genal-python 1.2__tar.gz → 1.2.2__tar.gz

{genal_python-1.2 → genal_python-1.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: genal-python
-Version: 1.2
+Version: 1.2.2
 Summary: A python toolkit for polygenic risk scoring and mendelian randomization.
 Author-email: Cyprien Rivier <riviercyprien@gmail.com>
 Requires-Python: >=3.8

{genal_python-1.2 → genal_python-1.2.2}/genal/MRpresso.py

@@ -77,13 +77,11 @@ def mr_presso(
     Random_data_o = np.vstack([r[2] for r in results])
 
     global_p = np.sum([r > RSSobs[0] for r in RSSexp]) / n_iterations
-    global_p_str = (
-        global_p if global_p > 1 / n_iterations else f"< {1/n_iterations:.1e}"
-    )
+    
     if outlier_test:
-        GlobalTest = {"RSSobs": RSSobs[0], "global_test_p": global_p_str}
+        GlobalTest = {"RSSobs": RSSobs[0], "global_test_p": global_p}
     else:
-        GlobalTest = {"RSSobs": RSSobs, "global_test_p": global_p_str}
+        GlobalTest = {"RSSobs": RSSobs, "global_test_p": global_p}
 
     # 3- Computing the single IV outlier test
     if global_p < significance_p and outlier_test:

{genal_python-1.2 → genal_python-1.2.2}/genal/__init__.py

@@ -4,7 +4,7 @@ from .tools import default_config, write_config, set_plink, install_plink, delet
 from .geno_tools import Combine_Geno
 from .constants import CONFIG_DIR
 
-__version__ = "1.2"
+__version__ = "1.2.2"
 
 config_path = os.path.join(CONFIG_DIR, "config.json")
 

{genal_python-1.2 → genal_python-1.2.2}/genal/geno_tools.py

@@ -181,8 +181,8 @@ def fill_coordinates_func(data, reference_panel_df):
     data.drop(columns=["CHR", "POS"], inplace=True, errors="ignore")
     data = data.merge(reference_panel_df[["CHR", "POS", "SNP"]], on="SNP", how="left")
     n_missing = data["CHR"].isna().sum()
-    data["CHR"] = data["CHR"].astype("Int32")
-    data["POS"] = data["POS"].astype("Int32")
+    data["CHR"] = data["CHR"].astype("Int64")
+    data["POS"] = data["POS"].astype("Int64")
     print(
         f"The coordinates columns (CHR for chromosome and POS for position) have been created. {n_missing}({n_missing/data.shape[0]*100:.3f}%) SNPs were not found in the reference data and their values set to nan."
     )
@@ -239,15 +239,15 @@ def fill_snpids_func(data, reference_panel_df):
 
 
 def check_int_column(data, int_col):
-    """Set the type of the int_col column to Int32 and non-numeric values to NA."""
+    """Set the type of the int_col column to Int64 and non-numeric values to NA."""
     nrows = data.shape[0]
     # Remove any non-digit characters, convert to numeric, setting non-numeric to NaN
     data[int_col] = pd.to_numeric(
-        data[int_col].astype(str).str.replace(r'[^\d]', '', regex=True),
+        data[int_col].astype(str).str.replace(r'(\d+)', '', regex=True),
         errors='coerce'
     )
-    # Convert to Int32 which handles NaN values
-    data[int_col] = data[int_col].astype('Int32')
+    # Convert to Int64 which handles NaN values, using round() first to handle floats
+    data[int_col] = data[int_col].round().astype('Int64')
     n_nan = data[int_col].isna().sum()
     if n_nan > 0:
         print(

{genal_python-1.2 → genal_python-1.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "flit_core.buildapi"
 
 [project]
 name = "genal-python"  # Updated name for PyPI
-version = "1.2"
+version = "1.2.2"
 authors = [{name = "Cyprien Rivier", email = "riviercyprien@gmail.com"}]
 description = "A python toolkit for polygenic risk scoring and mendelian randomization."
 readme = "README.md"