Format using ruff

src/copairs/__init__.py

@@ -1,4 +1,7 @@
 """
 Package to create pairwise lists based on sameby and diffby criteria
 """
+
 from .matching import Matcher, MatcherMultilabel
+
+__all__ = ["Matcher", "MatcherMultilabel"]

src/copairs/compute.py

@@ -99,13 +99,15 @@ def get_distance_fn(distance):
 
     if isinstance(distance, str):
         if distance not in distance_metrics:
-            raise ValueError(f"Unsupported distance metric: {distance}. Supported metrics are: {list(distance_metrics.keys())}")
+            raise ValueError(
+                f"Unsupported distance metric: {distance}. Supported metrics are: {list(distance_metrics.keys())}"
+            )
         distance_fn = distance_metrics[distance]
     elif callable(distance):
         distance_fn = distance
     else:
         raise ValueError("Distance must be either a string or a callable object.")
-    
+
     return batch_processing(distance_fn)
 
 

src/copairs/map/__init__.py

@@ -1,3 +1,5 @@
-from .map import mean_average_precision
 from . import multilabel
 from .average_precision import average_precision
+from .map import mean_average_precision
+
+__all__ = ["mean_average_precision", "multilabel", "average_precision"]

src/copairs/map/average_precision.py

@@ -28,7 +28,14 @@ def build_rank_lists(pos_pairs, neg_pairs, pos_sims, neg_sims):
 
 
 def average_precision(
-    meta, feats, pos_sameby, pos_diffby, neg_sameby, neg_diffby, batch_size=20000, distance="cosine"
+    meta,
+    feats,
+    pos_sameby,
+    pos_diffby,
+    neg_sameby,
+    neg_diffby,
+    batch_size=20000,
+    distance="cosine",
 ) -> pd.DataFrame:
     columns = flatten_str_list(pos_sameby, pos_diffby, neg_sameby, neg_diffby)
     meta, columns = evaluate_and_filter(meta, columns)

src/copairs/map/filter.py

@@ -1,9 +1,9 @@
-from typing import Tuple, List
 import itertools
 import re
+from typing import List, Tuple
 
-import pandas as pd
 import numpy as np
+import pandas as pd
 
 
 def validate_pipeline_input(meta, feats, columns):
@@ -45,12 +45,12 @@ def extract_filters(columns, df_columns) -> Tuple[List[str], List[str]]:
         if col in df_columns:
             parsed_cols.append(col)
             continue
-        column_names = re.findall(r'(\w+)\s*[=<>!]+', col)
+        column_names = re.findall(r"(\w+)\s*[=<>!]+", col)
 
         valid_column_names = [col for col in column_names if col in df_columns]
         if not valid_column_names:
             raise ValueError(f"Invalid query or column name: {col}")
-        
+
         queries_to_eval.append(col)
         parsed_cols.extend(valid_column_names)
 
@@ -71,6 +71,8 @@ def apply_filters(df, query_list):
         if df_filtered.empty:
             raise ValueError(f"No data matched the query: {combined_query}")
     except Exception as e:
-        raise ValueError(f"Invalid combined query expression: {combined_query}. Error: {e}")
+        raise ValueError(
+            f"Invalid combined query expression: {combined_query}. Error: {e}"
+        )
 
     return df_filtered

src/copairs/map/multilabel.py

@@ -84,9 +84,7 @@ def average_precision(
     meta = meta.reset_index(drop=True).copy()
 
     logger.info("Indexing metadata...")
-    matcher = MatcherMultilabel(
-        meta, columns, multilabel_col=multilabel_col, seed=0
-    )
+    matcher = MatcherMultilabel(meta, columns, multilabel_col=multilabel_col, seed=0)
 
     logger.info("Finding positive pairs...")
     pos_pairs = matcher.get_all_pairs(sameby=pos_sameby, diffby=pos_diffby)

src/copairs/matching.py

@@ -1,11 +1,12 @@
 """
 Sample pairs with given column restrictions
 """
-from collections import namedtuple
+
 import itertools
 import logging
-from math import comb
 import re
+from collections import namedtuple
+from math import comb
 from typing import Dict, Sequence, Set, Union
 
 import numpy as np
@@ -442,5 +443,8 @@ def _only_diffby_multi(self):
         pairs = itertools.chain.from_iterable(pairs.values())
         pairs = set(map(frozenset, pairs))
         all_pairs = itertools.combinations(range(self.size), 2)
-        filter_fn = lambda x: set(x) not in pairs
+
+        def filter_fn(x):
+            return set(x) not in pairs
+
         return {None: list(filter(filter_fn, all_pairs))}

src/copairs/plot.py

@@ -1,4 +1,5 @@
 from typing import Optional
+
 from plotly import graph_objects as go
 from plotly.subplots import make_subplots
 

src/copairs/replicating.py

@@ -1,10 +1,12 @@
 """Class for getting Percent replicating metric"""
+
 from typing import List, Literal
 
 import numpy as np
 import pandas as pd
 
 from copairs.compute import get_distance_fn
+
 from .matching import Matcher
 
 

tests/helpers.py

@@ -1,8 +1,8 @@
 from itertools import product
 from typing import Dict
 
-import pandas as pd
 import numpy as np
+import pandas as pd
 
 from copairs.matching import ColumnList
 

tests/test_compute.py

@@ -1,4 +1,3 @@
-import pytest
 import numpy as np
 
 from copairs import compute
@@ -90,4 +89,3 @@ def test_abs_cosine():
     abs_cosine_fn = compute.get_distance_fn("abs_cosine")
     abs_cosine = abs_cosine_fn(feats, pairs, batch_size)
     assert np.allclose(abs_cosine_gt, abs_cosine)
-

tests/test_map.py

@@ -1,7 +1,7 @@
+import numpy as np
 import pandas as pd
 import pytest
 from sklearn.metrics import average_precision_score
-import numpy as np
 
 from copairs import compute
 from copairs.map import average_precision
@@ -140,8 +140,8 @@ def test_raise_no_pairs():
         average_precision(meta, feats, pos_sameby, pos_diffby, neg_sameby, neg_diffby)
     with pytest.raises(UnpairedException, match="Unable to find negative pairs."):
         average_precision(meta, feats, pos_diffby, [], pos_sameby, [])
-        
-        
+
+
 def test_raise_nan_error():
     length = 10
     vocab_size = {"p": 5, "w": 3, "l": 4}
@@ -154,14 +154,20 @@ def test_raise_nan_error():
     meta = simulate_random_dframe(length, vocab_size, pos_sameby, pos_diffby, rng)
     length = len(meta)
     feats = rng.uniform(size=(length, n_feats))
-    
+
     # add null values
     feats_nan = feats.copy()
-    feats_nan[2,2] = None
+    feats_nan[2, 2] = None
     meta_nan = meta.copy()
-    meta_nan.loc[1,"p"] = None
-    
+    meta_nan.loc[1, "p"] = None
+
     with pytest.raises(ValueError, match="features should not have null values."):
-        average_precision(meta, feats_nan, pos_sameby, pos_diffby, neg_sameby, neg_diffby)
-    with pytest.raises(ValueError, match="metadata columns should not have null values."):
-        average_precision(meta_nan, feats, pos_sameby, pos_diffby, neg_sameby, neg_diffby)
+        average_precision(
+            meta, feats_nan, pos_sameby, pos_diffby, neg_sameby, neg_diffby
+        )
+    with pytest.raises(
+        ValueError, match="metadata columns should not have null values."
+    ):
+        average_precision(
+            meta_nan, feats, pos_sameby, pos_diffby, neg_sameby, neg_diffby
+        )

tests/test_map_filter.py

@@ -1,6 +1,5 @@
-import pytest
-import pandas as pd
 import numpy as np
+import pytest
 
 from copairs.map.filter import evaluate_and_filter
 from tests.helpers import simulate_random_dframe
@@ -23,8 +22,8 @@ def mock_dataframe():
 def test_correct(mock_dataframe):
     df, parsed_cols = evaluate_and_filter(mock_dataframe, ["p == 'p1'", "w > 'w2'"])
     assert not df.empty
-    assert 'p' in parsed_cols and 'w' in parsed_cols
-    assert all(df['w'].str.extract(r'(\d+)')[0].astype(int) > 2)
+    assert "p" in parsed_cols and "w" in parsed_cols
+    assert all(df["w"].str.extract(r"(\d+)")[0].astype(int) > 2)
 
 
 def test_invalid_query(mock_dataframe):
@@ -44,6 +43,3 @@ def test_empty_result_from_valid_query(mock_dataframe):
     with pytest.raises(ValueError) as excinfo:
         evaluate_and_filter(mock_dataframe, ['p == "p4"'])
     assert "No data matched the query" in str(excinfo.value)
-
-
-

tests/test_matching.py

@@ -1,4 +1,5 @@
 """Test functions for Matcher"""
+
 from string import ascii_letters
 
 import numpy as np

tests/test_matching_multilabel.py

@@ -1,4 +1,5 @@
 import pandas as pd
+
 from copairs.matching import MatcherMultilabel
 from tests.helpers import simulate_random_plates
 

tests/test_replicating.py

@@ -3,10 +3,9 @@
 from copairs import Matcher
 from copairs.replicating import (
     corr_between_replicates,
-    correlation_test,
     corr_from_pairs,
+    correlation_test,
 )
-
 from tests.helpers import create_dframe
 
 SEED = 0