for group in range(0,5):
print("Test group " + str(group + 1))
trainStationList = []
testStationList = []
for i in range(0,5):
if i == group:
testStationList.extend(groups[i])
else:
trainStationList.extend(groups[i])
trainStations = set(float(station) for station in trainStationList)
testStations = set(float(station) for station in testStationList)
trainX, testX, trainY, testY = splitDataForXValidation(trainStations, testStations, "location", data, features_TW, "target")
print("\tTW #train: " + str(len(trainY)) + ", #test:" + str(len(testY)))
model = RandomForestRegressor(min_samples_leaf = 9, n_estimators = 59, n_jobs = -1, random_state=42)
model.fit(trainX, trainY)
prediction = model.predict(testX)
rmse = rmseEval(testY, prediction)[1]
print("\trmse: " + str(rmse))
dataDict[str(group) + "_obs"] = testY
ae = []
for i in range(0, len(testY)):
ae.append(abs(testY[i] - prediction[i]))
dataDict[str(group) + "_ae_tw"] = ae
rmseDict[str(group) + "_ae_tw"] = rmse
trainX, testX, trainY, testY = splitDataForXValidation(trainStations, testStations, "location", data, features_TWA, "target")
print("\tTWA #train: " + str(len(trainY)) + ", #test:" + str(len(testY)))
for i in range(0, 5):
if i == group:
testStationList.extend(groups[i])
else:
trainStationList.extend(groups[i])
trainStations = set(float(station) for station in trainStationList)
# reorder train stations
log(output_log, "\ttrainStationList:" + str(trainStationList))
trainStationList = [s for s in all_stations if float(s) in trainStations]
log(output_log, "\ttrainStationList:" + str(trainStationList))
testStations = set(float(station) for station in testStationList)
trainX, testX, trainY, testY = splitDataForXValidation(
trainStations, testStations, "location", data, features_TW, "target")
log(output_log,
"\tTW #train: " + str(len(trainY)) + ", #test:" + str(len(testY)))
model = RandomForestRegressor(min_samples_leaf=9,
n_estimators=59,
n_jobs=-1,
random_state=42)
model.fit(trainX, trainY)
prediction_TW = model.predict(testX)
rmse = rmseEval(testY, prediction_TW)[1]
log(output_log, "\trmse: " + str(rmse))
obs.extend(testY)
all_pred_TW.extend(prediction_TW)
trainX, testX, trainY, testY, trainLocation, testLocation = splitDataForXValidationWithLocation(
trainStations, testStations, "location", data, columns, "target")