def test_classification():
# autofeat with numpy arrays but as classification
X, target = get_random_data()
target = np.array(target > target.mean(), dtype=int)
afreg = AutoFeatClassifier(verbose=1, feateng_steps=3)
df = afreg.fit_transform(X, target)
assert afreg.score(X, target) >= 0.9999, "Accuracy should be 1."
assert afreg.score(df, target) >= 0.9999, "Accuracy should be 1."
assert list(df.columns)[:3] == ["x000", "x001",
"x002"], "Wrong column names"
if check.func.__name__ not in successful_tests:
print(check.func.__name__)
successful_tests.add(check.func.__name__)
check(estimator)
# additionally check the class, but don't run all the other tests
for estimator, check in check_estimator(AutoFeatRegressor,
generate_only=True):
if check.func.__name__ not in successful_tests:
print(check.func.__name__)
successful_tests.add(check.func.__name__)
check(estimator)
print("## Running sklearn Classifier tests")
# we allow for nan in transform
successful_tests = set(["check_estimators_nan_inf"])
for estimator, check in check_estimator(AutoFeatClassifier(
feateng_steps=1, featsel_runs=1, always_return_numpy=True),
generate_only=True):
if check.func.__name__ not in successful_tests:
print(check.func.__name__)
successful_tests.add(check.func.__name__)
check(estimator)
# additionally check the class, but don't run all the other tests
for estimator, check in check_estimator(AutoFeatClassifier,
generate_only=True):
if check.func.__name__ not in successful_tests:
print(check.func.__name__)
successful_tests.add(check.func.__name__)
check(estimator)
print("## Running custom tests")
print("# test_do_almost_nothing")
def test_autofeat(dataset, feateng_steps=2):
# load data
X, y, units = load_classification_dataset(dataset)
# split in training and test parts
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=12)
# run autofeat
afreg = AutoFeatClassifier(verbose=1,
feateng_steps=feateng_steps,
units=units)
# fit autofeat on less data, otherwise ridge reg model with xval will overfit on new features
X_train_tr = afreg.fit_transform(X_train, y_train)
X_test_tr = afreg.transform(X_test)
print("autofeat new features:", len(afreg.new_feat_cols_))
print("autofeat Acc. on training data:",
accuracy_score(y_train, afreg.predict(X_train_tr)))
print("autofeat Acc. on test data:",
accuracy_score(y_test, afreg.predict(X_test_tr)))
# train rreg on transformed train split incl cross-validation for parameter selection
print("# Logistic Regression")
rreg = LogisticRegression(class_weight="balanced")
param_grid = {"C": np.logspace(-4, 4, 10)}
with warnings.catch_warnings():
warnings.simplefilter("ignore")
gsmodel = GridSearchCV(rreg, param_grid, cv=5)
gsmodel.fit(X_train_tr, y_train)
print("best params:", gsmodel.best_params_)
print("best score:", gsmodel.best_score_)
print("Acc. on training data:",
accuracy_score(y_train, gsmodel.predict(X_train_tr)))
print("Acc. on test data:",
accuracy_score(y_test, gsmodel.predict(X_test_tr)))
print("# Random Forest")
rforest = RandomForestClassifier(n_estimators=100, random_state=13)
param_grid = {"min_samples_leaf": [0.0001, 0.001, 0.01, 0.05, 0.1, 0.2]}
gsmodel = GridSearchCV(rforest, param_grid, cv=5)
gsmodel.fit(X_train_tr, y_train)
print("best params:", gsmodel.best_params_)
print("best score:", gsmodel.best_score_)
print("Acc. on training data:",
accuracy_score(y_train, gsmodel.predict(X_train_tr)))
print("Acc. on test data:",
accuracy_score(y_test, gsmodel.predict(X_test_tr)))
if gsmodel:
pickle.dump(gsmodel,
open('model.pkl',
'wb')) # store the artifact in docker container
if not os.environ["INPUT_MYINPUT"] == 'zeroinputs':
inputs = ast.literal_eval(os.environ["INPUT_MYINPUT"])
print("\nThe Predicted Ouput is :")
output = gsmodel.predict([inputs])
print(output)
else:
output = ["None"]
print("\nUser didn't provided inputs to predict")
print(
"\n=======================Action Completed========================"
)
print(f"::set-output name=myOutput::{output[0]}")