def run_pipeline(events, models):
tNameId = bt.Feature_id_transform(min_size=0,
exclude_missing=True,
zero_based=True,
input_feature="name",
output_feature="nameId")
tAuto = pauto.Auto_transform(max_values_numeric_categorical=2,
exclude=["nameId", "name"])
sk_classifier = RandomForestClassifier(verbose=1)
classifier = ske.SKLearnClassifier(clf=sk_classifier,
target="nameId",
excluded=["name"])
cv = cf.Seldon_KFold(classifier, 5)
logger.info("cross validation scores %s", cv.get_scores())
transformers = [("tName", tNameId), ("tAuto", tAuto), ("cv", cv)]
p = Pipeline(transformers)
pw = sutl.Pipeline_wrapper()
df = pw.create_dataframe(events)
df2 = p.fit_transform(df)
pw.save_pipeline(p, models)
logger.info("cross validation scores %s", cv.get_scores())
def run_pipeline(events, models):
tNameId = bt.Feature_id_transform(min_size=0,
exclude_missing=True,
zero_based=True,
input_feature="name",
output_feature="nameId")
tAuto = pauto.Auto_transform(max_values_numeric_categorical=2,
exclude=["nameId", "name"])
xgb = xg.XGBoostClassifier(target="nameId",
target_readable="name",
excluded=["name"],
learning_rate=0.1,
silent=1)
cv = cf.Seldon_KFold(xgb, 5)
logger.info("cross validation scores %s", cv.get_scores())
transformers = [("tName", tNameId), ("tAuto", tAuto), ("cv", cv)]
p = Pipeline(transformers)
pw = sutl.Pipeline_wrapper()
df = pw.create_dataframe_from_files(events)
df2 = p.fit_transform(df)
pw.save_pipeline(p, models)
logger.info("cross validation scores %s", cv.get_scores())
def run_pipeline(events,models):
tAuto = pauto.Auto_transform(max_values_numeric_categorical=2,exclude=["label"])
detector = anod.iNNEDetector()
wrapper = aw.AnomalyWrapper(clf=detector,excluded=["label"])
transformers = [("tAuto",tAuto),("clf",wrapper)]
p = Pipeline(transformers)
pw = sutl.Pipeline_wrapper()
df = pw.create_dataframe_from_files(events)
df2 = p.fit_transform(df)
pw.save_pipeline(p,models)
def run_pipeline(events, models):
tNameId = bt.Feature_id_transform(min_size=0,
exclude_missing=True,
zero_based=True,
input_feature="name",
output_feature="nameId")
tAuto = pauto.Auto_transform(max_values_numeric_categorical=2,
exclude=["nameId", "name"])
keras = sk.KerasClassifier(model_create=create_model,
target="nameId",
target_readable="name")
transformers = [("tName", tNameId), ("tAuto", tAuto), ("keras", keras)]
p = Pipeline(transformers)
pw = sutl.Pipeline_wrapper()
df = pw.create_dataframe(events)
df2 = p.fit(df)
pw.save_pipeline(p, models)
def run_pipeline(events, models):
tNameId = bt.Feature_id_transform(min_size=0,
exclude_missing=True,
zero_based=True,
input_feature="name",
output_feature="nameId")
tAuto = pauto.Auto_transform(max_values_numeric_categorical=2,
exclude=["nameId", "name"])
xgb = xg.XGBoostClassifier(target="nameId",
target_readable="name",
excluded=["name"],
learning_rate=0.1,
silent=0)
transformers = [("tName", tNameId), ("tAuto", tAuto), ("xgb", xgb)]
p = Pipeline(transformers)
pw = sutl.Pipeline_wrapper()
df = pw.create_dataframe(events)
df2 = p.fit(df)
pw.save_pipeline(p, models)
import seldon.pipeline.auto_transforms as auto
import pandas as pd
df = pd.DataFrame([{
"a": 10,
"b": 1,
"c": "cat"
}, {
"a": 5,
"b": 2,
"c": "dog",
"d": "Nov 13 08:36:29 2015"
}, {
"a": 10,
"b": 3,
"d": "Oct 13 10:50:12 2015"
}])
t = auto.Auto_transform(max_values_numeric_categorical=2, date_cols=["d"])
t.fit(df)
df2 = t.transform(df)
print df2