Merge pull request rapidsai#280 from randerzander/doc_improvements

[REVIEW] Added IO module to docs, exposes read_csv, fixed warning with docstri…
vuule · Oct 15, 2018 · 30e5c49 · 30e5c49
2 parents 6b7de97 + 913e245
commit 30e5c49
Show file tree

Hide file tree

Showing 4 changed files with 23 additions and 41 deletions.
diff --git a/docs/source/api.rst b/docs/source/api.rst
@@ -3,35 +3,32 @@ API Reference
 
 .. currentmodule:: pygdf.dataframe
 
-
 DataFrame
 ---------
-
 .. autoclass:: DataFrame
     :members:
 
+.. automodule:: pygdf.multi
+    :members:
 
 Series
 ------
-
-.. autoclass:: Series
+.. autoclass:: pygdf.Series
     :members:
 
-
-
-.. currentmodule:: pygdf.groupby
-
 Groupby
 -------
-
+.. currentmodule:: pygdf.groupby
 .. autoclass:: Groupby
     :members:
 
-
-.. currentmodule:: pygdf.gpuarrow
+IO
+--------------
+.. automodule:: pygdf.io
+    :members:
 
 GpuArrowReader
 --------------
-
+.. currentmodule:: pygdf.gpuarrow
 .. autoclass:: GpuArrowReader
     :members:
diff --git a/pygdf/dataframe.py b/pygdf/dataframe.py
@@ -677,30 +677,23 @@ def merge(self, other, on=None, how='left', lsuffix='_x', rsuffix='_y',
         Parameters
         ----------
         other : DataFrame
-
         on : label or list; defaults to None
             Column or index level names to join on. These must be found in
-            both DataFrames. If on is None and not merging on indexes then
+            both DataFrames.
+
+            If on is None and not merging on indexes then
             this defaults to the intersection of the columns
             in both DataFrames.
-
-
-        how : str; defaults to 'left'
-              Only accepts "left"
-              - left: use only keys from left frame, similar to
-               a SQL left outer join; preserve key order
-
+        how : str, defaults to 'left'
+            Only accepts 'left'
+            left: use only keys from left frame, similar to
+            a SQL left outer join; preserve key order
         lsuffix : str, defaults to '_x'
-                 The suffix to apply to overlapping column names
-                 in the left side
-
+            Suffix applied to overlapping column names on the left side
         rsuffix : str, defaults to '_y'
-                 The suffix to apply to overlapping column names
-                 in the right side
-
+            Suffix applied to overlapping column names on the right side
         type : str, defaults to 'hash'
 
-
         Returns
         -------
         merged : DataFrame

diff --git a/pygdf/io.py b/pygdf/io.py
@@ -21,9 +21,8 @@ def read_csv(filepath, lineterminator='\n',
              delimiter=',', sep=None, delim_whitespace=False,
              skipinitialspace=False, names=None, dtype=None,
              skipfooter=0, skiprows=0, dayfirst=False):
-
     """
-    Read CSV data into dataframe.
+    Load and parse a CSV file into a DataFrame
 
     Parameters
     ----------
@@ -33,7 +32,7 @@ def read_csv(filepath, lineterminator='\n',
         Delimiter to be used.
     delim_whitespace : bool, default False
         Determines whether to use whitespace as delimiter.
-    lineterminator : char, default '\n'
+    lineterminator : char, default '\\n'
         Character to indicate end of line.
     skipinitialspace : bool, default False
         Skip spaces after delimiter.
@@ -51,9 +50,8 @@ def read_csv(filepath, lineterminator='\n',
     -------
     GPU ``DataFrame`` object.
 
-    Example
-    -------
-
+    Examples
+    --------
     foo.txt : ::
 
         50,50|40,60|30,70|20,80|
@@ -66,14 +64,8 @@ def read_csv(filepath, lineterminator='\n',
       col1 col2
     0 40   60
     1 30   70
-
     """
 
-# def read_csv(filepath, lineterminator='\n',
-#              delimiter=',', sep=None, delim_whitespace=False,
-#              skipinitialspace=False, names=None, dtype=None,
-#              skipfooter=0, skiprows=0, dayfirst=False):
-
     if names is None or dtype is None:
         msg = '''Automatic dtype detection not implemented:
         Column names and dtypes must be specified.'''

diff --git a/pygdf/serialize.py b/pygdf/serialize.py
@@ -82,7 +82,7 @@ def should_use_ipc(context):
         destination.
     """
     _CONFIG_USE_IPC = bool(int(os.environ.get("DASK_GDF_USE_IPC", "1")))
-    
+
     # User opt-out
     if not _CONFIG_USE_IPC:
         return False