def dDeriv(station1, station2, variable, startDate, endDate):
# compute directional derivative using
# (unitVector . windX2, windY2) (var1 - var2)
import numpy as np
import wUUtils as Util
# load longitude and latitude of both stations
lon, lat = Util.getStationLonLat([station1, station2])
# compute unit vector from station2 to station1
uVec = unitVector(lon, lat)
# print("unit vector: " + str(uVec))
# get mean wind vector at station2:
windX2 = Util.loadDailyVariableRange(station2, startDate, endDate, \
'WindMeanX', castFloat=True)
windY2 = Util.loadDailyVariableRange(station2, startDate, endDate, \
'WindMeanY', castFloat=True)
# get variable at station1 and station2
var1 = Util.loadDailyVariableRange(station1, startDate, endDate, \
variable, castFloat=True)
var2 = Util.loadDailyVariableRange(station2, startDate, endDate, \
variable, castFloat=True)
# construct wind vectors (N x 2 array)
windVec = np.vstack((windX2, windY2))
# project wind vector onto unit vector
proj = np.dot(uVec, windVec)
dD = (np.array(var1) - np.array(var2)) * proj
return dD, uVec
def oneCityPredict(model_params, startDate, endDate, actual=True):
# predict targetVar for a single station using
# previously generated regression model
import numpy as np
import wUUtils as Util
# extract city and feature data
station = model_params['station']
targetVar = model_params['targetVar']
features = model_params['features']
lag = model_params['lag']
regr = model_params['regr']
scale = model_params['scale']
if scale:
scaler = model_params['scaler']
# build list of dates in datetime format
date_list = Util.dateList(startDate, endDate)
date_list = date_list[lag:]
# if actual data available
if actual:
# load target variable data
target = Util.loadDailyVariableRange(station, startDate, endDate, \
targetVar, castFloat=True)
# "baseline" model is predicted target same as value on prediction day
baseline = target[:(-lag)]
baseline = np.array(baseline)
# shift vector by lag
target = target[lag:]
target = np.array(target)
else:
target = None
# load feature data
featureData = []
for feature in features:
# print("Adding " + feature)
fd = Util.loadDailyVariableRange(station, startDate, endDate, \
feature, castFloat=True)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# convert features to np arrays
featureData = (np.array(featureData)).T
if scale:
featureData = scaler.transform(featureData)
pred = regr.predict(featureData)
if actual:
print("R^2_mean:" + "\t" + str(regr.score(featureData,target)))
sse = ((pred-target)**2).sum()
ssm = ((baseline-target)**2).sum()
print("R^2_base:" + "\t" + str(1 - sse/ssm))
rmse = np.sqrt(((pred - target)**2).mean())
rmse_base = np.sqrt(((baseline - target)**2).mean())
print("RMSE:\t" + "\t" + str(rmse))
print("RMSE_base:\t" + str(rmse_base))
model_perf = {
'R2_mean': regr.score(featureData,target), \
'R2_base': 1 - sse/ssm, \
'RMSE': rmse}
return date_list, pred, target, model_perf
def oneCityModel(station, startDate, endDate, \
features, targetVar='TempMax', lag=1, scale=False):
# build regression model to predict "variable" for a single
# station using training data from only the same station
# between startdate and enddate
# features is a list of variables to use as predictors
import wUUtils as Util
import numpy as np
from sklearn import preprocessing
from sklearn import linear_model
# load target variable data
target = Util.loadDailyVariableRange(station, startDate, endDate, \
targetVar, castFloat=True)
# shift vector by lag
target = target[lag:]
# load feature data
featureData = []
for feature in features:
# print("Adding " + feature)
fd = Util.loadDailyVariableRange(station, startDate, endDate, \
feature, castFloat=True)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# convert target and features to np arrays
target = np.array(target)
featureData = (np.array(featureData)).T
# rescale features
scaler = None
if scale:
scaler = preprocessing.StandardScaler().fit(featureData)
featureData = scaler.transform(featureData)
regr = linear_model.LinearRegression()
regr.fit(featureData, target)
model_params = {
'station': station, \
'startDate': startDate, \
'endDate': endDate, \
'targetVar': targetVar, \
'features': features, \
'regr': regr, \
'lag': lag, \
'scale': scale, \
'scaler': scaler}
# report regression results:
print("R^2: " + str(regr.score(featureData,target)))
if scale:
print("Regression coefficients (scaled, sorted):")
print(" intercept" + ":\t" + str(regr.intercept_))
for ii in np.argsort(-np.abs(regr.coef_)):
print(" " + features[ii] + ":\t" + str(regr.coef_[ii]))
else:
print("Regression coefficients:")
print(" intercept" + ":\t" + str(regr.intercept_))
for ii in range(len(regr.coef_)):
print(" " + features[ii] + ":\t" + str(regr.coef_[ii]))
return featureData, target, model_params
def isDaytimeMinPress(station, startDate, endDate):
# binary variable for minimum pressure occurring before noon local time
import datetime
import wUUtils as Util
mTime = Util.loadDailyVariableRange(station, startDate, endDate, \
'PressMinTime', castFloat=False)
timeZone = Util.loadDailyVariableRange(station, startDate, endDate, \
'TimeZone', castFloat=True)
# convert minTime to datetime
mTime = [datetime.datetime.strptime(mm,"%Y-%m-%d %H:%M:%S") for mm in mTime]
hours = [(mm.hour + mm.minute/60 + timeZone[i]) % 24 \
for i,mm in enumerate(mTime)]
isDaytime = [int(hour > 8 and hour < 20) for hour in hours]
return(isDaytime)
def isMorningMaxWind(station, startDate, endDate):
# binary variable for maximum wind speed occurring before noon local time
import datetime
import wUUtils as Util
mTime = Util.loadDailyVariableRange(station, startDate, endDate, \
'WindMaxTime', castFloat=False)
timeZone = Util.loadDailyVariableRange(station, startDate, endDate, \
'TimeZone', castFloat=True)
# convert maxTime to datetime
mTime = [datetime.datetime.strptime(mm,"%Y-%m-%d %H:%M:%S") for mm in mTime]
hours = [(mm.hour + mm.minute/60 + timeZone[i]) % 24 \
for i,mm in enumerate(mTime)]
isMorning = [int(hour < 12) for hour in hours]
return(isMorning)
def contourPlotMeanVarOnMap(variable, startDate, endDate, \
npts = 20, ncntrs = 10, \
width_fac = 16, height_fac = 12):
import numpy as np
import wUUtils as Util
import matplotlib.pyplot as plt
import scipy.interpolate
from mpl_toolkits.basemap import Basemap
# open new figure window
plt.figure()
# setup Lambert Conformal basemap.
m = Basemap(width=width_fac*100000,height=height_fac*100000, \
projection='lcc', resolution='i', \
lat_1=45.,lat_0=43.6,lon_0=-82.)
# draw coastlines.
m.drawcoastlines()
m.drawcountries()
m.drawstates()
# draw a boundary around the map, fill the background.
# this background will end up being the ocean color, since
# the continents/data will be drawn on top.
m.drawmapboundary(fill_color='aqua')
# load data
stations = Util.getStationList()
lon, lat = Util.getStationLonLat(stations)
data = []
for station in stations:
vals = Util.loadDailyVariableRange(station, startDate, endDate, \
variable, castFloat=True)
data.append(np.mean(vals))
# print(zip(stations,data))
# convert data to arrays:
x, y, z = np.array(lon), np.array(lat), np.array(data)
# map data points to projection coordinates
xmap, ymap = m(x,y)
# Set up a regular grid of interpolation points
xi, yi = np.linspace(x.min(), x.max(), npts), \
np.linspace(y.min(), y.max(), npts)
# map regular lon-lat grid to projection coordinates
xi, yi = m(*np.meshgrid(xi,yi))
# Interpolate data to projected regular grid
# function is one of 'linear', 'multiquadric', 'gaussian',
# 'inverse', 'cubic', 'quintic', 'thin_plate'
rbf = scipy.interpolate.Rbf(xmap, ymap, z, \
function='linear')
zi = rbf(xi, yi)
# draw filled contours
cs = m.contourf(xi,yi,zi,ncntrs,cmap=plt.cm.jet)
# plot circles at original (projected) data points
m.scatter(xmap,ymap,c=z)
# add colorbar.
cbar = m.colorbar(cs,location='bottom',pad="5%")
cbar.set_label(variable)
plt.title(variable + " -- Mean " + startDate + " to " + endDate)
# display plot
plt.show()
def plotMeanWindVectorsOnMap(startDate, endDate, showIt=True):
import numpy as np
import wUUtils as Util
from mpl_toolkits.basemap import Basemap
import matplotlib.pyplot as plt
# setup Lambert Conformal basemap.
m = Basemap(width=3200000,height=2500000,projection='lcc',
resolution='i',lat_1=45.,lat_0=43.6,lon_0=-80.)
# draw coastlines.
m.drawcoastlines()
m.drawcountries()
m.drawstates()
# draw a boundary around the map, fill the background.
# this background will end up being the ocean color, since
# the continents will be drawn on top.
m.drawmapboundary(fill_color='aqua')
# fill continents, set lake color same as ocean color.
m.fillcontinents(color='wheat',lake_color='aqua')
# get station locations (Toronto, Montreal, Detroit)
stations = Util.getStationList()
lon, lat = Util.getStationLonLat(stations)
# convert to map projection coords.
# Note that lon,lat can be scalars, lists or numpy arrays.
xpt,ypt = m(lon,lat)
m.plot(xpt,ypt,'bo') # plot a blue dot there
# calculate mean wind at each station
windX = []
windY = []
for station in stations:
wX = Util.loadDailyVariableRange(station, startDate, endDate, \
'WindMeanX', castFloat=True)
windX.append(np.mean(wX))
wY = Util.loadDailyVariableRange(station, startDate, endDate, \
'WindMeanY', castFloat=True)
windY.append(np.mean(wY))
for istation in range(len(stations)):
stretch = 50000
dx, dy = stretch*windX[istation], stretch*windY[istation]
plt.arrow(xpt[istation],ypt[istation],dx,dy,color='r',width=12000,head_length=40000,head_width=40000)
plt.text(xpt[istation]+30000,ypt[istation]+20000,stations[istation], size='large')
plt.title("Time-mean Wind: " + startDate + " to " + endDate)
if showIt:
plt.show()
def dailyTempRange(station, startDate, endDate):
import datetime
import wUUtils as Util
# get daily range (positive if max occurs later than min)
maximum = Util.loadDailyVariableRange(station, startDate, endDate, \
'TempMax', castFloat=True)
minimum = Util.loadDailyVariableRange(station, startDate, endDate, \
'TempMin', castFloat=True)
maxTime = Util.loadDailyVariableRange(station, startDate, endDate, \
'TempMaxTime', castFloat=False)
minTime = Util.loadDailyVariableRange(station, startDate, endDate, \
'TempMinTime', castFloat=False)
# positive if maximum occurs later than minimum
plusminus = [2*int(datetime.datetime.strptime(maxTime[i],"%Y-%m-%d %H:%M:%S")
- datetime.datetime.strptime(minTime[i],"%Y-%m-%d %H:%M:%S")
> datetime.timedelta(0)) - 1 \
for i in range(len(maxTime))]
# calculate return value
vals = [float(plusminus[i]*(maximum[i]-minimum[i])) \
for i in range(len(plusminus))]
return vals
def advectionTaylorModel(stations, startDate, endDate, \
features, targetVar='TempMax', \
lag=1, order=0, verbose=False):
# build regression model to predict "variable" for a single
# station using training data from multiple stations
# between startdate and enddate. Uses a "Taylor expansion"
# by combining information from several days (higher order
# time derivatives)
#
# for each variable, at target station, use value, and
# at other stations, only the projection of its gradient
# in the direction of the target station
#
# stations: a list of station codes, the first entry is
# the target station (for which forecast is generated)
# features: a list of variables to use as predictors
# lag: the number of days in the future to forecast
# order: the number of days in the past to include
# (also maximum order of time derivative)
import numpy as np
import wUUtils as Util
import wUAdvection as Adv
reload(Adv)
from sklearn import linear_model
# load target variable data
target = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
targetVar, castFloat=True)
# shift vector by lag
target = target[lag:]
# load feature data
featureData = []
# add data for target station
for feature in features:
fd = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
feature, castFloat=True)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# for other stations, add the advection of each feature in the
# direction of the target station
for station in stations[1:]:
for feature in features:
# print("Adding " + feature + " from " + station)
fd, uVec = Adv.dDeriv(stations[0], station, \
feature, startDate, endDate)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# add in "derivative" terms
for ideriv in range(1,order+1):
ncols = len(stations)*len(features)
for ii in range(ncols):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[ii],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
target = target[-nrows:]
# convert target and features to np arrays
target = np.array(target)
featureData = (np.array(featureData)).T
regr = linear_model.LinearRegression()
regr.fit(featureData, target)
model_params = {
'stations': stations, \
'startDate': startDate, \
'endDate': endDate, \
'targetVar': targetVar, \
'features': features, \
'regr': regr, \
'lag': lag, \
'order': order}
# report regression results:
print("R^2: " + str(regr.score(featureData,target)))
if verbose:
print("Regression coefficients:")
print(" intercept" + ":\t" + str(regr.intercept_))
column = 0
for ideriv in range(order+1):
print(" " + str(ideriv) + "th derivative:")
for jj, station in enumerate(stations):
if jj > 0:
print(" Station (Adv): " + station)
else:
print(" Station: " + station)
for ii, feature in enumerate(features):
print(" " + feature + ":\t" + str(regr.coef_[column]))
column += 1
return featureData, target, model_params
def multiCityInteractionPredict(model_params, startDate, endDate, actual=True):
# predict targetVar for a single station using
# previously generated regression model
import numpy as np
import wUUtils as Util
# extract city and feature data
stations = model_params['stations']
targetVar = model_params['targetVar']
features = model_params['features']
regr = model_params['regr']
lag = model_params['lag']
order = model_params['order']
scale = model_params['scale']
prescalers = model_params['prescalers']
if scale:
scaler = model_params['scaler']
# build list of dates in datetime format
date_list = Util.dateList(startDate, endDate)
date_list = date_list[(lag+order):]
# if actual data available
if actual:
# load target variable data
target = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
targetVar, castFloat=True)
# "baseline" model is predicted target same as value on prediction day
baseline = target[order:(-lag)]
baseline = np.array(baseline)
# shift vector by lag
target = target[lag:]
target = np.array(target)
else:
target = None
# load feature data
featureData = []
idata = 0
for station in stations:
for feature in features:
# check if feature contains an interaction
if ':' in feature:
feat1 = feature.split(':')[0]
feat2 = feature.split(':')[1]
fd1 = Util.loadDailyVariableRange(station, startDate, endDate, \
feat1, castFloat=True)
fd2 = Util.loadDailyVariableRange(station, startDate, endDate, \
feat2, castFloat=True)
# rescale factors in interaction
prescaler1, prescaler2 = prescalers[idata]
fd1 = prescaler1.transform(fd1)
fd2 = prescaler2.transform(fd2)
# compute interaction
fd = (np.array(fd1)*np.array(fd2)).tolist()
else:
fd = Util.loadDailyVariableRange(station, startDate, endDate, \
feature, castFloat=True)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# increment feature counter
idata += 1
# add in "derivative" terms
for ideriv in range(1,order+1):
ncols = len(stations)*len(features)
for ii in range(ncols):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[ii],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
if actual:
target = target[-nrows:]
# convert features to np arrays
featureData = (np.array(featureData)).T
if scale:
featureData = scaler.transform(featureData)
pred = regr.predict(featureData)
if actual:
print("R^2_mean:" + "\t" + str(regr.score(featureData,target)))
sse = ((pred-target)**2).sum()
ssm = ((baseline-target)**2).sum()
print("R^2_base:" + "\t" + str(1 - sse/ssm))
rmse = np.sqrt(((pred - target)**2).mean())
print("RMSE:\t" + "\t" + str(rmse))
model_perf = {
'R2_mean': regr.score(featureData,target), \
'R2_base': 1 - sse/ssm, \
'RMSE': rmse}
else:
model_perf = None
return date_list, pred, target, model_perf
def multiCityInteractionModel(stations, startDate, endDate, \
features, targetVar='TempMax', \
lag=1, order=0, verbose=False, scale=False):
# build regression model to predict "variable" for a single
# station using training data from multiple stations
# between startdate and enddate. Uses a "Taylor expansion"
# by combining information from several days (higher order
# time derivatives)
#
# stations: a list of station codes, the first entry is
# the station for which forecast is generated
# features: a list of variables to use as predictors
# *** if a feature string contains a ":" it is parsed as
# an interaction between two features ...
# *** features in interaction terms pre-scaled!
# lag: the number of days in the future to forecast
# order: the number of days in the past to include
# (also maximum order of time derivative)
import numpy as np
import wUUtils as Util
from sklearn import preprocessing
from sklearn import linear_model
# load target variable data
target = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
targetVar, castFloat=True)
# shift vector by lag
target = target[lag:]
# load feature data
featureData = []
prescalers = []
for station in stations:
for feature in features:
# check if feature contains an interaction
if ':' in feature:
feat1 = feature.split(':')[0]
feat2 = feature.split(':')[1]
fd1 = Util.loadDailyVariableRange(station, startDate, endDate, \
feat1, castFloat=True)
fd2 = Util.loadDailyVariableRange(station, startDate, endDate, \
feat2, castFloat=True)
prescaler1 = preprocessing.StandardScaler().fit(fd1)
fd1 = prescaler1.transform(fd1)
prescaler2 = preprocessing.StandardScaler().fit(fd2)
fd2 = prescaler2.transform(fd2)
# save prescaler objects (for prediction)
prescalers.append([prescaler1,prescaler2])
# compute interaction
fd = (np.array(fd1)*np.array(fd2)).tolist()
else:
fd = Util.loadDailyVariableRange(station, startDate, endDate, \
feature, castFloat=True)
prescalers.append(None)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# add in "derivative" terms
for ideriv in range(1,order+1):
ncols = len(stations)*len(features)
for ii in range(ncols):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[ii],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
target = target[-nrows:]
# convert target and features to np arrays
target = np.array(target)
featureData = (np.array(featureData)).T
# rescale features
scaler = None
if scale:
scaler = preprocessing.StandardScaler().fit(featureData)
featureData = scaler.transform(featureData)
# fit regression model
regr = linear_model.LinearRegression()
regr.fit(featureData, target)
model_params = {
'stations': stations, \
'startDate': startDate, \
'endDate': endDate, \
'targetVar': targetVar, \
'features': features, \
'regr': regr, \
'lag': lag, \
'order': order, \
'scale': scale, \
'scaler': scaler, \
'prescalers': prescalers}
# report regression results:
print("R^2: " + str(regr.score(featureData,target)))
if verbose:
print("Regression coefficients:")
print(" intercept" + ":\t" + str(regr.intercept_))
column = 0
for ideriv in range(order+1):
print(" " + str(ideriv) + "th derivative:")
for jj, station in enumerate(stations):
print(" Station: " + station)
for ii, feature in enumerate(features):
print(" " + feature + ":\t" + str(regr.coef_[column]))
column += 1
return featureData, target, model_params
def oneCityTaylorModel(station, startDate, endDate, \
features, targetVar='TempMax', \
lag=1, order=0, verbose=True, scale=False):
# build regression model to predict "variable" for a single
# station using training data from only the same station
# between startdate and enddate
# features is a list of variables to use as predictors
# use a "Taylor expansion" by combining information from
# order is the maximum order of derivative to use
import numpy as np
import wUUtils as Util
from sklearn import preprocessing
from sklearn import linear_model
# load target variable data
target = Util.loadDailyVariableRange(station, startDate, endDate, \
targetVar, castFloat=True)
# shift vector by lag
target = target[lag:]
# load feature data
featureData = []
for feature in features:
# print("Adding " + feature)
fd = Util.loadDailyVariableRange(station, startDate, endDate, \
feature, castFloat=True)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# add in "derivative" terms
for ideriv in range(1,order+1):
for jfeat in range(len(features)):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[jfeat],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
# print("nrows ... " + str(nrows))
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
target = target[-nrows:]
# convert target and features to np arrays
target = np.array(target)
featureData = (np.array(featureData)).T
# rescale features
scaler = None
if scale:
scaler = preprocessing.StandardScaler().fit(featureData)
featureData = scaler.transform(featureData)
regr = linear_model.LinearRegression()
regr.fit(featureData, target)
model_params = {
'station': station, \
'startDate': startDate, \
'endDate': endDate, \
'targetVar': targetVar, \
'features': features, \
'regr': regr, \
'lag': lag, \
'order': order, \
'scale': scale, \
'scaler': scaler}
# report regression results:
print("R^2: " + str(regr.score(featureData,target)))
if verbose:
if scale:
print("Regression coefficients (scaled, sorted):")
print(" intercept" + ":\t" + str(regr.intercept_))
for ii in np.argsort(-np.abs(regr.coef_)):
ideriv = ii / len(features)
ifeat = ii - len(features)*ideriv
print(" " + str(ideriv) + 'th deriv of ' \
+ features[ifeat] + ":\t" + str(regr.coef_[ii]))
else:
print("Regression coefficients:")
print(" intercept" + ":\t" + str(regr.intercept_))
for ideriv in range(order+1):
print(" " + str(ideriv) + "th derivative:")
for ii, feature in enumerate(features):
column = len(features)*ideriv + ii
print(" " + feature + ":\t" + str(regr.coef_[column]))
return featureData, target, model_params
def pcaClusterPredict(modelParams, startDate, endDate, actual=True):
# predict targetVar for a single station using
# previously generated regression model
import numpy as np
import wUUtils as Util
import wUCluster as Clust
import wUPCA
reload(wUPCA)
# extract city and feature data
stations = modelParams['stations']
targetVar = modelParams['targetVar']
features = modelParams['features']
regrs = modelParams['regrs']
lag = modelParams['lag']
order = modelParams['order']
transformParams = modelParams['transformParams']
ncomp = transformParams['ncomp']
clusterVars = modelParams['clusterVars']
clusterParams = modelParams['clusterParams']
nclusters = clusterParams['nclusters']
cols = clusterParams['cols']
scaler = clusterParams['scaler']
clusterer = clusterParams['clusterer']
# build list of dates in datetime format
date_list = Util.dateList(startDate, endDate)
date_list = date_list[(lag+order):]
# if actual data available
if actual:
# load target variable data
target = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
targetVar, castFloat=True)
# shift vector by lag
target = target[lag:]
target = np.array(target)
else:
target = None
# load features data and compute PC
pcaData = wUPCA.pcaPredict(transformParams, startDate, endDate)
# flatten featureData into single list of lists, while shortening by lag
featureData = [data[:(-lag)] for dataList in pcaData for data in dataList]
# number of PC-transformed features
nfeat = sum(ncomp)
# add in "derivative" terms
for ideriv in range(1,order+1):
for ii in range(nfeat):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[ii],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
if actual:
target = target[-nrows:]
# assign points (rows) to clusters
clusterData = np.array([featureData[ii] for ii in cols]).T
classes = Clust.assignClusters(scaler, clusterer, clusterData)
# separate data into clusters
featureClusters = []
dateClusters = []
if actual:
targetClusters = []
for icl in range(nclusters):
# features
clust = [f for i,f in enumerate(zip(*featureData)) if classes[i]==icl]
featureClusters.append( map(list,zip(*clust)) )
if actual:
# targetVar
clust = [t for i,t in enumerate(target) if classes[i]==icl]
targetClusters.append(clust)
# dates
dateClusters.append([t for i,t in enumerate(date_list) if classes[i] == icl])
R2 = []
RMSE = []
preds = []
for icl in range(nclusters):
regr = regrs[icl]
# convert features and target to arrays
featureClusters[icl] = (np.array(featureClusters[icl])).T
# make predictions
if len(featureClusters[icl]) > 0:
preds.append(regr.predict(featureClusters[icl]))
else:
preds.append([])
if actual:
targetClusters[icl] = np.array(targetClusters[icl])
print('Cluster %d, %d rows:' % (icl,len(dateClusters[icl])) )
if len(featureClusters[icl]) > 0:
r2 = regrs[icl].score(featureClusters[icl],targetClusters[icl])
print(' R^2_mean:' + '\t' + str(r2))
rmse = np.sqrt(((preds[icl] - targetClusters[icl])**2).mean())
print(' RMSE:\t' + '\t' + str(rmse))
RMSE.append(rmse)
R2.append(r2)
else:
RMSE.append(None)
R2.append(None)
# assemble predictions into one list
date_list_mixed = np.concatenate(dateClusters).tolist()
pred_mixed = np.concatenate(preds).tolist()
pred = [pr for (d,pr) in sorted(zip(date_list_mixed,pred_mixed))]
if actual:
rmse = np.sqrt(((np.array(pred) - np.array(target))**2).mean())
print('\nOverall performance:')
print(' RMSE:' + '\t' + str(rmse))
modelPerf = {'RMSE': RMSE, 'R2': R2, 'RMSE_total': rmse }
else:
modelPerf = None
return date_list, pred, target, featureData, classes, modelPerf
def windQuadrant(station, startDate, endDate):
# integer variable for quadrant of maximum wind
import wUUtils as Util
windDir = Util.loadDailyVariableRange(station, startDate, endDate, \
'WindMaxDir', castFloat=True)
return [int(w)/90 for w in windDir]
def pcaTaylorModel(stations, startDate, endDate, \
features, ncomp=None, targetVar='TempMax', \
lag=1, order=0, smooth_window=0, verbose=False):
# build regression model to predict "variable" for a single
# station using training data from multiple stations
# between startdate and enddate.
#
# The set of values of each feature at all stations is converted
# to a truncated list of principal components for purposes of
# feature-reduction and reduction of multicolinearity
#
# Uses a "Taylor expansion" by combining information from
# several days (higher order time derivatives)
#
# stations: a list of station codes, the first entry is
# the station for which forecast is generated
# features: a list of variables to use as predictors
# ncomp: a list of same length as features containing the
# number of PCA to keep for each feature
# lag: the number of days in the future to forecast
# order: the number of days in the past to include
# (also maximum order of time derivative)
import numpy as np
import wUUtils as Util
import wUPCA
reload(wUPCA)
from sklearn import preprocessing
from sklearn import linear_model
# load target variable data
target = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
targetVar, castFloat=True)
if smooth_window > 0:
target = Util.smooth(target, smooth_window)
# shift vector by lag
target = target[lag:]
# load features data and compute PC
pcaData, transform_params = wUPCA.pcaConvert(stations, features, \
startDate, endDate, ncomp)
# flatten featureData into single list of lists, while shortening by lag
featureData = [data[:(-lag)] for dataList in pcaData for data in dataList]
if smooth_window > 0:
for data in featureData:
data = Util.smooth(data,smooth_window)
# number of PC-transformed features
if ncomp == None:
nfeat = len(stations)*len(features)
else:
nfeat = sum(ncomp)
# add in "derivative" terms
for ideriv in range(1,order+1):
for ii in range(nfeat):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[ii],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
target = target[-nrows:]
# convert target and features to np arrays
target = np.array(target)
featureData = (np.array(featureData)).T
# fit regression model
regr = linear_model.LinearRegression()
regr.fit(featureData, target)
model_params = {
'stations': stations, \
'startDate': startDate, \
'endDate': endDate, \
'targetVar': targetVar, \
'features': features, \
'regr': regr, \
'lag': lag, \
'order': order, \
'smooth_window': smooth_window, \
'transform_params': transform_params}
# report regression results:
print("R^2: " + str(regr.score(featureData,target)))
if verbose:
print("Regression coefficients:")
print(" intercept" + ":\t" + str(regr.intercept_))
column = 0
for ideriv in range(order+1):
print(" " + str(ideriv) + "th derivative:")
for ii, feature in enumerate(features):
print(" " + feature)
if ncomp == None:
nc = len(stations)
else:
nc = ncomp[ii]
for jj in range(nc):
print(" PC " + str(jj) + " :\t" + str(regr.coef_[column]))
column += 1
return featureData, target, model_params
def isEasterly(station, startDate, endDate):
# binary variable for max wind (0 = easterly, 1 = westerly)
import wUUtils as Util
windDir = Util.loadDailyVariableRange(station, startDate, endDate, \
'WindMaxDir', castFloat=True)
return [int(w > 0.0 and w < 180.0) for w in windDir]
def isNotFoggy(station, startDate, endDate):
# binary variable for fogginess (visibility < 5 km)
import wUUtils as Util
visibility = Util.loadDailyVariableRange(station, startDate, endDate, \
'VisibilityMean', castFloat=True)
return [int(v > 5.0) for v in visibility]
def advectionTaylorPredict(model_params, startDate, endDate, actual=True):
# predict targetVar for a single station using
# previously generated regression model
import numpy as np
import wUUtils as Util
import wUAdvection as Adv
# extract city and feature data
stations = model_params['stations']
targetVar = model_params['targetVar']
features = model_params['features']
regr = model_params['regr']
lag = model_params['lag']
order = model_params['order']
# build list of dates in datetime format
date_list = Util.dateList(startDate, endDate)
date_list = date_list[(lag+order):]
# if actual data available
if actual:
# load target variable data
target = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
targetVar, castFloat=True)
# "baseline" model is predicted target same as value on prediction day
baseline = target[order:(-lag)]
baseline = np.array(baseline)
# shift vector by lag
target = target[lag:]
target = np.array(target)
else:
target = None
# load feature data
featureData = []
# add data for target station
for feature in features:
fd = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
feature, castFloat=True)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# for other stations, add the advection of each feature in the
# direction of the target station
for station in stations[1:]:
for feature in features:
# print("Adding " + feature + " from " + station)
fd, uVec = Adv.dDeriv(stations[0], station, \
feature, startDate, endDate)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# add in "derivative" terms
for ideriv in range(1,order+1):
ncols = len(stations)*len(features)
for ii in range(ncols):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[ii],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
if actual:
target = target[-nrows:]
# convert features to np arrays
featureData = (np.array(featureData)).T
pred = regr.predict(featureData)
if actual:
print("R^2_mean:" + "\t" + str(regr.score(featureData,target)))
sse = ((pred-target)**2).sum()
ssm = ((baseline-target)**2).sum()
print("R^2_base:" + "\t" + str(1 - sse/ssm))
rmse = np.sqrt(((pred - target)**2).mean())
print("RMSE:\t" + "\t" + str(rmse))
model_perf = {
'R2_mean': regr.score(featureData,target), \
'R2_base': 1 - sse/ssm, \
'RMSE': rmse}
else:
model_perf = None
return date_list, pred, target, model_perf
def clusterRegression(stations, startDate, endDate, \
features, clusterFeatures=None, \
nclusters=1, ranseed=666, \
targetVar='TempMax', \
lag=1, order=0, scale=False, verbose=False):
# build regression model to predict a variable for a single
# station using training data from multiple stations
# between startdate and enddate. Uses a "Taylor expansion"
# by combining information from several days (higher order
# time derivatives)
#
# stations: a list of station codes, the first entry is
# the station for which forecast is generated
# features: a list of variables to use as predictors
# *** if a feature string contains a ":" it is parsed as
# an interaction between two features ...
# *** features in interaction terms pre-scaled!
# clusterFeatures: subset of features with respect to which
# k-means clustering is applied before training
# regression models
# nclusters: number of clusters to compute
# lag: the number of days in the future to forecast
# order: the number of days in the past to include
# (also maximum order of time derivative)
import wUCluster as Clust
reload(Clust)
import numpy as np
import wUUtils as Util
from sklearn import preprocessing
from sklearn import linear_model
# load target variable data
target = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
targetVar, castFloat=True)
# shift vector by lag
target = target[lag:]
# load feature data
featureData = []
prescalers = []
for station in stations:
for feature in features:
# check if feature contains an interaction
if ':' in feature:
feat1 = feature.split(':')[0]
feat2 = feature.split(':')[1]
fd1 = Util.loadDailyVariableRange(station, startDate, endDate, \
feat1, castFloat=True)
fd2 = Util.loadDailyVariableRange(station, startDate, endDate, \
feat2, castFloat=True)
prescaler1 = preprocessing.StandardScaler().fit(fd1)
fd1 = prescaler1.transform(fd1)
prescaler2 = preprocessing.StandardScaler().fit(fd2)
fd2 = prescaler2.transform(fd2)
# save prescaler objects (for prediction)
prescalers.append([prescaler1,prescaler2])
# compute interaction
fd = (np.array(fd1)*np.array(fd2)).tolist()
else:
fd = Util.loadDailyVariableRange(station, startDate, endDate, \
feature, castFloat=True)
prescalers.append(None)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# add in "derivative" terms
for ideriv in range(1,order+1):
ncols = len(stations)*len(features)
for ii in range(ncols):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[ii],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
target = target[-nrows:]
# apply k-means clustering
if clusterFeatures is not None:
classes, clusterParams = Clust.clusterFeatureData(featureData, stations, features, \
clusterFeatures, nclusters, \
ranseed)
classes, featureClusters = Clust.assignClustersAllFeatures(featureData, clusterParams)
targetClusters = []
for cl in range(nclusters):
targetClusters.append([t for i,t in enumerate(target) if classes[i] == cl])
else:
# everything is one cluster
classes = range(len(target))
featureClusters = [featureData]
targetClusters = [target]
clusterParams = { 'nclusters': 1 }
# train separate regression model for each cluster
regrs = []
scalers = []
for icl in range(nclusters):
# convert features and target to arrays
featureClusters[icl] = (np.array(featureClusters[icl])).T
targetClusters[icl] = np.array(targetClusters[icl])
scaler = None
if scale:
scaler = preprocessing.StandardScaler().fit(featureClusters[icl])
featureClusters[icl] = scaler.transform(featureClusters[icl])
scalers.append(scaler)
regr = linear_model.LinearRegression()
regr.fit(featureClusters[icl], targetClusters[icl])
regrs.append(regr)
print('Cluster %d, nrows %d, R^2 %f' \
% (icl, \
len(targetClusters[icl]), \
regr.score(featureClusters[icl],targetClusters[icl])) )
if verbose:
print("Regression coefficients:")
print(" intercept" + ":\t" + str(regr.intercept_))
column = 0
for ideriv in range(order+1):
print(" " + str(ideriv) + "th derivative:")
for jj, station in enumerate(stations):
print(" Station: " + station)
for ii, feature in enumerate(features):
print(" " + feature + ":\t" + str(regr.coef_[column]))
column += 1
# save model parameters
modelParams = {
'stations': stations, \
'startDate': startDate, \
'endDate': endDate, \
'targetVar': targetVar, \
'features': features, \
'regrs': regrs, \
'clusterParams': clusterParams, \
'classes': classes, \
'lag': lag, \
'order': order, \
'scale': scale, \
'scalers': scalers, \
'prescalers': prescalers}
return featureData, target, modelParams
def clusterRegressionPredict(modelParams, startDate, endDate, actual=True):
# predict targetVar for a single station using
# previously generated regression model
import wUCluster as Clust
reload(Clust)
import numpy as np
import wUUtils as Util
# extract city and feature data
stations = modelParams['stations']
targetVar = modelParams['targetVar']
features = modelParams['features']
regrs = modelParams['regrs']
clusterParams = modelParams['clusterParams']
nclusters = clusterParams['nclusters']
lag = modelParams['lag']
order = modelParams['order']
scale = modelParams['scale']
prescalers = modelParams['prescalers']
scalers = modelParams['scalers']
# build list of dates in datetime format
date_list = Util.dateList(startDate, endDate)
date_list = date_list[(lag+order):]
# if actual data available
if actual:
# load target variable data
target = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
targetVar, castFloat=True)
# "baseline" model is predicted target same as value on prediction day
baseline = target[order:(-lag)]
baseline = np.array(baseline)
# shift vector by lag
target = target[lag:]
target = np.array(target)
else:
target = None
# load feature data
featureData = []
idata = 0
for station in stations:
for feature in features:
# check if feature contains an interaction
if ':' in feature:
feat1 = feature.split(':')[0]
feat2 = feature.split(':')[1]
fd1 = Util.loadDailyVariableRange(station, startDate, endDate, \
feat1, castFloat=True)
fd2 = Util.loadDailyVariableRange(station, startDate, endDate, \
feat2, castFloat=True)
# rescale factors in interaction
prescaler1, prescaler2 = prescalers[idata]
fd1 = prescaler1.transform(fd1)
fd2 = prescaler2.transform(fd2)
# compute interaction
fd = (np.array(fd1)*np.array(fd2)).tolist()
else:
fd = Util.loadDailyVariableRange(station, startDate, endDate, \
feature, castFloat=True)
# shorten vector by lag
fd = fd[:(-lag)]
featureData.append(fd)
# increment feature counter
idata += 1
# add in "derivative" terms
for ideriv in range(1,order+1):
ncols = len(stations)*len(features)
for ii in range(ncols):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[ii],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
if actual:
target = target[-nrows:]
# allocate features to clusters
if clusterParams['nclusters'] > 1:
classes, featureClusters = Clust.assignClustersAllFeatures(featureData, clusterParams)
dateClusters = []
for icl in range(nclusters):
dateClusters.append([t for i,t in enumerate(date_list) if classes[i] == icl])
if actual:
targetClusters = []
for icl in range(nclusters):
targetClusters.append([t for i,t in enumerate(target) if classes[i] == icl])
else:
# everything is one cluster
classes = range(len(target))
featureClusters = [featureData]
dateClusters = [date_list]
if actual:
targetClusters = [target]
preds = []
RMSE = []
R2 = []
for icl in range(nclusters):
# convert features and target to arrays
featureClusters[icl] = (np.array(featureClusters[icl])).T
if scale:
scaler = scalers[icl]
featureClusters[icl] = scaler.transform(featureClusters[icl])
regr = regrs[icl]
preds.append(regr.predict(featureClusters[icl]))
if actual:
targetClusters[icl] = np.array(targetClusters[icl])
print('Cluster %d, %d rows:' % (icl,len(dateClusters[icl])) )
r2 = regrs[icl].score(featureClusters[icl],targetClusters[icl])
print(' R^2_mean:' + '\t' + str(r2))
rmse = np.sqrt(((preds[icl] - targetClusters[icl])**2).mean())
print(' RMSE:\t' + '\t' + str(rmse))
RMSE.append(rmse)
R2.append(r2)
# assemble predictions into one list
date_list_mixed = np.concatenate(dateClusters).tolist()
pred_mixed = np.concatenate(preds).tolist()
pred = [pr for (d,pr) in sorted(zip(date_list_mixed,pred_mixed))]
if actual:
rmse = np.sqrt(((np.array(pred) - np.array(target))**2).mean())
print('\nOverall performance:')
print(' RMSE:' + '\t' + str(rmse))
modelPerf = {'RMSE': RMSE, 'R2': R2, 'RMSE_total': rmse }
else:
modelPerf = None
return date_list, pred, target, featureData, classes, modelPerf
def isNortherly(station, startDate, endDate):
# binary variable for max wind (0 = northerly, 1 = southerly)
import wUUtils as Util
windDir = Util.loadDailyVariableRange(station, startDate, endDate, \
'WindMaxDir', castFloat=True)
return [int(w > 270.0 or w < 90.0) for w in windDir]
def pcaTaylorPredict(model_params, startDate, endDate, actual=True):
# predict targetVar for a single station using
# previously generated regression model
import numpy as np
import wUUtils as Util
import wUPCA
reload(wUPCA)
# extract city and feature data
stations = model_params['stations']
targetVar = model_params['targetVar']
features = model_params['features']
regr = model_params['regr']
lag = model_params['lag']
order = model_params['order']
transform_params = model_params['transform_params']
ncomp = transform_params['ncomp']
# build list of dates in datetime format
date_list = Util.dateList(startDate, endDate)
date_list = date_list[(lag+order):]
# if actual data available
if actual:
# load target variable data
target = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
targetVar, castFloat=True)
# "baseline" model is predicted target same as value on prediction day
baseline = target[order:(-lag)]
baseline = np.array(baseline)
# shift vector by lag
target = target[lag:]
target = np.array(target)
else:
target = None
# load features data and compute PC
pcaData = wUPCA.pcaPredict(transform_params, startDate, endDate)
# flatten featureData into single list of lists, while shortening by lag
featureData = [data[:(-lag)] for dataList in pcaData for data in dataList]
# number of PC-transformed features
nfeat = sum(ncomp)
# add in "derivative" terms
for ideriv in range(1,order+1):
for ii in range(nfeat):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[ii],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
if actual:
target = target[-nrows:]
# convert features to np arrays
featureData = (np.array(featureData)).T
pred = regr.predict(featureData)
if actual:
print("R^2_mean:" + "\t" + str(regr.score(featureData,target)))
sse = ((pred-target)**2).sum()
ssm = ((baseline-target)**2).sum()
print("R^2_base:" + "\t" + str(1 - sse/ssm))
rmse = np.sqrt(((pred - target)**2).mean())
print("RMSE:\t" + "\t" + str(rmse))
model_perf = {
'R2_mean': regr.score(featureData,target), \
'R2_base': 1 - sse/ssm, \
'RMSE': rmse}
else:
model_perf = None
return date_list, pred, target, model_perf
def pcaClusterModel(stations, startDate, endDate, \
features, ncomp=None, \
clusterVars=[], nclusters=1, \
targetVar='TempMax', \
lag=1, order=0, ranseed=666, verbose=False):
# build regression model to predict "variable" for a single
# station using training data from multiple stations
# between startdate and enddate.
#
# The set of values of each feature at all stations is converted
# to a truncated list of principal components for purposes of
# feature-reduction and reduction of multicolinearity
#
# Clustering is used to train multiple models for different
# partitions of the data
#
# Uses a "Taylor expansion" by combining information from
# several days (higher order time derivatives)
#
# stations: a list of station codes, the first entry is
# the station for which forecast is generated
# features: a list of variables to use as predictors
# ncomp: a list of same length as features containing the
# number of PCA to keep for each feature
# clusterVars: a list of pairs of form ('feature',npc), where
# where npc is the index of the PC to use for
# clustering
# lag: the number of days in the future to forecast
# order: the number of days in the past to include
# (also maximum order of time derivative)
import numpy as np
import wUUtils as Util
import wUPCA
import wUCluster as Clust
from sklearn import preprocessing
from sklearn import linear_model
# load target variable data
target = Util.loadDailyVariableRange(stations[0], startDate, endDate, \
targetVar, castFloat=True)
# shift vector by lag
target = target[lag:]
# load features data and compute PC
pcaData, transformParams = wUPCA.pcaConvert(stations, features, \
startDate, endDate, ncomp)
# flatten featureData into single list of lists, while shortening by lag
featureData = [data[:(-lag)] for dataList in pcaData for data in dataList]
# number of PC-transformed features
if ncomp == None:
nfeat = len(stations)*len(features)
else:
nfeat = sum(ncomp)
# add in "derivative" terms
for ideriv in range(1,order+1):
for ii in range(nfeat):
# print("Adding " + str(ideriv) + " derivative of " + feature[jfeat])
fd = np.diff(featureData[ii],n=ideriv)
featureData.append(fd)
# shorten vectors to length of highest order derivative
nrows = len(featureData[-1])
for column in range(len(featureData)):
featureData[column] = featureData[column][-nrows:]
target = target[-nrows:]
# apply clustering
# locate columns to be used for clustering
cols = []
for clusterPair in clusterVars:
ifeat = features.index(clusterPair[0]) # index of feature
col = sum(ncomp[:ifeat]) + clusterPair[1]
cols += [col]
if clusterPair[1] >= ncomp[ifeat]:
print('Requested cluster variable out of range')
print(clusterPair[0] + ' ' + str(clusterPair[1]) + ' >= ' + str(ncomp[ifeat]))
return
print('columns for clustering: ' + str(cols))
clusterData = np.array([featureData[ii] for ii in cols]).T
scaler, clusterer = Clust.computeClusters(clusterData, nclusters, ranseed)
classes = Clust.assignClusters(scaler, clusterer, clusterData)
clusterParams = { \
'scaler': scaler, \
'clusterer': clusterer, \
'nclusters': nclusters, \
'ranseed': ranseed, \
'cols': cols }
# separate data into clusters
featureClusters = []
targetClusters = []
for icl in range(nclusters):
# features
clust = [f for i,f in enumerate(zip(*featureData)) if classes[i]==icl]
featureClusters.append( map(list,zip(*clust)) )
# targetVar
clust = [t for i,t in enumerate(target) if classes[i]==icl]
targetClusters.append(clust)
# train separate regression model for each cluster
regrs = []
for icl in range(nclusters):
# convert features and target to arrays
featureClusters[icl] = (np.array(featureClusters[icl])).T
targetClusters[icl] = np.array(targetClusters[icl])
regr = linear_model.LinearRegression()
regr.fit(featureClusters[icl], targetClusters[icl])
regrs.append(regr)
print('Cluster %d, nrows %d, R^2 %f' \
% (icl, \
len(targetClusters[icl]), \
regr.score(featureClusters[icl],targetClusters[icl])) )
if verbose:
print("\nCluster " + str(icl))
print("Regression coefficients:")
print(" intercept" + ":\t" + str(regr.intercept_))
column = 0
for ideriv in range(order+1):
print(" " + str(ideriv) + "th derivative:")
for ii, feature in enumerate(features):
print(" " + feature)
for jj in range(ncomp[ii]):
print(" PC " + str(jj) + " :\t" + str(regr.coef_[column]))
column += 1
modelParams = {
'stations': stations, \
'startDate': startDate, \
'endDate': endDate, \
'targetVar': targetVar, \
'features': features, \
'clusterVars': clusterVars, \
'clusterParams': clusterParams, \
'classes': classes, \
'regrs': regrs, \
'lag': lag, \
'order': order, \
'transformParams': transformParams}
return featureData, target, modelParams