def test_validate_hdl2(self):
train_df, test_df = datasets.load("titanic", return_train_test=True)
trained_pipeline = AutoFlowClassifier(
initial_runs=1,
run_limit=3,
n_jobs=1,
included_highR_nan_imputers=["operate.pop"],
debug=True,
n_jobs_in_algorithm=5,
resource_manager=self.mock_resource_manager)
column_descriptions = {
"id": "PassengerId",
"target": "Survived",
"text": "Name"
}
try:
trained_pipeline.fit(X_train=train_df,
X_test=test_df,
column_descriptions=column_descriptions,
splitter=KFold(n_splits=3,
shuffle=True,
random_state=42),
fit_ensemble_params=True,
is_not_realy_run=True)
assert Exception("didn't detect wrong HDL.")
except Exception as e:
self.assertEqual(
str(e),
"In step 'highR_nan->nan', user defined packege : 'operate.pop' does not exist!"
)
def test_splitter(self):
X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
random_state=42)
groups = np.zeros([X_train.shape[0]])
groups[:len(groups) // 2] = 1
pipe = AutoFlowClassifier(DAG_workflow={
"num->target": ["linearsvc", "svc", "logistic_regression"]
},
initial_runs=1,
run_limit=1,
debug=True,
resource_manager=self.mock_resource_manager)
pipe.fit(X_train, y_train, groups=groups)
score = pipe.score(X_test, y_test)
print(score)
y_true_indexes = pipe.estimator.y_true_indexes_list[0]
splitter = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
for observed_y_true_index, (_, valid_index) in zip(
y_true_indexes, splitter.split(X_train, y_train, groups)):
assert np.all(observed_y_true_index == valid_index)
self.assertGreater(score, 0.5)
def test_classifier(self):
X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y)
hdl_bank = get_default_hdl_bank()
hdl_bank["classification"]["mlp"] = {
"hidden_layer_sizes": {
"_type": "int_quniform",
"_value": [10, 1000, 10]
},
"activation": {
"_type": "choice",
"_value": ["relu", "tanh", "logistic"]
},
}
trained_pipeline = AutoFlowClassifier(
initial_runs=1,
run_limit=2,
n_jobs=1,
included_classifiers=["mlp"],
hdl_bank=hdl_bank,
model_registry={"mlp": MLPClassifier},
debug=True,
random_state=55,
resource_manager=self.mock_resource_manager)
trained_pipeline.fit(
X_train=X,
y_train=y,
X_test=X_test,
y_test=y_test,
splitter=KFold(n_splits=3, shuffle=True, random_state=42),
)
joblib.dump(trained_pipeline, "autoflow_classification.bz2")
# ---
predict_pipeline = joblib.load("autoflow_classification.bz2")
score = predict_pipeline.score(X_test, y_test)
print(score)
import pandas as pd
from sklearn.model_selection import KFold
from autoflow import AutoFlowClassifier
train_df = pd.read_csv("./data/train_classification.csv")
test_df = pd.read_csv("./data/test_classification.csv")
trained_pipeline = AutoFlowClassifier(initial_runs=5,
run_limit=10,
n_jobs=3,
included_classifiers=["lightgbm"],
db_type="postgresql",
db_params={
"user": "******",
"host": "0.0.0.0",
"port": 5432
},
store_path="/autoflow",
file_system="hdfs",
should_store_intermediate_result=True,
file_system_params={
"url": "http://0.0.0.0:50070",
"user": "******"
})
column_descriptions = {
"id": "PassengerId",
"target": "Survived",
"ignore": "Name"
}
trained_pipeline.fit(
X_train=train_df,
from pathlib import Path
import joblib
import pandas as pd
from sklearn.model_selection import KFold
import autoflow
from autoflow import AutoFlowClassifier
examples_path = Path(autoflow.__file__).parent.parent / "examples"
train_df = pd.read_csv(examples_path / "data/train_classification.csv")
test_df = pd.read_csv(examples_path / "data/test_classification.csv")
trained_pipeline = AutoFlowClassifier(
initial_runs=1,
run_limit=1,
n_jobs=1,
included_classifiers=["lightgbm"],
debug=True,
should_store_intermediate_result=True,
hdl_metadata={"key1": "hdl_metadata_test1"})
column_descriptions = {
"id": "PassengerId",
"target": "Survived",
"ignore": "Name"
}
# if not os.path.exists("autoflow_classification.bz2"):
trained_pipeline.fit(task_metadata={"key1": "task_metadata_test1"},
dataset_metadata={"key1": "dataset_metadata_test1"},
X_train=train_df,
X_test=test_df,
column_descriptions=column_descriptions,
splitter=KFold(n_splits=3, shuffle=True, random_state=42),
# @Author : qichun tang # @Contact : [email protected] import joblib import pandas as pd from sklearn.model_selection import ShuffleSplit from autoflow import AutoFlowClassifier train_df = pd.read_csv("./data/train_classification.csv") test_df = pd.read_csv("./data/test_classification.csv") trained_pipeline = AutoFlowClassifier( initial_runs=12, run_limit=12, n_jobs=3, included_classifiers=[ "scale.standardize|svc", "scale.standardize|knn", "scale.standardize|logistic_regression", "gaussian_nb", "extra_trees", "lightgbm" ], ) column_descriptions = { "id": "PassengerId", "target": "Survived", "ignore": "Name" } trained_pipeline.fit( X_train=train_df, X_test=test_df, column_descriptions=column_descriptions, fit_ensemble_params=False, splitter=ShuffleSplit(n_splits=1, test_size=0.25, random_state=42),
import pandas as pd
from sklearn.model_selection import KFold
import autoflow
from autoflow import AutoFlowClassifier
from autoflow.datasets import load
train_df = load("qsar")
trained_pipeline = AutoFlowClassifier(
initial_runs=1,
run_limit=5,
n_jobs=1,
included_classifiers=["lightgbm"],
debug=True,
num2purified_workflow={
"num->compressed": {
"_name": "compress.f1score",
"threshold": 0.9,
"n_jobs": 12,
# "cache_intermediate":False
},
"compressed->purified": ["scale.standardize", "operate.keep_going"],
}
# should_store_intermediate_result=True, # 测试对中间结果存储的正确性
)
column_descriptions = {"target": "target"}
# if not os.path.exists("autoflow_classification.bz2"):
trained_pipeline.fit(X_train=train_df,
column_descriptions=column_descriptions,
splitter=KFold(n_splits=3, shuffle=True, random_state=42),
fit_ensemble_params=False)
# @Author : qichun tang # @Contact : [email protected] import pickle from pathlib import Path from sklearn.model_selection import KFold from autoflow import AutoFlowClassifier from autoflow import datasets train_df, test_df = datasets.load("titanic", return_train_test=True) trained_pipeline = AutoFlowClassifier( initial_runs=1, run_limit=1, n_jobs=1, included_classifiers=["catboost"], debug=True, n_jobs_in_algorithm=5 # should_store_intermediate_result=True, # 测试对中间结果存储的正确性 ) column_descriptions = { "id": "PassengerId", "target": "Survived", "text": "Name" } # if not os.path.exists("autoflow_classification.bz2"): trained_pipeline.fit( X_train=train_df, X_test=test_df, column_descriptions=column_descriptions, splitter=KFold(n_splits=3, shuffle=True, random_state=42),
"hidden_layer_sizes": {
"_type": "int_quniform",
"_value": [10, 1000, 10]
},
"activation": {
"_type": "choice",
"_value": ["relu", "tanh", "logistic"]
},
}
train_df = pd.read_csv("./data/train_classification.csv")
test_df = pd.read_csv("./data/test_classification.csv")
trained_pipeline = AutoFlowClassifier(initial_runs=5,
run_limit=10,
n_jobs=1,
included_classifiers=["mlp"],
should_store_intermediate_result=True,
hdl_bank=hdl_bank,
model_registry={"mlp": MLPClassifier},
debug=True,
random_state=55)
column_descriptions = {
"id": "PassengerId",
"target": "Survived",
"ignore": "Name"
}
trained_pipeline.fit(
X_train=train_df,
X_test=test_df,
column_descriptions=column_descriptions,
splitter=KFold(n_splits=3, shuffle=True, random_state=42),
)
import os
from pathlib import Path
import pandas as pd
import autoflow
from autoflow import AutoFlowClassifier, DataManager
examples_path = Path(autoflow.__file__).parent.parent / "examples"
train_df = pd.read_csv(examples_path / "data/train_classification.csv")
test_df = pd.read_csv(examples_path / "data/test_classification.csv")
pipe = AutoFlowClassifier(initial_runs=5, run_limit=10, n_jobs=1, included_classifiers=["lightgbm"])
column_descriptions = {
"id": "PassengerId",
"target": "Survived",
"ignore": "Name"
}
pipe.data_manager = DataManager(X_train=train_df, X_test=test_df, column_descriptions=column_descriptions)
pipe.hdl_constructors[0].run(pipe.data_manager, pipe.random_state, pipe.highR_cat_threshold)
graph = pipe.hdl_constructors[0].draw_workflow_space()
open("workflow_space.gv").write(graph.source)
cmd = f'''dot -Tpng -Gsize=9,15\! -Gdpi=300 -oworkflow_space.png workflow_space.gv'''
os.system(cmd)
import joblib
import pandas as pd
from sklearn.model_selection import KFold
from autoflow import AutoFlowClassifier
# load data from csv file
train_df = pd.read_csv("../data/train_classification.csv")
test_df = pd.read_csv("../data/test_classification.csv")
# initial_runs -- initial runs are totally random search, to provide experience for SMAC algorithm.
# run_limit -- is the maximum number of runs.
# n_jobs -- defines how many search processes are started.
# included_classifiers -- restrict the search space . lightgbm is the only classifier that needs to be selected
# per_run_time_limit -- restrict the run time. if a trial during 60 seconds, it is expired, should be killed.
trained_pipeline = AutoFlowClassifier(initial_runs=5, run_limit=10, n_jobs=1, included_classifiers=["lightgbm"],
per_run_time_limit=60)
# describing meaning of columns. `id`, `target` and `ignore` all has specific meaning
# `id` is a column name means unique descriptor of each rows,
# `target` column in the dataset is what your model will learn to predict
# `ignore` is some columns which contains irrelevant information
column_descriptions = {
"id": "PassengerId",
"target": "Survived",
"ignore": "Name"
}
if not os.path.exists("autoflow_classification.bz2"):
# pass `train_df`, `test_df` and `column_descriptions` to classifier,
# if param `fit_ensemble_params` set as "auto", Stack Ensemble will be used
# ``splitter`` is train-valid-dataset splitter, in here it is set as 3-Fold Cross Validation
trained_pipeline.fit(
X_train=train_df, X_test=test_df, column_descriptions=column_descriptions,
