pandasGEXpress/parse_gct - modify to allow returning only row metadata or only col metadata to be more consistent with parse_gctx and allow consistent usage of parse

Author: Dave Lahr

cmapPy/pandasGEXpress/parse.py

@@ -2,7 +2,7 @@
 Generic parse method to parse either a .gct or a .gctx. 
 
 Takes in a file path corresponding to either a .gct or .gctx, 
-	and parses to a GCToo instance accordingly.
+    and parses to a GCToo instance accordingly.
 
 Note: Supports GCT1.2, GCT1.3, and GCTX1.0 files. 
 """
@@ -20,43 +20,43 @@
 
 
 def parse(file_path, convert_neg_666=True, rid=None, cid=None, ridx=None, cidx=None,
-          row_meta_only=False, col_meta_only=False, make_multiindex=False):
+        row_meta_only=False, col_meta_only=False, make_multiindex=False):
     """
-	Identifies whether file_path corresponds to a .gct or .gctx file and calls the
-	correct corresponding parse method.
+    Identifies whether file_path corresponds to a .gct or .gctx file and calls the
+    correct corresponding parse method.
 
-	Input:
-		Mandatory:
-		- gct(x)_file_path (str): full path to gct(x) file you want to parse.
-		
-		Optional:
-		- row_meta_only (bool): Whether to load data + metadata (if False), or just row metadata (if True) 
-			as pandas DataFrame
-		- col_meta_only (bool): Whether to load data + metadata (if False), or just col metadata (if True) 
-			as pandas DataFrame
-		- convert_neg_666 (bool): whether to convert -666 values to numpy.nan or not 
-			(see Note below for more details on this). Default = False.
-		- rid (list of strings): list of row ids to specifically keep from gctx. Default=None. 
-		- cid (list of strings): list of col ids to specifically keep from gctx. Default=None.
-		- make_multiindex (bool): whether to create a multi-index df combining
+    Input:
+        Mandatory:
+        - gct(x)_file_path (str): full path to gct(x) file you want to parse.
+
+        Optional:
+        - row_meta_only (bool): Whether to load data + metadata (if False), or just row metadata (if True)
+            as pandas DataFrame
+        - col_meta_only (bool): Whether to load data + metadata (if False), or just col metadata (if True)
+            as pandas DataFrame
+        - convert_neg_666 (bool): whether to convert -666 values to numpy.nan or not
+            (see Note below for more details on this). Default = False.
+        - rid (list of strings): list of row ids to specifically keep from gctx. Default=None.
+        - cid (list of strings): list of col ids to specifically keep from gctx. Default=None.
+        - make_multiindex (bool): whether to create a multi-index df combining
             the 3 component dfs
 
-	Output:
-		- myGCToo (GCToo)
+    Output:
+        - myGCToo (GCToo)
 
-	Note: why does convert_neg_666 exist? 
-		- In CMap--for somewhat obscure historical reasons--we use "-666" as our null value 
-		for metadata. However (so that users can take full advantage of pandas' methods, 
-		including those for filtering nan's etc) we provide the option of converting these 
-		into numpy.NaN values, the pandas default. 
-	"""
+    Note: why does convert_neg_666 exist?
+        - In CMap--for somewhat obscure historical reasons--we use "-666" as our null value
+        for metadata. However (so that users can take full advantage of pandas' methods,
+        including those for filtering nan's etc) we provide the option of converting these
+        into numpy.NaN values, the pandas default.
+    """
     if file_path.endswith(".gct"):
         # Ignoring arguments that won't be passed to parse_gct
-        for unused_arg in ["rid", "cid", "cidx", "row_meta_only", "col_meta_only"]:
+        for unused_arg in ["rid", "cid", "cidx"]:
             if eval(unused_arg):
                 msg = "parse_gct does not use the argument {}. Ignoring it...".format(unused_arg)
-                logger.info(msg)
-        curr = parse_gct.parse(file_path, convert_neg_666, make_multiindex)
+                logger.warning(msg)
+        curr = parse_gct.parse(file_path, convert_neg_666, row_meta_only, col_meta_only, make_multiindex)
     elif file_path.endswith(".gctx"):
         curr = parse_gctx.parse(file_path, convert_neg_666, rid, cid, ridx, cidx, row_meta_only, col_meta_only,
                                 make_multiindex)

cmapPy/pandasGEXpress/parse_gct.py

@@ -79,13 +79,17 @@
 DATA_TYPE = np.float32
 
 
-def parse(file_path, convert_neg_666=True, make_multiindex=False):
+def parse(file_path, convert_neg_666=True, row_meta_only=False, col_meta_only=False, make_multiindex=False):
     """ The main method.
 
     Args:
         - file_path (string): full path to gct(x) file you want to parse
         - convert_neg_666 (bool): whether to convert -666 values to numpy.nan
             (see Note below for more details). Default = True.
+        - row_meta_only (bool): Whether to load data + metadata (if False), or just row metadata (if True)
+            as pandas DataFrame
+        - col_meta_only (bool): Whether to load data + metadata (if False), or just col metadata (if True)
+            as pandas DataFrame
         - make_multiindex (bool): whether to create a multi-index df combining
             the 3 component dfs
 
@@ -123,11 +127,16 @@ def parse(file_path, convert_neg_666=True, make_multiindex=False):
         file_path, num_data_rows, num_data_cols,
         num_row_metadata, num_col_metadata, nan_values)
 
-    # Create the gctoo object and assemble 3 component dataframes
-    gctoo_obj = create_gctoo_obj(file_path, version,
-        row_metadata, col_metadata, data, make_multiindex)
+    if row_meta_only:
+        return row_metadata
+    elif col_meta_only:
+        return col_metadata
+    else:
+        # Create the gctoo object and assemble 3 component dataframes
+        gctoo_obj = create_gctoo_obj(file_path, version,
+            row_metadata, col_metadata, data, make_multiindex)
 
-    return gctoo_obj
+        return gctoo_obj
 
 
 def read_version_and_dims(file_path):