import pandas as pd
from hyperflow.estimator.base import HyperFlowEstimator
from hyperflow.hdl.hdl_constructor import HDL_Constructor
from hyperflow.tuner.tuner import Tuner
df = pd.read_csv("../data/QSAR.csv")
hdl_constructor = HDL_Constructor(
DAG_descriptions={
"num->var": "compress.variance",
"var->pea": {
"_name": "compress.pearson",
"n_jobs": 6
},
"pea->target": "logistic_regression"
})
tuner = Tuner(run_limit=12, initial_runs=12, search_method="smac")
hyperflow_pipeline = HyperFlowEstimator(tuner, hdl_constructor)
column_descriptions = {"id": "Name", "target": "labels"}
hyperflow_pipeline.fit(X=df, column_descriptions=column_descriptions, n_jobs=3)
from hyperflow.tuner.tuner import Tuner
df = pd.read_csv("../examples/classification/train_classification.csv")
ss = ShuffleSplit(n_splits=1, random_state=0, test_size=0.25)
train_ix, test_ix = next(ss.split(df))
df_train = df.iloc[train_ix, :]
df_test = df.iloc[test_ix, :]
tuner = Tuner(
initial_runs=5,
run_limit=12,
)
hdl_constructor = HDL_Constructor(
DAG_descriptions={
"nan->imp": "impute.fill_abnormal",
"imp->{cat_name=cat,num_name=num}": "operate.split.cat_num",
"cat->num": "encode.cat_boost|scale.standardize",
"num->target": "reduce.pca|lightgbm"
})
hyperflow_pipeline = HyperFlowEstimator(tuner, hdl_constructor)
column_descriptions = {
"id": "PassengerId",
"target": "Survived",
"ignore": "Name"
}
hyperflow_pipeline.fit(X=df_train,
X_test=df_test,
column_descriptions=column_descriptions,
n_jobs=1)
if ind.any():
temp = newfeature[:, i]
a = temp[~np.isnan(temp)].mean()
newfeature[:, i][np.isnan(temp)] = a
# 标准化
stdScale = StandardScaler().fit(newfeature)
newfeaturenorm = stdScale.transform(newfeature)
# 区间化
bins = [-9, -5, -3, -1, 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 24]
new_range = pd.cut(df.Label, bins)
newlabel = np.array(df.Label)
return newfeaturenorm, newlabel, new_range
x_train, y_train, y_range = data_preprocessing()
tuner = Tuner(
initial_runs=12,
run_limit=120,
)
hdl_constructor = HDL_Constructor(DAG_descriptions={"num->target": "lightgbm"})
resource_manager = ResourceManager(os.getcwd() + "/for_hxw_result")
hyperflow_pipeline = HyperFlowEstimator(tuner,
hdl_constructor,
ensemble_builder=False)
hyperflow_pipeline.fit(X=x_train, y=y_train, n_jobs=3)
joblib.dump(hyperflow_pipeline, "hyperflow_pipeline_for_hxw.bz")