def run(self):
""" Run the model: ingest and process the input metric data and emit output
messages containing anomaly scores
"""
numRowsToSkip = self._inputSpec["rowOffset"]
datetimeFormat = self._inputSpec["datetimeFormat"]
inputRowTimestampIndex = self._inputSpec["timestampIndex"]
inputRowValueIndex = self._inputSpec["valueIndex"]
g_log.info("Processing model=%s", self._modelId)
for inputRow in self._csvReader:
g_log.debug("Got inputRow=%r", inputRow)
if numRowsToSkip > 0:
numRowsToSkip -= 1
g_log.debug("Skipping header row %s; %s rows left to skip",
inputRow, numRowsToSkip)
continue
if len(inputRow) > inputRowValueIndex:
if not (na.isNA(str(inputRow[inputRowValueIndex])) or
na.isNA(str(inputRow[inputRowTimestampIndex]))):
# Extract timestamp and value
# NOTE: the order must match the `inputFields` that we passed to the
# Aggregator constructor
fields = [
date_time_utils.parseDatetime(inputRow[inputRowTimestampIndex],
datetimeFormat),
float(inputRow[inputRowValueIndex])
]
# Aggregate
aggRow, _ = self._aggregator.next(fields, None)
g_log.debug("Aggregator returned %s for %s", aggRow, fields)
if aggRow is not None:
self._emitOutputMessage(
dataRow=aggRow,
anomalyProbability=self._computeAnomalyProbability(aggRow))
# Reap remaining data from aggregator
aggRow, _ = self._aggregator.next(None, curInputBookmark=None)
g_log.debug("Aggregator reaped %s in final call", aggRow)
if aggRow is not None:
self._emitOutputMessage(
dataRow=aggRow,
anomalyProbability=self._computeAnomalyProbability(aggRow))
def _readCSVFile(fileName, rowOffset, timestampIndex, valueIndex,
datetimeFormat):
"""
Read csv data file, the data file must have two columns
that contains time stamps and data values
:param str fileName: path to input csv file
:param int rowOffset: index of first data row in csv
:param int timestampIndex: column index of the timestamp
:param int valueIndex: column index of the value
:param str datetimeFormat: datetime format string for python's
datetime.strptime
:returns: Sequence of two tuples (timestamp, value), where
timestamp of type datetime.datetime and value is a number (int of float)
"""
with open(fileName, "rU") as csvFile:
fileReader = _createCsvReader(csvFile)
for _ in xrange(rowOffset):
fileReader.next() # skip header line
samples = []
numRows = 0
for row in fileReader:
if len(row) > valueIndex:
if not (na.isNA(str(row[valueIndex]))
or na.isNA(str(row[timestampIndex]))):
timestamp = date_time_utils.parseDatetime(
row[timestampIndex], datetimeFormat)
# use utc timezone if timezone information is not provided
if timestamp.tzinfo is None:
timestamp = timestamp.replace(tzinfo=tz.tzutc())
samples.append((timestamp, float(row[valueIndex])))
numRows += 1
if numRows >= MAX_NUM_ROWS:
break
return samples
def _readCSVFile(fileName, rowOffset, timestampIndex, valueIndex, datetimeFormat):
"""
Read csv data file, the data file must have two columns
that contains time stamps and data values
:param str fileName: path to input csv file
:param int rowOffset: index of first data row in csv
:param int timestampIndex: column index of the timestamp
:param int valueIndex: column index of the value
:param str datetimeFormat: datetime format string for python's
datetime.strptime
:returns: Sequence of two tuples (timestamp, value), where
timestamp of type datetime.datetime and value is a number (int of float)
"""
with open(fileName, "rU") as csvFile:
fileReader = _createCsvReader(csvFile)
for _ in xrange(rowOffset):
fileReader.next() # skip header line
samples = []
numRows = 0
for row in fileReader:
if len(row) > valueIndex:
if not (na.isNA(str(row[valueIndex])) or na.isNA(str(row[timestampIndex]))):
timestamp = date_time_utils.parseDatetime(row[timestampIndex], datetimeFormat)
# use utc timezone if timezone information is not provided
if timestamp.tzinfo is None:
timestamp = timestamp.replace(tzinfo=tz.tzutc())
samples.append((timestamp, float(row[valueIndex])))
numRows += 1
if numRows >= MAX_NUM_ROWS:
break
return samples
