def updateFeatureMatrixRowWithSection(self, featureMatrix, i,
section_entry):
section = section_entry.data
featureMatrix[i, 0] = section.distance
featureMatrix[i, 1] = section.duration
featureMatrix[i, 2] = section.sensed_mode.value
# TODO: Figure out if I can get the section id from the new style sections
# featureMatrix[i, 3] = section['_id']
featureMatrix[i, 4] = easf.calOverallSectionSpeed(section)
speeds = section['speeds']
if speeds is not None and len(speeds) > 0:
featureMatrix[i, 5] = np.mean(speeds)
featureMatrix[i, 6] = np.std(speeds)
featureMatrix[i, 7] = np.max(speeds)
else:
# They will remain zero
pass
accels = easf.calAccels(section)
if accels is not None and len(accels) > 0:
featureMatrix[i, 8] = np.max(accels)
else:
# They will remain zero
pass
featureMatrix[i, 9] = False
featureMatrix[i, 10] = easf.calHCR(section_entry)
featureMatrix[i, 11] = easf.calSR(section_entry)
featureMatrix[i, 12] = easf.calVCR(section_entry)
if 'start_loc' in section and section['end_loc'] != None:
startCoords = section['start_loc']['coordinates']
featureMatrix[i, 13] = startCoords[0]
featureMatrix[i, 14] = startCoords[1]
if 'end_loc' in section and section['end_loc'] != None:
endCoords = section['end_loc']['coordinates']
featureMatrix[i, 15] = endCoords[0]
featureMatrix[i, 16] = endCoords[1]
featureMatrix[i, 17] = section['start_local_dt']['hour']
featureMatrix[i, 18] = section['end_local_dt']['hour']
if (hasattr(self, "bus_cluster")):
featureMatrix[i, 19] = easf.mode_start_end_coverage(
section, self.bus_cluster, 105)
if (hasattr(self, "train_cluster")):
featureMatrix[i, 20] = easf.mode_start_end_coverage(
section, self.train_cluster, 600)
if (hasattr(self, "air_cluster")):
featureMatrix[i, 21] = easf.mode_start_end_coverage(
section, self.air_cluster, 600)
if self.last_section_done is None or self.last_section_done.data.end_ts < section_entry.data.end_ts:
self.last_section_done = section_entry
# Replace NaN and inf by zeros so that it doesn't crash later
featureMatrix[i] = np.nan_to_num(featureMatrix[i])
def updateFeatureMatrixRowWithSection(self, featureMatrix, i, section_entry):
section = section_entry.data
featureMatrix[i, 0] = section.distance
featureMatrix[i, 1] = section.duration
featureMatrix[i, 2] = section.sensed_mode.value
# TODO: Figure out if I can get the section id from the new style sections
# featureMatrix[i, 3] = section['_id']
featureMatrix[i, 4] = easf.calOverallSectionSpeed(section)
speeds = section['speeds']
if speeds is not None and len(speeds) > 0:
featureMatrix[i, 5] = np.mean(speeds)
featureMatrix[i, 6] = np.std(speeds)
featureMatrix[i, 7] = np.max(speeds)
else:
# They will remain zero
pass
accels = easf.calAccels(section)
if accels is not None and len(accels) > 0:
featureMatrix[i, 8] = np.max(accels)
else:
# They will remain zero
pass
featureMatrix[i, 9] = False
featureMatrix[i, 10] = easf.calHCR(section_entry)
featureMatrix[i, 11] = easf.calSR(section_entry)
featureMatrix[i, 12] = easf.calVCR(section_entry)
if 'start_loc' in section and section['end_loc'] != None:
startCoords = section['start_loc']['coordinates']
featureMatrix[i, 13] = startCoords[0]
featureMatrix[i, 14] = startCoords[1]
if 'end_loc' in section and section['end_loc'] != None:
endCoords = section['end_loc']['coordinates']
featureMatrix[i, 15] = endCoords[0]
featureMatrix[i, 16] = endCoords[1]
featureMatrix[i, 17] = section['start_local_dt']['hour']
featureMatrix[i, 18] = section['end_local_dt']['hour']
if (hasattr(self, "bus_cluster")):
featureMatrix[i, 19] = easf.mode_start_end_coverage(section, self.bus_cluster,105)
if (hasattr(self, "train_cluster")):
featureMatrix[i, 20] = easf.mode_start_end_coverage(section, self.train_cluster,600)
if (hasattr(self, "air_cluster")):
featureMatrix[i, 21] = easf.mode_start_end_coverage(section, self.air_cluster,600)
if self.last_section_done is None or self.last_section_done.data.end_ts < section_entry.data.end_ts:
self.last_section_done = section_entry
# Replace NaN and inf by zeros so that it doesn't crash later
featureMatrix[i] = np.nan_to_num(featureMatrix[i])
def get_unknown_prediction(i, section_entry):
"""
For unknown sections, we sometimes have points and sometimes not. If we
have points, use the median speed as always. Otherwise, we cannot to fine
grained speed specific checks. We can do checks on overall speed and GIS
features. If nothing matches, we should probably leave as UNKNOWN.
"""
if len(section_entry.data["speeds"]) > 0 and \
eaid.is_walking_speed(pd.Series(section_entry.data["speeds"]).median()):
logging.debug("median speed is walking, UNKNOWN -> WALKING")
return {'WALKING': 1}
if eaid.is_walking_speed(easf.calOverallSectionSpeed(section_entry.data)):
logging.debug("overall speed is walking, UNKNOWN -> WALKING")
return {'WALKING': 1}
else:
predicted_transit_mode = _get_transit_prediction(i, section_entry)
if predicted_transit_mode is not None:
logging.debug("predicted transit mode is not None, UNKNOWN -> %s" %
predicted_transit_mode)
return {predicted_transit_mode: 1}
else:
# could be either car or bike, dunno which
logging.debug("no luck finding a match, stay UNKNOWN")
return {'UNKNOWN': 1}