__str__ based bytes_repr for Pipeline objects

Author: tclose

pydra_ml/report.py

@@ -223,7 +223,7 @@ def gen_report_shap_class(results, output_dir="./", plot_top_n_shap=16):
                         f"""There were no {quadrant.upper()}s, this will output NaNs
                         in the csv and figure for this split column"""
                     )
-                shaps_i_quadrant = shaps_i[
+                shaps_i_quadrant = np.array(shaps_i)[
                     indexes.get(quadrant)
                 ]  # shape (P, F) P prediction x F feature_names
                 abs_weighted_shap_values = np.abs(shaps_i_quadrant) * split_performance
@@ -325,7 +325,7 @@ def gen_report_shap_regres(results, output_dir="./", plot_top_n_shap=16):
                         f"""There were no {quadrant.upper()}s, this will
                         output NaNs in the csv and figure for this split column"""
                     )
-                shaps_i_quadrant = shaps_i[
+                shaps_i_quadrant = np.array(shaps_i)[
                     indexes.get(quadrant)
                 ]  # shape (P, F) P prediction x F feature_names
                 abs_weighted_shap_values = np.abs(shaps_i_quadrant) * split_performance

pydra_ml/tasks.py

@@ -1,13 +1,12 @@
 #!/usr/bin/env python
 
-import cloudpickle as cp
 from pydra.utils.hash import Cache, register_serializer
 from sklearn.pipeline import Pipeline
 
 
 @register_serializer
 def bytes_repr_Pipeline(obj: Pipeline, cache: Cache):
-    yield cp.dumps(obj)
+    yield str(obj).encode()
 
 
 def read_file(filename, x_indices=None, target_vars=None, group=None):

pydra_ml/tests/test_classifier.py

@@ -1,5 +1,4 @@
 import os
-
 import numpy as np
 
 from ..classifier import gen_workflow, run_workflow
@@ -35,7 +34,7 @@ def test_classifier(tmpdir):
         "metrics": ["roc_auc_score", "accuracy_score"],
     }
     wf = gen_workflow(inputs, cache_dir=tmpdir)
-    results = run_workflow(wf, "cf", {"n_procs": 1})
+    results = run_workflow(wf, "serial", {"n_procs": 1})
     assert results[0][0]["ml_wf.clf_info"][1] == "MLPClassifier"
     assert results[0][0]["ml_wf.permute"]
     assert results[0][1].output.score[0][0] < results[1][1].output.score[0][0]