):
positions.append(P)
examples.append(X)
print(f'>> finished generating examples for {region.name}:{region.start}-{region.end}')
return region.name, positions, examples
def generate_train(args):
bam_X, bam_Y, ref, region = args
alignments = get_aligns(bam_Y, ref_name=region.name, start=region.start, end=region.end)
filtered = filter_aligns(alignments)
print(f'Finished generating labels for {region.name}:{region.start}-{region.end}.')
if not filtered:
print('No alignments.')
return None
positions, examples, labels = [], [], []
for a in filtered:
pos_labels = dict()
n_pos = set()
t_pos, t_labels = get_pos_and_labels(a, ref, region)
for p, l in zip(t_pos, t_labels):
if l == ENCODED_UNKNOWN:
n_pos.add(p)
else:
pos_labels[p] = l
pos_sorted = sorted(list(pos_labels.keys()))
region_string = f'{region.name}:{pos_sorted[0][0]+1}-{pos_sorted[-1][0]}'
result = gen.generate_features(bam_X, str(ref), region_string)
for P, X in zip(*result):
Y = []
to_yield = True
for p in P:
assert is_in_region(p[0], filtered)
if p in n_pos:
to_yield = False
break
try:
y_label = pos_labels[p]
except KeyError:
if p[1] != 0:
y_label = encoding[GAP]
else:
raise KeyError(f'No label mapping for position {p}.')
Y.append(y_label)
if to_yield:
positions.append(P)
examples.append(X)
labels.append(Y)
print(f'Finished generating examples for {region.name}:{region.start}-{region.end}.')
return region.name, positions, examples, labels
def generate_infer(args):
bam_X, ref, region = args
region_string = f'{region.name}:{region.start+1}-{region.end}'
result = gen.generate_features(bam_X, ref, region_string)
positions, examples = [], []
for P, X in zip(*result):
positions.append(P)
examples.append(X)
print(f'Finished generating examples for {region.name}:{region.start}-{region.end}.')
return region.name, positions, examples, None
def generate_train_data(args):
"""
Generates train data for the region provided through arguments.
Parameters
----------
reads_path : path to the aligned reads file
truth_genome_path : path to the truth genome
ref : reference sequence
region : region for which data is required
Returns
-------
region_name : region name
positions : positions corresponding provided region
examples : examples corresponding provided region
labels : labels corresponding provided region
"""
reads_path, truth_genome_path, ref, region = args
aligns = get_aligns(truth_genome_path, region)
filtered_aligns = filter_aligns(aligns)
print(f'>> finished generating labels for {region.name}:{region.start}-{region.end}')
if not filtered_aligns:
print(f'>> no alignments')
return None
positions = []
examples = []
labels = []
for align in filtered_aligns:
position_label_dict = dict()
positions_with_unknown_base = set()
pos, lbls = get_postions_and_labels(align, ref, region)
for position, label in zip(pos, lbls):
if label == Coder.encode(Coder.UNKNOWN):
positions_with_unknown_base.add(position)
else:
position_label_dict[position] = label
sorted_positions = sorted(list(position_label_dict.keys()))
region_string = f'{region.name}:{sorted_positions[0][0] + 1}-{sorted_positions[-1][0]}'
result = gen.generate_features(reads_path, str(ref), region_string)
for P, X in zip(*result):
Y = []
to_yield = True
for p in P:
assert is_in_region(p[0], filtered_aligns)
if p in positions_with_unknown_base:
to_yield = False
break
try:
y_label = position_label_dict[p]
except KeyError:
if p[1] != 0:
y_label = Coder.encode(Coder.GAP)
else:
raise KeyError(f'error: No label mapping for position {p}!')
Y.append(y_label)
if to_yield:
positions.append(P)
examples.append(X)
labels.append(Y)
print(f'>> finished generating examples for {region.name}:{region.start}-{region.end}')
return region.name, positions, examples, labels
import gmplot
from gmplot import GoogleMapPlotter as gmp
import gen
from sklearn.externals import joblib
from collections import Counter
from sklearn.preprocessing import minmax_scale
clf = joblib.load('classifier.pkl')
cameras = ['116.avi', '117.avi', '118.avi']
traffic = []
for c in cameras:
count, density = gen.generate_features(c)
traffic_stat = clf.predict([count, density])
if traffic_stat == 2:
print(c, ' : High traffic')
elif traffic_stat == 1:
print(c, ' : Medium traffic')
else:
print(c, ' : Low traffic')
traffic.append(traffic_stat)
count = [traffic.count(0), traffic.count(1), traffic.count(2)]
status = count.index(max(count))
color = ['green', 'yellow', 'red']
gmap = gmp.from_geocode(
"Veermata Jijabai Technological Institute, Mumbai, Maharashtra")
gmap.scatter([19.018892, 19.024714], [72.855786, 72.856964],
color[status],