pythonflex 0.2.3__tar.gz → 0.2.4__tar.gz

{pythonflex-0.2.3 → pythonflex-0.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pythonflex
-Version: 0.2.3
+Version: 0.2.4
 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-0.2.3 → pythonflex-0.2.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pythonflex"
-version = "0.2.3"
+version = "0.2.4"
 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-0.2.4/src/pythonflex/utils.py

@@ -0,0 +1,101 @@
+import os
+import re
+import tempfile
+import joblib
+import numpy as np
+import pandas as pd
+
+# Constants
+TMP_ROOT = ".tmp"
+VALID_EXTS = {".parquet", ".npy", ".pkl"}  # Removed .feather
+
+# Helper to sanitize names (make filesystem-safe)
+def _sanitize(name):
+    if not name:
+        return "data"
+    # Replace forbidden/problematic chars with '_', collapse multiples, strip edges
+    safe = re.sub(r'[<>:"/\\|?*$,\s]+', '_', str(name).strip())
+    safe = re.sub(r'_+', '_', safe).strip('_')
+    return safe if safe else "data"
+
+# Helper to get safe path
+def _safe_path(category, name=None, ext=".pkl"):
+    safe_category = _sanitize(category)
+    dir_path = os.path.join(TMP_ROOT, safe_category)
+    os.makedirs(dir_path, exist_ok=True)
+    safe_name = _sanitize(name) if name else "data"
+    return os.path.join(dir_path, f"{safe_name}{ext}")
+
+# Save function - Parquet for DataFrames
+def dsave(data, category, name=None, path=None):
+    # If data is dict and no name, recurse on each item
+    if name is None and isinstance(data, dict):
+        for k, v in data.items():
+            dsave(v, category, k)
+        return
+
+    # Choose format based on type
+    if isinstance(data, pd.DataFrame):
+        ext = ".parquet"
+        save_func = lambda p: data.to_parquet(p)
+    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)
+
+    target = _safe_path(category, name, ext)
+
+    # Atomic save: Write to temp file, then rename
+    with tempfile.NamedTemporaryFile(dir=os.path.dirname(target), delete=False, suffix=ext) as tf:
+        tmp_path = tf.name
+        tf.close()
+        save_func(tmp_path)
+    os.replace(tmp_path, target)
+
+# Load function - Parquet for DataFrames
+def dload(category, name=None, path=None):
+    dir_path = os.path.join(TMP_ROOT, _sanitize(category))
+
+    if not os.path.exists(dir_path):
+        return {}
+
+    if name is None:
+        # Load all in category as dict
+        out = {}
+        for filename in os.listdir(dir_path):
+            if not any(filename.endswith(ext) for ext in VALID_EXTS):
+                continue
+            k = os.path.splitext(filename)[0]
+            full_path = os.path.join(dir_path, filename)
+            try:
+                if filename.endswith(".parquet"):
+                    out[k] = pd.read_parquet(full_path)
+                elif filename.endswith(".npy"):
+                    out[k] = np.load(full_path, mmap_mode="r")
+                elif filename.endswith(".pkl"):
+                    out[k] = joblib.load(full_path, mmap_mode="r")
+            except (EOFError, ValueError, OSError):
+                print(f"Warning: '{full_path}' is corrupted. Skipping...")
+                os.remove(full_path)
+        return out
+
+    # Load specific name - try extensions in order
+    for ext in VALID_EXTS:
+        target = _safe_path(category, name, ext)
+        if os.path.exists(target):
+            try:
+                if ext == ".parquet":
+                    return pd.read_parquet(target)
+                elif ext == ".npy":
+                    return np.load(target, mmap_mode="r")
+                elif ext == ".pkl":
+                    return joblib.load(target, mmap_mode="r")
+            except (EOFError, ValueError, OSError) as e:
+                print(f"Warning: '{target}' is corrupted ({e}). Trying next format...")
+                os.remove(target)
+                continue
+    
+    print(f"Warning: No valid file found for {category}/{name}")
+    return {}

pythonflex-0.2.3/src/pythonflex/utils.py

@@ -1,138 +0,0 @@
-import os
-import re  # For sanitization (built-in, minimal regex)
-import tempfile
-import joblib
-import numpy as np
-import pandas as pd
-
-# Constants - ADD .parquet to valid extensions
-TMP_ROOT = ".tmp"
-VALID_EXTS = {".feather", ".parquet", ".npy", ".pkl"}
-
-# REMOVE THE MONKEY PATCH FROM HERE - it should be in your main script!
-
-# Helper to sanitize names (make filesystem-safe)
-def _sanitize(name):
-    if not name:
-        return "data"
-    # Replace forbidden/problematic chars with '_', collapse multiples, strip edges
-    safe = re.sub(r'[<>:"/\\|?*$,\s]+', '_', str(name).strip())
-    safe = re.sub(r'_+', '_', safe).strip('_')
-    return safe if safe else "data"
-
-# Helper to get safe path
-def _safe_path(category, name=None, ext=".pkl"):
-    safe_category = _sanitize(category)
-    dir_path = os.path.join(TMP_ROOT, safe_category)
-    os.makedirs(dir_path, exist_ok=True)
-    safe_name = _sanitize(name) if name else "data"
-    return os.path.join(dir_path, f"{safe_name}{ext}")
-
-# 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):
-        for k, v in data.items():
-            dsave(v, category, k)
-        return
-
-    # Choose best extension based on type
-    if isinstance(data, pd.DataFrame):
-        # 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)
-
-    target = _safe_path(category, name, ext)
-
-    # Atomic save: Write to temp file, then rename
-    with tempfile.NamedTemporaryFile(dir=os.path.dirname(target), delete=False) as tf:
-        tmp_path = tf.name
-        tf.close()  # Close so save_func can write
-        save_func(tmp_path)
-    os.replace(tmp_path, target)  # Atomic move
-
-# 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))
-
-    if not os.path.exists(dir_path):
-        return {}
-
-    if name is None:
-        # Load all in category as dict
-        out = {}
-        for filename in os.listdir(dir_path):
-            if not any(filename.endswith(ext) for ext in VALID_EXTS):
-                continue
-            k = os.path.splitext(filename)[0]  # Key from filename (without ext)
-            full_path = os.path.join(dir_path, filename)
-            try:
-                if filename.endswith(".feather"):
-                    out[k] = pd.read_feather(full_path)
-                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
-                elif filename.endswith(".pkl"):
-                    out[k] = joblib.load(full_path, mmap_mode="r")  # MMap for perf
-            except (EOFError, ValueError, OSError):
-                print(f"Warning: '{full_path}' is corrupted. Skipping...")
-                os.remove(full_path)  # Delete corrupted file
-        return out
-
-    # 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":
-                    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) 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 {}