mistakes = mistakes + 1
counter = counter + 1
lossF = mistakes / counter
# enumerator <union>/<join> indicates an approach of next level slices combination process:
# in case of <join> in order to create new node of current level slicer
# combines only nodes of previous layer with each other
# <union> case implementation is based on DPSize algorithm
enumerator = "join"
if enumerator == "join":
slicer.process(all_features,
clf,
complete_x,
lossF,
x_size,
complete_y,
predictions,
debug=True,
alpha=6,
k=10,
w=0.5,
loss_type=1)
elif enumerator == "union":
union_slicer.process(all_features,
clf,
complete_x,
lossF,
x_size,
complete_y,
predictions,
debug=True,
alpha=6,
for item in x_test:
complete_x.append((counter, item))
complete_y.append((counter, y_test[counter]))
counter = counter + 1
x_size = counter
model = LinearRegression()
model.fit(x_train, y_train)
preds = (model.predict(x_test) - y_test)**2
f_l2 = sum(preds) / x_size
errors = []
counter = 0
for pred in preds:
errors.append((counter, pred))
counter = counter + 1
# alpha is size significance coefficient
# verbose option is for returning debug info while creating slices and printing it
# k is number of top-slices we want
# w is a weight of error function significance (1 - w) is a size significance propagated into optimization function
slicer.process(all_features,
model,
complete_x,
f_l2,
x_size,
y_test,
errors,
debug=True,
alpha=5,
k=10,
w=0.5,
loss_type=0)
for item in x:
complete_row = (counter, item)
complete_x.append(complete_row)
complete_y.append((counter, y[counter]))
counter = counter + 1
x_size = counter
# train model on a whole dataset
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.3,
random_state=0)
model = LinearRegression()
model.fit(x_train, y_train)
f_l2 = sum((model.predict(x_test) - y_test)**2) / x_size
# alpha is size significance coefficient
# verbose option is for returning debug info while creating slices and printing it
# k is number of top-slices we want
# w is a weight of error function significance (1 - w) is a size significance propagated into optimization function
slicer.process(enc,
model,
complete_x,
complete_y,
f_l2,
x_size,
x_test,
y_test,
debug=True,
alpha=4,
k=10,
w=0.5)