def test_save_and_load(self):
self.assertTrue(
"Private" in list(self.data["train"]["X"]["workclass"]))
early_stop = EarlyStopping({"metric": {"name": "logloss"}})
metric_logger = MetricLogger({"metric_names": ["logloss", "auc"]})
il = IterativeLearner(self.train_params,
callbacks=[early_stop, metric_logger])
il.train(self.data)
y_predicted = il.predict(self.data["train"]["X"])
metric = Metric({"name": "logloss"})
loss_1 = metric(self.data["train"]["y"], y_predicted)
json_desc = il.to_json()
il2 = IterativeLearner(self.train_params, callbacks=[])
self.assertTrue(il.uid != il2.uid)
il2.from_json(json_desc)
self.assertTrue(il.uid == il2.uid)
y_predicted_2 = il2.predict(self.data["train"]["X"])
loss_2 = metric(self.data["train"]["y"], y_predicted_2)
assert_almost_equal(loss_1, loss_2)
uids = [i.uid for i in il.learners]
uids2 = [i.uid for i in il2.learners]
for u in uids:
self.assertTrue(u in uids2)
def test_fit_and_predict_kfold(self):
self.assertTrue(
"Private" in list(self.data["train"]["X"]["workclass"]))
early_stop = EarlyStopping({"metric": {"name": "logloss"}})
metric_logger = MetricLogger({"metric_names": ["logloss", "auc"]})
params = copy.deepcopy(self.train_params)
params["validation"] = {
"validation_type": "kfold",
"k_folds": 5,
"shuffle": True,
}
il = IterativeLearner(params, callbacks=[early_stop, metric_logger])
il.train(self.data)
oof = il.get_out_of_folds()
self.assertEqual(len(np.unique(oof.index)), oof.shape[0])
self.assertTrue(
np.array_equal(oof.index, self.data["train"]["X"].index))
self.assertTrue(oof.shape[0], self.data["train"]["X"].shape[0])
self.assertTrue(
"Private" in list(self.data["train"]["X"]["workclass"]))
y_predicted = il.predict(self.data["train"]["X"])
self.assertTrue(
"Private" in list(self.data["train"]["X"]["workclass"]))
metric = Metric({"name": "logloss"})
loss = metric(self.data["train"]["y"], y_predicted)
self.assertTrue(loss < 0.6)
def test_fit_and_predict(self):
il = IterativeLearner(self.train_params, callbacks=[])
il.train(self.data)
y_predicted = il.predict(self.X)
metric = Metric({"name": "logloss"})
loss = metric(self.y, y_predicted)
self.assertTrue(loss < 0.4)
def test_save_and_load(self):
il = IterativeLearner(self.train_params, callbacks=[])
il.train(self.data)
metric = Metric({"name": "logloss"})
loss = metric(self.y, il.predict(self.X))
json_desc = il.to_json()
il2 = IterativeLearner(json_desc.get("params"), callbacks=[])
self.assertTrue(il.uid != il2.uid)
il2.from_json(json_desc)
self.assertTrue(il.uid == il2.uid)
loss2 = metric(self.y, il2.predict(self.X))
assert_almost_equal(loss, loss2)
uids = [i.uid for i in il.learners]
uids2 = [i.uid for i in il2.learners]
for u in uids:
self.assertTrue(u in uids2)
def test_fit_and_predict(self):
early_stop = EarlyStopping({"metric": {"name": "logloss"}})
metric_logger = MetricLogger({"metric_names": ["logloss", "auc"]})
il = IterativeLearner(self.train_params,
callbacks=[early_stop, metric_logger])
il.train(self.data)
y_predicted = il.predict(self.X)
metric = Metric({"name": "logloss"})
loss = metric(self.y, y_predicted)
self.assertTrue(loss < 0.4)
def test_fit_and_predict_split(self):
self.assertTrue("Private" in list(self.data["train"]["X"]["workclass"]))
early_stop = EarlyStopping({"metric": {"name": "logloss"}})
metric_logger = MetricLogger({"metric_names": ["logloss", "auc"]})
il = IterativeLearner(self.train_params, callbacks=[early_stop, metric_logger])
il.train(self.data)
self.assertTrue("Private" in list(self.data["train"]["X"]["workclass"]))
y_predicted = il.predict(self.data["train"]["X"])
self.assertTrue("Private" in list(self.data["train"]["X"]["workclass"]))
metric = Metric({"name": "logloss"})
loss = metric(self.data["train"]["y"], y_predicted)
self.assertTrue(loss < 0.6)
def run(self):
# read data
logger.info("ComputeBatchPrediction::run")
batch = MLBatchPrediction.objects.get(pk=self.job_params.get("db_id"))
logger.info("batch", batch)
# {'parent_mlmodel': 9, 'parent_dataframe': 1, 'db_id': 1, 'created_by_id': 1, 'parent_organization_id': 1, 'parent_project_id': 1}
mlmodel = MLModel.objects.get(pk=self.job_params.get("parent_mlmodel"))
logger.info(mlmodel.save_details)
logger.info(mlmodel.all_params)
il = IterativeLearner(mlmodel.all_params)
il.load(mlmodel.save_details)
logger.info(batch.parent_dataframe.absolute_path)
input_df = DataServe.get(batch.parent_dataframe.absolute_path)
predictions = il.predict(input_df)
logger.info(predictions)
filename = "predictions-{0}.csv".format(str(uuid.uuid4())[:8])
organization_slug = batch.parent_organization.slug
project_id = batch.parent_project.id
relative_dir = "org_{0}_proj_{1}".format(organization_slug, project_id)
relative_path = os.path.join(relative_dir, filename)
result_absolute_path = Storage().get_path(relative_dir, filename)
logger.info(result_absolute_path)
df = pd.DataFrame({"prediction": predictions})
df.to_csv(result_absolute_path, index=False)
# create mljar data frame
result_df = DataFrame(
source_id=self.job_params.get("parent_dataframe"), # fix this
absolute_path=result_absolute_path,
file_size=1, # TODO fix the file size
columns_details="", # we can describe any data frame (always :-))
preview_absolute_path="",
created_by_id=self.job_params["created_by_id"],
parent_organization_id=self.job_params["parent_organization_id"],
parent_project_id=self.job_params["parent_project_id"],
)
result_df.save()
batch.result_dataframe = result_df
batch.status = "done"
batch.save()