def compute_mse(regressor, param):
# get wind park and corresponding target. forecast is for the target
# wind mill
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_mill(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
from sklearn.grid_search import GridSearchCV from sklearn import linear_model # get windpark and corresponding target. forecast is for the target windmill 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 length is 3 time # steps and time horizon (forecast) is 3 time steps. feature_window = 3 horizon = 3 mapping = PowerMapping() X = mapping.get_features_park(windpark, feature_window, horizon) Y = mapping.get_labels_mill(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 # fitting the pattern-label pairs reg = linear_model.LinearRegression() 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])