Merge pull request #340 from tristan-f-r/data-pickle-repr

test(evaluate): dynamically serialize data.pickle

Author: tristan-f-r

test/evaluate/input/data.pickle

@@ -0,0 +1,25 @@
+A	B	0.98	U
+B	C	0.77	U
+C	D	0.77	U
+D	E	0.77	U
+E	F	0.77	U
+F	G	0.12	U
+G	H	0.89	U
+H	I	0.59	U
+I	J	0.50	U
+J	K	0.76	U
+K	L	0.92	U
+L	M	0.66	U
+M	N	0.66	U
+N	O	0.66	U
+O	P	0.66	U
+P	Q	0.66	U
+Q	R	0.66	U
+R	S	0.66	U
+S	T	0.66	U
+T	U	0.66	U
+U	V	0.66	U
+V	W	0.66	U
+W	X	0.66	U
+X	Y	0.66	U
+Y	Z	0.66	U

test/evaluate/input/input-interactome.txt

@@ -0,0 +1,3 @@
+NODEID	prize	active	dummy	sources	targets
+N							
+C	5.7	True			True

test/evaluate/input/input-nodes.txt

@@ -1,9 +1,11 @@
 import filecmp
+import pickle
 from pathlib import Path
 
 import pandas as pd
 
 import spras.analysis.ml as ml
+from spras.dataset import Dataset
 from spras.evaluation import Evaluation
 
 INPUT_DIR = 'test/evaluate/input/'
@@ -17,10 +19,24 @@ class TestEvaluate:
     @classmethod
     def setup_class(cls):
         """
-        Create the expected output directory
+        Create the expected output directory and pickled toy dataset file
         """
         Path(OUT_DIR).mkdir(parents=True, exist_ok=True)
 
+        out_dataset = Path(OUT_DIR, 'data.pickle')
+        out_dataset.unlink(missing_ok=True)
+
+        dataset = Dataset({
+            "label": 'toy',
+            "edge_files": ["input-interactome.txt"],
+            "node_files": ["input-nodes.txt"],
+            "data_dir": INPUT_DIR,
+            "other_files": []
+        })
+
+        with open(out_dataset, "wb") as f:
+            pickle.dump(dataset, f)
+
     def test_precision_recall_pca_chosen_pathway(self):
         output_file = Path(OUT_DIR + "test-pr-per-pathway-pca-chosen.txt")
         output_file.unlink(missing_ok=True)
@@ -63,7 +79,7 @@ def test_node_ensemble(self):
         out_path_file = Path(OUT_DIR + 'node-ensemble.csv')
         out_path_file.unlink(missing_ok=True)
         ensemble_network = [INPUT_DIR + 'ensemble-network.tsv']
-        input_network = INPUT_DIR + 'data.pickle'
+        input_network = OUT_DIR + 'data.pickle'
         node_ensemble_dict = Evaluation.edge_frequency_node_ensemble(GS_NODE_TABLE, ensemble_network, input_network)
         node_ensemble_dict['ensemble'].to_csv(out_path_file, sep='\t', index=False)
         assert filecmp.cmp(out_path_file, EXPECT_DIR + 'expected-node-ensemble.csv', shallow=False)
@@ -72,7 +88,7 @@ def test_empty_node_ensemble(self):
         out_path_file = Path(OUT_DIR + 'empty-node-ensemble.csv')
         out_path_file.unlink(missing_ok=True)
         empty_ensemble_network = [INPUT_DIR + 'empty-ensemble-network.tsv']
-        input_network = INPUT_DIR + 'data.pickle'
+        input_network = OUT_DIR + 'data.pickle'
         node_ensemble_dict = Evaluation.edge_frequency_node_ensemble(GS_NODE_TABLE, empty_ensemble_network,
                                                                      input_network)
         node_ensemble_dict['empty'].to_csv(out_path_file, sep='\t', index=False)
@@ -84,7 +100,7 @@ def test_multiple_node_ensemble(self):
         out_path_empty_file = Path(OUT_DIR + 'empty-node-ensemble.csv')
         out_path_empty_file.unlink(missing_ok=True)
         ensemble_networks = [INPUT_DIR + 'ensemble-network.tsv', INPUT_DIR + 'empty-ensemble-network.tsv']
-        input_network = INPUT_DIR + 'data.pickle'
+        input_network = OUT_DIR + 'data.pickle'
         node_ensemble_dict = Evaluation.edge_frequency_node_ensemble(GS_NODE_TABLE, ensemble_networks, input_network)
         node_ensemble_dict['ensemble'].to_csv(out_path_file, sep='\t', index=False)
         assert filecmp.cmp(out_path_file, EXPECT_DIR + 'expected-node-ensemble.csv', shallow=False)