def main(config="../../config.yaml", param="./gbdt_config_reg.yaml"):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
print('config is {}'.format(config))
if isinstance(config, str):
config = JobConfig.load_from_file(config)
data_base_dir = config["data_base_dir"]
print('data base dir is', data_base_dir)
else:
data_base_dir = config.data_base_dir
# prepare data
df_guest = pd.read_csv(os.path.join(data_base_dir, data_guest),
index_col=idx)
df_host = pd.read_csv(os.path.join(data_base_dir, data_host),
index_col=idx)
df = df_guest.join(df_host, rsuffix='host')
y = df[label_name]
X = df.drop(label_name, axis=1)
clf = GradientBoostingRegressor(random_state=0, n_estimators=50)
clf.fit(X, y)
y_predict = clf.predict(X)
result = {"mean_absolute_error": mean_absolute_error(y, y_predict)}
print(result)
return {}, result
def main(config="../../config.yaml", param="./lr_config.yaml"):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
assert isinstance(param, dict)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
if isinstance(config, str):
config = JobConfig.load_from_file(config)
data_base_dir = config["data_base_dir"]
else:
data_base_dir = config.data_base_dir
config_param = {
"penalty": param["penalty"],
"max_iter": 100,
"alpha": param["alpha"],
"learning_rate": "optimal",
"eta0": param["learning_rate"]
}
# prepare data
df_guest = pandas.read_csv(os.path.join(data_base_dir, data_guest),
index_col=idx)
df_host = pandas.read_csv(os.path.join(data_base_dir, data_host),
index_col=idx)
# df_test = pandas.read_csv(data_test, index_col=idx)
df = pandas.concat([df_guest, df_host], axis=0)
# df = df_guest.join(df_host, rsuffix="host")
y_train = df[label_name]
x_train = df.drop(label_name, axis=1)
# y_test = df_test[label_name]
# x_test = df_test.drop(label_name, axis=1)
x_test, y_test = x_train, y_train
# lm = LogisticRegression(max_iter=20)
lm = SGDClassifier(loss="log", **config_param)
lm_fit = lm.fit(x_train, y_train)
y_pred = lm_fit.predict(x_test)
acc = accuracy_score(y_test, y_pred)
result = {"accuracy": acc}
print('multi result', result)
return {}, result
def main(config="../../config.yaml", param="./hetero_nn_breast_config.yaml"):
if isinstance(config, str):
config = JobConfig.load_from_file(config)
data_base_dir = config["data_base_dir"]
else:
data_base_dir = config.data_base_dir
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
# prepare data
Xb = pandas.read_csv(os.path.join(data_base_dir, data_guest),
index_col=idx)
Xa = pandas.read_csv(os.path.join(data_base_dir, data_host), index_col=idx)
y = Xb[label_name]
if param["loss"] == "categorical_crossentropy":
labels = y.copy()
label_encoder = LabelEncoder()
y = label_encoder.fit_transform(y)
y = to_categorical(y)
Xb = Xb.drop(label_name, axis=1)
model = build(param, Xb.shape[1], Xa.shape[1])
model.fit([Xb, Xa],
y,
epochs=param["epochs"],
verbose=0,
batch_size=param["batch_size"],
shuffle=True)
eval_result = {}
for metric in param["metrics"]:
if metric.lower() == "auc":
predict_y = model.predict([Xb, Xa])
auc = metrics.roc_auc_score(y, predict_y)
eval_result["auc"] = auc
elif metric == "accuracy":
predict_y = np.argmax(model.predict([Xb, Xa]), axis=1)
predict_y = label_encoder.inverse_transform(predict_y)
acc = metrics.accuracy_score(y_true=labels, y_pred=predict_y)
eval_result["accuracy"] = acc
print(eval_result)
data_summary = {}
return data_summary, eval_result
def main(config="../../config.yaml", param="param_conf.yaml"):
if isinstance(param, str):
param = JobConfig.load_from_file(param)
if isinstance(config, str):
config = JobConfig.load_from_file(config)
data_base_dir = config["data_base_dir"]
else:
data_base_dir = config.data_base_dir
epoch = param["epoch"]
lr = param["lr"]
batch_size = param.get("batch_size", -1)
optimizer_name = param.get("optimizer", "Adam")
loss = param.get("loss", "categorical_crossentropy")
metrics = param.get("metrics", ["accuracy"])
layers = param["layers"]
is_multy = param["is_multy"]
data = dataset[param.get("dataset", "vehicle")]
model = Sequential()
for layer_config in layers:
layer = getattr(tensorflow.keras.layers, layer_config["name"])
layer_params = layer_config["params"]
model.add(layer(**layer_params))
model.compile(
optimizer=getattr(optimizers, optimizer_name)(learning_rate=lr),
loss=loss,
metrics=metrics,
)
data_path = pathlib.Path(data_base_dir)
data_with_label = pandas.concat([
pandas.read_csv(data_path.joinpath(data["guest"]), index_col=0),
pandas.read_csv(data_path.joinpath(data["host"]), index_col=0),
]).values
data = data_with_label[:, 1:]
if is_multy:
labels = to_categorical(data_with_label[:, 0])
else:
labels = data_with_label[:, 0]
if batch_size < 0:
batch_size = len(data_with_label)
model.fit(data, labels, epochs=epoch, batch_size=batch_size)
evaluate = model.evaluate(data, labels)
metric_summary = {"accuracy": evaluate[1]}
data_summary = {}
return data_summary, metric_summary
def main(param=""):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
data_test = param["data_test"]
idx = param["idx"]
label_name = param["label_name"]
# prepare data
# prepare data
df_guest = pd.read_csv(data_guest, index_col=idx)
df_host = pd.read_csv(data_host, index_col=idx)
df_test = pd.read_csv(data_test, index_col=idx)
df = pd.concat([df_guest, df_host], axis=0)
y = df[label_name]
X = df.drop(label_name, axis=1)
X_guest = df_guest.drop(label_name, axis=1)
y_guest = df_guest[label_name]
clf = GradientBoostingClassifier(
n_estimators=50,
learning_rate=0.3,
)
clf.fit(X, y)
y_pred = clf.predict(X_guest)
acc = accuracy_score(y_guest, y_pred)
result = {"accuracy": acc}
print(result)
return {}, result
def main(param="./linr_config.yaml"):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
# prepare data
df_guest = pandas.read_csv(data_guest, index_col=idx)
df_host = pandas.read_csv(data_host, index_col=idx)
df = df_guest.join(df_host, rsuffix="host")
y = df[label_name]
X = df.drop(label_name, axis=1)
lm = SGDRegressor(loss="squared_loss",
penalty=param["penalty"],
fit_intercept=True,
max_iter=param["max_iter"],
average=param["batch_size"])
lm_fit = lm.fit(X, y)
y_pred = lm_fit.predict(X)
mse = mean_squared_error(y, y_pred)
rmse = np.sqrt(mse)
r2 = r2_score(y, y_pred)
explained_var = explained_variance_score(y, y_pred)
metric_summary = {
"r2_score": r2,
"mean_squared_error": mse,
"root_mean_squared_error": rmse,
"explained_variance": explained_var
}
data_summary = {}
return data_summary, metric_summary
def main(param=""):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
# prepare data
df_guest = pd.read_csv(data_guest, index_col=idx)
df_host = pd.read_csv(data_host, index_col=idx)
df = df_guest.join(df_host, rsuffix='host')
y = df[label_name]
X = df.drop(label_name, axis=1)
clf = GradientBoostingClassifier(
random_state=0,
n_estimators=120 if 'epsilon' in data_guest else 50,
learning_rate=0.1)
clf.fit(X, y)
y_prob = clf.predict(X)
try:
auc_score = roc_auc_score(y, y_prob)
except:
print(f"no auc score available")
return
result = {"auc": auc_score}
print(result)
return {}, result
def main(param=""):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
data_test = param["data_test"]
idx = param["idx"]
label_name = param["label_name"]
# prepare data
df_guest = pd.read_csv(data_guest, index_col=idx)
df_host = pd.read_csv(data_host, index_col=idx)
df_test = pd.read_csv(data_test, index_col=idx)
df = pd.concat([df_guest, df_host], axis=0)
y = df[label_name]
X = df.drop(label_name, axis=1)
X = df.drop(label_name, axis=1)
X_guest = df_guest.drop(label_name, axis=1)
y_guest = df_guest[label_name]
clf = GradientBoostingRegressor(n_estimators=50)
clf.fit(X, y)
y_predict = clf.predict(X_guest)
result = {
"mean_squared_error": mean_squared_error(y_guest, y_predict),
"mean_absolute_error": mean_absolute_error(y_guest, y_predict)
}
print(result)
return {}, result
def main(param=""):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
# prepare data
df_guest = pd.read_csv(data_guest, index_col=idx)
df_host = pd.read_csv(data_host, index_col=idx)
df = df_guest.join(df_host, rsuffix='host')
y = df[label_name]
X = df.drop(label_name, axis=1)
clf = GradientBoostingRegressor(random_state=0,
n_estimators=50,
learning_rate=0.1)
clf.fit(X, y)
y_predict = clf.predict(X)
result = {
"mean_absolute_error": mean_absolute_error(y, y_predict),
}
print(result)
return {}, result
def main(config="../../config.yaml", param="./vechile_config.yaml"):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
assert isinstance(param, dict)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
if isinstance(config, str):
config = JobConfig.load_from_file(config)
data_base_dir = config["data_base_dir"]
else:
data_base_dir = config.data_base_dir
config_param = {
"penalty": param["penalty"],
"max_iter": param["max_iter"],
"alpha": param["alpha"],
"learning_rate": "optimal",
"eta0": param["learning_rate"],
"random_state": 105
}
# prepare data
df_guest = pandas.read_csv(os.path.join(data_base_dir, data_guest),
index_col=idx)
df_host = pandas.read_csv(os.path.join(data_base_dir, data_host),
index_col=idx)
df = df_guest.join(df_host, rsuffix="host")
y = df[label_name]
X = df.drop(label_name, axis=1)
# lm = LogisticRegression(max_iter=20)
lm = SGDClassifier(loss="log", **config_param, shuffle=False)
lm_fit = lm.fit(X, y)
y_pred = lm_fit.predict(X)
recall = recall_score(y, y_pred, average="macro")
pr = precision_score(y, y_pred, average="macro")
acc = accuracy_score(y, y_pred)
result = {"accuracy": acc}
print(result)
return {}, result
def main(config="../../config.yaml", param="./gbdt_config_binary.yaml"):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
print('config is {}'.format(config))
if isinstance(config, str):
config = JobConfig.load_from_file(config)
data_base_dir = config["data_base_dir"]
print('data base dir is', data_base_dir)
else:
data_base_dir = config.data_base_dir
# prepare data
df_guest = pd.read_csv(os.path.join(data_base_dir, data_guest),
index_col=idx)
df_host = pd.read_csv(os.path.join(data_base_dir, data_host),
index_col=idx)
df = pd.concat([df_guest, df_host], axis=0)
y = df[label_name]
X = df.drop(label_name, axis=1)
X_guest = df_guest.drop(label_name, axis=1)
y_guest = df_guest[label_name]
clf = GradientBoostingClassifier(
n_estimators=120 if 'epsilon' in data_guest else 50, learning_rate=0.1)
clf.fit(X, y)
y_prob = clf.predict(X_guest)
try:
auc_score = roc_auc_score(y_guest, y_prob)
except:
print(f"no auc score available")
return
result = {"auc": auc_score}
import time
print(result)
print(data_guest)
time.sleep(3)
return {}, result
def main(config="../../config.yaml", param="./gbdt_config_multi.yaml"):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
print('config is {}'.format(config))
if isinstance(config, str):
config = JobConfig.load_from_file(config)
data_base_dir = config["data_base_dir"]
print('data base dir is', data_base_dir)
else:
data_base_dir = config.data_base_dir
# prepare data
df_guest = pd.read_csv(os.path.join(data_base_dir, data_guest),
index_col=idx)
df_host = pd.read_csv(os.path.join(data_base_dir, data_host),
index_col=idx)
df = df_guest.join(df_host, rsuffix='host')
y = df[label_name]
X = df.drop(label_name, axis=1)
clf = GradientBoostingClassifier(random_state=0,
n_estimators=50,
learning_rate=0.3)
clf.fit(X, y)
y_pred = clf.predict(X)
try:
auc_score = roc_auc_score(y, y_pred)
except BaseException:
print(f"no auc score available")
acc = accuracy_score(y, y_pred)
result = {"accuracy": acc}
print('multi result', result)
return {}, result
def main(config="../../config.yaml", param="./gbdt_config_multi.yaml"):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
print('config is {}'.format(config))
if isinstance(config, str):
config = JobConfig.load_from_file(config)
data_base_dir = config["data_base_dir"]
print('data base dir is', data_base_dir)
else:
data_base_dir = config.data_base_dir
# prepare data
df_guest = pd.read_csv(os.path.join(data_base_dir, data_guest),
index_col=idx)
df_host = pd.read_csv(os.path.join(data_base_dir, data_host),
index_col=idx)
df = pd.concat([df_guest, df_host], axis=0)
y = df[label_name]
X = df.drop(label_name, axis=1)
X_guest = df_guest.drop(label_name, axis=1)
y_guest = df_guest[label_name]
clf = GradientBoostingClassifier(
n_estimators=50,
learning_rate=0.3,
)
clf.fit(X, y)
y_pred = clf.predict(X_guest)
acc = accuracy_score(y_guest, y_pred)
result = {"accuracy": acc}
print(result)
return {}, result
def main(param):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
assert isinstance(param, dict)
data_guest = param["data_guest"]
data_host = param["data_host"]
idx = param["idx"]
label_name = param["label_name"]
config_param = {
"penalty": param["penalty"],
"max_iter": 100,
"alpha": param["alpha"],
"learning_rate": "optimal",
"eta0": param["learning_rate"]
}
# prepare data
df_guest = pandas.read_csv(data_guest, index_col=idx)
df_host = pandas.read_csv(data_host, index_col=idx)
df = df_guest.join(df_host, rsuffix="host")
y = df[label_name]
X = df.drop(label_name, axis=1)
# x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)
x_train, x_test, y_train, y_test = X, X, y, y
# lm = LogisticRegression(max_iter=20)
lm = SGDClassifier(loss="log", **config_param)
lm_fit = lm.fit(x_train, y_train)
y_pred = lm_fit.predict(x_test)
y_prob = lm_fit.predict_proba(x_test)[:, 1]
try:
auc_score = roc_auc_score(y_test, y_prob)
except:
print(f"no auc score available")
return
recall = recall_score(y_test, y_pred, average="macro")
pr = precision_score(y_test, y_pred, average="macro")
acc = accuracy_score(y_test, y_pred)
# y_predict_proba = est.predict_proba(X_test)[:, 1]
fpr, tpr, thresholds = roc_curve(y_test, y_prob)
ks = max(tpr - fpr)
result = {"auc": auc_score, "recall": recall, "precision": pr, "accuracy": acc, "ks": ks}
print(result)
print(f"coef_: {lm_fit.coef_}, intercept_: {lm_fit.intercept_}, n_iter: {lm_fit.n_iter_}")
return {}, result
def main(param=""):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
data_guest = param["data_guest"]
data_host = param["data_host"]
data_test = param["data_test"]
idx = param["idx"]
label_name = param["label_name"]
# prepare data
df_guest = pd.read_csv(data_guest, index_col=idx)
df_host = pd.read_csv(data_host, index_col=idx)
df = pd.concat([df_guest, df_host], axis=0)
y = df[label_name]
X = df.drop(label_name, axis=1)
X_guest = df_guest.drop(label_name, axis=1)
y_guest = df_guest[label_name]
clf = GradientBoostingClassifier(
n_estimators=120 if 'epsilon' in data_guest else 50, learning_rate=0.1)
clf.fit(X, y)
y_prob = clf.predict(X_guest)
try:
auc_score = roc_auc_score(y_guest, y_prob)
except:
print(f"no auc score available")
return
result = {"auc": auc_score}
import time
print(result)
print(data_guest)
time.sleep(3)
return {}, result
def main(config="../../config.yaml", param="./lr_config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
backend = config.backend
work_mode = config.work_mode
if isinstance(param, str):
param = JobConfig.load_from_file(param)
assert isinstance(param, dict)
data_set = param.get("data_guest").split('/')[-1]
if data_set == "default_credit_hetero_guest.csv":
guest_data_table = 'default_credit_hetero_guest'
host_data_table = 'default_credit_hetero_host'
elif data_set == 'breast_hetero_guest.csv':
guest_data_table = 'breast_hetero_guest'
host_data_table = 'breast_hetero_host'
elif data_set == 'give_credit_hetero_guest.csv':
guest_data_table = 'give_credit_hetero_guest'
host_data_table = 'give_credit_hetero_host'
elif data_set == 'epsilon_5k_hetero_guest.csv':
guest_data_table = 'epsilon_5k_hetero_guest'
host_data_table = 'epsilon_5k_hetero_host'
else:
raise ValueError(f"Cannot recognized data_set: {data_set}")
guest_train_data = {
"name": guest_data_table,
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": host_data_table,
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
# define DataIO components
dataio_0 = DataIO(name="dataio_0") # start component numbering at 0
# get DataIO party instance of guest
dataio_0_guest_party_instance = dataio_0.get_party_instance(role='guest',
party_id=guest)
# configure DataIO for guest
dataio_0_guest_party_instance.component_param(with_label=True,
output_format="dense")
# get and configure DataIO party instance of host
dataio_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
# define Intersection component
intersection_0 = Intersection(name="intersection_0")
lr_param = {
"validation_freqs": None,
"early_stopping_rounds": None,
}
config_param = {
"penalty": param["penalty"],
"max_iter": param["max_iter"],
"alpha": param["alpha"],
"learning_rate": param["learning_rate"],
"optimizer": param["optimizer"],
"batch_size": param["batch_size"],
"early_stop": "diff",
"tol": 1e-5,
"init_param": {
"init_method": param.get("init_method", 'random_uniform')
}
}
lr_param.update(config_param)
print(f"lr_param: {lr_param}, data_set: {data_set}")
hetero_lr_0 = HeteroLR(name='hetero_lr_0', **lr_param)
evaluation_0 = Evaluation(name='evaluation_0', eval_type="binary")
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
pipeline.add_component(hetero_lr_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_lr_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
# query component summary
print(pipeline.get_component("evaluation_0").get_summary())
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
}
}
result_summary = pipeline.get_component("evaluation_0").get_summary()
return data_summary, result_summary
def main(config="../../config.yaml", param="./lr_config.yaml"):
# obtain config
if isinstance(param, str):
param = JobConfig.load_from_file(param)
assert isinstance(param, dict)
data_guest = param["data_guest"]
data_host = param["data_host"]
data_test = param["data_test"]
idx = param["idx"]
label_name = param["label_name"]
if isinstance(config, str):
config = JobConfig.load_from_file(config)
data_base_dir = config["data_base_dir"]
else:
data_base_dir = config.data_base_dir
config_param = {
"penalty": param["penalty"],
"max_iter": 100,
"alpha": param["alpha"],
"learning_rate": "optimal",
"eta0": param["learning_rate"]
}
# prepare data
df_guest = pandas.read_csv(os.path.join(data_base_dir, data_guest),
index_col=idx)
df_host = pandas.read_csv(os.path.join(data_base_dir, data_host),
index_col=idx)
# df_test = pandas.read_csv(data_test, index_col=idx)
df = pandas.concat([df_guest, df_host], axis=0)
# df = df_guest.join(df_host, rsuffix="host")
y_train = df[label_name]
x_train = df.drop(label_name, axis=1)
# y_test = df_test[label_name]
# x_test = df_test.drop(label_name, axis=1)
x_test, y_test = x_train, y_train
# lm = LogisticRegression(max_iter=20)
lm = SGDClassifier(loss="log", **config_param)
lm_fit = lm.fit(x_train, y_train)
y_pred = lm_fit.predict(x_test)
y_prob = lm_fit.predict_proba(x_test)[:, 1]
auc_score = roc_auc_score(y_test, y_prob)
recall = recall_score(y_test, y_pred, average="macro")
pr = precision_score(y_test, y_pred, average="macro")
acc = accuracy_score(y_test, y_pred)
# y_predict_proba = est.predict_proba(X_test)[:, 1]
fpr, tpr, thresholds = roc_curve(y_test, y_prob)
ks = max(tpr - fpr)
result = {"auc": auc_score}
print(f"result: {result}")
print(
f"coef_: {lm_fit.coef_}, intercept_: {lm_fit.intercept_}, n_iter: {lm_fit.n_iter_}"
)
return {}, result
def main(config="../../config.yaml", param="param_conf.yaml", namespace=""):
num_host = 1
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
epoch = param["epoch"]
lr = param["lr"]
batch_size = param.get("batch_size", -1)
optimizer_name = param.get("optimizer", "Adam")
encode_label = param.get("encode_label", True)
loss = param.get("loss", "categorical_crossentropy")
metrics = param.get("metrics", ["accuracy"])
layers = param["layers"]
data = getattr(dataset, param.get("dataset", "vehicle"))
guest_train_data = data["guest"]
host_train_data = data["host"][:num_host]
for d in [guest_train_data, *host_train_data]:
d["namespace"] = f"{d['namespace']}{namespace}"
hosts = config.parties.host[:num_host]
pipeline = PipeLine() \
.set_initiator(role='guest', party_id=config.parties.guest[0]) \
.set_roles(guest=config.parties.guest[0], host=hosts, arbiter=config.parties.arbiter)
reader_0 = Reader(name="reader_0")
reader_0.get_party_instance(
role='guest', party_id=config.parties.guest[0]).algorithm_param(
table=guest_train_data)
for i in range(num_host):
reader_0.get_party_instance(role='host', party_id=hosts[i]) \
.algorithm_param(table=host_train_data[i])
dataio_0 = DataIO(name="dataio_0", with_label=True)
dataio_0.get_party_instance(role='guest', party_id=config.parties.guest[0]) \
.algorithm_param(with_label=True, output_format="dense")
dataio_0.get_party_instance(
role='host', party_id=hosts).algorithm_param(with_label=True)
homo_nn_0 = HomoNN(name="homo_nn_0",
encode_label=encode_label,
max_iter=epoch,
batch_size=batch_size,
early_stop={
"early_stop": "diff",
"eps": 0.0
})
for layer_config in layers:
layer = getattr(tensorflow.keras.layers, layer_config["name"])
layer_params = layer_config["params"]
homo_nn_0.add(layer(**layer_params))
homo_nn_0.compile(optimizer=getattr(optimizers,
optimizer_name)(learning_rate=lr),
metrics=metrics,
loss=loss)
evaluation_0 = Evaluation(name='evaluation_0',
eval_type="multi",
metrics=["accuracy", "precision", "recall"])
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(homo_nn_0,
data=Data(train_data=dataio_0.output.data))
pipeline.add_component(evaluation_0, data=Data(data=homo_nn_0.output.data))
pipeline.compile()
pipeline.fit(backend=config.backend, work_mode=config.work_mode)
metric_summary = pipeline.get_component("evaluation_0").get_summary()
data_summary = dict(train={
"guest": guest_train_data["name"],
**{f"host_{i}": host_train_data[i]["name"]
for i in range(num_host)}
},
test={
"guest": guest_train_data["name"],
**{
f"host_{i}": host_train_data[i]["name"]
for i in range(num_host)
}
})
return data_summary, metric_summary
def main(config="../../config.yaml",
param="./xgb_config_binary.yaml",
namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
backend = config.backend
work_mode = config.work_mode
# data sets
guest_train_data = {
"name": param['data_guest_train'],
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": param['data_host_train'],
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": param['data_guest_val'],
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": param['data_host_val'],
"namespace": f"experiment{namespace}"
}
# init pipeline
pipeline = PipeLine().set_initiator(role="guest",
party_id=guest).set_roles(
guest=guest,
host=host,
)
# set data reader and data-io
reader_0, reader_1 = Reader(name="reader_0"), Reader(name="reader_1")
reader_0.get_party_instance(
role="guest", party_id=guest).algorithm_param(table=guest_train_data)
reader_0.get_party_instance(
role="host", party_id=host).algorithm_param(table=host_train_data)
reader_1.get_party_instance(
role="guest",
party_id=guest).algorithm_param(table=guest_validate_data)
reader_1.get_party_instance(
role="host", party_id=host).algorithm_param(table=host_validate_data)
dataio_0, dataio_1 = DataIO(name="dataio_0"), DataIO(name="dataio_1")
dataio_0.get_party_instance(role="guest", party_id=guest).algorithm_param(
with_label=True, output_format="dense")
dataio_0.get_party_instance(
role="host", party_id=host).algorithm_param(with_label=False)
dataio_1.get_party_instance(role="guest", party_id=guest).algorithm_param(
with_label=True, output_format="dense")
dataio_1.get_party_instance(
role="host", party_id=host).algorithm_param(with_label=False)
# data intersect component
intersect_0 = Intersection(name="intersection_0")
intersect_1 = Intersection(name="intersection_1")
# secure boost component
hetero_fast_sbt_0 = HeteroFastSecureBoost(
name="hetero_fast_sbt_0",
num_trees=param['tree_num'],
task_type=param['task_type'],
objective_param={"objective": param['loss_func']},
encrypt_param={"method": "iterativeAffine"},
tree_param={"max_depth": param['tree_depth']},
validation_freqs=1,
subsample_feature_rate=1,
learning_rate=param['learning_rate'],
guest_depth=param['guest_depth'],
host_depth=param['host_depth'],
tree_num_per_party=param['tree_num_per_party'],
work_mode=param['work_mode'])
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0",
eval_type=param['eval_type'])
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(intersect_1, data=Data(data=dataio_1.output.data))
pipeline.add_component(hetero_fast_sbt_0,
data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_fast_sbt_0.output.data))
pipeline.compile()
pipeline.fit(backend=backend, work_mode=work_mode)
return {}, pipeline.get_component("evaluation_0").get_summary()
def main(config="../../config.yaml", param="./xgb_config_binary.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
backend = config.backend
work_mode = config.work_mode
# data sets
guest_train_data = {"name": param['data_guest_train'], "namespace": f"experiment{namespace}"}
host_train_data = {"name": param['data_host_train'], "namespace": f"experiment{namespace}"}
guest_validate_data = {"name": param['data_guest_val'], "namespace": f"experiment{namespace}"}
host_validate_data = {"name": param['data_host_val'], "namespace": f"experiment{namespace}"}
# init pipeline
pipeline = PipeLine().set_initiator(role="guest", party_id=guest).set_roles(guest=guest, host=host,)
# set data reader and data-io
reader_0, reader_1 = Reader(name="reader_0"), Reader(name="reader_1")
reader_0.get_party_instance(role="guest", party_id=guest).component_param(table=guest_train_data)
reader_0.get_party_instance(role="host", party_id=host).component_param(table=host_train_data)
reader_1.get_party_instance(role="guest", party_id=guest).component_param(table=guest_validate_data)
reader_1.get_party_instance(role="host", party_id=host).component_param(table=host_validate_data)
dataio_0, dataio_1 = DataIO(name="dataio_0"), DataIO(name="dataio_1")
dataio_0.get_party_instance(role="guest", party_id=guest).component_param(with_label=True, output_format="dense")
dataio_0.get_party_instance(role="host", party_id=host).component_param(with_label=False)
dataio_1.get_party_instance(role="guest", party_id=guest).component_param(with_label=True, output_format="dense")
dataio_1.get_party_instance(role="host", party_id=host).component_param(with_label=False)
# data intersect component
intersect_0 = Intersection(name="intersection_0")
intersect_1 = Intersection(name="intersection_1")
# secure boost component
hetero_fast_sbt_0 = HeteroFastSecureBoost(name="hetero_fast_sbt_0",
num_trees=param['tree_num'],
task_type=param['task_type'],
objective_param={"objective": param['loss_func']},
encrypt_param={"method": "iterativeAffine"},
tree_param={"max_depth": param['tree_depth']},
validation_freqs=1,
subsample_feature_rate=1,
learning_rate=param['learning_rate'],
guest_depth=param['guest_depth'],
host_depth=param['host_depth'],
tree_num_per_party=param['tree_num_per_party'],
work_mode=param['work_mode']
)
hetero_fast_sbt_1 = HeteroFastSecureBoost(name="hetero_fast_sbt_1")
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0", eval_type=param['eval_type'])
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(dataio_1, data=Data(data=reader_1.output.data), model=Model(dataio_0.output.model))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(intersect_1, data=Data(data=dataio_1.output.data))
pipeline.add_component(hetero_fast_sbt_0, data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(hetero_fast_sbt_1, data=Data(test_data=intersect_1.output.data),
model=Model(hetero_fast_sbt_0.output.model))
pipeline.add_component(evaluation_0, data=Data(data=hetero_fast_sbt_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
sbt_0_data = pipeline.get_component("hetero_fast_sbt_0").get_output_data().get("data")
sbt_1_data = pipeline.get_component("hetero_fast_sbt_1").get_output_data().get("data")
sbt_0_score = extract_data(sbt_0_data, "predict_result")
sbt_0_label = extract_data(sbt_0_data, "label")
sbt_1_score = extract_data(sbt_1_data, "predict_result")
sbt_1_label = extract_data(sbt_1_data, "label")
sbt_0_score_label = extract_data(sbt_0_data, "predict_result", keep_id=True)
sbt_1_score_label = extract_data(sbt_1_data, "predict_result", keep_id=True)
metric_summary = parse_summary_result(pipeline.get_component("evaluation_0").get_summary())
if param['eval_type'] == "regression":
desc_sbt_0 = regression_metric.Describe().compute(sbt_0_score)
desc_sbt_1 = regression_metric.Describe().compute(sbt_1_score)
metric_summary["script_metrics"] = {"hetero_fast_sbt_train": desc_sbt_0,
"hetero_fast_sbt_validate": desc_sbt_1}
elif param['eval_type'] == "binary":
metric_sbt = {
"score_diversity_ratio": classification_metric.Distribution.compute(sbt_0_score_label, sbt_1_score_label),
"ks_2samp": classification_metric.KSTest.compute(sbt_0_score, sbt_1_score),
"mAP_D_value": classification_metric.AveragePrecisionScore().compute(sbt_0_score, sbt_1_score, sbt_0_label,
sbt_1_label)}
metric_summary["distribution_metrics"] = {"hetero_fast_sbt": metric_sbt}
elif param['eval_type'] == "multi":
metric_sbt = {
"score_diversity_ratio": classification_metric.Distribution.compute(sbt_0_score_label, sbt_1_score_label)}
metric_summary["distribution_metrics"] = {"hetero_fast_sbt": metric_sbt}
data_summary = {"train": {"guest": guest_train_data["name"], "host": host_train_data["name"]},
"test": {"guest": guest_train_data["name"], "host": host_train_data["name"]}
}
return data_summary, metric_summary
def main(config="../../config.yaml",
param='./xgb_config_binary.yaml',
namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
guest_train_data = {
"name": param['data_guest_train'],
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": param['data_guest_val'],
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": param['data_host_train'],
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": param['data_host_val'],
"namespace": f"experiment{namespace}"
}
pipeline = PipeLine().set_initiator(
role='guest', party_id=guest).set_roles(guest=guest,
host=host,
arbiter=arbiter)
dataio_0, dataio_1 = DataIO(name="dataio_0"), DataIO(name='dataio_1')
reader_0, reader_1 = Reader(name="reader_0"), Reader(name='reader_1')
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
dataio_0.get_party_instance(role='guest', party_id=guest).component_param(
with_label=True, output_format="dense")
dataio_0.get_party_instance(role='host', party_id=host).component_param(
with_label=True, output_format="dense")
reader_1.get_party_instance(
role='guest',
party_id=guest).component_param(table=guest_validate_data)
reader_1.get_party_instance(
role='host', party_id=host).component_param(table=host_validate_data)
dataio_1.get_party_instance(role='guest', party_id=guest).component_param(
with_label=True, output_format="dense")
dataio_1.get_party_instance(role='host', party_id=host).component_param(
with_label=True, output_format="dense")
homo_secureboost_0 = HomoSecureBoost(
name="homo_secureboost_0",
num_trees=param['tree_num'],
task_type=param['task_type'],
objective_param={"objective": param['loss_func']},
tree_param={"max_depth": param['tree_depth']},
validation_freqs=1,
subsample_feature_rate=1,
learning_rate=param['learning_rate'],
bin_num=50)
homo_secureboost_1 = HomoSecureBoost(name="homo_secureboost_1")
evaluation_0 = Evaluation(name='evaluation_0',
eval_type=param['eval_type'])
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(reader_1)
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(homo_secureboost_0,
data=Data(train_data=dataio_0.output.data,
validate_data=dataio_1.output.data))
pipeline.add_component(homo_secureboost_1,
data=Data(test_data=dataio_1.output.data),
model=Model(homo_secureboost_0.output.model))
pipeline.add_component(evaluation_0,
data=Data(homo_secureboost_0.output.data))
pipeline.compile()
pipeline.fit()
sbt_0_data = pipeline.get_component(
"homo_secureboost_0").get_output_data().get("data")
sbt_1_data = pipeline.get_component(
"homo_secureboost_1").get_output_data().get("data")
sbt_0_score = extract_data(sbt_0_data, "predict_result")
sbt_0_label = extract_data(sbt_0_data, "label")
sbt_1_score = extract_data(sbt_1_data, "predict_result")
sbt_1_label = extract_data(sbt_1_data, "label")
sbt_0_score_label = extract_data(sbt_0_data,
"predict_result",
keep_id=True)
sbt_1_score_label = extract_data(sbt_1_data,
"predict_result",
keep_id=True)
metric_summary = parse_summary_result(
pipeline.get_component("evaluation_0").get_summary())
if param['eval_type'] == "regression":
desc_sbt_0 = regression_metric.Describe().compute(sbt_0_score)
desc_sbt_1 = regression_metric.Describe().compute(sbt_1_score)
metric_summary["script_metrics"] = {
"sbt_train": desc_sbt_0,
"sbt_validate": desc_sbt_1
}
elif param['eval_type'] == "binary":
metric_sbt = {
"score_diversity_ratio":
classification_metric.Distribution.compute(sbt_0_score_label,
sbt_1_score_label),
"ks_2samp":
classification_metric.KSTest.compute(sbt_0_score, sbt_1_score),
"mAP_D_value":
classification_metric.AveragePrecisionScore().compute(
sbt_0_score, sbt_1_score, sbt_0_label, sbt_1_label)
}
metric_summary["distribution_metrics"] = {"homo_sbt": metric_sbt}
elif param['eval_type'] == "multi":
metric_sbt = {
"score_diversity_ratio":
classification_metric.Distribution.compute(sbt_0_score_label,
sbt_1_score_label)
}
metric_summary["distribution_metrics"] = {"homo_sbt": metric_sbt}
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_validate_data["name"],
"host": host_validate_data["name"]
}
}
return data_summary, metric_summary
def main(config="../../config.yaml", param="./linr_config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
backend = config.backend
work_mode = config.work_mode
if isinstance(param, str):
param = JobConfig.load_from_file(param)
"""
guest = 9999
host = 10000
arbiter = 9999
backend = 0
work_mode = 1
param = {"penalty": "L2", "max_iter": 5}
"""
guest_train_data = {
"name": "motor_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "motor_hetero_host",
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).algorithm_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=host).algorithm_param(table=host_train_data)
# define DataIO components
dataio_0 = DataIO(name="dataio_0") # start component numbering at 0
# get DataIO party instance of guest
dataio_0_guest_party_instance = dataio_0.get_party_instance(role='guest',
party_id=guest)
# configure DataIO for guest
dataio_0_guest_party_instance.algorithm_param(
with_label=True,
output_format="dense",
label_name=param["label_name"],
label_type="float")
# get and configure DataIO party instance of host
dataio_0.get_party_instance(
role='host', party_id=host).algorithm_param(with_label=False)
# define Intersection component
intersection_0 = Intersection(name="intersection_0")
param = {
"penalty": param["penalty"],
"validation_freqs": None,
"early_stopping_rounds": None,
"max_iter": param["max_iter"],
"optimizer": param["optimizer"],
"learning_rate": param["learning_rate"],
"init_param": param["init_param"],
"batch_size": param["batch_size"],
"alpha": param["alpha"]
}
hetero_linr_0 = HeteroLinR(name='hetero_linr_0', **param)
evaluation_0 = Evaluation(name='evaluation_0',
eval_type="regression",
metrics=[
"r2_score", "mean_squared_error",
"root_mean_squared_error",
"explained_variance"
])
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
pipeline.add_component(hetero_linr_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_linr_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
pipeline.fit(backend=backend, work_mode=work_mode)
metric_summary = pipeline.get_component("evaluation_0").get_summary()
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
}
}
return data_summary, metric_summary
def main(config="../../config.yaml", param="param_conf.yaml", namespace=""):
num_host = 1
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
epoch = param["epoch"]
lr = param["lr"]
batch_size = param.get("batch_size", -1)
optimizer_name = param.get("optimizer", "Adam")
encode_label = param.get("encode_label", True)
loss = param.get("loss", "categorical_crossentropy")
metrics = param.get("metrics", ["accuracy"])
layers = param["layers"]
data = getattr(dataset, param.get("dataset", "vehicle"))
guest_train_data = data["guest"]
host_train_data = data["host"][:num_host]
for d in [guest_train_data, *host_train_data]:
d["namespace"] = f"{d['namespace']}{namespace}"
hosts = config.parties.host[:num_host]
pipeline = PipeLine() \
.set_initiator(role='guest', party_id=config.parties.guest[0]) \
.set_roles(guest=config.parties.guest[0], host=hosts, arbiter=config.parties.arbiter)
reader_0 = Reader(name="reader_0")
reader_0.get_party_instance(role='guest', party_id=config.parties.guest[0]).component_param(table=guest_train_data)
for i in range(num_host):
reader_0.get_party_instance(role='host', party_id=hosts[i]) \
.component_param(table=host_train_data[i])
dataio_0 = DataIO(name="dataio_0", with_label=True)
dataio_0.get_party_instance(role='guest', party_id=config.parties.guest[0]) \
.component_param(with_label=True, output_format="dense")
dataio_0.get_party_instance(role='host', party_id=hosts).component_param(with_label=True)
homo_nn_0 = HomoNN(name="homo_nn_0", encode_label=encode_label, max_iter=epoch, batch_size=batch_size,
early_stop={"early_stop": "diff", "eps": 0.0})
for layer_config in layers:
layer = getattr(tensorflow.keras.layers, layer_config["name"])
layer_params = layer_config["params"]
homo_nn_0.add(layer(**layer_params))
homo_nn_0.compile(optimizer=getattr(optimizers, optimizer_name)(learning_rate=lr), metrics=metrics,
loss=loss)
homo_nn_1 = HomoNN(name="homo_nn_1")
if param["loss"] == "categorical_crossentropy":
eval_type = "multi"
else:
eval_type = "binary"
evaluation_0 = Evaluation(name='evaluation_0', eval_type="multi", metrics=["accuracy", "precision", "recall"])
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(homo_nn_0, data=Data(train_data=dataio_0.output.data))
pipeline.add_component(homo_nn_1, data=Data(test_data=dataio_0.output.data),
model=Model(homo_nn_0.output.model))
pipeline.add_component(evaluation_0, data=Data(data=homo_nn_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=config.backend, work_mode=config.work_mode)
pipeline.fit(job_parameters)
metric_summary = parse_summary_result(pipeline.get_component("evaluation_0").get_summary())
nn_0_data = pipeline.get_component("homo_nn_0").get_output_data().get("data")
nn_1_data = pipeline.get_component("homo_nn_1").get_output_data().get("data")
nn_0_score = extract_data(nn_0_data, "predict_result")
nn_0_label = extract_data(nn_0_data, "label")
nn_1_score = extract_data(nn_1_data, "predict_result")
nn_1_label = extract_data(nn_1_data, "label")
nn_0_score_label = extract_data(nn_0_data, "predict_result", keep_id=True)
nn_1_score_label = extract_data(nn_1_data, "predict_result", keep_id=True)
if eval_type == "binary":
metric_nn = {
"score_diversity_ratio": classification_metric.Distribution.compute(nn_0_score_label, nn_1_score_label),
"ks_2samp": classification_metric.KSTest.compute(nn_0_score, nn_1_score),
"mAP_D_value": classification_metric.AveragePrecisionScore().compute(nn_0_score, nn_1_score, nn_0_label,
nn_1_label)}
metric_summary["distribution_metrics"] = {"homo_nn": metric_nn}
elif eval_type == "multi":
metric_nn = {
"score_diversity_ratio": classification_metric.Distribution.compute(nn_0_score_label, nn_1_score_label)}
metric_summary["distribution_metrics"] = {"homo_nn": metric_nn}
data_summary = dict(
train={"guest": guest_train_data["name"], **{f"host_{i}": host_train_data[i]["name"] for i in range(num_host)}},
test={"guest": guest_train_data["name"], **{f"host_{i}": host_train_data[i]["name"] for i in range(num_host)}}
)
return data_summary, metric_summary
def main(config="../../config.yaml",
param="./hetero_nn_breast_config.yaml",
namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
backend = config.backend
work_mode = config.work_mode
guest_train_data = {
"name": param["guest_table_name"],
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": param["host_table_name"],
"namespace": f"experiment{namespace}"
}
pipeline = PipeLine().set_initiator(role='guest',
party_id=guest).set_roles(guest=guest,
host=host)
reader_0 = Reader(name="reader_0")
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
dataio_0 = DataIO(name="dataio_0")
dataio_0.get_party_instance(
role='guest', party_id=guest).component_param(with_label=True)
dataio_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
intersection_0 = Intersection(name="intersection_0")
hetero_nn_0 = HeteroNN(name="hetero_nn_0",
epochs=param["epochs"],
interactive_layer_lr=param["learning_rate"],
batch_size=param["batch_size"],
early_stop="diff")
hetero_nn_0.add_bottom_model(
Dense(units=param["bottom_layer_units"],
input_shape=(10, ),
activation="tanh",
kernel_initializer=initializers.RandomUniform(minval=-1,
maxval=1,
seed=123)))
hetero_nn_0.set_interactve_layer(
Dense(units=param["interactive_layer_units"],
input_shape=(param["bottom_layer_units"], ),
activation="relu",
kernel_initializer=initializers.RandomUniform(minval=-1,
maxval=1,
seed=123)))
hetero_nn_0.add_top_model(
Dense(units=param["top_layer_units"],
input_shape=(param["interactive_layer_units"], ),
activation=param["top_act"],
kernel_initializer=initializers.RandomUniform(minval=-1,
maxval=1,
seed=123)))
opt = getattr(optimizers, param["opt"])(lr=param["learning_rate"])
hetero_nn_0.compile(optimizer=opt,
metrics=param["metrics"],
loss=param["loss"])
if param["loss"] == "categorical_crossentropy":
eval_type = "multi"
else:
eval_type = "binary"
evaluation_0 = Evaluation(name="evaluation_0", eval_type=eval_type)
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
pipeline.add_component(hetero_nn_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_nn_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
}
}
return data_summary, pipeline.get_component("evaluation_0").get_summary()
def main(config="../../config.yaml",
param='./xgb_config_binary.yaml',
namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
backend = config.backend
work_mode = config.work_mode
guest_train_data = {
"name": param['data_guest_train'],
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": param['data_guest_val'],
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": param['data_host_train'],
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": param['data_host_val'],
"namespace": f"experiment{namespace}"
}
pipeline = PipeLine().set_initiator(
role='guest', party_id=guest).set_roles(guest=guest,
host=host,
arbiter=arbiter)
dataio_0, dataio_1 = DataIO(name="dataio_0"), DataIO(name='dataio_1')
reader_0, reader_1 = Reader(name="reader_0"), Reader(name='reader_1')
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
dataio_0.get_party_instance(role='guest', party_id=guest).component_param(
with_label=True, output_format="dense")
dataio_0.get_party_instance(role='host', party_id=host).component_param(
with_label=True, output_format="dense")
reader_1.get_party_instance(
role='guest',
party_id=guest).component_param(table=guest_validate_data)
reader_1.get_party_instance(
role='host', party_id=host).component_param(table=host_validate_data)
dataio_1.get_party_instance(role='guest', party_id=guest).component_param(
with_label=True, output_format="dense")
dataio_1.get_party_instance(role='host', party_id=host).component_param(
with_label=True, output_format="dense")
homo_secureboost_0 = HomoSecureBoost(
name="homo_secureboost_0",
num_trees=param['tree_num'],
task_type=param['task_type'],
objective_param={"objective": param['loss_func']},
tree_param={"max_depth": param['tree_depth']},
validation_freqs=1,
subsample_feature_rate=1,
learning_rate=param['learning_rate'],
bin_num=50)
evaluation_0 = Evaluation(name='evaluation_0',
eval_type=param['eval_type'])
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(reader_1)
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(homo_secureboost_0,
data=Data(train_data=dataio_0.output.data,
validate_data=dataio_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(homo_secureboost_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
}
}
return data_summary, pipeline.get_component('evaluation_0').get_summary()
def main(config="../../config.yaml", param="./lr_config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
if isinstance(param, str):
param = JobConfig.load_from_file(param)
assert isinstance(param, dict)
data_set = param.get("data_guest").split('/')[-1]
if data_set == "default_credit_hetero_guest.csv":
guest_data_table = 'default_credit_hetero_guest'
host_data_table = 'default_credit_hetero_host'
elif data_set == 'breast_hetero_guest.csv':
guest_data_table = 'breast_hetero_guest'
host_data_table = 'breast_hetero_host'
elif data_set == 'give_credit_hetero_guest.csv':
guest_data_table = 'give_credit_hetero_guest'
host_data_table = 'give_credit_hetero_host'
elif data_set == 'epsilon_5k_hetero_guest.csv':
guest_data_table = 'epsilon_5k_hetero_guest'
host_data_table = 'epsilon_5k_hetero_host'
else:
raise ValueError(f"Cannot recognized data_set: {data_set}")
guest_train_data = {"name": guest_data_table, "namespace": f"experiment{namespace}"}
host_train_data = {"name": host_data_table, "namespace": f"experiment{namespace}"}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(role='host', party_id=host).component_param(table=host_train_data)
# define DataTransform components
data_transform_0 = DataTransform(name="data_transform_0") # start component numbering at 0
# get DataTransform party instance of guest
data_transform_0_guest_party_instance = data_transform_0.get_party_instance(role='guest', party_id=guest)
# configure DataTransform for guest
data_transform_0_guest_party_instance.component_param(with_label=True, output_format="dense")
# get and configure DataTransform party instance of host
data_transform_0.get_party_instance(role='host', party_id=host).component_param(with_label=False)
# define Intersection component
intersection_0 = Intersection(name="intersection_0")
lr_param = {
}
config_param = {
"penalty": param["penalty"],
"max_iter": param["max_iter"],
"alpha": param["alpha"],
"learning_rate": param["learning_rate"],
"optimizer": param["optimizer"],
"batch_size": param["batch_size"],
"shuffle": False,
"masked_rate": 0,
"early_stop": "diff",
"tol": 1e-5,
"floating_point_precision": param.get("floating_point_precision"),
"init_param": {
"init_method": param.get("init_method", 'random_uniform'),
"random_seed": param.get("random_seed", 103)
}
}
lr_param.update(config_param)
print(f"lr_param: {lr_param}, data_set: {data_set}")
hetero_lr_0 = HeteroLR(name='hetero_lr_0', **lr_param)
hetero_lr_1 = HeteroLR(name='hetero_lr_1')
evaluation_0 = Evaluation(name='evaluation_0', eval_type="binary")
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0, data=Data(data=data_transform_0.output.data))
pipeline.add_component(hetero_lr_0, data=Data(train_data=intersection_0.output.data))
pipeline.add_component(hetero_lr_1, data=Data(test_data=intersection_0.output.data),
model=Model(hetero_lr_0.output.model))
pipeline.add_component(evaluation_0, data=Data(data=hetero_lr_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
job_parameters = JobParameters()
pipeline.fit(job_parameters)
lr_0_data = pipeline.get_component("hetero_lr_0").get_output_data().get("data")
lr_1_data = pipeline.get_component("hetero_lr_1").get_output_data().get("data")
lr_0_score = extract_data(lr_0_data, "predict_result")
lr_0_label = extract_data(lr_0_data, "label")
lr_1_score = extract_data(lr_1_data, "predict_result")
lr_1_label = extract_data(lr_1_data, "label")
lr_0_score_label = extract_data(lr_0_data, "predict_result", keep_id=True)
lr_1_score_label = extract_data(lr_1_data, "predict_result", keep_id=True)
result_summary = parse_summary_result(pipeline.get_component("evaluation_0").get_summary())
metric_lr = {
"score_diversity_ratio": classification_metric.Distribution.compute(lr_0_score_label, lr_1_score_label),
"ks_2samp": classification_metric.KSTest.compute(lr_0_score, lr_1_score),
"mAP_D_value": classification_metric.AveragePrecisionScore().compute(lr_0_score, lr_1_score, lr_0_label,
lr_1_label)}
result_summary["distribution_metrics"] = {"hetero_lr": metric_lr}
data_summary = {"train": {"guest": guest_train_data["name"], "host": host_train_data["name"]},
"test": {"guest": guest_train_data["name"], "host": host_train_data["name"]}
}
return data_summary, result_summary
def main(config="../../config.yaml",
param="./sshe_linr_config.yaml",
namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
if isinstance(param, str):
param = JobConfig.load_from_file(param)
guest_train_data = {
"name": "motor_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "motor_hetero_host",
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
# define DataTransform components
data_transform_0 = DataTransform(
name="data_transform_0") # start component numbering at 0
# get DataTransform party instance of guest
data_transform_0_guest_party_instance = data_transform_0.get_party_instance(
role='guest', party_id=guest)
# configure DataTransform for guest
data_transform_0_guest_party_instance.component_param(
with_label=True,
output_format="dense",
label_name=param["label_name"],
label_type="float")
# get and configure DataTransform party instance of host
data_transform_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
# define Intersection component
intersection_0 = Intersection(name="intersection_0")
param = {
"penalty": param["penalty"],
"max_iter": param["max_iter"],
"optimizer": param["optimizer"],
"learning_rate": param["learning_rate"],
"init_param": param["init_param"],
"batch_size": param["batch_size"],
"alpha": param["alpha"],
"early_stop": param["early_stop"],
"reveal_strategy": param["reveal_strategy"],
"tol": 1e-6,
"reveal_every_iter": True
}
hetero_sshe_linr_0 = HeteroSSHELinR(name='hetero_sshe_linr_0', **param)
hetero_sshe_linr_1 = HeteroSSHELinR(name='hetero_sshe_linr_1')
evaluation_0 = Evaluation(name='evaluation_0',
eval_type="regression",
metrics=[
"r2_score", "mean_squared_error",
"root_mean_squared_error",
"explained_variance"
])
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(hetero_sshe_linr_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(hetero_sshe_linr_1,
data=Data(test_data=intersection_0.output.data),
model=Model(hetero_sshe_linr_0.output.model))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_sshe_linr_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
pipeline.fit()
metric_summary = parse_summary_result(
pipeline.get_component("evaluation_0").get_summary())
data_linr_0 = extract_data(
pipeline.get_component("hetero_sshe_linr_0").get_output_data().get(
"data"), "predict_result")
data_linr_1 = extract_data(
pipeline.get_component("hetero_sshe_linr_1").get_output_data().get(
"data"), "predict_result")
desc_linr_0 = regression_metric.Describe().compute(data_linr_0)
desc_linr_1 = regression_metric.Describe().compute(data_linr_1)
metric_summary["script_metrics"] = {
"linr_train": desc_linr_0,
"linr_validate": desc_linr_1
}
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
}
}
return data_summary, metric_summary
def main(config="../../config.yaml",
param="./vechile_config.yaml",
namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
backend = config.backend
work_mode = config.work_mode
if isinstance(param, str):
param = JobConfig.load_from_file(param)
assert isinstance(param, dict)
"""
guest = 9999
host = 10000
arbiter = 9999
backend = 0
work_mode = 1
param = {"penalty": "L2", "max_iter": 5}
"""
data_set = param.get("data_guest").split('/')[-1]
if data_set == "vehicle_scale_hetero_guest.csv":
guest_data_table = 'vehicle_scale_hetero_guest'
host_data_table = 'vehicle_scale_hetero_host'
else:
raise ValueError(f"Cannot recognized data_set: {data_set}")
guest_train_data = {
"name": guest_data_table,
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": host_data_table,
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
# define DataIO components
dataio_0 = DataIO(name="dataio_0") # start component numbering at 0
# get DataIO party instance of guest
dataio_0_guest_party_instance = dataio_0.get_party_instance(role='guest',
party_id=guest)
# configure DataIO for guest
dataio_0_guest_party_instance.component_param(with_label=True,
output_format="dense")
# get and configure DataIO party instance of host
dataio_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
# define Intersection component
intersection_0 = Intersection(name="intersection_0")
lr_param = {
"validation_freqs": None,
"early_stopping_rounds": None,
}
config_param = {
"penalty": param["penalty"],
"max_iter": param["max_iter"],
"alpha": param["alpha"],
"learning_rate": param["learning_rate"],
"optimizer": param["optimizer"],
"batch_size": param["batch_size"],
"early_stop": "diff",
"init_param": {
"init_method": param.get("init_method", 'random_uniform'),
"random_seed": param.get("random_seed", 103)
}
}
lr_param.update(config_param)
print(f"lr_param: {lr_param}, data_set: {data_set}")
hetero_lr_0 = HeteroLR(name='hetero_lr_0', **lr_param)
hetero_lr_1 = HeteroLR(name='hetero_lr_1')
evaluation_0 = Evaluation(name='evaluation_0', eval_type="multi")
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
pipeline.add_component(hetero_lr_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(hetero_lr_1,
data=Data(test_data=intersection_0.output.data),
model=Model(hetero_lr_0.output.model))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_lr_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
# query component summary
result_summary = parse_summary_result(
pipeline.get_component("evaluation_0").get_summary())
lr_0_data = pipeline.get_component("hetero_lr_0").get_output_data().get(
"data")
lr_1_data = pipeline.get_component("hetero_lr_1").get_output_data().get(
"data")
lr_0_score_label = extract_data(lr_0_data, "predict_result", keep_id=True)
lr_1_score_label = extract_data(lr_1_data, "predict_result", keep_id=True)
metric_lr = {
"score_diversity_ratio":
classification_metric.Distribution.compute(lr_0_score_label,
lr_1_score_label)
}
result_summary["distribution_metrics"] = {"hetero_lr": metric_lr}
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
}
}
return data_summary, result_summary
def main(config="../../config.yaml", param="./hetero_nn_breast_config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
guest_train_data = {"name": param["guest_table_name"], "namespace": f"experiment{namespace}"}
host_train_data = {"name": param["host_table_name"], "namespace": f"experiment{namespace}"}
pipeline = PipeLine().set_initiator(role='guest', party_id=guest).set_roles(guest=guest, host=host)
reader_0 = Reader(name="reader_0")
reader_0.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data)
reader_0.get_party_instance(role='host', party_id=host).component_param(table=host_train_data)
dataio_0 = DataIO(name="dataio_0")
dataio_0.get_party_instance(role='guest', party_id=guest).component_param(with_label=True)
dataio_0.get_party_instance(role='host', party_id=host).component_param(with_label=False)
intersection_0 = Intersection(name="intersection_0")
hetero_nn_0 = HeteroNN(name="hetero_nn_0", epochs=param["epochs"],
interactive_layer_lr=param["learning_rate"], batch_size=param["batch_size"],
early_stop="diff")
hetero_nn_0.add_bottom_model(Dense(units=param["bottom_layer_units"], input_shape=(10,), activation="tanh",
kernel_initializer=initializers.RandomUniform(minval=-1, maxval=1, seed=123)))
hetero_nn_0.set_interactve_layer(
Dense(units=param["interactive_layer_units"], input_shape=(param["bottom_layer_units"],), activation="relu",
kernel_initializer=initializers.RandomUniform(minval=-1, maxval=1, seed=123)))
hetero_nn_0.add_top_model(
Dense(units=param["top_layer_units"], input_shape=(param["interactive_layer_units"],),
activation=param["top_act"],
kernel_initializer=initializers.RandomUniform(minval=-1, maxval=1, seed=123)))
opt = getattr(optimizers, param["opt"])(lr=param["learning_rate"])
hetero_nn_0.compile(optimizer=opt, metrics=param["metrics"],
loss=param["loss"])
hetero_nn_1 = HeteroNN(name="hetero_nn_1")
if param["loss"] == "categorical_crossentropy":
eval_type = "multi"
else:
eval_type = "binary"
evaluation_0 = Evaluation(name="evaluation_0", eval_type=eval_type)
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(hetero_nn_0, data=Data(train_data=intersection_0.output.data))
pipeline.add_component(hetero_nn_1, data=Data(test_data=intersection_0.output.data),
model=Model(hetero_nn_0.output.model))
pipeline.add_component(evaluation_0, data=Data(data=hetero_nn_0.output.data))
pipeline.compile()
pipeline.fit()
nn_0_data = pipeline.get_component("hetero_nn_0").get_output_data().get("data")
nn_1_data = pipeline.get_component("hetero_nn_1").get_output_data().get("data")
nn_0_score = extract_data(nn_0_data, "predict_result")
nn_0_label = extract_data(nn_0_data, "label")
nn_1_score = extract_data(nn_1_data, "predict_result")
nn_1_label = extract_data(nn_1_data, "label")
nn_0_score_label = extract_data(nn_0_data, "predict_result", keep_id=True)
nn_1_score_label = extract_data(nn_1_data, "predict_result", keep_id=True)
metric_summary = parse_summary_result(pipeline.get_component("evaluation_0").get_summary())
if eval_type == "binary":
metric_nn = {
"score_diversity_ratio": classification_metric.Distribution.compute(nn_0_score_label, nn_1_score_label),
"ks_2samp": classification_metric.KSTest.compute(nn_0_score, nn_1_score),
"mAP_D_value": classification_metric.AveragePrecisionScore().compute(nn_0_score, nn_1_score, nn_0_label,
nn_1_label)}
metric_summary["distribution_metrics"] = {"hetero_nn": metric_nn}
elif eval_type == "multi":
metric_nn = {
"score_diversity_ratio": classification_metric.Distribution.compute(nn_0_score_label, nn_1_score_label)}
metric_summary["distribution_metrics"] = {"hetero_nn": metric_nn}
data_summary = {"train": {"guest": guest_train_data["name"], "host": host_train_data["name"]},
"test": {"guest": guest_train_data["name"], "host": host_train_data["name"]}
}
return data_summary, metric_summary
