def make_anchor_tabular(dirname: Optional[Path] = None) -> AnchorTabular:
# train model
iris_data = load_iris()
clf = LogisticRegression(solver="liblinear", multi_class="ovr")
clf.fit(iris_data.data, iris_data.target)
# create explainer
explainer = AnchorTabular(clf.predict,
feature_names=iris_data.feature_names)
explainer.fit(iris_data.data, disc_perc=(25, 50, 75))
if dirname is not None:
explainer.save(dirname)
return explainer
import numpy as np
from sklearn.datasets import load_iris
from alibi.explainers import AnchorTabular
import requests
dataset = load_iris()
feature_names = dataset.feature_names
iris_data = dataset.data
model_url = "http://localhost:8003/seldon/seldon/iris/api/v1.0/predictions"
def predict_fn(X):
data = {"data": {"ndarray": X.tolist()}}
r = requests.post(model_url, json={"data": {"ndarray": [[1, 2, 3, 4]]}})
return np.array(r.json()["data"]["ndarray"])
explainer = AnchorTabular(predict_fn, feature_names)
explainer.fit(iris_data, disc_perc=(25, 50, 75))
explainer.save("./explainer/")
def make_anchor_tabular_income(
dirname: Optional[Path] = None) -> AnchorTabular:
# adapted from:
# https://docs.seldon.io/projects/alibi/en/latest/examples/anchor_tabular_adult.html
np.random.seed(0)
# prepare data
adult = fetch_adult()
data = adult.data
target = adult.target
feature_names = adult.feature_names
category_map = adult.category_map
data_perm = np.random.permutation(np.c_[data, target])
data = data_perm[:, :-1]
target = data_perm[:, -1]
# build model
idx = 30000
X_train, Y_train = data[:idx, :], target[:idx]
X_test, Y_test = data[idx + 1:, :], target[idx + 1:]
ordinal_features = [
x for x in range(len(feature_names))
if x not in list(category_map.keys())
]
ordinal_transformer = Pipeline(steps=[
("imputer", SimpleImputer(strategy="median")),
("scaler", StandardScaler()),
])
categorical_features = list(category_map.keys())
categorical_transformer = Pipeline(steps=[
("imputer", SimpleImputer(strategy="median")),
("onehot", OneHotEncoder(handle_unknown="ignore")),
])
preprocessor = ColumnTransformer(transformers=[
("num", ordinal_transformer, ordinal_features),
("cat", categorical_transformer, categorical_features),
])
clf = RandomForestClassifier(n_estimators=50)
model_pipeline = Pipeline(steps=[
("preprocess", preprocessor),
("classifier", clf),
])
model_pipeline.fit(X_train, Y_train)
explainer = AnchorTabular(model_pipeline.predict,
feature_names,
categorical_names=category_map,
seed=1)
explainer.fit(X_train, disc_perc=[25, 50, 75])
if dirname is not None:
explainer.save(dirname)
return explainer