def evalColumns(columns):
overallY = []
overallPred = []
for location in locations:
location2s = [l for l in locations if l != location]
print("Location: " + str(location) + ", location2: " + str(location2s))
# generating testPreds
testPreds = {}
for datagroup in topDatagroups:
tag, features = getTagAndFeatures(datagroup)
trainX, testX, trainY, testY = splitDataForXValidation(location, "location", data, features, "target")
model = RandomForestRegressor(min_samples_leaf = 9, n_estimators = 59, n_jobs = -1, random_state=42)
model.fit(trainX, trainY)
prediction = model.predict(testX)
testPreds[tag] = prediction
trainPreds = defaultdict(list)
for datagroup in topDatagroups:
tag, features = getTagAndFeatures(datagroup)
print("\ttag: " + str(tag) + ", features: " + str(features))
for location2 in location2s:
trainX1, trainX2, trainY1, trainY2, testX, testY = splitDataForXValidationSampled2(location, location2, "location", data, features, "target")
model = RandomForestRegressor(min_samples_leaf = 9, n_estimators = 59, n_jobs = -1, random_state=42)
model.fit(trainX1, trainY1)
train1Prediction = model.predict(trainX1)
train2Prediction = model.predict(trainX2)
testPrediction = model.predict(testX)
train1Rmse = str(rmseEval(trainY1, train1Prediction)[1])
train2Rmse = str(rmseEval(trainY2, train2Prediction)[1])
testRmse = str(rmseEval(testY, testPrediction)[1])
print("\t\ttrain1 rmse: " + train1Rmse)
print("\t\ttrain2 rmse: " + train2Rmse)
print("\t\ttest rmse: " + testRmse)
for x in train2Prediction:
trainPreds[tag].append(x)
# get combined train2y
combinedTrain2Y = []
for location2 in location2s:
trainX1, trainX2, trainY1, trainY2, testX, testY = splitDataForXValidationSampled2(location, location2, "location", data, all_features, "target")
combinedTrain2Y = combinedTrain2Y + trainY2
# calculate labels
labelTrain2Y = []
for i in range(0, len(combinedTrain2Y)):
bestModel = 0
bestAbs = abs(combinedTrain2Y[i] - trainPreds[topTags[0]][i])
for j in range(0, len(topTags)):
tag = topTags[j]
modelAbs = abs(combinedTrain2Y[i] - trainPreds[tag][i])
if modelAbs < bestAbs:
bestAbs = modelAbs
bestModel = j
labelTrain2Y.append(bestModel)
# generating testX
_, testX, _, _ = splitDataForXValidation(location, "location", data, all_features, "target")
# trainX2
tX2 = []
for location2 in location2s:
_, trainX2, _, _, _, _ = splitDataForXValidationSampled2(location, location2, "location", data, all_features, "target")
for row in trainX2:
tX2.append(row)
for tag in topTags:
for i in range(0, len(trainPreds[tag])):
tX2[i].append(trainPreds[tag][i])
reducedTrainX2 = []
for d in tX2:
reducedD = []
for i in range(0, len(all_columns)):
if columns[i]:
reducedD.append(d[i])
reducedTrainX2.append(reducedD)
model = RandomForestClassifier(random_state=42, n_estimators=100, max_depth=15)
model.fit(reducedTrainX2, labelTrain2Y)
for tag in topTags:
for i in range(0, len(testPreds[tag])):
testX[i].append(testPreds[tag][i])
reducedTestX = []
for d in testX:
reducedD = []
for i in range(0, len(all_columns)):
if columns[i]:
reducedD.append(d[i])
reducedTestX.append(reducedD)
pred = model.predict(reducedTestX)
finalPrediction = []
for i in range(0, len(testY)):
p = testPreds[topTags[pred[i]]][i]
finalPrediction.append(p)
rmse = str(rmseEval(testY, finalPrediction)[1])
print("\tRMSE: " + str(rmse))
for x in testY:
overallY.append(x)
for x in finalPrediction:
overallPred.append(x)
rmse = rmseEval(overallPred, overallY)[1]
return rmse
pred.append(prediction_twa[i])
return pred
allObservations = []
allPredictions = []
allPredictionsTW = []
allPredictionsTWA = []
for location in locations:
location2s = [l for l in locations if l != location]
log("Location: " + str(location) + ", location2: " + str(location2s))
# tw_4stations
trainX, testX, trainY, testY = splitDataForXValidation(
location, "location", data, tw_features, "target")
allObservations.extend(testY)
model = create_model()
model.fit(trainX, trainY)
predictionTW = model.predict(testX)
rmse = rmseEval(testY, predictionTW)[1]
log("\tTW:" + str(rmse))
allPredictionsTW.extend(predictionTW)
# tw_4stations
trainX, testX, trainY, testY = splitDataForXValidation(
location, "location", data, twa_features, "target")
model = create_model()
model.fit(trainX, trainY)
predictionTWA = model.predict(testX)
rmse = rmseEval(testY, predictionTWA)[1]
for datagroup in data_groups:
dgtag, _ = getTagAndFeatures(datagroup)
if dgtag == tag:
top10datagroups.append(datagroup)
break
for location in locations:
location2 = [l for l in locations if l != location][0]
print("Location: " + str(location) + ", location2: " + str(location2))
# generating testPreds
testPreds = {}
for datagroup in top10datagroups:
tag, features = getTagAndFeatures(datagroup)
trainX, testX, trainY, testY = splitDataForXValidation(
location, "location", data, features, "target")
model = RandomForestRegressor(min_samples_leaf=9,
n_estimators=59,
n_jobs=-1,
random_state=42)
model.fit(trainX, trainY)
prediction = model.predict(testX)
testPreds[tag] = prediction
trainPreds = {}
t2Y = None
tY = None
for datagroup in top10datagroups:
tag, features = getTagAndFeatures(datagroup)
locations = [2.0, 3.0, 4.0, 6.0, 8.0]
data = {}
columns = ['timestamp', 'location']
loadData(DATA_FILE, [], data, columns)
columnsTW = [
'hour', 'day_of_week', 'month', 'bank_holiday', 'race_day',
'winddirection', 'windspeed', 'temperature', 'rain', 'pressure'
]
for location in locations:
print("location: " + str(location))
# save down trainX, trainY, testX, testY
trainX, testX, trainY, testY = splitDataForXValidation(
location, "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)
testPrediction = model.predict(testX)
testRmse = str(rmseEval(testY, testPrediction)[1])
print("\tRFR+All rmse: " + str(testRmse))
trainX, testX, trainY, testY = splitDataForXValidation(
location, "location", data, columnsTW, "target")
print("\t#train: " + str(len(trainY)) + ", #test:" + str(len(testY)))
model = RandomForestRegressor(min_samples_leaf=9,
n_estimators=59,
def eval_one(step):
eval_features = []
for i in range(0, len(all_features)):
if step[i]:
eval_features.append(all_features[i])
allObservations = []
allPredictions = []
allPredictionsTW = []
allPredictionsTWA = []
allLabel = []
allLabelPrediction = []
for location in locations:
location2s = [l for l in locations if l != location]
# tw_4stations
trainX, testX, trainY, testY = splitDataForXValidation(
location, "location", data, tw_features, "target")
allObservations.extend(testY)
model = create_model()
model.fit(trainX, trainY)
predictionTW = model.predict(testX)
allPredictionsTW.extend(predictionTW)
# tw_4stations
trainX, testX, trainY, testY = splitDataForXValidation(
location, "location", data, twa_features, "target")
model = create_model()
model.fit(trainX, trainY)
predictionTWA = model.predict(testX)
allPredictionsTWA.extend(predictionTWA)
#combination
classifier_X = []
classifier_Y = []
for loc in location2s:
# tw_3stations
trainX, testX, trainY, testY = splitDataForXValidationForCombination(
loc, location, "location", data, tw_features, "target")
model = create_model()
model.fit(trainX, trainY)
prediction_3station_TW = model.predict(testX)
# twa_3stations
trainX, testX, trainY, testY = splitDataForXValidationForCombination(
loc, location, "location", data, twa_features, "target")
model = create_model()
model.fit(trainX, trainY)
prediction_3station_TWA = model.predict(testX)
trainX, testX, trainY, testY = splitDataForXValidationForCombination(
loc, location, "location", data, eval_features, "target")
classifier_X.extend(testX)
label = generate_label(testY, prediction_3station_TW,
prediction_3station_TWA)
classifier_Y.extend(label)
model = create_classifier_model()
model.fit(classifier_X, classifier_Y)
_, testX, _, testY = splitDataForXValidation(location, "location",
data, eval_features,
"target")
classifier_prediction = model.predict(testX)
classifier_testLabel = generate_label(testY, predictionTW,
predictionTWA)
allLabel.extend(classifier_testLabel)
allLabelPrediction.extend(classifier_prediction)
combined_prediction = generate_combined_prediction(
classifier_prediction, predictionTW, predictionTWA)
allPredictions.extend(combined_prediction)
rmse = rmseEval(allObservations, allPredictions)[1]
accuracy = calculate_accuracy(allLabel, allLabelPrediction)
return rmse, accuracy