# std = np.std([tree.feature_importances_ for tree in model.model.estimators_],
# axis=0)
# indices = np.argsort(importances)[::-1]
# print("Feature ranking:")
# for f in range(0,len(model.modelColumns)):
# print(model.modelColumns[indices[f]] + " -> " + str(importances[indices[f]]))
end = time.time()
print(end - start)
# load apply data
dataFile2 = "/media/sf_lur/data/grid_hour.csv"
data2 = {}
columns2 = []
loadData(dataFile2, [], data2, columns2)
start = time.time()
predictionData = applyRandomForest(data2, model, {'estimators': 59, 'leaf': 9})
end = time.time()
print(end - start)
output = open("/media/sf_lur/data/apply_grid.csv", 'w')
output.write("location,timestamp,prediction\n")
for i in range(0, len(predictionData)):
output.write(str(int(data2["location"][i])) + "," + str(int(data2["timestamp"][i])) + "," + str(predictionData[i]))
output.write("\n")
output.close()
outputColumns = []
for v in values:
sName = stationNames[str(v)]
print("location: " + str(v) + " -> " + sName)
trainData, testData = splitDataForXValidation(v, "location", data)
trainColumns = []
for c in trainData:
if c != "target":
trainColumns.append(c)
model = trainRandomForest(trainData, trainColumns, "target", {
'estimators': 59,
'leaf': 9
})
predictionData = applyRandomForest(testData, model, 0)
rae = raeEval(testData["target"], predictionData)
print(str(len(rae[1])))
print(str(len(predictionData)))
print(str(len(testData["target"])))
# write header
if len(outputColumns) == 0:
outputColumns = deepcopy(trainColumns)
for c in outputColumns:
output.write(c)
output.write(",")
output.write("error_rae\n")
for i in range(0, len(testData["target"])):
for c in outputColumns: