def data_collection():
rawDataPath = '../../Data/'
derivedDataPath = '../../DataOutput/'
forecastVar = 'conc'
hemStr = 'N'
startYr = 1980
forecastYr = 2012
startMonth = 1
stopMonth = 12
regionMask = np.load(derivedDataPath + 'Regions/regionMaskA100km')
numFeat = 18
numSamples = (forecastYr - startYr) * (stopMonth+1 - startMonth)
#data collection
#start off with just the summer months and without ice thickness
feat = []
for year in range(startYr, forecastYr):
for index, month in enumerate(range(startMonth, stopMonth+1)):
#set month to array
sample = np.zeros(numFeat)
sample[0] = (month-1) #gridded months are actually indexed at 0
#divide by 100 to put in the same magnitude as the other values
sample[1] = np.ma.mean(ff.get_pmas_month(rawDataPath, year, month-1))
#set region features to array
iceConc = ff.get_gridvar(derivedDataPath, forecastVar, month,
array(year), hemStr)
for regInd in range(16):
regionData = iceConc.data
regionData[iceConc.mask == True] = 0 #get rid of nan
desiredRegion = regionMask == regInd
sample[regInd+2] = np.ma.mean(np.multiply(regionData, desiredRegion))
#sample[regInd+1] = np.ma.mean(np.multiply(regionData, desiredRegion))
"""
for regInd in range(numFeat-1):
regionData = iceThick.data
regionData[iceThick.mask == True] = 0 #get rid of nan
desiredRegion = regionMask == regInd
sample[numFeat+regInd] = np.ma.mean(np.multiply(regionData, desiredRegion))
"""
feat.append(sample)
feat = np.reshape(feat, (numSamples, numFeat))
groundTruth = feat[1:np.size(feat,0), 1: np.size(feat,1)]
feat = feat[0:np.size(feat,0)-1, :]
return feat, groundTruth
def data_collection():
rawDataPath = '../../Data/'
derivedDataPath = '../../DataOutput/'
forecastVar = 'conc'
iceType = 'extent'
hemStr = 'N'
siiVersion = 'v3.0'
startYr = 1990
forecastYr = 2010
startMonth = 2
stopMonth = 11
regionMask = np.load(derivedDataPath + 'Regions/regionMaskA100km')
numFeat = 18
numSamples = (forecastYr - startYr) * (stopMonth + 1 - startMonth)
#data collection
#start off with just the summer months and without ice thickness
feat = []
groundTruth = []
for year in range(startYr, forecastYr):
for index, month in enumerate(range(startMonth, stopMonth + 1)):
_, extent = ff.get_ice_extentN(rawDataPath, month, year, year,
iceType, siiVersion, hemStr)
groundTruth.append(extent[0])
#set month to array
sample = np.zeros(numFeat)
sample[0] = (month - 1) #gridded months are actually indexed at 0
#divide by 100 to put in the same magnitude as the other values
sample[1] = np.ma.mean(
ff.get_pmas_month(rawDataPath, year, month - 1))
#set region features to array
iceConc = ff.get_gridvar(derivedDataPath, forecastVar, month,
array(year), hemStr)
for regInd in range(16):
regionData = iceConc.data
regionData[iceConc.mask == True] = 0 #get rid of nan
desiredRegion = regionMask == regInd
sample[regInd + 2] = np.ma.mean(
np.multiply(regionData, desiredRegion))
#sample[regInd+1] = np.ma.mean(np.multiply(regionData, desiredRegion))
feat.append(sample)
feat = np.reshape(feat, (numSamples, numFeat))
groundTruth = np.reshape(groundTruth, (numSamples, 1))
return feat, groundTruth
yrForecast = 2015
randSeedNum = 50
#thick, forecastThickMean = ff.get_ice_thickness(rawDataPath, startYr, yrForecast, forecastMonth)
yrsTrain, extentTrain = ff.get_ice_extentN(rawDataPath,
predMonth,
startYr,
yrForecast - 1,
icetype=iceType,
version=siiVersion,
hemStr=hemStr)
extentDetrendTrain, lineTrain = ff.get_varDT(yrsTrain, extentTrain)
varTrain = ff.get_gridvar(derivedDataPath, forecastVar, forecastMonth,
yrsTrain, hemStr)
varForecast = ff.get_gridvar(derivedDataPath, forecastVar, forecastMonth,
array(yrForecast), hemStr)
years, extentYr = ff.get_ice_extentN(rawDataPath,
predMonth,
yrForecast,
yrForecast,
icetype=iceType,
version=siiVersion,
hemStr=hemStr)
observed = extentYr[-1]
extentTrendPersist = (lineTrain[-1] + (lineTrain[-1] - lineTrain[-2])
) #add to detrended forecast predictions
regionMask = np.load(derivedDataPath + 'Regions/regionMaskA100km')
fmonth = 7
iceType = 'extent'
siiVersion = 'v3.0'
forecastVar = 'conc'
hemStr = 'N'
rawDataPath = '../../Data/'
derivedDataPath = '../../DataOutput/'
regionMask = np.load(derivedDataPath + 'Regions/regionMaskA100km')
sample = np.zeros(numFeat)
sample[0] = (month - 1)
sample[1] = np.ma.mean(ff.get_pmas_month(rawDataPath, year, month - 1))
#set region features to array
iceConc = ff.get_gridvar(derivedDataPath, forecastVar, month, array(year),
hemStr)
for regInd in range(16):
regionData = iceConc.data
regionData[iceConc.mask == True] = 0 #get rid of nan
desiredRegion = regionMask == regInd
sample[regInd +
2] = 100 * np.ma.mean(np.multiply(regionData, desiredRegion))
sample = np.reshape(sample, (1, -1))
feat = pcaConc.transform(sample)
#feat=sample
_, extent = ff.get_ice_extentN(rawDataPath, fmonth, year, year, iceType,
siiVersion, hemStr)
gTruth = extent[0]