class FakeTestingConfig2:
name: str = field("Name of FakeTesting2")
num: float
features: Features = Features(
DefFeature("default", int, 1), DefFeature("features", int, 10)
)
label: str = "unlabeled"
def test_config_set(self):
config = FakeTesting.config(
parse_unknown(
"--test-fake-name",
"feedface",
"--test-num",
"-4.2",
"--test-fake-label",
"default-label",
"--test-fake-readonly",
"--test-files",
"a",
"b",
"c",
"--test-fake-source",
"csv",
"--test-source-filename",
"file.csv",
"--test-features",
"Year:int:1",
"Commits:int:10",
))
self.assertEqual(config.num, -4.2)
self.assertEqual(config.files, ["a", "b", "c"])
self.assertEqual(config.name, "feedface")
self.assertEqual(config.label, "default-label")
self.assertTrue(config.readonly)
self.assertTrue(isinstance(config.source, CSVSource))
self.assertEqual(config.source.config.filename, "file.csv")
self.assertEqual(
config.features,
Features(DefFeature("Year", int, 1),
DefFeature("Commits", int, 10)),
)
async def test_predict(self):
self.required_plugins("dffml-model-scikit")
# Import SciKit modules
dffml_model_scikit = importlib.import_module("dffml_model_scikit")
# Instantiate the model
model = dffml_model_scikit.LinearRegressionModel(
directory=self.mktempdir(),
predict=DefFeature("Salary", int, 1),
features=Features(
DefFeature("Years", int, 1),
DefFeature("Expertise", int, 1),
DefFeature("Trust", float, 1),
),
)
training_data = CSVSource(filename=self.train_filename)
test_data = CSVSource(filename=self.test_filename)
predict_data = CSVSource(filename=self.predict_filename)
# Train the model
await train(model, training_data)
# Assess accuracy
await accuracy(model, test_data)
# Make prediction
predictions = [
prediction async for prediction in predict(model, predict_data)
]
self.assertEqual(predictions[0][2]["Salary"]["value"], 70)
self.assertEqual(predictions[1][2]["Salary"]["value"], 80)
def test_config_defaults(self):
config = FakeTesting.config(
parse_unknown(
"--test-fake-name",
"feedface",
"--test-num",
"-4.2",
"--test-files",
"a",
"b",
"c",
"--test-source-filename",
"file.json",
"--test-features",
"def:Year:int:1",
"def:Commits:int:10",
))
self.assertEqual(config.num, -4.2)
self.assertEqual(config.files, ["a", "b", "c"])
self.assertEqual(config.name, "feedface")
self.assertEqual(config.label, "unlabeled")
self.assertFalse(config.readonly)
self.assertTrue(isinstance(config.source, JSONSource))
self.assertEqual(config.source.config.filename, "file.json")
self.assertEqual(
config.features,
Features(DefFeature("Year", int, 1),
DefFeature("Commits", int, 10)),
)
default=pathlib.Path(
"~", ".cache", "dffml", f"scikit-{entry_point_name}"
),
),
),
"features": (Features, field("Features to train on")),
},
**config_fields,
}
if estimator_type in unsupervised_estimators:
dffml_config_properties["predict"] = (
Feature,
field(
"Name used as meaning of prediction",
default=DefFeature(name="cluster", dtype=str, length=1),
),
)
dffml_config = make_config_numpy(
name + "ModelConfig", cls, properties=dffml_config_properties
)
dffml_cls_ctx = type(
name + "ModelContext",
(parentContext,),
{"applicable_features": applicable_features_function},
)
dffml_cls = type(
name + "Model",
"dffml",
f"scikit-{entry_point_name}",
),
),
),
"features": (Features, field("Features to train on")),
},
**config_fields,
}
if estimator_type in unsupervised_estimators:
dffml_config_properties["predict"] = (
Feature,
field(
"field here for compability with other functions,no need to change",
default=DefFeature(name="Prediction", dtype="str", length=10),
),
)
dffml_config = make_config_numpy(name + "ModelConfig",
cls,
properties=dffml_config_properties)
dffml_cls_ctx = type(
name + "ModelContext",
(parentContext, ),
{"applicable_features": applicable_features_function},
)
dffml_cls = type(
name + "Model",
from dffml.source.csv import CSVSource, CSVSourceConfig
from dffml_model_tensorflow.dnnr import (
DNNRegressionModel,
DNNRegressionModelConfig,
)
training_data = CSVSource(
CSVSourceConfig(filename="training.csv", readonly=True))
test_data = CSVSource(CSVSourceConfig(filename="test.csv", readonly=True))
predict_data = CSVSource(CSVSourceConfig(filename="predict.csv",
readonly=True))
model = DNNRegressionModel(
DNNRegressionModelConfig(
features=Features(
DefFeature("Years", int, 1),
DefFeature("Expertise", int, 1),
DefFeature("Trust", float, 1),
),
predict="Salary",
))
Train(model=model, sources=[training_data])()
accuracy = Accuracy(model=model, sources=[test_data])()
row0, row1 = PredictAll(model=model, sources=[predict_data])()
print("Accuracy", accuracy)
print(row0)
print(row1)
from dffml.source.csv import CSVSource, CSVSourceConfig
from dffml_model_tensorflow.dnnr import (
DNNRegressionModel,
DNNRegressionModelConfig,
)
training_data = CSVSource(
CSVSourceConfig(filename="training.csv", readwrite=False))
test_data = CSVSource(CSVSourceConfig(filename="test.csv", readwrite=False))
predict_data = CSVSource(
CSVSourceConfig(filename="predict.csv", readwrite=False))
model = DNNRegressionModel(
DNNRegressionModelConfig(
features=Features(
DefFeature("Years", int, 1),
DefFeature("Expertise", int, 1),
DefFeature("Trust", float, 1),
),
predict=DefFeature("Salary", float, 1),
))
Train(model=model, sources=[training_data])()
accuracy = Accuracy(model=model, sources=[test_data])()
row0, row1 = PredictAll(model=model, sources=[predict_data])()
print("Accuracy", accuracy)
print(row0)
print(row1)