gemmapy 2.0.5__tar.gz → 2.0.7__tar.gz

{gemmapy-2.0.5 → gemmapy-2.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gemmapy
-Version: 2.0.5
+Version: 2.0.7
 Summary: a Python Wrapper for the Gemma API
 Keywords: gemma,bioinformatics
 Requires-Python: >=3.10

{gemmapy-2.0.5 → gemmapy-2.0.7}/gemmapy/_processors.py

@@ -422,6 +422,8 @@ def process_expression(d, dataset, api):
     # more non-uniformities
     df = sub.read_tsv(d)
     m_cols = list(df.columns)
+    m_cols = [x.replace(".","") for x in m_cols]
+    df.columns = m_cols
     # we use the order returned by get_dataset_samples as authoritative which makes
     # it a bit awkward when we need to access a property left out of the processed output
     # this could be simplified by ordering by ids but I don't want to break
@@ -437,17 +439,18 @@ def process_expression(d, dataset, api):
     
     sample_names = samples.sample_name
     
-    sample_internal_names = [x.replace("|",".").replace("-",".").replace(" ","") for x in sample_internal_names]
-    
+    sample_internal_names = [x.replace("|","").replace("-","").replace(" ","").replace(".","").replace("/","") for x in sample_internal_names]
+
     def find_match(x):
-        match = None
-        for i in range(len(m_cols)):
-            if m_cols[i].find(x+"_") != -1:
-                match = i
-        return match
-    
+        pattern = r"(?<![A-Za-z])" + re.escape(x) + r"_"
+        o = [i for i, col in enumerate(m_cols) if re.search(pattern, col)]
+        if (len(o)==0 | len(o)>1):
+            return None
+        else:
+            return o[0]
+
     sample_matches = [find_match(x) for x in sample_internal_names]
-    
+
     
     rename_dict = sub.make_dict([m_cols[i] for i in sample_matches],sample_names)
 

{gemmapy-2.0.5 → gemmapy-2.0.7}/gemmapy/_subprocessors.py

@@ -146,7 +146,7 @@ def process_FactorValueBasicValueObject(d):
             "predicate.URI":[np.nan],
             "object":[np.nan],
             "object_URI":[np.nan],
-            "summary":[np.nan],
+            "summary":[access_field(d,"summary")],
             "ID":[access_field(d,'id')],
             "factor_ID":[access_field(d,"experimental_factor_id")],
             "factor_category":[access_field(d,"experimental_factor_category","category")],

{gemmapy-2.0.5 → gemmapy-2.0.7}/gemmapy/gemmapy_api.py

@@ -1382,18 +1382,17 @@ class GemmaPy(object):
         
         text = [get_text(x) for x in categories.factor_ID]
         
-        
         if meta_type =='text':
             design_frame = pd.DataFrame({
-                categories.factor_category[i]:text[i] for i in range(len(text))
+                categories.factor_category.tolist()[i]:text[i] for i in range(len(text))
                 })
         elif meta_type == 'uri':
             design_frame = pd.DataFrame({
-                categories.factor_category_URI[i]:factor_URIs[i] for i in range(len(factor_URIs))
+                categories.factor_category_URI.tolist()[i]:factor_URIs[i] for i in range(len(factor_URIs))
                 })
         elif meta_type =='both':
-            merged_name = [["|".join([categories.factor_category[i],
-                                      categories.factor_category_URI[i]])] for i in range(len(text))]
+            merged_name = [["|".join([categories.factor_category.tolist()[i],
+                                      categories.factor_category_URI.tolist()[i]])] for i in range(len(text))]
             
             merged_col = [["|".join([text[i][j],factor_URIs[i][j]]) 
                            for j in range(len(text[i]))] for i in range(len(text))]
@@ -1422,7 +1421,7 @@ class GemmaPy(object):
                                      result_set].subset_factor.drop_duplicates()
             # result set should have the same subset for all contrasts
             assert len(subset) == 1
-            if subset[0].shape[0]!=0:
+            if subset.tolist()[0].shape[0]!=0:
                 subset_ids = subset[0].ID
                 
                 in_subset = [any(sub.list_in_list(x.ID, subset_ids)) for x in factor_values]
@@ -1615,15 +1614,14 @@ class GemmaPy(object):
             # probe ids are usually unique but there are exceptions
             
             unique_probes = packed_info['exp'].Probe
-            append = pd.Series(sub.rep(0,len(unique_probes)))
+            append = pd.Series(sub.rep(0,len(unique_probes)), index = unique_probes.index)
             dups = unique_probes.duplicated()
             while dups.any():
                 append[dups] = append[dups]+1
                 dups = (unique_probes + append.astype('string')).duplicated()
-            
+
             append = append.astype('string')
             append[append=='0'] = ""
-            append.index= unique_probes.index
             unique_probes = unique_probes + append
             packed_info['unique_probes'] = unique_probes
             

{gemmapy-2.0.5 → gemmapy-2.0.7}/gemmapy/sdk/api_client.py

@@ -73,7 +73,7 @@ class ApiClient(object):
             self.default_headers[header_name] = header_value
         self.cookie = cookie
         # Set default User-Agent.
-        self.user_agent = 'gemmapy/"2.0.5"'
+        self.user_agent = 'gemmapy/"2.0.7"'
 
     def __del__(self):
         self.pool.close()

{gemmapy-2.0.5 → gemmapy-2.0.7}/gemmapy.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gemmapy
-Version: 2.0.5
+Version: 2.0.7
 Summary: a Python Wrapper for the Gemma API
 Keywords: gemma,bioinformatics
 Requires-Python: >=3.10

{gemmapy-2.0.5 → gemmapy-2.0.7}/pyproject.toml

@@ -7,7 +7,7 @@ name = "gemmapy"
 description = "a Python Wrapper for the Gemma API"
 keywords = ["gemma", "bioinformatics"]
 readme = "README.rst"
-version = "2.0.5"
+version = "2.0.7"
 requires-python = ">=3.10"
 dependencies = [
     'certifi >= 14.05.14',