# 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 # with reconstruction def run(pars): method, rate = pars mse = experiment(method, windpark, windpark_test, damaged_series[rate], rate) return method, rate, mse results = map(run, list(chain(product(methods, rates))))
error, var, std = scores(measurements, reconstructed) return error, var, std # generating destroyed measurements which are constant over all # methods data = [] park = 'reno' windpark = NREL().get_windpark_nearest(parks[park], 5, 2004) 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 def run(pars): method, rate = pars error, var, std = experiment(method, windpark, damaged_series[rate], rate) return method, rate, error, var, std results = map(run, list(chain(product(methods, rates)))) encoding = lambda method, rate, error, park, var, std :\ {"method": method,\ "rate": rate,\ "rmse": error,\
from windml.preprocessing.preprocessing import interpolate from windml.visualization.plot_timeseries import plot_timeseries import matplotlib.pyplot as plt import matplotlib.dates as md from pylab import * from numpy import array, zeros, float32, int32 # 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) target = windpark.get_target() measurements = target.get_measurements()[300:1000] damaged, indices = destroy(measurements, method="nmar", percentage=.80,\ min_length=10, max_length=100) neighbors = windpark.get_turbines()[:-1] nseries = [t.get_measurements()[300:1000] for t in neighbors] tinterpolated = interpolate(damaged, method='mreg',\ timestep=600,\ neighbor_series = nseries,\ reg = 'linear_model') d = array([m[0] for m in tinterpolated]) y1 = array([m[1] for m in tinterpolated]) #score y2 = array([m[2] for m in tinterpolated]) #speed d_hat = array([m[0] for m in damaged]) y1_hat = array([m[1] for m in damaged])
from sklearn.model_selection import GridSearchCV from sklearn.model_selection import KFold import matplotlib.pyplot as plt import matplotlib.dates as md from pylab import * from numpy import array, zeros, float32, int32 # get windpark and corresponding target. forecast is for the target turbine park_id = NREL.park_id['tehachapi'] windpark = NREL().get_windpark(park_id, 5, 2004) target = windpark.get_target() measurements = target.get_measurements()[300:1000] damaged, indices = destroy(measurements, method='nmar', percentage=.80,\ min_length=10, max_length=100) neighbors = windpark.get_turbines()[:-1] nseries = [t.get_measurements()[300:1000] for t in neighbors] gamma_range = [0.0001, 0.000001] C_range = [2**i for i in range(-3, 5, 1)] regargs = { "epsilon": 0.1, "cv_method": "kfold", "cv_args": { "k_folds": 10 }, "kernel": 'rbf', "tuned_parameters": [{ 'kernel': ['rbf'],
# License: BSD 3 clause from windml.datasets.nrel import NREL from windml.visualization.plot_timeseries import plot_timeseries from windml.preprocessing.preprocessing import destroy import matplotlib.pyplot as plt import matplotlib.dates as md from pylab import * from numpy import array ds = NREL() turbine = ds.get_turbine(NREL.park_id['tehachapi'], 2004) measurements = turbine.get_measurements()[:1000] damaged, indices = destroy(measurements, method='mar', percentage=.80) d = array([m[0] for m in measurements]) y1 = array([m[1] for m in measurements]) #score y2 = array([m[2] for m in measurements]) #speed d_hat = array([m[0] for m in damaged]) y1_hat = array([m[1] for m in damaged]) y2_hat = array([m[2] for m in damaged]) d_time = [] for i in range (len(d)): d_act = datetime.datetime.fromtimestamp(d[i]) d_time.append(d_act) d_time_hat = []
# License: BSD 3 clause from windml.datasets.nrel import NREL from windml.visualization.plot_timeseries import plot_timeseries from windml.preprocessing.preprocessing import destroy import matplotlib.pyplot as plt import matplotlib.dates as md from pylab import * from numpy import array ds = NREL() turbine = ds.get_turbine(NREL.park_id['tehachapi'], 2004) measurements = turbine.get_measurements()[:1000] damaged, indices = destroy(measurements, method='mar', percentage=.80) d = array([m[0] for m in measurements]) y1 = array([m[1] for m in measurements]) #score y2 = array([m[2] for m in measurements]) #speed d_hat = array([m[0] for m in damaged]) y1_hat = array([m[1] for m in damaged]) y2_hat = array([m[2] for m in damaged]) d_time = [] for i in range(len(d)): d_act = datetime.datetime.fromtimestamp(d[i]) d_time.append(d_act) d_time_hat = []