def plot_instances_for_gps_error_model():
smoothing_ground_truth_map = json.load(open("/Users/shankari/cluster_ground_truth/smoothing/caltrain/smoothing_removed_points"))
needsSmoothing = []
fineWithoutSmoothing = []
for (sid, rp_list) in smoothing_ground_truth_map.items():
sectionJSON = get_section_db().find_one({"_id": sid})
if sectionJSON is None:
print("Unable to find section %s in the database" % sid)
else:
if len(rp_list) > 0:
needsSmoothing.append(sectionJSON)
else:
fineWithoutSmoothing.append(sectionJSON)
print("-" * 20, "Needs smoothing", '-' * 20)
for section in needsSmoothing:
if section is not None:
print(section["_id"], fc.calAvgSpeed(section), fc.getIthMaxSpeed(section, 1), np.percentile(fc.calSpeeds(section), [90, 95, 99]))
print("-" * 20, "Fine without smoothing", '-' * 20)
for section in fineWithoutSmoothing:
if section is not None:
print(section["_id"], fc.calAvgSpeed(section), fc.getIthMaxSpeed(section, 1), np.percentile(fc.calSpeeds(section), [90, 95, 99]))
other_manual_candidates = find_other_sections_manual(needsSmoothing, fineWithoutSmoothing)
other_auto_candidates = find_other_sections_auto(needsSmoothing, fineWithoutSmoothing)
print(other_auto_candidates)
gsfgtc.generate_cluster_comparison(other_manual_candidates, "/tmp/other_manual")
gsfgtc.generate_cluster_comparison(other_auto_candidates, "/tmp/other_auto")
def plot_instances_for_gps_error_model():
smoothing_ground_truth_map = json.load(
open(
"/Users/shankari/cluster_ground_truth/smoothing/caltrain/smoothing_removed_points"
))
needsSmoothing = []
fineWithoutSmoothing = []
for (sid, rp_list) in smoothing_ground_truth_map.items():
sectionJSON = get_section_db().find_one({"_id": sid})
if sectionJSON is None:
print("Unable to find section %s in the database" % sid)
else:
if len(rp_list) > 0:
needsSmoothing.append(sectionJSON)
else:
fineWithoutSmoothing.append(sectionJSON)
print("-" * 20, "Needs smoothing", '-' * 20)
for section in needsSmoothing:
if section is not None:
print(section["_id"], fc.calAvgSpeed(section),
fc.getIthMaxSpeed(section, 1),
np.percentile(fc.calSpeeds(section), [90, 95, 99]))
print("-" * 20, "Fine without smoothing", '-' * 20)
for section in fineWithoutSmoothing:
if section is not None:
print(section["_id"], fc.calAvgSpeed(section),
fc.getIthMaxSpeed(section, 1),
np.percentile(fc.calSpeeds(section), [90, 95, 99]))
other_manual_candidates = find_other_sections_manual(
needsSmoothing, fineWithoutSmoothing)
other_auto_candidates = find_other_sections_auto(needsSmoothing,
fineWithoutSmoothing)
print(other_auto_candidates)
gsfgtc.generate_cluster_comparison(other_manual_candidates,
"/tmp/other_manual")
gsfgtc.generate_cluster_comparison(other_auto_candidates,
"/tmp/other_auto")
def get_feature_row(section):
ret_arr = np.zeros((5))
ret_arr[0] = fc.calAvgSpeed(section)
ret_arr[1] = fc.getIthMaxSpeed(section, 1)
percentiles = np.percentile(fc.calSpeeds(section), [90, 95, 99])
ret_arr[2] = percentiles[0]
ret_arr[3] = percentiles[1]
ret_arr[4] = percentiles[2]
return ret_arr
def get_feature_row(section):
ret_arr = np.zeros((5))
ret_arr[0] = fc.calAvgSpeed(section)
ret_arr[1] = fc.getIthMaxSpeed(section, 1)
percentiles = np.percentile(fc.calSpeeds(section), [90, 95, 99])
ret_arr[2] = percentiles[0]
ret_arr[3] = percentiles[1]
ret_arr[4] = percentiles[2]
return ret_arr