def checkDataType(dataFilePath): """ Return the data type (transactional or non-transactional) The data type is determined via a data type indicator, defined as the ratio between median absolute deviation and median of the sampling interval. @param dataFilePath: Name of a csv file, the file must have two columns with header "timestamp", and "value" @return dataType: a string with value "transactional" or "non-transactional" """ (timestamp, sig) = readCSVfiles(dataFilePath) medianSamplingInterval, medianAbsoluteDev = estimateMedianAbsoluteDeviation(timestamp) dataTypeIndicator = medianAbsoluteDev / medianSamplingInterval if dataTypeIndicator > 0.2: dataType = "transactional" else: dataType = "non-transactional" return dataType, dataTypeIndicator
def checkDataType(dataFilePath):
"""
Return the data type (transactional or non-transactional)
The data type is determined via a data type indicator, defined as the
ratio between median absolute deviation and median of the sampling interval.
@param dataFilePath: Name of a csv file, the file must have two columns
with header "timestamp", and "value"
@return dataType: a string with value "transactional" or "non-transactional"
"""
(timestamp, sig) = readCSVfiles(dataFilePath)
medianSamplingInterval, medianAbsoluteDev = estimateMedianAbsoluteDeviation(
timestamp)
dataTypeIndicator = medianAbsoluteDev / medianSamplingInterval
if dataTypeIndicator > 0.2:
dataType = "transactional"
else:
dataType = "non-transactional"
return dataType, dataTypeIndicator
score_value = loadNABscore("value_only")
score_time_of_day = loadNABscore("time_of_day")
score_day_of_week = loadNABscore("day_of_week")
# score_both = loadNABscore("time_of_day_and_day_of_week")
fileList = score_value['File'].values
better_with_time_of_day = (score_time_of_day['Score'] > score_value['Score'])
better_with_day_of_week = (score_day_of_week['Score'] > score_value['Score'])
dataPath = NABPath + '/data'
useTimeOfDayEncoder = []
useDayOfWeekEncoder = []
for i in xrange(len(score_value)):
filename = join(dataPath, score_value['File'][i])
(timestamp, value) = readCSVfiles(filename)
(new_sampling_interval, useTimeOfDay,
useDayOfWeek) = get_suggested_timescale_and_encoder(timestamp, value)
useTimeOfDayEncoder.append(useTimeOfDay)
useDayOfWeekEncoder.append(useDayOfWeek)
print " file: ", filename, " useTimeOfDay: ", useTimeOfDay, " useDayOfWeek: ", useDayOfWeek, \
" aggregation window: ", new_sampling_interval
useTimeOfDayEncoder = np.array(useTimeOfDayEncoder)
useDayOfWeekEncoder = np.array(useDayOfWeekEncoder)
resultMat = np.array(
[score_time_of_day['Score'] > score_value['Score'], useTimeOfDayEncoder])
result = pd.DataFrame(np.transpose([
score_value = loadNABscore("value_only")
score_time_of_day = loadNABscore("time_of_day")
score_day_of_week = loadNABscore("day_of_week")
# score_both = loadNABscore("time_of_day_and_day_of_week")
fileList = score_value['File'].values
better_with_time_of_day = (score_time_of_day['Score'] > score_value['Score'])
better_with_day_of_week = (score_day_of_week['Score'] > score_value['Score'])
dataPath = NABPath+'/data'
useTimeOfDayEncoder = []
useDayOfWeekEncoder = []
for i in xrange(len(score_value)):
filename = join(dataPath, score_value['File'][i])
(timestamp, value) = readCSVfiles(filename)
(new_sampling_interval, useTimeOfDay, useDayOfWeek) = get_suggested_timescale_and_encoder(timestamp, value)
useTimeOfDayEncoder.append(useTimeOfDay)
useDayOfWeekEncoder.append(useDayOfWeek)
print " file: ", filename, " useTimeOfDay: ", useTimeOfDay, " useDayOfWeek: ", useDayOfWeek, \
" aggregation window: ", new_sampling_interval
useTimeOfDayEncoder = np.array(useTimeOfDayEncoder)
useDayOfWeekEncoder = np.array(useDayOfWeekEncoder)
resultMat = np.array([score_time_of_day['Score'] > score_value['Score'], useTimeOfDayEncoder])
result = pd.DataFrame(np.transpose([score_day_of_week.File.values,
useTimeOfDayEncoder,
