From f1cbe331f56051b641b0a4b22410fd04f2eb4323 Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Tue, 3 Jun 2025 16:59:51 -0700
Subject: [PATCH 01/12] fix: check if edge weights are between 0 and 1

Closes #237.
---
 spras/dataset.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/spras/dataset.py b/spras/dataset.py
index cf79a3b15..caa47a8b6 100644
--- a/spras/dataset.py
+++ b/spras/dataset.py
@@ -89,6 +89,9 @@ def load_files_from_dict(self, dataset_dict):
                 "Direction",
             ]
 
+            if not pd.Series(self.interactome.Weight).between(0, 1).all():
+                raise ValueError("A member of the Weight column is not between 0 and 1.")
+
             # Make directionality column case-insensitive
             self.interactome["Direction"] = self.interactome["Direction"].str.upper()
             if not self.interactome["Direction"].isin(["U", "D"]).all():

From f89e7332ea2f38a7bae8677ff625d2c9e4edf5dd Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Wed, 4 Jun 2025 08:44:52 -0700
Subject: [PATCH 02/12] fix: better err message on invalid ranges

---
 spras/dataset.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/spras/dataset.py b/spras/dataset.py
index caa47a8b6..6e9914bc1 100644
--- a/spras/dataset.py
+++ b/spras/dataset.py
@@ -89,8 +89,12 @@ def load_files_from_dict(self, dataset_dict):
                 "Direction",
             ]
 
-            if not pd.Series(self.interactome.Weight).between(0, 1).all():
-                raise ValueError("A member of the Weight column is not between 0 and 1.")
+            weight_series = pd.Series(self.interactome.Weight)
+            weight_series_out_range = ~weight_series.between(0, 1)
+            if weight_series_out_range.any():
+                # Offset the index by 1 to match the file line numbers.
+                weight_true = (weight_series_out_range.index[weight_series_out_range == True] + 1).tolist()
+                raise ValueError(f"The following lines of the interactome: ({str(weight_true)}) have weights not between 0 and 1.")
 
             # Make directionality column case-insensitive
             self.interactome["Direction"] = self.interactome["Direction"].str.upper()

From 8e4016b57dd57e67e20ed65da9677edbb1ffe148 Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Fri, 13 Jun 2025 09:30:18 -0700
Subject: [PATCH 03/12] test: dataset

---
 spras/dataset.py                              | 14 ++++++++--
 test/dataset/fixtures/empty/network.txt       |  0
 test/dataset/fixtures/empty/nodes.txt         |  0
 test/dataset/fixtures/empty/scores.txt        |  0
 test/dataset/fixtures/in-range/network.txt    |  2 ++
 .../dataset/fixtures/in-range/node-prizes.txt |  3 ++
 test/dataset/fixtures/in-range/sources.txt    |  1 +
 test/dataset/fixtures/in-range/targets.txt    |  1 +
 test/dataset/test_dataset.py                  | 28 +++++++++++++++++++
 9 files changed, 46 insertions(+), 3 deletions(-)
 create mode 100644 test/dataset/fixtures/empty/network.txt
 create mode 100644 test/dataset/fixtures/empty/nodes.txt
 create mode 100644 test/dataset/fixtures/empty/scores.txt
 create mode 100644 test/dataset/fixtures/in-range/network.txt
 create mode 100644 test/dataset/fixtures/in-range/node-prizes.txt
 create mode 100644 test/dataset/fixtures/in-range/sources.txt
 create mode 100644 test/dataset/fixtures/in-range/targets.txt
 create mode 100644 test/dataset/test_dataset.py

diff --git a/spras/dataset.py b/spras/dataset.py
index 6e9914bc1..7f68d31b6 100644
--- a/spras/dataset.py
+++ b/spras/dataset.py
@@ -1,5 +1,6 @@
 import os
 import pickle as pkl
+from typing import TypedDict
 import warnings
 
 import pandas as pd
@@ -11,13 +12,20 @@
 Methods and intermediate state for loading data and putting it into pandas tables for use by pathway reconstruction algorithms.
 """
 
+class DatasetDict(TypedDict):
+    label: str
+    node_files: list[str | os.PathLike]
+    edge_files: list[str | os.PathLike]
+    other_files: list[str | os.PathLike]
+    data_dir: str | os.PathLike
+
 
 class Dataset:
 
     NODE_ID = "NODEID"
     warning_threshold = 0.05  # Threshold for scarcity of columns to warn user
 
-    def __init__(self, dataset_dict):
+    def __init__(self, dataset_dict: DatasetDict):
         self.label = None
         self.interactome = None
         self.node_table = None
@@ -43,7 +51,7 @@ def from_file(cls, file_name):
         with open(file_name, "rb") as f:
             return pkl.load(f)
 
-    def load_files_from_dict(self, dataset_dict):
+    def load_files_from_dict(self, dataset_dict: DatasetDict):
         """
         Loads data files from dataset_dict, which is one dataset dictionary from the list
         in the config file with the fields in the config file.
@@ -120,7 +128,7 @@ def load_files_from_dict(self, dataset_dict):
                     os.path.join(data_loc, node_file), header=None
                 )
                 single_node_table.columns = [self.NODE_ID]
-                new_col_name = node_file.split(".")[0]
+                new_col_name = str(node_file).split(".")[0]
                 single_node_table[new_col_name] = True
 
             # Use only keys from the existing node table so that nodes that are not in the interactome are ignored
diff --git a/test/dataset/fixtures/empty/network.txt b/test/dataset/fixtures/empty/network.txt
new file mode 100644
index 000000000..e69de29bb
diff --git a/test/dataset/fixtures/empty/nodes.txt b/test/dataset/fixtures/empty/nodes.txt
new file mode 100644
index 000000000..e69de29bb
diff --git a/test/dataset/fixtures/empty/scores.txt b/test/dataset/fixtures/empty/scores.txt
new file mode 100644
index 000000000..e69de29bb
diff --git a/test/dataset/fixtures/in-range/network.txt b/test/dataset/fixtures/in-range/network.txt
new file mode 100644
index 000000000..01116bd07
--- /dev/null
+++ b/test/dataset/fixtures/in-range/network.txt
@@ -0,0 +1,2 @@
+A	B	2.98	U
+B	C	0.77	U
diff --git a/test/dataset/fixtures/in-range/node-prizes.txt b/test/dataset/fixtures/in-range/node-prizes.txt
new file mode 100644
index 000000000..d03c30492
--- /dev/null
+++ b/test/dataset/fixtures/in-range/node-prizes.txt
@@ -0,0 +1,3 @@
+NODEID	prize	active	dummy
+A	2	true	true
+C	5.7	true
diff --git a/test/dataset/fixtures/in-range/sources.txt b/test/dataset/fixtures/in-range/sources.txt
new file mode 100644
index 000000000..f70f10e4d
--- /dev/null
+++ b/test/dataset/fixtures/in-range/sources.txt
@@ -0,0 +1 @@
+A
diff --git a/test/dataset/fixtures/in-range/targets.txt b/test/dataset/fixtures/in-range/targets.txt
new file mode 100644
index 000000000..3cc58df83
--- /dev/null
+++ b/test/dataset/fixtures/in-range/targets.txt
@@ -0,0 +1 @@
+C
diff --git a/test/dataset/test_dataset.py b/test/dataset/test_dataset.py
new file mode 100644
index 000000000..da210c03b
--- /dev/null
+++ b/test/dataset/test_dataset.py
@@ -0,0 +1,28 @@
+import pandas
+from pathlib import Path
+import pytest
+
+from spras.dataset import Dataset
+
+FIXTURES_PATH = Path('test', 'dataset', 'fixtures')
+
+class TestDataset:
+    def test_not_allow_no_cols(self):
+        with pytest.raises(pandas.errors.EmptyDataError):
+            Dataset({
+                'label': 'empty',
+                'edge_files': ['network.txt'],
+                'node_files': ['scores.txt', 'nodes.txt'],
+                'other_files': [],
+                'data_dir': FIXTURES_PATH / 'empty'
+            })
+    
+    def test_not_allow_edge_weights_oor(self):
+        with pytest.raises(ValueError):
+            Dataset({
+                'label': 'empty',
+                'edge_files': ['network.txt'],
+                'node_files': ['node-prizes.txt', 'sources.txt', 'targets.txt'],
+                'other_files': [],
+                'data_dir': FIXTURES_PATH / 'in-range'
+            })
\ No newline at end of file

From f275e57b239720ee1884bfc18817175751acea27 Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Fri, 13 Jun 2025 09:33:10 -0700
Subject: [PATCH 04/12] test: one for some normal dataset

---
 test/dataset/fixtures/in-range/network.txt        |  4 ++--
 test/dataset/fixtures/not-in-range/network.txt    |  2 ++
 .../dataset/fixtures/not-in-range/node-prizes.txt |  3 +++
 test/dataset/fixtures/not-in-range/sources.txt    |  1 +
 test/dataset/fixtures/not-in-range/targets.txt    |  1 +
 test/dataset/test_dataset.py                      | 15 +++++++++++++--
 6 files changed, 22 insertions(+), 4 deletions(-)
 create mode 100644 test/dataset/fixtures/not-in-range/network.txt
 create mode 100644 test/dataset/fixtures/not-in-range/node-prizes.txt
 create mode 100644 test/dataset/fixtures/not-in-range/sources.txt
 create mode 100644 test/dataset/fixtures/not-in-range/targets.txt

diff --git a/test/dataset/fixtures/in-range/network.txt b/test/dataset/fixtures/in-range/network.txt
index 01116bd07..5dd49410b 100644
--- a/test/dataset/fixtures/in-range/network.txt
+++ b/test/dataset/fixtures/in-range/network.txt
@@ -1,2 +1,2 @@
-A	B	2.98	U
-B	C	0.77	U
+A	B	1	U
+B	C	0.5	U
diff --git a/test/dataset/fixtures/not-in-range/network.txt b/test/dataset/fixtures/not-in-range/network.txt
new file mode 100644
index 000000000..01116bd07
--- /dev/null
+++ b/test/dataset/fixtures/not-in-range/network.txt
@@ -0,0 +1,2 @@
+A	B	2.98	U
+B	C	0.77	U
diff --git a/test/dataset/fixtures/not-in-range/node-prizes.txt b/test/dataset/fixtures/not-in-range/node-prizes.txt
new file mode 100644
index 000000000..d03c30492
--- /dev/null
+++ b/test/dataset/fixtures/not-in-range/node-prizes.txt
@@ -0,0 +1,3 @@
+NODEID	prize	active	dummy
+A	2	true	true
+C	5.7	true
diff --git a/test/dataset/fixtures/not-in-range/sources.txt b/test/dataset/fixtures/not-in-range/sources.txt
new file mode 100644
index 000000000..f70f10e4d
--- /dev/null
+++ b/test/dataset/fixtures/not-in-range/sources.txt
@@ -0,0 +1 @@
+A
diff --git a/test/dataset/fixtures/not-in-range/targets.txt b/test/dataset/fixtures/not-in-range/targets.txt
new file mode 100644
index 000000000..3cc58df83
--- /dev/null
+++ b/test/dataset/fixtures/not-in-range/targets.txt
@@ -0,0 +1 @@
+C
diff --git a/test/dataset/test_dataset.py b/test/dataset/test_dataset.py
index da210c03b..667897cc9 100644
--- a/test/dataset/test_dataset.py
+++ b/test/dataset/test_dataset.py
@@ -24,5 +24,16 @@ def test_not_allow_edge_weights_oor(self):
                 'edge_files': ['network.txt'],
                 'node_files': ['node-prizes.txt', 'sources.txt', 'targets.txt'],
                 'other_files': [],
-                'data_dir': FIXTURES_PATH / 'in-range'
-            })
\ No newline at end of file
+                'data_dir': FIXTURES_PATH / 'not-in-range'
+            })
+
+    def test_normal(self):
+        dataset = Dataset({
+            'label': 'empty',
+            'edge_files': ['network.txt'],
+            'node_files': ['node-prizes.txt', 'sources.txt', 'targets.txt'],
+            'other_files': [],
+            'data_dir': FIXTURES_PATH / 'in-range'
+        })
+
+        assert len(dataset.get_interactome()) == 2
\ No newline at end of file

From 04632f1d2a9e04743f909fad0af6ef2d847a8e58 Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Fri, 13 Jun 2025 16:33:30 +0000
Subject: [PATCH 05/12] style: fmt

---
 spras/dataset.py             | 2 +-
 test/dataset/test_dataset.py | 7 ++++---
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/spras/dataset.py b/spras/dataset.py
index 7f68d31b6..861e44948 100644
--- a/spras/dataset.py
+++ b/spras/dataset.py
@@ -1,7 +1,7 @@
 import os
 import pickle as pkl
-from typing import TypedDict
 import warnings
+from typing import TypedDict
 
 import pandas as pd
 
diff --git a/test/dataset/test_dataset.py b/test/dataset/test_dataset.py
index 667897cc9..c9705dc5a 100644
--- a/test/dataset/test_dataset.py
+++ b/test/dataset/test_dataset.py
@@ -1,5 +1,6 @@
-import pandas
 from pathlib import Path
+
+import pandas
 import pytest
 
 from spras.dataset import Dataset
@@ -16,7 +17,7 @@ def test_not_allow_no_cols(self):
                 'other_files': [],
                 'data_dir': FIXTURES_PATH / 'empty'
             })
-    
+
     def test_not_allow_edge_weights_oor(self):
         with pytest.raises(ValueError):
             Dataset({
@@ -36,4 +37,4 @@ def test_normal(self):
             'data_dir': FIXTURES_PATH / 'in-range'
         })
 
-        assert len(dataset.get_interactome()) == 2
\ No newline at end of file
+        assert len(dataset.get_interactome()) == 2

From e5ad211b605810eddee041426e5edf942f44c336 Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Tue, 24 Jun 2025 16:38:15 +0000
Subject: [PATCH 06/12] docs: on datasetdict

---
 spras/dataset.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/spras/dataset.py b/spras/dataset.py
index 861e44948..8588ce4bc 100644
--- a/spras/dataset.py
+++ b/spras/dataset.py
@@ -13,13 +13,16 @@
 """
 
 class DatasetDict(TypedDict):
+    """
+    Type class containing a collection of information pertaining to creating a Dataset
+    object. This layout is replicated directly in SPRAS configuration files.
+    """
     label: str
     node_files: list[str | os.PathLike]
     edge_files: list[str | os.PathLike]
     other_files: list[str | os.PathLike]
     data_dir: str | os.PathLike
 
-
 class Dataset:
 
     NODE_ID = "NODEID"

From e9ad2fd0e0fd7ab26fdebfeca3882b07c5bbc171 Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Tue, 24 Jun 2025 16:52:40 +0000
Subject: [PATCH 07/12] chore: update naming for empty ds

---
 test/dataset/fixtures/empty/{nodes.txt => node-prizes.txt} | 0
 test/dataset/fixtures/empty/{scores.txt => sources.txt}    | 0
 test/dataset/test_dataset.py                               | 2 +-
 3 files changed, 1 insertion(+), 1 deletion(-)
 rename test/dataset/fixtures/empty/{nodes.txt => node-prizes.txt} (100%)
 rename test/dataset/fixtures/empty/{scores.txt => sources.txt} (100%)

diff --git a/test/dataset/fixtures/empty/nodes.txt b/test/dataset/fixtures/empty/node-prizes.txt
similarity index 100%
rename from test/dataset/fixtures/empty/nodes.txt
rename to test/dataset/fixtures/empty/node-prizes.txt
diff --git a/test/dataset/fixtures/empty/scores.txt b/test/dataset/fixtures/empty/sources.txt
similarity index 100%
rename from test/dataset/fixtures/empty/scores.txt
rename to test/dataset/fixtures/empty/sources.txt
diff --git a/test/dataset/test_dataset.py b/test/dataset/test_dataset.py
index c9705dc5a..beef71ebe 100644
--- a/test/dataset/test_dataset.py
+++ b/test/dataset/test_dataset.py
@@ -13,7 +13,7 @@ def test_not_allow_no_cols(self):
             Dataset({
                 'label': 'empty',
                 'edge_files': ['network.txt'],
-                'node_files': ['scores.txt', 'nodes.txt'],
+                'node_files': ['sources.txt', 'node-prizes.txt'],
                 'other_files': [],
                 'data_dir': FIXTURES_PATH / 'empty'
             })

From 54be58e2d48b86a66e57232c3eee7d1a87b06a7e Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Tue, 24 Jun 2025 16:55:58 +0000
Subject: [PATCH 08/12] test: empty sources, targets, node-prizes, or network

---
 test/dataset/fixtures/dataless/network.txt    |  2 ++
 .../dataset/fixtures/dataless/node-prizes.txt |  1 +
 test/dataset/fixtures/dataless/sources.txt    |  0
 test/dataset/fixtures/dataless/targets.txt    |  0
 .../fixtures/empty-network/network.txt        |  0
 .../fixtures/empty-network/node-prizes.txt    |  3 +++
 .../fixtures/empty-network/sources.txt        |  1 +
 .../fixtures/empty-network/targets.txt        |  1 +
 test/dataset/test_dataset.py                  | 20 +++++++++++++++++++
 9 files changed, 28 insertions(+)
 create mode 100644 test/dataset/fixtures/dataless/network.txt
 create mode 100644 test/dataset/fixtures/dataless/node-prizes.txt
 create mode 100644 test/dataset/fixtures/dataless/sources.txt
 create mode 100644 test/dataset/fixtures/dataless/targets.txt
 create mode 100644 test/dataset/fixtures/empty-network/network.txt
 create mode 100644 test/dataset/fixtures/empty-network/node-prizes.txt
 create mode 100644 test/dataset/fixtures/empty-network/sources.txt
 create mode 100644 test/dataset/fixtures/empty-network/targets.txt

diff --git a/test/dataset/fixtures/dataless/network.txt b/test/dataset/fixtures/dataless/network.txt
new file mode 100644
index 000000000..5dd49410b
--- /dev/null
+++ b/test/dataset/fixtures/dataless/network.txt
@@ -0,0 +1,2 @@
+A	B	1	U
+B	C	0.5	U
diff --git a/test/dataset/fixtures/dataless/node-prizes.txt b/test/dataset/fixtures/dataless/node-prizes.txt
new file mode 100644
index 000000000..26897b5a6
--- /dev/null
+++ b/test/dataset/fixtures/dataless/node-prizes.txt
@@ -0,0 +1 @@
+NODEID	prize	active	dummy
diff --git a/test/dataset/fixtures/dataless/sources.txt b/test/dataset/fixtures/dataless/sources.txt
new file mode 100644
index 000000000..e69de29bb
diff --git a/test/dataset/fixtures/dataless/targets.txt b/test/dataset/fixtures/dataless/targets.txt
new file mode 100644
index 000000000..e69de29bb
diff --git a/test/dataset/fixtures/empty-network/network.txt b/test/dataset/fixtures/empty-network/network.txt
new file mode 100644
index 000000000..e69de29bb
diff --git a/test/dataset/fixtures/empty-network/node-prizes.txt b/test/dataset/fixtures/empty-network/node-prizes.txt
new file mode 100644
index 000000000..d03c30492
--- /dev/null
+++ b/test/dataset/fixtures/empty-network/node-prizes.txt
@@ -0,0 +1,3 @@
+NODEID	prize	active	dummy
+A	2	true	true
+C	5.7	true
diff --git a/test/dataset/fixtures/empty-network/sources.txt b/test/dataset/fixtures/empty-network/sources.txt
new file mode 100644
index 000000000..8c7e5a667
--- /dev/null
+++ b/test/dataset/fixtures/empty-network/sources.txt
@@ -0,0 +1 @@
+A
\ No newline at end of file
diff --git a/test/dataset/fixtures/empty-network/targets.txt b/test/dataset/fixtures/empty-network/targets.txt
new file mode 100644
index 000000000..7371f47a6
--- /dev/null
+++ b/test/dataset/fixtures/empty-network/targets.txt
@@ -0,0 +1 @@
+B
\ No newline at end of file
diff --git a/test/dataset/test_dataset.py b/test/dataset/test_dataset.py
index beef71ebe..2fe2c0a15 100644
--- a/test/dataset/test_dataset.py
+++ b/test/dataset/test_dataset.py
@@ -17,6 +17,26 @@ def test_not_allow_no_cols(self):
                 'other_files': [],
                 'data_dir': FIXTURES_PATH / 'empty'
             })
+    
+    def test_dataless(self):
+        with pytest.raises(pandas.errors.EmptyDataError):
+            Dataset({
+                'label': 'dataless',
+                'edge_files': ['network.txt'],
+                'node_files': ['sources.txt', 'node-prizes.txt'],
+                'other_files': [],
+                'data_dir': FIXTURES_PATH / 'dataless'
+            })
+    
+    def test_empty_network(self):
+        with pytest.raises(pandas.errors.EmptyDataError):
+            Dataset({
+                'label': 'empty-network',
+                'edge_files': ['network.txt'],
+                'node_files': ['sources.txt', 'node-prizes.txt'],
+                'other_files': [],
+                'data_dir': FIXTURES_PATH / 'empty-network'
+            })
 
     def test_not_allow_edge_weights_oor(self):
         with pytest.raises(ValueError):

From a6788a31629ba774475db41c66e99140f3f9767d Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Tue, 24 Jun 2025 16:57:52 +0000
Subject: [PATCH 09/12] test: empty headers

---
 test/dataset/fixtures/empty-headers/network.txt     |  2 ++
 test/dataset/fixtures/empty-headers/node-prizes.txt |  1 +
 test/dataset/fixtures/empty-headers/sources.txt     |  0
 test/dataset/fixtures/empty-headers/targets.txt     |  0
 test/dataset/test_dataset.py                        | 10 ++++++++++
 5 files changed, 13 insertions(+)
 create mode 100644 test/dataset/fixtures/empty-headers/network.txt
 create mode 100644 test/dataset/fixtures/empty-headers/node-prizes.txt
 create mode 100644 test/dataset/fixtures/empty-headers/sources.txt
 create mode 100644 test/dataset/fixtures/empty-headers/targets.txt

diff --git a/test/dataset/fixtures/empty-headers/network.txt b/test/dataset/fixtures/empty-headers/network.txt
new file mode 100644
index 000000000..5dd49410b
--- /dev/null
+++ b/test/dataset/fixtures/empty-headers/network.txt
@@ -0,0 +1,2 @@
+A	B	1	U
+B	C	0.5	U
diff --git a/test/dataset/fixtures/empty-headers/node-prizes.txt b/test/dataset/fixtures/empty-headers/node-prizes.txt
new file mode 100644
index 000000000..26897b5a6
--- /dev/null
+++ b/test/dataset/fixtures/empty-headers/node-prizes.txt
@@ -0,0 +1 @@
+NODEID	prize	active	dummy
diff --git a/test/dataset/fixtures/empty-headers/sources.txt b/test/dataset/fixtures/empty-headers/sources.txt
new file mode 100644
index 000000000..e69de29bb
diff --git a/test/dataset/fixtures/empty-headers/targets.txt b/test/dataset/fixtures/empty-headers/targets.txt
new file mode 100644
index 000000000..e69de29bb
diff --git a/test/dataset/test_dataset.py b/test/dataset/test_dataset.py
index 2fe2c0a15..6e7b612d6 100644
--- a/test/dataset/test_dataset.py
+++ b/test/dataset/test_dataset.py
@@ -18,6 +18,16 @@ def test_not_allow_no_cols(self):
                 'data_dir': FIXTURES_PATH / 'empty'
             })
     
+    def test_not_allow_no_cols_headers(self):
+        with pytest.raises(pandas.errors.EmptyDataError):
+            Dataset({
+                'label': 'empty-headers',
+                'edge_files': ['network.txt'],
+                'node_files': ['sources.txt', 'node-prizes.txt'],
+                'other_files': [],
+                'data_dir': FIXTURES_PATH / 'empty-headers'
+            })
+    
     def test_dataless(self):
         with pytest.raises(pandas.errors.EmptyDataError):
             Dataset({

From 79f168282cefe3590953290fbd5bd23696022783 Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Tue, 24 Jun 2025 17:16:21 +0000
Subject: [PATCH 10/12] style: fmt

---
 test/dataset/test_dataset.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/test/dataset/test_dataset.py b/test/dataset/test_dataset.py
index 6e7b612d6..d01d16506 100644
--- a/test/dataset/test_dataset.py
+++ b/test/dataset/test_dataset.py
@@ -17,7 +17,7 @@ def test_not_allow_no_cols(self):
                 'other_files': [],
                 'data_dir': FIXTURES_PATH / 'empty'
             })
-    
+
     def test_not_allow_no_cols_headers(self):
         with pytest.raises(pandas.errors.EmptyDataError):
             Dataset({
@@ -27,7 +27,7 @@ def test_not_allow_no_cols_headers(self):
                 'other_files': [],
                 'data_dir': FIXTURES_PATH / 'empty-headers'
             })
-    
+
     def test_dataless(self):
         with pytest.raises(pandas.errors.EmptyDataError):
             Dataset({
@@ -37,7 +37,7 @@ def test_dataless(self):
                 'other_files': [],
                 'data_dir': FIXTURES_PATH / 'dataless'
             })
-    
+
     def test_empty_network(self):
         with pytest.raises(pandas.errors.EmptyDataError):
             Dataset({

From d0fc7e2dc14e59428b92cb651599857c76d77ae9 Mon Sep 17 00:00:00 2001
From: "Tristan F.-R." <pub.tristanf@gmail.com>
Date: Fri, 11 Jul 2025 20:17:15 +0000
Subject: [PATCH 11/12] refactor: drop unused dataset edge weight restriction

---
 spras/dataset.py                                   |  7 -------
 test/dataset/fixtures/not-in-range/network.txt     |  2 --
 test/dataset/fixtures/not-in-range/node-prizes.txt |  3 ---
 test/dataset/fixtures/not-in-range/sources.txt     |  1 -
 test/dataset/fixtures/not-in-range/targets.txt     |  1 -
 .../fixtures/{in-range => standard}/network.txt    |  0
 .../{in-range => standard}/node-prizes.txt         |  0
 .../fixtures/{in-range => standard}/sources.txt    |  0
 .../fixtures/{in-range => standard}/targets.txt    |  0
 test/dataset/test_dataset.py                       | 14 ++------------
 10 files changed, 2 insertions(+), 26 deletions(-)
 delete mode 100644 test/dataset/fixtures/not-in-range/network.txt
 delete mode 100644 test/dataset/fixtures/not-in-range/node-prizes.txt
 delete mode 100644 test/dataset/fixtures/not-in-range/sources.txt
 delete mode 100644 test/dataset/fixtures/not-in-range/targets.txt
 rename test/dataset/fixtures/{in-range => standard}/network.txt (100%)
 rename test/dataset/fixtures/{in-range => standard}/node-prizes.txt (100%)
 rename test/dataset/fixtures/{in-range => standard}/sources.txt (100%)
 rename test/dataset/fixtures/{in-range => standard}/targets.txt (100%)

diff --git a/spras/dataset.py b/spras/dataset.py
index 8588ce4bc..88f664460 100644
--- a/spras/dataset.py
+++ b/spras/dataset.py
@@ -100,13 +100,6 @@ def load_files_from_dict(self, dataset_dict: DatasetDict):
                 "Direction",
             ]
 
-            weight_series = pd.Series(self.interactome.Weight)
-            weight_series_out_range = ~weight_series.between(0, 1)
-            if weight_series_out_range.any():
-                # Offset the index by 1 to match the file line numbers.
-                weight_true = (weight_series_out_range.index[weight_series_out_range == True] + 1).tolist()
-                raise ValueError(f"The following lines of the interactome: ({str(weight_true)}) have weights not between 0 and 1.")
-
             # Make directionality column case-insensitive
             self.interactome["Direction"] = self.interactome["Direction"].str.upper()
             if not self.interactome["Direction"].isin(["U", "D"]).all():
diff --git a/test/dataset/fixtures/not-in-range/network.txt b/test/dataset/fixtures/not-in-range/network.txt
deleted file mode 100644
index 01116bd07..000000000
--- a/test/dataset/fixtures/not-in-range/network.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-A	B	2.98	U
-B	C	0.77	U
diff --git a/test/dataset/fixtures/not-in-range/node-prizes.txt b/test/dataset/fixtures/not-in-range/node-prizes.txt
deleted file mode 100644
index d03c30492..000000000
--- a/test/dataset/fixtures/not-in-range/node-prizes.txt
+++ /dev/null
@@ -1,3 +0,0 @@
-NODEID	prize	active	dummy
-A	2	true	true
-C	5.7	true
diff --git a/test/dataset/fixtures/not-in-range/sources.txt b/test/dataset/fixtures/not-in-range/sources.txt
deleted file mode 100644
index f70f10e4d..000000000
--- a/test/dataset/fixtures/not-in-range/sources.txt
+++ /dev/null
@@ -1 +0,0 @@
-A
diff --git a/test/dataset/fixtures/not-in-range/targets.txt b/test/dataset/fixtures/not-in-range/targets.txt
deleted file mode 100644
index 3cc58df83..000000000
--- a/test/dataset/fixtures/not-in-range/targets.txt
+++ /dev/null
@@ -1 +0,0 @@
-C
diff --git a/test/dataset/fixtures/in-range/network.txt b/test/dataset/fixtures/standard/network.txt
similarity index 100%
rename from test/dataset/fixtures/in-range/network.txt
rename to test/dataset/fixtures/standard/network.txt
diff --git a/test/dataset/fixtures/in-range/node-prizes.txt b/test/dataset/fixtures/standard/node-prizes.txt
similarity index 100%
rename from test/dataset/fixtures/in-range/node-prizes.txt
rename to test/dataset/fixtures/standard/node-prizes.txt
diff --git a/test/dataset/fixtures/in-range/sources.txt b/test/dataset/fixtures/standard/sources.txt
similarity index 100%
rename from test/dataset/fixtures/in-range/sources.txt
rename to test/dataset/fixtures/standard/sources.txt
diff --git a/test/dataset/fixtures/in-range/targets.txt b/test/dataset/fixtures/standard/targets.txt
similarity index 100%
rename from test/dataset/fixtures/in-range/targets.txt
rename to test/dataset/fixtures/standard/targets.txt
diff --git a/test/dataset/test_dataset.py b/test/dataset/test_dataset.py
index d01d16506..4cb988632 100644
--- a/test/dataset/test_dataset.py
+++ b/test/dataset/test_dataset.py
@@ -48,23 +48,13 @@ def test_empty_network(self):
                 'data_dir': FIXTURES_PATH / 'empty-network'
             })
 
-    def test_not_allow_edge_weights_oor(self):
-        with pytest.raises(ValueError):
-            Dataset({
-                'label': 'empty',
-                'edge_files': ['network.txt'],
-                'node_files': ['node-prizes.txt', 'sources.txt', 'targets.txt'],
-                'other_files': [],
-                'data_dir': FIXTURES_PATH / 'not-in-range'
-            })
-
-    def test_normal(self):
+    def test_standard(self):
         dataset = Dataset({
             'label': 'empty',
             'edge_files': ['network.txt'],
             'node_files': ['node-prizes.txt', 'sources.txt', 'targets.txt'],
             'other_files': [],
-            'data_dir': FIXTURES_PATH / 'in-range'
+            'data_dir': FIXTURES_PATH / 'standard'
         })
 
         assert len(dataset.get_interactome()) == 2

From 74e3080e6752cdb316d0c5d460e584b9da081de0 Mon Sep 17 00:00:00 2001
From: "Tristan F." <LeoDog896@hotmail.com>
Date: Thu, 21 Aug 2025 19:55:58 +0000
Subject: [PATCH 12/12] fix: never parse index_col from node data

---
 spras/dataset.py                              |  2 +-
 .../fixtures/toy-372/input-interactome.txt    |  2 ++
 test/dataset/fixtures/toy-372/input-nodes.txt |  3 +++
 test/dataset/test_dataset.py                  | 22 +++++++++++++++++++
 4 files changed, 28 insertions(+), 1 deletion(-)
 create mode 100644 test/dataset/fixtures/toy-372/input-interactome.txt
 create mode 100644 test/dataset/fixtures/toy-372/input-nodes.txt

diff --git a/spras/dataset.py b/spras/dataset.py
index 891f4d6f9..c2271235c 100644
--- a/spras/dataset.py
+++ b/spras/dataset.py
@@ -121,7 +121,7 @@ def load_files_from_dict(self, dataset_dict: DatasetDict):
         # Load generic node tables
         self.node_table = pd.DataFrame(node_set, columns=[self.NODE_ID])
         for node_file in node_data_files:
-            single_node_table = pd.read_table(os.path.join(data_loc, node_file))
+            single_node_table = pd.read_table(os.path.join(data_loc, node_file), index_col=False)
             # If we have only 1 column, assume this is an indicator variable
             if len(single_node_table.columns) == 1:
                 single_node_table = pd.read_table(
diff --git a/test/dataset/fixtures/toy-372/input-interactome.txt b/test/dataset/fixtures/toy-372/input-interactome.txt
new file mode 100644
index 000000000..f252ca4ca
--- /dev/null
+++ b/test/dataset/fixtures/toy-372/input-interactome.txt
@@ -0,0 +1,2 @@
+C	D	0.77	U
+N	O	0.66	U
\ No newline at end of file
diff --git a/test/dataset/fixtures/toy-372/input-nodes.txt b/test/dataset/fixtures/toy-372/input-nodes.txt
new file mode 100644
index 000000000..2efa6f320
--- /dev/null
+++ b/test/dataset/fixtures/toy-372/input-nodes.txt
@@ -0,0 +1,3 @@
+NODEID	prize	active	dummy	sources	targets
+N											
+C	5.7	True			True
diff --git a/test/dataset/test_dataset.py b/test/dataset/test_dataset.py
index 4cb988632..52333ca91 100644
--- a/test/dataset/test_dataset.py
+++ b/test/dataset/test_dataset.py
@@ -2,6 +2,7 @@
 
 import pandas
 import pytest
+import numpy as np
 
 from spras.dataset import Dataset
 
@@ -58,3 +59,24 @@ def test_standard(self):
         })
 
         assert len(dataset.get_interactome()) == 2
+    
+    # 372 is a PR, but for the relevant comment, see
+    # https://github.com/Reed-CompBio/spras/pull/372/files#r2291953612.
+    # Note that the input-nodes file has more tabs than the original fixture.
+    def test_372(self):
+        dataset = Dataset({
+            'label': 'toy-372',
+            'edge_files': ['input-interactome.txt'],
+            'node_files': ['input-nodes.txt'],
+            'data_dir': FIXTURES_PATH / 'toy-372',
+            'other_files': []
+        })
+
+        node_table = dataset.node_table
+        assert node_table is not None
+
+        assert node_table[node_table[Dataset.NODE_ID] == 'C'].iloc[0]['prize'] == 5.7
+        assert node_table[node_table[Dataset.NODE_ID] == 'C'].iloc[0]['active'] == True
+
+        assert np.isnan(node_table[node_table[Dataset.NODE_ID] == 'C'].iloc[0]['sources'])
+        assert node_table[node_table[Dataset.NODE_ID] == 'C'].iloc[0]['targets'] == True