def evalTrainStationTestStation(trainStation, testStation):
trainX, _, trainY, _ = splitDataForXValidation(set([trainStation]), set(),
"location",
dataByStation[trainStation],
columns, "target")
_, testX2, _, testY2 = splitDataForXValidation(set(), set([testStation]),
"location",
dataByStation[testStation],
columns, "target")
model = RandomForestRegressor(max_depth=10,
n_estimators=60,
n_jobs=-1,
random_state=42)
model.fit(trainX, trainY)
prediction = model.predict(testX2)
rmse = rmseEval(testY2, prediction)[1]
print("Training on station " + str(trainStation) +
", applying on station " + str(testStation) + ": rmse: " + str(rmse))
"timestamp", 'natural_area', 'building_count', 'leisure_area',
'landuse_area', 'lane_length', 'length', 'building_area'
], data, columns)
for iteration in range(0, 5):
print("iter_" + str(iteration))
trainStations = []
testStations = []
for i in range(0, 5):
if i == iteration:
testStations = testStations + locations_grouped[i]
else:
trainStations = trainStations + locations_grouped[i]
print("\ttrainStations: " + str(trainStations))
print("\ttestStations: " + str(testStations))
trainStationSet = set(s for s in trainStations)
testStationSet = set(s for s in testStations)
trainX, testX, trainY, testY = splitDataForXValidation(
trainStationSet, testStationSet, "location", data, columns, "target")
print("\t#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))
loc66Data = defaultdict(list)
loc51Data = defaultdict(list)
for i in range(0, len(data["location"])):
if data["location"][i] == 61.0:
for c in columns:
loc61Data[c].append(data[c][i])
if data["location"][i] == 66.0:
for c in columns:
loc66Data[c].append(data[c][i])
if data["location"][i] == 51.0:
for c in columns:
loc51Data[c].append(data[c][i])
trainX, testX, trainY, testY = splitDataForXValidation(set([61.0]), set(),
"location", loc61Data,
columns, "target")
trainX2, testX2, trainY2, testY2 = splitDataForXValidation(
set(), set([61.0]), "location", loc61Data, columns, "target")
model = RandomForestRegressor(max_depth=10,
n_estimators=60,
n_jobs=-1,
random_state=42)
model.fit(trainX, trainY)
prediction = model.predict(testX2)
rmse = rmseEval(testY2, prediction)[1]
print("Training on station 61, applying on station 61: rmse: " + str(rmse))
trainX, testX, trainY, testY = splitDataForXValidation(set([61.0]), set(),
"location", loc61Data,
columns, "target")