Docs update: clarify, add missing functions, misc fixes

doc/source/conf.py

@@ -21,7 +21,7 @@
 # -- Project information -----------------------------------------------------
 
 project = 'TileDB-Py'
-copyright = '2019, TileDB, Inc.'
+copyright = '2020, TileDB, Inc.'
 author = 'TileDB, Inc.'
 
 # The short X.Y version

doc/source/python-api.rst

@@ -21,6 +21,19 @@ There is also a submodule ``libtiledb`` which contains the necessary bindings to
    import tiledb
    tiledb.libtiledb.version()  # Native TileDB library version number
 
+Data import helpers
+-------------------
+
+.. autofunction:: tiledb.from_numpy
+.. autofunction:: tiledb.from_csv
+.. autofunction:: tiledb.from_pandas
+
+Auxiliary high-level functions
+------------------------------
+
+.. autofunction:: tiledb.open
+.. autofunction:: tiledb.empty_like
+
 Exceptions
 ----------
 
@@ -98,6 +111,7 @@ Array
    :members:
 
 .. autofunction:: tiledb.consolidate
+.. autofunction:: tiledb.vacuum
 
 Dense Array
 -----------
@@ -107,6 +121,7 @@ Dense Array
 
    .. automethod:: __getitem__(selection)
    .. automethod:: __setitem__(selection, value)
+   .. automethod:: from_numpy(uri, array, ctx=None, **kwargs)
 
 Sparse Array
 ------------
@@ -120,6 +135,7 @@ Sparse Array
 Object Management
 -----------------
 
+.. autofunction:: tiledb.array_exists
 .. autofunction:: tiledb.group_create
 .. autofunction:: tiledb.object_type
 .. autofunction:: tiledb.remove

tiledb/dataframe_.py

@@ -319,10 +319,12 @@ def from_pandas(uri, dataframe, **kwargs):
     :param uri: URI for new TileDB array
     :param dataframe: pandas DataFrame
     :param mode: Creation mode, one of 'ingest' (default), 'schema_only', 'append'
-    :param kwargs: optional keyword arguments for Pandas and TileDB.
-        TileDB arguments: tile_order, cell_order, allows_duplicates, sparse,
-                          mode, attrs_filters, coords_filters
-    :return:
+
+    :Keyword Arguments: optional keyword arguments for TileDB, see ``tiledb.from_csv``.
+
+    :raises: :py:exc:`tiledb.TileDBError`
+    :return: None
+
     """
     import pandas as pd
 
@@ -500,29 +502,32 @@ def open_dataframe(uri):
 
 
 def from_csv(uri, csv_file, **kwargs):
-    """Create TileDB array at given URI from a CSV file
+    """
+    Create TileDB array at given URI from a CSV file or list of files
 
     :param uri: URI for new TileDB array
     :param csv_file: input CSV file or list of CSV files.
                      Note: multi-file ingestion requires a `chunksize` argument. Files will
                      be read in batches of at least `chunksize` rows before writing to the
                      TileDB array.
-    :param kwargs:
-                - Any pandas.read_csv supported keyword argument.
-                - TileDB-specific arguments:
-                    'allows_duplicates': Generated schema should allow duplicates
-                    'cell_order': Schema cell order
-                    'tile_order': Schema tile order
-                    'mode': (default 'ingest'), Ingestion mode: 'ingest', 'schema_only', 'append'
-                    'full_domain': Dimensions should be created with full range of the dtype
-                    'attrs_filters': FilterList to apply to all Attributes
-                    'coords_filters': FilterList to apply to all coordinates (Dimensions)
-                    'sparse': (default True) Create sparse schema
-                    'tile': Schema tiling (capacity)
-                    'date_spec': Dictionary of {'column_name': format_spec} to apply to date/time
-                        columns which are not correctly inferred by pandas 'parse_dates'.
-                        Format must be specified using the Python format codes:
-                        https://docs.python.org/3/library/datetime.html#strftime-and-strptime-behavior
+
+    :Keyword Arguments:
+        - Any ``pandas.read_csv`` supported keyword argument.
+        - TileDB-specific arguments:
+            * ``allows_duplicates``: Generated schema should allow duplicates
+            * ``cell_order``: Schema cell order
+            * ``tile_order``: Schema tile order
+            * ``mode``: (default ``ingest``), Ingestion mode: ``ingest``, ``schema_only``,
+              ``append``
+            * ``full_domain``: Dimensions should be created with full range of the dtype
+            * ``attrs_filters``: FilterList to apply to all Attributes
+            * ``coords_filters``: FilterList to apply to all coordinates (Dimensions)
+            * ``sparse``: (default True) Create sparse schema
+            * ``tile``: Schema tiling (capacity)
+            * ``date_spec``: Dictionary of {``column_name``: format_spec} to apply to date/time
+              columns which are not correctly inferred by pandas 'parse_dates'.
+              Format must be specified using the Python format codes:
+              https://docs.python.org/3/library/datetime.html#strftime-and-strptime-behavior
     :return: None
 
     **Example:**

tiledb/highlevel.py

@@ -75,7 +75,8 @@ def empty_like(uri, arr, config=None, key=None, tile=None):
 
 def from_numpy(uri, array, ctx=None, **kw):
     """
-    Convenience method, see `tiledb.DenseArray.from_numpy`
+    Convenience method to create a TileDB array from a Numpy array.
+    See documentation of :func:`tiledb.DenseArray.from_numpy`.
     """
     if not ctx:
         ctx = default_ctx()