update chi test

chaochungkuo · Mar 2, 2024 · 2218bc3 · 2218bc3
1 parent 2560ac7
commit 2218bc3
Show file tree

Hide file tree

Showing 4 changed files with 12 additions and 4 deletions.
diff --git a/docs/requirements.txt b/docs/requirements.txt
@@ -4,4 +4,5 @@ numpy
 pysam==0.22.0
 tqdm
 pyBigWig==0.3.22
-pandas
+pandas
+scipy
diff --git a/genomkit/coverages/gcoverages.py b/genomkit/coverages/gcoverages.py
@@ -64,8 +64,8 @@ def calculate_coverage_from_bam(self, filename: str):
 
     def calculate_coverage_GRegions(self, regions, scores,
                                     strandness: bool = False):
-        """Calculate the coverage from two GRegions. `regions` defines the loci for the coverage
-        `scores` contains the scores loaded into the coverage.
+        """Calculate the coverage from two GRegions. `regions` defines the loci
+        for the coverage `scores` contains the scores loaded into the coverage.
 
         :param regions: Define the loci and the length of the coverage
         :type regions: GRegions

diff --git a/genomkit/regions/gregions_set.py b/genomkit/regions/gregions_set.py
@@ -104,3 +104,9 @@ def count_overlaps(self, query_set, percentage: bool = False):
         if percentage:
             df = df.div(df.sum(axis=1), axis=0) * 100
         return df
+
+    def test_association(self, another_set):
+        from scipy.stats import chi2_contingency
+        contingency_table = self.count_overlaps(query_set=another_set)
+        chi2_stat, p_val, _, _ = chi2_contingency(contingency_table)
+        return chi2_stat, p_val
diff --git a/requirements.txt b/requirements.txt
@@ -2,4 +2,5 @@ numpy
 pysam==0.22.0
 tqdm
 pyBigWig==0.3.22
-pandas
+pandas
+scipy