def _tag_and_classify(self, ch, method, properties, body):
"""Tag data and runs it through the classifier"""
self._update_last_tag()
input_data = simplejson.loads(body)
timestamp = input_data["timestamp"]
if self.maxval is not None and self.minval is not None:
value = np.clip(input_data["channel_0"], self.minval, self.maxval)
else:
value = input_data["channel_0"]
classificationResults = classifyNextRecord(self._network,
self.network_config,
timestamp,
value,
self.last_tag["channel_0"])
inferredCategory = classificationResults["bestInference"]
_LOGGER.debug("Raw results: %s" % classificationResults)
buffer = [{"timestamp": timestamp, "channel_0": inferredCategory}]
self.output_metric_publisher.publish(self.routing_keys[self.output_metric],
buffer)
num_correct = 0
for category in range(_NUM_CATEGORIES):
csvFile = open(_INPUT_FILES[category], "rb")
reader = csv.reader(csvFile)
# skip 3 header rows
reader.next()
reader.next()
reader.next()
for row in reader:
data = dict(zip(headers, row))
x = int(data["x"]) / 1000000 # s
y = float(data["y"])
label = int(category)
classificationResults = classifyNextRecord(network, _CONFIG, x, y, label)
inferredCategory = classificationResults["bestInference"]
print "Actual: %s | Predicted: %s " % (category,
inferredCategory)
if int(inferredCategory) == int(category):
num_correct += 1
print "ACCURACY: %s " % (float(num_correct) / (_NUM_RECORDS *
_NUM_CATEGORIES))
print "Serializing model to: %s" % _MODEL_NAME
setNetworkLearningMode(network, _REGION_NAMES, False)
network.save(_MODEL_NAME)
print "Predict 40: %s" % classifyNextRecord(network, _CONFIG, -1, 40, -1)
reader.next()
readers[category] = reader
num_correct = 0.0
for row_id in range(_NUM_RECORDS):
# alternate categories
for category in range(_NUM_CATEGORIES):
row = readers[category].next()
data = dict(zip(headers, row))
x = int(data["x"]) / 1000000 # s
y = float(data["y"])
label = int(category)
classificationResults = classifyNextRecord(network,
_CONFIG,
x,
y,
label)
inferredCategory = classificationResults["bestInference"]
print "Timestamp: %s, Data: %d " % (x, y)
print "Actual: %s | Predicted: %s " % (category,
inferredCategory)
if int(inferredCategory) == int(category):
num_correct += 1
print "ACCURACY: %s " % (num_correct / (_NUM_RECORDS * _NUM_CATEGORIES))
setNetworkLearningMode(network, _REGION_NAMES, False)
network.save("motor_imagery.nta")
#
