def initExperiment(_args):
FileHandler().createFolder("results")
resultFolder = "results/" + args.name + "/"
FileHandler().createFolder(resultFolder)
resultFile = resultFolder + "result.csv"
if _args.classification:
e = Experiment(args.classification, args.name)
models = initModels(_args, Type.CLASSIFICATION)
e.classification(models, 10)
if _args.gen_code:
exportCode(_args, resultFolder, _args.classification, models)
if _args.visualize:
files = [e.path("cv_" + str(i) + ".csv") for i in range(len(models))]
xTicks = [model.modelName for model in models]
ResultVisualizer().boxplots(files, _args.visualize, xTicks, ylabel=_args.visualize)
elif _args.correlation:
csv = CSV()
csv.load(args.correlation)
csv.computeCorrelationMatrix(resultFile)
if _args.visualize:
ResultVisualizer().colorMap(resultFile)
elif _args.regression:
e = Experiment(args.regression, args.name)
models = initModels(_args, Type.REGRESSION)
e.regression(models, 10)
if _args.gen_code:
exportCode(_args, resultFolder, _args.regression, models)
if _args.visualize:
files = [e.path("cv_" + str(i) + ".csv") for i in range(len(models))]
xTicks = [model.modelName for model in models]
ResultVisualizer().boxplots(files, _args.visualize, xTicks, ylabel=_args.visualize)
print("[LIMITS]: results written to src/" + resultFolder)
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)
def regressionRF(_training, _trees, _depth, _file):
e = Experiment(_training, verbose=False)
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
header, result = e.regression([rf], 10)
mem = computeMemorySize(_training, rf, True)
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)
def run(self, _training, _models, _platforms):
R = ResultMatrix()
M = [];
for model in _models:
# run the cross validation to compute the model performance
M.append(model.toString())
e = Experiment(_training)
header, result = e.regression([model], 10)
R.add(header, result)
# train with the global training data and export code
training_arff = "tmp/recommend.arff"
csv = CSV()
csv.load(_training)
csv.convertToARFF(training_arff, False)
attributes = csv.findAttributes(0)
lAtt = len(attributes)-1
WEKA().train(model, training_arff, "0")
data = "\n".join(FileHandler().read("tmp/raw0.txt"))
codeFile = "recommend.c"
model.exportCode(data, csv, attributes, codeFile)
# complile platform-specific code
for platform in _platforms:
""
#print(model.toString() + " : " + platform.toString())
print(R.header, R.data)
print(M)
from models.randomforest.RandomForest import RandomForest
from experiment.Experiment import Experiment
from code.CodeGenerator import CodeGenerator
from data.CSV import CSV
from data.ResultMatrix import ResultMatrix
import numpy as np
import matplotlib.pyplot as plt
from plot.PlotTool import PlotTool
from plot.ResultVisualizer import ResultVisualizer
# define the training data set and set up the model
training = "../examples/mnoA.csv"
model = RandomForest()
model.config.trees = 10
model.config.depth = 5
# perform a 10-fold cross validation
e = Experiment(training, "example_rf_mdi")
e.regression([model], 10)
#
M = CSV(e.path("features_0.csv")).toMatrix()
M.normalizeRows()
M.sortByMean()
M.save(e.path("rf_features.csv"))
#
ResultVisualizer().barchart(e.path("rf_features.csv"), xlabel="Feature", ylabel="Relative Feature Importance", savePNG=e.path(e.id+".png"))
from models.ann.ANN import ANN
from models.m5.M5 import M5
from models.randomforest.RandomForest import RandomForest
from models.svm.SVM import SVM
from experiment.Experiment import Experiment
from plot.ResultVisualizer import ResultVisualizer
import matplotlib.pyplot as plt
# define the training data set and set up the model
training = "../examples/mnoA.csv"
models = [ANN(), M5(), RandomForest(), SVM()]
# perform a 10-fold cross validation
e = Experiment(training, "example_experiment")
e.regression(models, 10)
# visualize
files = [e.path("cv_" + str(i) + ".csv") for i in range(len(models))]
fig, axs = plt.subplots(2, 2)
fig.set_size_inches(8, 5)
xticks = [model.modelName for model in models]
ResultVisualizer().boxplots(files,
"r2",
xticks,
ylabel='R2',
fig=fig,
ax=axs[0][0],
show=False)
ResultVisualizer().boxplots(files,
"mae",