def regressionRF(_training, _trees, _depth, _file, _resultFolder,
_discretization):
csv = CSV(training)
attributes = csv.findAttributes(0)
R = ResultMatrix()
for numTrees in range(1, _trees + 1):
for depth in range(1, _depth + 1):
rf = RandomForest()
rf.config.trees = numTrees
rf.config.depth = depth
# perform a cross validation to generate the training/test files
e = Experiment(_training,
"example_rf_sweet_spot_disc",
verbose=False)
e.regression([rf], 10)
#
r, c = CodeEvaluator().crossValidation(rf, _training, attributes,
e.tmp(), _discretization)
result = np.hstack([r.data.mean(0), r.data.std(0)])
header = r.header + [x + "_std" for x in r.header]
mem = computeMemorySize(_training, rf, _resultFolder,
_discretization)
header += ["arduino", "msp", "esp"]
result = np.hstack([result, mem])
print([
"#trees=" + str(numTrees) + "/" + str(_trees) + " depth=" +
str(depth) + "/" + str(_depth) + ' mem=', mem
],
flush=True)
R.add(header, result)
R.save(_file)
from plot.ResultVisualizer import ResultVisualizer
# define the training data set and set up the model
training = "../examples/mnoA.csv"
model = ANN()
# perform a 10-fold cross validation
e = Experiment(training, "example_ann_feature_importance")
e.regression([model], 10)
#
M = ResultMatrix()
csv = CSV(training)
attributes = csv.findAttributes(0)
for i in range(10):
training = e.tmp() + "training_mnoA_" + str(i) + ".csv"
data = "\n".join(FileHandler().read(e.tmp() + "raw0_" + str(i) + ".txt"))
ANN_WEKA(model).initModel(data, csv, attributes, training)
M.add(csv.header[1:], model.computeInputLayerRanking())
M.normalizeRows()
M.sortByMean()
M.save(e.path("ann_features.csv"))
#
ResultVisualizer().barchart(e.path("ann_features.csv"),
xlabel="Feature",
ylabel="Relative Feature Importance",
savePNG=e.path(e.id + ".png"))
from code.CodeGenerator import CodeGenerator
from code.CodeEvaluator import CodeEvaluator
from data.FileHandler import FileHandler
from data.ResultMatrix import ResultMatrix
# define the training data set and set up the model
training = "../examples/mnoA.csv"
model = RandomForest()
model.config.trees = 10
model.config.depth = 10
csv = CSV(training)
attributes = csv.findAttributes(0)
# perform a 10-fold cross validation
e = Experiment(training, "example_model_reapplication")
e.regression([model], 10)
#
ce = CodeEvaluator()
R, C = ce.crossValidation(model, training, attributes, e.tmp())
R.printAggregated()
#
ResultVisualizer().scatter(
[e.tmp() + "predictions_" + str(i) + ".csv" for i in range(10)],
"prediction",
"label",
xlabel='Predicted Data Rate [MBit/s]',
ylabel='Measured Data Rate [MBit/s',
savePNG=e.path("example_model_reapplication.png"))
from data.CSV import CSV
# define the training data set and set up the model
training = "../examples/mnoA.csv"
training = "../examples/vehicleClassification.csv"
csv = CSV(training)
attributes = csv.findAttributes(0)
d = csv.discretizeData()
model = RandomForest()
model.config.trees = 10
model.config.depth = 5
# perform a 10-fold cross validation
e = Experiment(training, "example_rf_disc")
e.classification([model], 10)
# export the C++ code
CodeGenerator().export(training, model, e.path("rf.cpp"), d)
#
ce = CodeEvaluator()
R, C = ce.crossValidation(model, training, attributes, e.tmp(), d)
R.printAggregated()
# all results are written to results/example_rf_disc/
# define the training data set and set up the model
training = "../examples/mnoA.csv"
model = SVM()
# perform a 10-fold cross validation
e = Experiment(training, "example_svm_feature_importance")
e.regression([model], 10)
csv = CSV(training)
attributes = csv.findAttributes(0)
features = csv.header[1:]
#
for i in range(10):
training = e.tmp() + "training_mnoA_" + str(i) + ".csv"
data = "\n".join(FileHandler().read(e.tmp() + "raw0_" + str(i) + ".txt"))
SVM_WEKA(model).initModel(data, csv, attributes, training)
model.exportWeights(csv.header[1:],
e.tmp() + "svm_features_" + str(i) + ".csv")
#
M = ResultMatrix()
for i in range(10):
csv = CSV(e.tmp() + "svm_features_" + str(i) + ".csv")
D = csv.data[0].split(",")
M.add(csv.header, np.array([abs(float(x)) for x in D]))
M.normalizeRows()
M.sortByMean()
from models.randomforest.RandomForest import RandomForest from weka.models.RandomForest import RandomForest as RandomForest_WEKA from experiment.Experiment import Experiment from data.CSV import CSV from code.CodeGenerator import CodeGenerator from data.FileHandler import FileHandler # define the training data set and set up the model training = "../examples/vehicleClassification.csv" model = RandomForest() model.config.depth = 7 # perform a 10-fold cross validation e = Experiment(training, "example_rf") e.classification([model], 10) # csv = CSV() csv.load(training) attributes = csv.findAttributes(0) data = "\n".join(FileHandler().read(e.tmp() + "raw0_0.txt")) RandomForest_WEKA(model).initModel(data, attributes) model.exportEps(model.depth+1, 10, 10, len(attributes)-1)