def test_predict_proba_in_regression(self):
model = AutoML(explain_level=0,
verbose=0,
random_state=1,
results_path=self.automl_dir)
model.fit(boston.data, boston.target)
with self.assertRaises(AutoMLException) as context:
# Try to call predict_proba in regression task
model.predict_proba(boston.data)
def define_and_evaluate_mljar_pipeline(X, y, random_state=0):
outer_cv = StratifiedKFold(n_splits=4, shuffle=True, random_state=random_state)
nested_scores = []
for train_inds, test_inds in outer_cv.split(X, y):
X_train, y_train = X[train_inds, :], y[train_inds]
X_test, y_test = X[test_inds, :], y[test_inds]
binary = len((set(y))) == 2
eval_metric = "auc" if binary else "logloss"
ml_task = "binary_classification" if binary else "multiclass_classification"
shutil.rmtree("AutoML_1", ignore_errors=True)
automl = AutoML(results_path="AutoML_1", mode="Compete", eval_metric=eval_metric, total_time_limit=SEC, ml_task=ml_task)
automl.fit(X_train, y_train)
y_pred = automl.predict_proba(X_test)
# same as roc_auc_ovr_weighted
if binary:
score = roc_auc_score(y_test, y_pred[:, 1], average="weighted", multi_class="ovr")
else:
score = roc_auc_score(y_test, y_pred, average="weighted", multi_class="ovr")
nested_scores.append(score)
return nested_scores
import pandas as pd
from supervised import AutoML
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
sub = pd.read_csv("sample_submission.csv")
x_cols = train.columns[2:]
print(x_cols)
automl = AutoML(mode="Compete", eval_metric="auc", total_time_limit=4 * 3600)
automl.fit(train[x_cols], train["target"])
sub[sub.columns[1:]] = automl.predict_proba(test)[:, 1]
sub.to_csv("sub_1.csv", index=False)
import pandas as pd
from supervised import AutoML
train = pd.read_csv("~/Downloads/tabular-playground-series-mar-2021/train.csv")
test = pd.read_csv("~/Downloads/tabular-playground-series-mar-2021/test.csv")
X_train = train.drop(["id", "target"], axis=1)
y_train = train.target
X_test = test.drop(["id"], axis=1)
automl = AutoML(
mode="Optuna",
eval_metric="auc",
algorithms=["CatBoost"],
optuna_time_budget=1800, # tune each algorithm for 30 minutes
total_time_limit=48 *
3600, # total time limit, set large enough to have time to compute all steps
features_selection=False)
automl.fit(X_train, y_train)
preds = automl.predict_proba(X_test)
submission = pd.DataFrame({"id": test.id, "target": preds[:, 1]})
submission.to_csv("1_submission.csv", index=False)
import pandas as pd
from supervised import AutoML
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
sub = pd.read_csv("sample_submission.csv")
x_cols = train.columns[2:]
automl = AutoML(mode="Compete",
total_time_limit=4 * 3600,
stack_models=True,
features_selection=False)
automl.fit(train[x_cols], train["target"])
sub["PredictedProb"] = automl.predict_proba(test)[:, 1]
sub.to_csv("sub_1.csv", index=False)
import pandas as pd
from supervised import AutoML
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
sub = pd.read_csv("sample_submission.csv")
x_cols = train.columns[2:]
automl = AutoML(mode="Compete", total_time_limit=4 * 3600, eval_metric="auc")
automl.fit(train[x_cols], train["target"])
sub["target"] = automl.predict_proba(test)[:, 1]
sub.to_csv("sub_1.csv", index=False)
