FATE联邦学习初探（三）

在上传数据完成之后，接下来根据给出的案例来完成一个简单的实验。

首先需要确保数据上传成功，没成功的可以参考联邦学习初探（二）_顿顿有鱼有虾的博客-CSDN博客

然后，还需要确保FATE Flow Service也是成功配置的。

pipeline init --ip 127.0.0.1 --port 9380

 首先是训练阶段的代码

from pipeline.backend.pipeline import PipeLine
from pipeline.component import Reader, DataTransform, Intersection, HeteroSecureBoost, Evaluation
from pipeline.interface import Data
import os

pipeline = PipeLine() \
        .set_initiator(role='guest', party_id=9999) \
        .set_roles(guest=9999, host=10000)


reader_0 = Reader(name="reader_0")
# set guest parameter
reader_0.get_party_instance(role='guest', party_id=9999).component_param(
    table={"name": "breast_hetero_guest", "namespace": "experiment"})
# set host parameter
reader_0.get_party_instance(role='host', party_id=10000).component_param(
    table={"name": "breast_hetero_host", "namespace": "experiment"})


data_transform_0 = DataTransform(name="data_transform_0")
# set guest parameter
data_transform_0.get_party_instance(role='guest', party_id=9999).component_param(
    with_label=True)
data_transform_0.get_party_instance(role='host', party_id=[10000]).component_param(
    with_label=False)



intersect_0 = Intersection(name="intersect_0")


hetero_secureboost_0 = HeteroSecureBoost(name="hetero_secureboost_0",
                                         num_trees=5,
                                         bin_num=16,
                                         task_type="classification",
                                         objective_param={"objective": "cross_entropy"},
                                         encrypt_param={"method": "paillier"},
                                         tree_param={"max_depth": 3})


evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")



pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersect_0, data=Data(data=data_transform_0.output.data))
pipeline.add_component(hetero_secureboost_0, data=Data(train_data=intersect_0.output.data))
pipeline.add_component(evaluation_0, data=Data(data=hetero_secureboost_0.output.data))
pipeline.compile()


pipeline.fit()


pipeline.dump("pipeline_saved.pkl")

成功运行训练之后，会生成一个.pkl文件，文件中保存的即为训练好的模型

 接下来使用训练好的模型进行预测

from pipeline.backend.pipeline import PipeLine
from pipeline.component import Reader, DataTransform, Intersection, HeteroSecureBoost, Evaluation
from pipeline.interface import Data
import os




pipeline = PipeLine.load_model_from_file('pipeline_saved.pkl')
pipeline.deploy_component([pipeline.data_transform_0, pipeline.intersect_0, pipeline.hetero_secureboost_0])


reader_1 = Reader(name="reader_1")
reader_1.get_party_instance(role="guest", party_id=9999).component_param(table={"name": "breast_hetero_guest", "namespace": "experiment"})
reader_1.get_party_instance(role="host", party_id=10000).component_param(table={"name": "breast_hetero_host", "namespace": "experiment"})



evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")


predict_pipeline = PipeLine()
predict_pipeline.add_component(reader_1)\
                .add_component(pipeline, 
                               data=Data(predict_input={pipeline.data_transform_0.input.data: reader_1.output.data}))\
                .add_component(evaluation_0, data=Data(data=pipeline.hetero_secureboost_0.output.data))

predict_pipeline.predict()

预测完成后，控制台输出如下所示

同时我们还可以通过访问浏览器体验算法过程看板，访问：Http://${ip}:8080, ip为127.0.0.1或本机实际ip