def evalOne(enabledColumns):
features = [all_features[i] for i in range(0, len(all_features)) if enabledColumns[i]]
Y = []
P = []
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)
# reorder train stations
# print("\ttrainStationList:" + str(trainStationList))
trainStationList = [s for s in all_stations if float(s) in trainStations]
# print("\ttrainStationList:" + str(trainStationList))
testStations = set(float(station) for station in testStationList)
# print("\ttestStationList:" + str(testStationList))
trainX, testX, trainY, testY, trainLocation, testLocation = splitDataForXValidationWithLocation(trainStations, testStations, "location", data, features, "target")
train_lower = [float(trainStationList[i]) for i in range(0, len(trainStationList)) if i < (len(trainStationList) / 2.0)]
# train_upper = [float(trainStationList[i]) for i in range(0, len(trainStationList)) if i >= (len(trainStationList) / 2.0)]
test_lower = [float(testStationList[i]) for i in range(0, len(testStationList)) if i < (len(testStationList) / 2.0)]
# test_upper = [float(testStationList[i]) for i in range(0, len(testStationList)) if i >= (len(testStationList) / 2.0)]
trainY = []
for l in trainLocation:
if l in train_lower:
trainY.append(0)
else:
trainY.append(1)
testY = []
for l in testLocation:
if l in test_lower:
testY.append(0)
else:
testY.append(1)
model = RandomForestClassifier(random_state=42, n_estimators=20, max_depth=9, n_jobs=-1)
model.fit(trainX, trainY)
predY = model.predict(testX)
Y.extend(testY)
P.extend(predY)
f1 = f1_score(Y, P)
accuracy = accuracy_score(Y, P)
return f1, accuracy
if i == group:
testStationList.extend(groups[i])
else:
trainStationList.extend(groups[i])
trainStations = set(float(station) for station in trainStationList)
# reorder train stations
print("\ttrainStationList:" + str(trainStationList))
trainStationList = [s for s in all_stations if float(s) in trainStations]
print("\ttrainStationList:" + str(trainStationList))
testStations = set(float(station) for station in testStationList)
print("\ttestStationList:" + str(testStationList))
trainX, testX, trainY, testY, trainLocation, testLocation = splitDataForXValidationWithLocation(trainStations, testStations, "location", data, columns, "target")
train_lower = [float(trainStationList[i]) for i in range(0, len(trainStationList)) if i < (len(trainStationList) / 2.0)]
train_upper = [float(trainStationList[i]) for i in range(0, len(trainStationList)) if i >= (len(trainStationList) / 2.0)]
test_lower = [float(testStationList[i]) for i in range(0, len(testStationList)) if i < (len(testStationList) / 2.0)]
test_upper = [float(testStationList[i]) for i in range(0, len(testStationList)) if i >= (len(testStationList) / 2.0)]
trainY = []
for l in trainLocation:
if l in train_lower:
trainY.append(0)
else:
trainY.append(1)
testY = []