pythonflex 0.2.1__tar.gz → 0.2.3__tar.gz

{pythonflex-0.2.1 → pythonflex-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pythonflex
-Version: 0.2.1
+Version: 0.2.3
 Summary: pythonFLEX is a benchmarking toolkit for evaluating CRISPR screen results against biological gold standards. The toolkit computes gene-level and complex-level performance metrics, helping researchers systematically assess the biological relevance and resolution of their CRISPR screening data.
 Author-email: Yasir Demirtaş <tyasird@hotmail.com>
 Requires-Python: >=3.9

{pythonflex-0.2.1 → pythonflex-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pythonflex"
-version = "0.2.1"
+version = "0.2.3"
 description = "pythonFLEX is a benchmarking toolkit for evaluating CRISPR screen results against biological gold standards. The toolkit computes gene-level and complex-level performance metrics, helping researchers systematically assess the biological relevance and resolution of their CRISPR screening data."
 readme = "README.md"
 authors = [

{pythonflex-0.2.1 → pythonflex-0.2.3}/src/pythonflex/utils.py

@@ -9,19 +9,7 @@ import pandas as pd
 TMP_ROOT = ".tmp"
 VALID_EXTS = {".feather", ".parquet", ".npy", ".pkl"}
 
-# Minimal fix - just patch the problematic save
-original_to_feather = pd.DataFrame.to_feather
-def safe_to_feather(self, path, **kwargs):
-    try:
-        return original_to_feather(self, path, **kwargs)
-    except ValueError as e:
-        if "feather does not support serializing" in str(e):
-            # FIXED: Better path handling
-            parquet_path = os.path.splitext(path)[0] + '.parquet'
-            self.to_parquet(parquet_path, **kwargs)
-        else:
-            raise
-pd.DataFrame.to_feather = safe_to_feather
+# REMOVE THE MONKEY PATCH FROM HERE - it should be in your main script!
 
 # Helper to sanitize names (make filesystem-safe)
 def _sanitize(name):
@@ -40,7 +28,7 @@ def _safe_path(category, name=None, ext=".pkl"):
     safe_name = _sanitize(name) if name else "data"
     return os.path.join(dir_path, f"{safe_name}{ext}")
 
-# Save function
+# Save function - with built-in parquet fallback
 def dsave(data, category, name=None, path=None):  # 'path' ignored for compatibility with old code
     # If data is dict and no name, recurse on each item
     if name is None and isinstance(data, dict):
@@ -50,14 +38,41 @@ def dsave(data, category, name=None, path=None):  # 'path' ignored for compatibi
 
     # Choose best extension based on type
     if isinstance(data, pd.DataFrame):
-        ext = ".feather"
-        save_func = lambda p: data.to_feather(p)
+        # Try Feather first, fallback to Parquet if it fails
+        target_feather = _safe_path(category, name, ".feather")
+        target_parquet = _safe_path(category, name, ".parquet")
+        
+        # Try Feather first
+        try:
+            with tempfile.NamedTemporaryFile(dir=os.path.dirname(target_feather), delete=False, suffix='.feather') as tf:
+                tmp_path = tf.name
+                tf.close()
+                data.to_feather(tmp_path)
+            os.replace(tmp_path, target_feather)
+            return
+        except ValueError as e:
+            if "feather does not support serializing" in str(e):
+                print(f"Feather failed for {name}, using Parquet instead")
+                # Clean up failed feather temp file
+                if os.path.exists(tmp_path):
+                    os.unlink(tmp_path)
+                
+                # Save as Parquet
+                with tempfile.NamedTemporaryFile(dir=os.path.dirname(target_parquet), delete=False, suffix='.parquet') as tf:
+                    tmp_path = tf.name
+                    tf.close()
+                    data.to_parquet(tmp_path)
+                os.replace(tmp_path, target_parquet)
+                return
+            else:
+                raise
+                
     elif isinstance(data, np.ndarray):
         ext = ".npy"
         save_func = lambda p: np.save(p, data, allow_pickle=False)
     else:
         ext = ".pkl"
-        save_func = lambda p: joblib.dump(data, p, compress=0)  # Add compress=3 if needed
+        save_func = lambda p: joblib.dump(data, p, compress=0)
 
     target = _safe_path(category, name, ext)
 
@@ -68,7 +83,7 @@ def dsave(data, category, name=None, path=None):  # 'path' ignored for compatibi
         save_func(tmp_path)
     os.replace(tmp_path, target)  # Atomic move
 
-# Load function - FIXED: Added parquet support
+# Load function - with parquet support and better error handling
 def dload(category, name=None, path=None):  # 'path' ignored for compatibility
     dir_path = os.path.join(TMP_ROOT, _sanitize(category))
 
@@ -86,7 +101,7 @@ def dload(category, name=None, path=None):  # 'path' ignored for compatibility
             try:
                 if filename.endswith(".feather"):
                     out[k] = pd.read_feather(full_path)
-                elif filename.endswith(".parquet"):  # ADDED
+                elif filename.endswith(".parquet"):
                     out[k] = pd.read_parquet(full_path)
                 elif filename.endswith(".npy"):
                     out[k] = np.load(full_path, mmap_mode="r")  # MMap for perf
@@ -97,21 +112,27 @@ def dload(category, name=None, path=None):  # 'path' ignored for compatibility
                 os.remove(full_path)  # Delete corrupted file
         return out
 
-    # Load specific name (try extensions in order)
-    for ext in VALID_EXTS:
+    # Load specific name (try extensions in order - prefer parquet for reliability)
+    preferred_order = [".parquet", ".feather", ".npy", ".pkl"]
+    
+    for ext in preferred_order:
+        if ext not in VALID_EXTS:
+            continue
         target = _safe_path(category, name, ext)
         if os.path.exists(target):
             try:
                 if ext == ".feather":
                     return pd.read_feather(target)
-                elif ext == ".parquet":  # ADDED
+                elif ext == ".parquet":
                     return pd.read_parquet(target)
                 elif ext == ".npy":
                     return np.load(target, mmap_mode="r")  # MMap for perf
                 elif ext == ".pkl":
                     return joblib.load(target, mmap_mode="r")  # MMap for perf
-            except (EOFError, ValueError, OSError):
-                print(f"Warning: '{target}' is corrupted. Deleting and returning {{}}...")
-                os.remove(target)
-                return {}
+            except (EOFError, ValueError, OSError) as e:
+                print(f"Warning: '{target}' is corrupted ({e}). Trying next format...")
+                os.remove(target)  # Delete corrupted file
+                continue  # Try next format instead of returning {}
+    
+    print(f"Warning: No valid file found for {category}/{name}")
     return {}