test(evaluate): dynamically serialize data.pickle

test/evaluate/input/input-interactome.txt

@@ -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-nodes.txt

@@ -0,0 +1,27 @@
+NODEID	prize	active	dummy	sources	targets
+N					
+T					
+I					
+Z					
+Q					
+P					
+C	5.7	True			True
+O					
+W					
+Y					
+1S					
+1L					
+1B					
+1D					
+1V					
+1K					
+1M					
+1H					
+1U					
+1R					
+2X					
+2J					
+2E					
+2F					
+2G					
+2A	2.0	True	True	True	

test/evaluate/test_evaluate.py

@@ -1,8 +1,10 @@
 import filecmp
+import pickle
 from pathlib import Path
 
 import pandas as pd
 
+from spras.dataset import Dataset
 from spras.evaluation import Evaluation
 
 INPUT_DIR = 'test/evaluate/input/'
@@ -15,15 +17,26 @@ class TestEvaluate:
     @classmethod
     def setup_class(cls):
         """
-        Create the expected output directory
+        Create the expected output directory and pickled file
         """
         Path(OUT_DIR).mkdir(parents=True, exist_ok=True)
 
+        dataset = Dataset({
+            "label": 'data0',
+            "edge_files": ["input-interactome.txt"],
+            "node_files": ["input-nodes.txt"],
+            "data_dir": "test/evaluate/input",
+            "other_files": []
+        })
+
+        with open("test/evaluate/output/data.pickle", "wb") as handle:
+            pickle.dump(dataset, handle)
+
     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)
@@ -32,7 +45,7 @@ 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)
@@ -44,7 +57,7 @@ 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)