def setUpClass(cls):
ds = NREL()
cls.turbine = ds.get_turbine(NREL.park_id['tehachapi'], 2004, 2005)
cls.windpark = ds.get_windpark(NREL.park_id['tehachapi'], 3, 2004,
2005)
cls.pmapping = PowerMapping()
cls.pdmapping = PowerDiffMapping()
def down(citynum, methodnum):
cityname = [
'tehachapi', 'cheyenne', 'palmsprings', 'lasvegas', 'lancaster'
]
method = [
'KMeans', 'SpectralClustering', 'AgglomerativeClustering', 'Birch'
]
target_idx = NREL.park_id[cityname[citynum]]
year_from, year_to = 2004, 2006
if sys.version_info < (3, ):
mode = 'rU'
else:
mode = 'r'
csvfile = 'cluster/' + method[methodnum] + '200.csv'
pick = []
with open(csvfile, mode) as csv_arch:
reader = csv.reader(csv_arch, delimiter=',')
for row in reader:
pick.append(int(row[0]))
nrel = NREL()
d = 0
turbines = nrel.fetch_nrel_meta_data_all()
for row in turbines:
turbine_index = np.int(row[0])
if (turbine_index != target_idx):
if (pick[turbine_index - 1] == pick[target_idx - 1]):
d = d + 1
for y in range(year_from, year_to + 1):
measurement = nrel.fetch_nrel_data(
row[0], y, ['date', 'corrected_score', 'speed'])
def test_nmar_destroyer(self):
turbine = NREL().get_turbine(NREL.park_id['tehachapi'], 2004)
timeseries = turbine.get_measurements()[:1000]
damaged, indices = NMARDestroyer().destroy(timeseries, percentage=.50,\
min_length=10, max_length=50)
misses = MissingDataFinder().find(damaged, 600)
assert(len(misses) > 0)
def test_mreg_interpolation_multi(self):
park_id = NREL.park_id['tehachapi']
windpark = NREL().get_windpark(park_id, 3, 2004)
target = windpark.get_target()
timestep = 600
measurements = target.get_measurements()[300:350]
damaged, indices = MARDestroyer().destroy(measurements, percentage=.50)
before_misses = MissingDataFinder().find(damaged, timestep)
neighbors = windpark.get_turbines()[:-1]
count_neighbors = len(neighbors)
reg = 'knn' # KNeighborsRegressor(10, 'uniform')
regargs = {'n' : 8, 'variant' : 'uniform'}
processed = 0
missed = {k : count_neighbors for k in indices}
exclude = []
damaged_nseries = []
for neighbor in neighbors:
nseries = neighbor.get_measurements()[300:350]
damaged, indices = MARDestroyer().destroy(nseries, percentage=.50, exclude=exclude)
for index in indices:
if(index not in missed.keys()):
missed[index] = count_neighbors
missed[index] -= 1
if(missed[index] == 1):
exclude.append(index) # exclude in next iterations
damaged_nseries.append(damaged)
t_hat = MRegInterpolation().interpolate(damaged, timestep=timestep,\
neighbor_series=damaged_nseries, reg=reg, regargs=regargs)
after_misses = MissingDataFinder().find(t_hat, timestep)
assert(len(after_misses) < 1)
def test_marthres_destroyer(self):
turbine = NREL().get_turbine(NREL.park_id['tehachapi'], 2004)
timeseries = turbine.get_measurements()[:1000]
damaged, indices = MARThresDestroyer().destroy(timeseries, percentage=.50,\
lower_bound = 0, upper_bound = 20)
misses = MissingDataFinder().find(damaged, 600)
assert(len(misses) > 0)
def compute_mse(regressor, horizon):
# get wind park and corresponding target.
windpark = NREL().get_windpark(NREL.park_id['tehachapi'], 3, 2004, 2005)
target = windpark.get_target()
# use power mapping for pattern-label mapping.
feature_window = 3
mapping = PowerMapping()
X = mapping.get_features_park(windpark, feature_window, horizon)
y = mapping.get_labels_turbine(target, feature_window, horizon)
# train roughly for the year 2004, test for 2005.
train_to = int(math.floor(len(X) * 0.5))
test_to = len(X)
train_step, test_step = 25, 25
X_train=X[:train_to:train_step]
y_train=y[:train_to:train_step]
X_test=X[train_to:test_to:test_step]
y_test=y[train_to:test_to:test_step]
if(regressor == 'svr'):
reg = SVR(kernel='rbf', epsilon=0.1, C = 100.0,\
gamma = 0.0001).fit(X_train,y_train)
mse = mean_squared_error(reg.predict(X_test),y_test)
elif(regressor == 'knn'):
reg = KNeighborsRegressor(10, 'uniform').fit(X_train,y_train)
mse = mean_squared_error(reg.predict(X_test),y_test)
return mse
def compute_mse(regressor, param):
# get wind park and corresponding target. forecast is for the target
# turbine
park_id = NREL.park_id['tehachapi']
windpark = NREL().get_windpark(park_id, 3, 2004)
target = windpark.get_target()
# use power mapping for pattern-label mapping. Feature window length
# is 3 time steps and time horizon (forecast) is 3 time steps.
feature_window = 6
horizon = 3
mapping = PowerMapping()
X = mapping.get_features_park(windpark, feature_window, horizon)
Y = mapping.get_labels_turbine(target, feature_window, horizon)
# train roughly for the year 2004.
train_to = int(math.floor(len(X) * 0.5))
# test roughly for the year 2005.
test_to = len(X)
# train and test only every fifth pattern, for performance.
train_step, test_step = 5, 5
if (regressor == 'rf'):
# random forest regressor
reg = RandomForestRegressor(n_estimators=param, criterion='mse')
reg = reg.fit(X[0:train_to:train_step], Y[0:train_to:train_step])
y_hat = reg.predict(X[train_to:test_to:test_step])
elif (regressor == 'knn'):
# TODO the regressor does not need to be newly trained in
# the case of KNN
reg = KNeighborsRegressor(param, 'uniform')
# fitting the pattern-label pairs
reg = reg.fit(X[0:train_to:train_step], Y[0:train_to:train_step])
y_hat = reg.predict(X[train_to:test_to:test_step])
else:
raise Exception("No regressor set.")
# naive is also known as persistence model.
naive_hat = zeros(len(y_hat), dtype=float32)
for i in range(0, len(y_hat)):
# naive label is the label as horizon time steps before.
# we have to consider to use only the fifth label here, too.
naive_hat[i] = Y[train_to + (i * test_step) - horizon]
# computing the mean squared errors of Linear and naive prediction.
mse_y_hat, mse_naive_hat = 0, 0
for i in range(0, len(y_hat)):
y = Y[train_to + (i * test_step)]
mse_y_hat += (y_hat[i] - y)**2
mse_naive_hat += (naive_hat[i] - y)**2
mse_y_hat /= float(len(y_hat))
mse_naive_hat /= float(len(y_hat))
return mse_y_hat, mse_naive_hat
def test_backward_copy_interpolation(self):
park_id = NREL.park_id['tehachapi']
windpark = NREL().get_windpark(park_id, 10, 2004)
target = windpark.get_target()
timestep = 600
measurements = target.get_measurements()[300:500]
damaged, indices = MARDestroyer().destroy(measurements, percentage=.50)
before_misses = MissingDataFinder().find(damaged, timestep)
t_hat = BackwardCopy().interpolate(measurements, timestep=timestep)
after_misses = MissingDataFinder().find(t_hat, timestep)
assert(measurements.shape[0] == t_hat.shape[0])
assert(len(after_misses) < 1)
def test_mreg_interpolation(self):
park_id = NREL.park_id['tehachapi']
windpark = NREL().get_windpark(park_id, 3, 2004)
target = windpark.get_target()
timestep = 600
measurements = target.get_measurements()[300:500]
damaged, indices = MARDestroyer().destroy(measurements, percentage=.50)
before_misses = MissingDataFinder().find(damaged, timestep)
neighbors = windpark.get_turbines()[:-1]
reg = 'knn' # KNeighborsRegressor(10, 'uniform')
regargs = {'n' : 8, 'variant' : 'uniform'}
nseries = [t.get_measurements()[300:500] for t in neighbors]
t_hat = MRegInterpolation().interpolate(damaged, timestep=timestep,\
neighbor_series=nseries, reg=reg, regargs=regargs)
after_misses = MissingDataFinder().find(t_hat, timestep)
assert(len(after_misses) < 1)
def fun(citynum,methodnum,K):
park_id = NREL.park_id[cityname[citynum]]
windpark = NREL().get_windpark(park_id, 10, 2004,2006)
pla=[]
kk=windpark.get_turbines()
for i in range(len(kk)):
pla.append(kk[i].idx)
feature_window, horizon = 3, 3
mapping = PowerMapping()
data_1 = np.array(mapping.get_features_park(windpark, feature_window, horizon))
data_train = np.array(mapping.get_features_park(windpark, 1, 1))
lendata=len(data_1)
data1 = data_1[:lendata:3]
l1=len(data_train)
data_train1=data_train[:l1:3]
half=int(math.floor(len(data1) * 0.5))
traindata_1=data_train1[0:half,:]
traindata1=np.transpose(traindata_1)
traindata1=preprocessing.scale(np.array(traindata1),with_mean=True,with_std=True)
if methodnum==0:
ans = KMeans(n_clusters=K, random_state=0).fit(traindata1).predict(traindata1)
if methodnum==1:
ans = SpectralClustering(n_clusters=K, random_state=0).fit_predict(traindata1)
if methodnum==2:
ans = AgglomerativeClustering(n_clusters=K).fit_predict(traindata1)
if methodnum==3:
ans = Birch(n_clusters=K).fit_predict(traindata1)
if methodnum==4:
ans = DBSCAN(eps = 0.1).fit_predict(traindata1)
fo = open('cluster10/'+cityname[citynum]+method[methodnum]+str(K)+'.csv','w', newline='')
csv_write = csv.writer(fo,dialect='excel')
for i in range(len(ans)):
cc=[];
cc.append(pla[i])
cc.append(ans[i])
csv_write.writerow(cc)
fo.close()
def test_topological_interpolation(self):
park_id = NREL.park_id['tehachapi']
windpark = NREL().get_windpark(park_id, 10, 2004)
target = windpark.get_target()
timestep = 600
measurements = target.get_measurements()[300:500]
damaged, indices = NMARDestroyer().destroy(measurements, percentage=.80,\
min_length=10, max_length=100)
tloc = (target.longitude, target.latitude)
neighbors = windpark.get_turbines()[:-1]
nseries = [t.get_measurements()[300:500] for t in neighbors]
nlocs = [(t.longitude, t.latitude) for t in neighbors]
t_hat = TopologicInterpolation().interpolate(\
damaged, method="topologic",\
timestep=timestep, location=tloc,\
neighbor_series = nseries,\
neighbor_locations = nlocs)
misses = MissingDataFinder().find(t_hat, timestep)
assert(measurements.shape[0] == t_hat.shape[0])
assert(len(misses) < 1)
import numpy as np
import matplotlib.pyplot as plt
import math
import time
import csv
from windml.datasets.nrel import NREL
from windml.mapping.power_mapping import PowerMapping
from sklearn import preprocessing
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
start = time.clock()
park_id = NREL.park_id['cheyenne']
windpark = NREL().get_windpark(park_id, 5, 2004,2006)
target = windpark.get_target()
feature_window, horizon = 3, 3
mapping = PowerMapping()
data_1 = np.array(mapping.get_features_park(windpark, feature_window, horizon))
data_2 = np.array(mapping.get_labels_turbine(target, feature_window, horizon)).reshape(-1,1)
#目标多向前取feature_window个点
#data1 = np.array(mapping.get_features_park(windpark, feature_window*2, horizon))
#data2 = np.array(mapping.get_labels_turbine(target, feature_window*2, horizon)).reshape(-1,1)
#region = int(data1.shape[1]/(feature_window*2))
#for i in range(region-1):
# for j in range(feature_window):
# data1=np.delete(data1,[(i+1)*feature_window],axis = 1)
#
def test_nrel_repair(self):
ds = NREL()
target = ds.get_turbine(NREL.park_id['tehachapi'], 2004)
measurements = target.get_measurements()[:43504]
measurements = NRELRepair().repair(measurements)
assert(NRELRepair().validate(measurements))
for i in range(0, len(y_hat)):
y = YT[i]
mse_y_hat += (y_hat[i] - y)**2
mse_y_hat /= float(len(y_hat))
return mse_y_hat
# generating destroyed measurements which are constant over all
# methods
data = []
for park in parks.keys():
windpark = NREL().get_windpark_nearest(parks[park], 5, 2004)
windpark_test = NREL().get_windpark_nearest(parks[park], 5, 2005)
target = windpark.get_target()
measurements = repair_nrel(target.get_measurements()[:10000])
for i in range(2):
damaged_series = {}
de = lambda rate: (rate, (destroy(
measurements, method=destroy_method, percentage=rate)[0]))
dseries = map(de, rates)
for rate, series in dseries:
damaged_series[rate] = series
citynum = 4
methodnum = 3
target_idx = NREL.park_id[cityname[citynum]]
year_from, year_to = 2004, 2006
if sys.version_info < (3, ):
mode = 'rU'
else:
mode = 'r'
csvfile = 'cluster/' + method[methodnum] + '200.csv'
pick = []
with open(csvfile, mode) as csv_arch:
reader = csv.reader(csv_arch, delimiter=',')
for row in reader:
pick.append(int(row[0]))
nrel = NREL()
d = 0
turbines = nrel.fetch_nrel_meta_data_all()
result = Windpark(target_idx, 0)
for row in turbines:
turbine_index = np.int(row[0])
if (turbine_index != target_idx):
if (pick[turbine_index - 1] == pick[target_idx - 1]):
d = d + 1
newturbine = Turbine(row[0], row[1], row[2], row[3], row[4],
row[5], row[6])
for y in range(year_from, year_to + 1):
measurement = nrel.fetch_nrel_data(
row[0], y, ['date', 'corrected_score', 'speed'])
if y == year_from:
measurements = measurement
""" Topography of a Windpark ------------------------------------------------------------------------- This example shows the topography of a wind park near Tehachapi. The black dots illustrate the locations of turbines. The red dot is the target turbine. """ # Author: Nils A. Treiber <*****@*****.**> # License: BSD 3 clause from windml.datasets.nrel import NREL from windml.visualization.show_coord_topo import show_coord_topo radius = 30 name = 'tehachapi' windpark = NREL().get_windpark(NREL.park_id['tehachapi'], 30, 2004) print "Working on windpark around target turbine", str(windpark.get_target_idx()) print "Plotting windpark ..." title = "Some Turbines of NREL Data Set" show_coord_topo(windpark, title)
def test_get_turbine(self):
ds = NREL()
target = ds.get_turbine(NREL.park_id['tehachapi'], 2004, 2005)
t = target.get_measurements()[0]
assert (len(t) == 3)
def test_get_windpark(self):
ds = NREL()
windpark = ds.get_windpark(NREL.park_id['tehachapi'], 10, 2004, 2005)
assert (len(windpark.turbines) == 66)
-------------------------------------------------------------------------
This examples shows a statistical overview of the power levels of a wind turbine.
"""
# Author: Oliver Kramer <*****@*****.**>
# License: BSD 3 clause
import matplotlib.pyplot as plt
import numpy as np
import windml.util.features
from windml.datasets.nrel import NREL
from windml.visualization.show_coord_topo import show_coord_topo
ds = NREL()
windpark = ds.get_windpark(NREL.park_id['tehachapi'], 2, 2004)
X = np.array(windpark.get_powermatrix())
feat, month_power, ramps_up, ramps_down, power_freq =\
windml.util.features.compute_highlevel_features(windpark.turbines[0])
help = [
i * windml.util.features.interval_width
for i in range(1, 30 / windml.util.features.interval_width + 1)
]
labels = [
str(i - windml.util.features.interval_width) + "-" + str(i) for i in help
]
with plt.style.context("fivethirtyeight"):
# Justin P. Heinermann <*****@*****.**> # Stefan Oehmcke <*****@*****.**> # License: BSD 3 clause from __future__ import print_function import math import matplotlib.pyplot as plt from numpy import zeros, float32 from windml.datasets.nrel import NREL from windml.mapping.power_mapping import PowerMapping from sklearn.neighbors import KNeighborsRegressor from sklearn.metrics import mean_squared_error # get windpark and corresponding target. forecast is for the target turbine park_id = NREL.park_id['tehachapi'] windpark = NREL().get_windpark(park_id, 3, 2004, 2005) target = windpark.get_target() # use power mapping for pattern-label mapping. feature_window, horizon = 3, 3 mapping = PowerMapping() X = mapping.get_features_park(windpark, feature_window, horizon) y = mapping.get_labels_turbine(target, feature_window, horizon) # train roughly for the year 2004, test roughly for the year 2005. train_to, test_to = int(math.floor(len(X) * 0.5)), len(X) # train and test only every fifth pattern, for performance. train_step, test_step = 5, 5 X_train = X[:train_to:train_step] y_train = y[:train_to:train_step] X_test = X[train_to:test_to:test_step]
def setUpClass(cls):
ds = NREL()
cls.turbine = ds.get_turbine(NREL.park_id['tehachapi'], 2004)
cls.windpark = ds.get_windpark(NREL.park_id['tehachapi'], 3, 2004)