def test_hyper_dt(self):
rs = RandomSearcher(
mini_dt_space,
optimize_direction=OptimizeDirection.Maximize,
)
hdt = HyperDT(rs,
callbacks=[SummaryCallback()],
reward_metric='accuracy',
dnn_params={
'hidden_units': ((256, 0, False), (256, 0, False)),
'dnn_activation': 'relu',
},
cache_preprocessed_data=True,
cache_home=homedir + '/cache')
x1 = np.random.randint(0, 10, size=(100), dtype='int')
x2 = np.random.randint(0, 2, size=(100)).astype('str')
x3 = np.random.randint(0, 2, size=(100)).astype('str')
x4 = np.random.normal(0.0, 1.0, size=(100))
y = np.random.randint(0, 2, size=(100), dtype='int')
df = pd.DataFrame({'x1': x1, 'x2': x2, 'x3': x3, 'x4': x4})
hdt.search(df, y, df, y, max_trails=3, epochs=1)
best_trial = hdt.get_best_trail()
estimator = hdt.final_train(best_trial.space_sample, df, y, epochs=1)
score = estimator.predict(df)
result = estimator.evaluate(df, y)
assert len(score) == 100
assert result
assert isinstance(estimator.model, DeepTable)
def test_boston(self):
print("Loading datasets...")
boston_dataset = load_boston()
df_train = pd.DataFrame(boston_dataset.data)
df_train.columns = boston_dataset.feature_names
self.y = pd.Series(boston_dataset.target)
self.X = df_train
self.X_train, \
self.X_test, \
self.y_train, \
self.y_test = train_test_split(self.X, self.y, test_size=0.2, random_state=42)
rs = RandomSearcher(
mini_dt_space,
optimize_direction=OptimizeDirection.Maximize,
)
hdt = HyperDT(
rs,
callbacks=[
SummaryCallback(),
FileLoggingCallback(rs, output_dir=f'hotexamples_com/hyn_logs')
],
reward_metric='RootMeanSquaredError',
dnn_params={
'hidden_units': ((256, 0, False), (256, 0, False)),
'dnn_activation': 'relu',
},
)
hdt.search(self.X_train,
self.y_train,
self.X_test,
self.y_test,
max_trails=3)
best_trial = hdt.get_best_trail()
estimator = hdt.final_train(best_trial.space_sample, self.X, self.y)
score = estimator.predict(self.X_test)
result = estimator.evaluate(self.X_test, self.y_test)
assert result
assert isinstance(estimator.model, DeepTable)
def bankdata(self):
rs = RandomSearcher(
mini_dt_space,
optimize_direction=OptimizeDirection.Maximize,
)
hdt = HyperDT(
rs,
callbacks=[
SummaryCallback(),
FileLoggingCallback(rs, output_dir=f'hotexamples_com/hyn_logs')
],
reward_metric='accuracy',
max_trails=3,
dnn_params={
'hidden_units': ((256, 0, False), (256, 0, False)),
'dnn_activation': 'relu',
},
)
df = dsutils.load_bank()
df.drop(['id'], axis=1, inplace=True)
df_train, df_test = train_test_split(df,
test_size=0.2,
random_state=42)
y = df_train.pop('y')
y_test = df_test.pop('y')
hdt.search(df_train, y, df_test, y_test)
assert hdt.best_model
best_trial = hdt.get_best_trail()
estimator = hdt.final_train(best_trial.space_sample, df_train, y)
score = estimator.predict(df)
result = estimator.evaluate(df, y)
assert len(score) == 100
assert result
assert isinstance(estimator.model, DeepTable)
print("data shape: ")
print(df.shape)
df.drop(['id'], axis=1, inplace=True)
y = df.pop("y")
X = df
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=12)
t1 = time.time()
hdt.search(X_train, y_train, X_test, y_test, max_trails=1)
best_trial = hdt.get_best_trail()
estimator = hdt.final_train(best_trial.space_sample, X_train, y_train)
print("escaped: ")
print(time.time() - t1)
r = estimator.evaluate(X_test, y_test, metrics=['accuracy', 'auc'])
print(r)
y_score = estimator.predict_proba(X_test)
# y_pred = estimator.predict(X_test)
from sklearn.metrics import roc_curve
fpr, tpr, thresholds = roc_curve(y_test, y_score, pos_label='yes')
ks = max(tpr - fpr)
print(ks)