def doRender(self, handlerId):
html='<div class="pd_save"><table width=100%><tr><th>Model</th><th>Accuracy</th><th>Precision</th><th>Recall</th></tr>'
confusionHtml = '<p>Confusion Tables for each Model</p>'
for modelName,model in Configuration.getModels():
label= model.__class__.__name__
labeledDataRDD, sqlTableName = Configuration.getLabeledData(self.entity)
predictionAndLabels = model.predict(labeledDataRDD.map(lambda lp: lp.features))
metrics = MulticlassMetrics(\
predictionAndLabels.zip(labeledDataRDD.map(lambda lp: lp.label)).map(lambda t: (float(t[0]),float(t[1])))\
)
html+='<tr><td>{0}</td><td>{1:.2f}%</td><td>{2:.2f}%</td><td>{3:.2f}%</td></tr>'\
.format(label,metrics.weightedFMeasure(beta=1.0)*100, metrics.weightedPrecision*100,metrics.weightedRecall*100 )
displayConfusionTable = True
if ( displayConfusionTable ):
#get labels from RDD
handler=training.getTrainingHandler()
classLabels = labeledDataRDD.map(lambda t: t.label).distinct().map(lambda l: handler.getClassLabel(l)).collect()
confusionMatrix = metrics.call("confusionMatrix")
confusionMatrixArray = confusionMatrix.toArray()
#labels = metrics.call("labels")
confusionHtml += "<p>" + label + "<p>"
confusionHtml += "<table>"
confusionHtml+="<tr><td></td>"
for classLabel in classLabels:
confusionHtml+="<td>" + str(classLabel) + "</td>"
confusionHtml+="</tr>"
for i, row in enumerate(confusionMatrixArray):
confusionHtml += "<tr>"
confusionHtml += "<td>" + classLabels[i] + "</td>"
for j, cell in enumerate(row):
confusionHtml+="<td style='text-align:center'>" + ("<b>" if (i==j) else "") + str(cell) + ("</b>" if (i==j) else "") + "</td>"
confusionHtml += "</tr>"
confusionHtml += "</table>"
html+='</table></div>'
if ( displayConfusionTable ):
html+=confusionHtml
self._addHTML(html)
def runModel(flight, date, departureAirport=None):
if not Configuration.isReadyForRun():
raise ValueError(
"Unable to predict flight delay because no models are available. Please run configure for more details"
)
if departureAirport is None:
departureAirport = "LAS"
response = getFlightSchedule(flight, date, departureAirport)
myLogger.debug("Schedule for flight {0} at date {1} : {2}".format(
flight, date, response))
if "error" in response:
return {
"error": "Unable to access schedule {0}".format(response["error"])
}
payload = {}
appendix = response['appendix']
payload["flightInfo"] = scheduledFlight = response["scheduledFlight"]
def getAirportJSON(code):
for airport in appendix["airports"]:
if airport['fs'] == code:
return airport
payload["departureAirportInfo"] = departureInfo = {}
departureInfo["airportInfo"] = depAirportJSON = getAirportJSON(
scheduledFlight['departureAirportFsCode'])
departureInfo["weatherForecast"] = depWeather = getWeather(
depAirportJSON['latitude'], depAirportJSON['longitude'],
scheduledFlight["departureTimeUTC"])
payload["arrivalAirportInfo"] = arrivalInfo = {}
arrivalInfo["airportInfo"] = arrAirportJSON = getAirportJSON(
scheduledFlight['arrivalAirportFsCode'])
arrivalInfo["weatherForecast"] = arrWeather = getWeather(
arrAirportJSON['latitude'], arrAirportJSON['longitude'],
scheduledFlight["arrivalTimeUTC"])
payload["prediction"] = prediction = {}
prediction["models"] = predictionModels = []
#create the features vector
features = createFeaturesVector(depWeather, arrWeather, scheduledFlight,
depAirportJSON, arrAirportJSON)
#count the predicted classes to make an overall prediction
predictedClasses = []
trainingHandler = getTrainingHandler()
for modelVar, model in Configuration.getModels():
p = model.predict(features)
predictedClasses.append(p)
predictionModels.append({
"model": model.__class__.__name__,
"prediction": trainingHandler.getClassLabel(p)
})
classes = Counter(predictedClasses).most_common()
if len(classes) > 1 and classes[0][1] == classes[1][1]:
prediction["overall"] = "Undecided: {0}/{1}".format(
trainingHandler.getClassLabel(classes[0][0]),
trainingHandler.getClassLabel(classes[1][0]))
else:
prediction["overall"] = trainingHandler.getClassLabel(classes[0][0])
"""
payload["prediction"]={
"overall": "Delayed between 13 and 41 minutes",
"models":[
{"model":"NaiveBayesModel", "prediction":"Delayed between 13 and 41 minutes"},
{"model":"DecisionTreeModel: Delayed between 13 and 41 minutes"},
{"model":"LogisticRegressionModel: Delayed between 13 and 41 minutes"},
{"model":"RandomForestModel: Delayed between 13 and 41 minutes"}
]
}
"""
myLogger.debug("runModel Payload {0}".format(payload))
try:
saveFlightResults(payload)
except:
myLogger.exception("Unable to save flight results {0}".format(payload))
return json.dumps(payload)
#payload format
"""
def runModel(flight, date, departureAirport=None):
if not Configuration.isReadyForRun():
raise ValueError("Unable to predict flight delay because no models are available. Please run configure for more details")
if departureAirport is None:
departureAirport = "LAS"
response = getFlightSchedule(flight, date, departureAirport)
myLogger.debug("Schedule for flight {0} at date {1} : {2}".format(flight, date, response ))
if "error" in response:
return {"error": "Unable to access schedule {0}".format(response["error"])}
payload={}
appendix=response['appendix']
payload["flightInfo"]=scheduledFlight=response["scheduledFlight"]
def getAirportJSON(code):
for airport in appendix["airports"]:
if airport['fs'] == code:
return airport
payload["departureAirportInfo"]=departureInfo={}
departureInfo["airportInfo"]=depAirportJSON=getAirportJSON( scheduledFlight['departureAirportFsCode'] )
departureInfo["weatherForecast"]= depWeather = getWeather(depAirportJSON['latitude'], depAirportJSON['longitude'], scheduledFlight["departureTimeUTC"])
payload["arrivalAirportInfo"]=arrivalInfo={}
arrivalInfo["airportInfo"]=arrAirportJSON=getAirportJSON( scheduledFlight['arrivalAirportFsCode'] )
arrivalInfo["weatherForecast"]= arrWeather=getWeather(arrAirportJSON['latitude'], arrAirportJSON['longitude'], scheduledFlight["arrivalTimeUTC"] )
payload["prediction"]=prediction = {}
prediction["models"]=predictionModels = []
#create the features vector
features = createFeaturesVector(depWeather, arrWeather, scheduledFlight, depAirportJSON, arrAirportJSON)
#count the predicted classes to make an overall prediction
predictedClasses = []
trainingHandler = getTrainingHandler();
for modelVar,model in Configuration.getModels():
p = model.predict(features)
predictedClasses.append(p)
predictionModels.append({
"model": model.__class__.__name__,
"prediction": trainingHandler.getClassLabel(p)
})
classes = Counter(predictedClasses).most_common()
if len(classes)>1 and classes[0][1]==classes[1][1]:
prediction["overall"] = "Undecided: {0}/{1}".format(trainingHandler.getClassLabel(classes[0][0]), trainingHandler.getClassLabel(classes[1][0]))
else:
prediction["overall"] = trainingHandler.getClassLabel(classes[0][0])
"""
payload["prediction"]={
"overall": "Delayed between 13 and 41 minutes",
"models":[
{"model":"NaiveBayesModel", "prediction":"Delayed between 13 and 41 minutes"},
{"model":"DecisionTreeModel: Delayed between 13 and 41 minutes"},
{"model":"LogisticRegressionModel: Delayed between 13 and 41 minutes"},
{"model":"RandomForestModel: Delayed between 13 and 41 minutes"}
]
}
"""
myLogger.debug("runModel Payload {0}".format(payload))
try:
saveFlightResults(payload)
except:
myLogger.exception("Unable to save flight results {0}".format(payload))
return json.dumps(payload)
#payload format
"""
