def test_gradient_boosting(n_samples=1000):
"""
Testing workability of GradientBoosting with different loss function
"""
# Generating some samples correlated with first variable
distance = 0.6
testX, testY = generate_sample(n_samples, 10, distance)
trainX, trainY = generate_sample(n_samples, 10, distance)
# We will try to get uniform distribution along this variable
uniform_features = ['column0']
loss1 = LogLossFunction()
loss2 = AdaLossFunction()
loss3 = losses.CompositeLossFunction()
loss4 = losses.KnnAdaLossFunction(uniform_features=uniform_features,
uniform_label=1)
loss5 = losses.KnnAdaLossFunction(uniform_features=uniform_features,
uniform_label=[0, 1])
loss6bin = losses.BinFlatnessLossFunction(uniform_features,
fl_coefficient=2.,
uniform_label=0)
loss7bin = losses.BinFlatnessLossFunction(uniform_features,
fl_coefficient=2.,
uniform_label=[0, 1])
loss6knn = losses.KnnFlatnessLossFunction(uniform_features,
fl_coefficient=2.,
uniform_label=1)
loss7knn = losses.KnnFlatnessLossFunction(uniform_features,
fl_coefficient=2.,
uniform_label=[0, 1])
for loss in [
loss1, loss2, loss3, loss4, loss5, loss6bin, loss7bin, loss6knn,
loss7knn
]:
clf = UGradientBoostingClassifier(loss=loss, min_samples_split=20, max_depth=5, learning_rate=0.2,
subsample=0.7, n_estimators=25, train_features=None) \
.fit(trainX[:n_samples], trainY[:n_samples])
result = clf.score(testX, testY)
assert result >= 0.7, "The quality is too poor: {} with loss: {}".format(
result, loss)
trainX['fake_request'] = numpy.random.randint(0, 4, size=len(trainX))
for loss in [
losses.MSELossFunction(),
losses.MAELossFunction(),
losses.RankBoostLossFunction(request_column='fake_request')
]:
print(loss)
clf = UGradientBoostingRegressor(loss=loss,
max_depth=3,
n_estimators=50,
learning_rate=0.01,
subsample=0.5,
train_features=list(
trainX.columns[1:]))
clf.fit(trainX, trainY)
roc_auc = roc_auc_score(testY, clf.predict(testX))
assert roc_auc >= 0.7, "The quality is too poor: {} with loss: {}".format(
roc_auc, loss)
def test_gradient_boosting(n_samples=1000):
"""
Testing workability of GradientBoosting with different loss function
"""
# Generating some samples correlated with first variable
distance = 0.6
testX, testY = generate_sample(n_samples, 10, distance)
trainX, trainY = generate_sample(n_samples, 10, distance)
# We will try to get uniform distribution along this variable
uniform_features = ['column0']
loss1 = LogLossFunction()
loss2 = AdaLossFunction()
loss3 = losses.CompositeLossFunction()
loss4 = losses.KnnAdaLossFunction(uniform_features=uniform_features, uniform_label=1)
loss5 = losses.KnnAdaLossFunction(uniform_features=uniform_features, uniform_label=[0, 1])
loss6bin = losses.BinFlatnessLossFunction(uniform_features, fl_coefficient=2., uniform_label=0)
loss7bin = losses.BinFlatnessLossFunction(uniform_features, fl_coefficient=2., uniform_label=[0, 1])
loss6knn = losses.KnnFlatnessLossFunction(uniform_features, fl_coefficient=2., uniform_label=1)
loss7knn = losses.KnnFlatnessLossFunction(uniform_features, fl_coefficient=2., uniform_label=[0, 1])
for loss in [loss1, loss2, loss3, loss4, loss5, loss6bin, loss7bin, loss6knn, loss7knn]:
clf = UGradientBoostingClassifier(loss=loss, min_samples_split=20, max_depth=5, learning_rate=0.2,
subsample=0.7, n_estimators=25, train_features=None) \
.fit(trainX[:n_samples], trainY[:n_samples])
result = clf.score(testX, testY)
assert result >= 0.7, "The quality is too poor: {} with loss: {}".format(result, loss)
trainX['fake_request'] = numpy.random.randint(0, 4, size=len(trainX))
for loss in [losses.MSELossFunction(),
losses.MAELossFunction(),
losses.RankBoostLossFunction(request_column='fake_request')]:
print(loss)
clf = UGradientBoostingRegressor(loss=loss, max_depth=3, n_estimators=50, learning_rate=0.01, subsample=0.5,
train_features=list(trainX.columns[1:]))
clf.fit(trainX, trainY)
roc_auc = roc_auc_score(testY, clf.predict(testX))
assert roc_auc >= 0.7, "The quality is too poor: {} with loss: {}".format(roc_auc, loss)
X_train = train[features]
y_train = train['signal']
X_val = test[features]
y_val = test['signal']
loss = BinFlatnessLossFunction(['mass'],
n_bins=15,
uniform_label=0,
fl_coefficient=15,
power=2)
ugbc = UGradientBoostingClassifier(loss=loss,
n_estimators=550,
max_depth=6,
learning_rate=0.15,
train_features=features,
subsample=0.7,
random_state=123)
ugbc.fit(train[features + ['mass']], train['signal'])
pred_raw = ugbc.predict(test[features])
#print(pred_raw)
pred = pd.DataFrame(data={'signal': pred_raw})
#print(pred.head(5))
#accuracy_fn(pred,y_val)
#print(pred_raw.sum())
print(((pred_raw == y_val) & y_val).sum())
print(y_val.sum())
#print(pred['signal'].sum())
#print((pred['signal']==test['signal']).sum())
