Renaming modin.dataframe to modin.pandas

.travis.yml

@@ -33,7 +33,7 @@ install:
 script:
   - export PATH="$HOME/miniconda/bin:$PATH"
 
-  - python -m pytest modin/dataframe/test/test_dataframe.py
-  - python -m pytest modin/dataframe/test/test_concat.py
-  - python -m pytest modin/dataframe/test/test_io.py
-  - python -m pytest modin/dataframe/test/test_groupby.py
+  - python -m pytest modin/pandas/test/test_dataframe.py
+  - python -m pytest modin/pandas/test/test_concat.py
+  - python -m pytest modin/pandas/test/test_io.py
+  - python -m pytest modin/pandas/test/test_groupby.py

README.rst

@@ -9,7 +9,7 @@ Modin
 
 |
 
-*Modin is the parent project of Pandas on Ray*
+*Modin is a library for unifying the way you interact with your data*
 
 Modin can be installed with pip: ``pip install modin``
 
@@ -24,7 +24,7 @@ Pandas on Ray
 |.. code-block:: python                        |.. code-block:: python                           |
 |                                              |                                                 |
 | # Normal pandas import                       | # Pandas on Ray import                          |
-| import pandas as pd                          | import modin.dataframe as pd                    |
+| import pandas as pd                          | import modin.pandas as pd                       |
 |                                              |                                                 |
 | df = pd.DataFrame({'col1': [1, 2, 3],        | df = pd.DataFrame({'col1': [1, 2, 3],           |
 |                    'col2': [1.0, 2.0, 3.0]}) |                    'col2': [1.0, 2.0, 3.0]})    |

docs/index.rst

@@ -7,7 +7,7 @@ Modin
     <a href="https://github.com/modin-project/modin"><img style="position: absolute; top: 0; right: 0; border: 0;" src="https://camo.githubusercontent.com/365986a132ccd6a44c23a9169022c0b5c890c387/68747470733a2f2f73332e616d617a6f6e6177732e636f6d2f6769746875622f726962626f6e732f666f726b6d655f72696768745f7265645f6161303030302e706e67" alt="Fork me on GitHub" data-canonical-src="https://s3.amazonaws.com/github/ribbons/forkme_right_red_aa0000.png"></a>
   </embed>
 
-*Modin is the parent project of Pandas on Ray*
+*Modin is a library for unifying the way you interact with your data*
 
 Modin can be installed with pip: ``pip install modin``
 
@@ -22,7 +22,7 @@ Pandas on Ray
 |.. code-block:: python                        |.. code-block:: python                           |
 |                                              |                                                 |
 | # Normal pandas import                       | # Pandas on Ray import                          |
-| import pandas as pd                          | import modin.dataframe as pd                    |
+| import pandas as pd                          | import modin.pandas as pd                       |
 |                                              |                                                 |
 | df = pd.DataFrame({'col1': [1, 2, 3],        | df = pd.DataFrame({'col1': [1, 2, 3],           |
 |                    'col2': [1.0, 2.0, 3.0]}) |                    'col2': [1.0, 2.0, 3.0]})    |

docs/pandas_on_ray.rst

@@ -13,7 +13,7 @@ to use Pandas on Ray just like you would Pandas.
 .. code-block:: python
 
   # import pandas as pd
-  import modin.dataframe as pd
+  import modin.pandas as pd
 
 Currently, we have part of the Pandas API implemented and are working toward
 full functional parity with Pandas.
@@ -29,7 +29,7 @@ output:
 
 .. code-block:: text
 
-  >>> import modin.dataframe as pd
+  >>> import modin.pandas as pd
 
   Waiting for redis server at 127.0.0.1:14618 to respond...
   Waiting for redis server at 127.0.0.1:31410 to respond...
@@ -39,7 +39,7 @@ output:
   View the web UI at http://localhost:8889/notebooks/ray_ui36796.ipynb?token=ac25867d62c4ae87941bc5a0ecd5f517dbf80bd8e9b04218
   ======================================================================
 
-Once you have executed  ``import modin.dataframe as pd``, you're ready to begin
+Once you have executed  ``import modin.pandas as pd``, you're ready to begin
 running your pandas pipeline as you were before.
 
 APIs Supported

docs/pandas_supported.rst

@@ -716,7 +716,7 @@ this.
 List of Other Supported Operations Available on Import
 ------------------------------------------------------
 
-If you ``import modin.dataframe as pd`` the following operations are available
+If you ``import modin.pandas as pd`` the following operations are available
 from ``pd.<op>``, e.g. ``pd.concat``. If you do not see an operation that
 **pandas** enables and would like to request it, feel free to `open an issue`_.
 Make sure you tell us your primary use-case so we can make it happen faster!

modin/dataframe/concat.py → modin/pandas/concat.py

@@ -37,7 +37,7 @@ def concat(objs, axis=0, join='outer', join_axes=None, ignore_index=False,
     if type_check is not None:
         raise ValueError("cannot concatenate object of type \"{0}\"; only "
                          "pandas.Series, pandas.DataFrame, "
-                         "and modin.dataframe.DataFrame objs are "
+                         "and modin.pandas.DataFrame objs are "
                          "valid", type(type_check))
 
     all_series = all(isinstance(obj, pandas.Series)

modin/dataframe/dataframe.py → modin/pandas/dataframe.py

@@ -65,22 +65,22 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
                 Dict can contain Series, arrays, constants, or list-like
                 objects.
             index (pandas.Index, list, ObjectID): The row index for this
-                dataframe.
-            columns (pandas.Index): The column names for this dataframe, in
+                DataFrame.
+            columns (pandas.Index): The column names for this DataFrame, in
                 pandas Index object.
             dtype: Data type to force. Only a single dtype is allowed.
                 If None, infer
             copy (boolean): Copy data from inputs.
                 Only affects DataFrame / 2d ndarray input
             col_partitions ([ObjectID]): The list of ObjectIDs that contain
-                the column dataframe partitions.
+                the column DataFrame partitions.
             row_partitions ([ObjectID]): The list of ObjectIDs that contain the
-                row dataframe partitions.
+                row DataFrame partitions.
             block_partitions: A 2D numpy array of block partitions.
             row_metadata (_IndexMetadata):
-                Metadata for the new dataframe's rows
+                Metadata for the new DataFrame's rows
             col_metadata (_IndexMetadata):
-                Metadata for the new dataframe's columns
+                Metadata for the new DataFrame's columns
         """
         if isinstance(data, DataFrame):
             self._frame_data = data._frame_data
@@ -2001,7 +2001,7 @@ def filter(self, items=None, like=None, regex=None, axis=None):
             axis: axis to filter on
 
         Returns:
-            A new dataframe with the filter applied.
+            A new DataFrame with the filter applied.
         """
         nkw = com._count_not_none(items, like, regex)
         if nkw > 1:
@@ -2159,13 +2159,13 @@ def gt(self, other, axis='columns', level=None):
         return self._operator_helper(pandas.DataFrame.gt, other, axis, level)
 
     def head(self, n=5):
-        """Get the first n rows of the dataframe.
+        """Get the first n rows of the DataFrame.
 
         Args:
             n (int): The number of rows to return.
 
         Returns:
-            A new dataframe with the first n rows of the dataframe.
+            A new DataFrame with the first n rows of the DataFrame.
         """
         if n >= len(self._row_metadata):
             return self.copy()
@@ -2254,7 +2254,7 @@ def info_helper(df):
         lines = result.split('\n')
 
         # Class denoted in info() output
-        class_string = '<class \'modin.dataframe.dataframe.DataFrame\'>\n'
+        class_string = '<class \'modin.pandas.dataframe.DataFrame\'>\n'
 
         # Create the Index info() string by parsing self.index
         index_string = self.index.summary() + '\n'
@@ -3492,7 +3492,7 @@ def reset_index(self, level=None, drop=False, inplace=False, col_level=0,
         Args:
             level: Only remove the given levels from the index. Removes all
                 levels by default
-            drop: Do not try to insert index into dataframe columns. This
+            drop: Do not try to insert index into DataFrame columns. This
                 resets the index to the default integer index.
             inplace: Modify the DataFrame in place (do not create a new object)
             col_level : If the columns have multiple levels, determines which
@@ -4244,13 +4244,13 @@ def swaplevel(self, i=-2, j=-1, axis=0):
             "github.com/ray-project/ray.")
 
     def tail(self, n=5):
-        """Get the last n rows of the dataframe.
+        """Get the last n rows of the DataFrame.
 
         Args:
             n (int): The number of rows to return.
 
         Returns:
-            A new dataframe with the last n rows of this dataframe.
+            A new DataFrame with the last n rows of this DataFrame.
         """
         if n >= len(self._row_metadata):
             return self
@@ -4873,10 +4873,10 @@ def __setitem__(self, key, value):
             self.insert(loc=loc, column=key, value=value)
 
     def __len__(self):
-        """Gets the length of the dataframe.
+        """Gets the length of the DataFrame.
 
         Returns:
-            Returns an integer length of the dataframe object.
+            Returns an integer length of the DataFrame object.
         """
         return len(self._row_metadata)
 
@@ -4899,7 +4899,7 @@ def __iter__(self):
         """Iterate over the columns
 
         Returns:
-            An Iterator over the columns of the dataframe.
+            An Iterator over the columns of the DataFrame.
         """
         return iter(self.columns)
 
@@ -5260,7 +5260,7 @@ def _copartition(self, other, new_index):
         return zip(new_partitions_self, new_partitions_other)
 
     def _operator_helper(self, func, other, axis, level, *args):
-        """Helper method for inter-dataframe and scalar operations"""
+        """Helper method for inter-DataFrame and scalar operations"""
         if isinstance(other, DataFrame):
             return self._inter_df_op_helper(
                 lambda x, y: func(x, y, axis, level, *args),

modin/dataframe/index_metadata.py → modin/pandas/index_metadata.py

@@ -36,7 +36,7 @@ def __init__(self, dfs=None, index=None, axis=0, lengths_oid=None,
         """Inits a IndexMetadata from Ray DataFrame partitions
 
         Args:
-            dfs ([ObjectID]): ObjectIDs of dataframe partitions
+            dfs ([ObjectID]): ObjectIDs of DataFrame partitions
             index (pandas.Index): Index of the Ray DataFrame.
             axis: Axis of partition (0=row partitions, 1=column partitions)
 
@@ -72,7 +72,7 @@ def _set__lengths(self, lengths):
     _lengths = property(_get__lengths, _set__lengths)
 
     def _get__coord_df(self):
-        """Get the coordinate dataframe wrapped by this _IndexMetadata.
+        """Get the coordinate DataFrame wrapped by this _IndexMetadata.
 
         Since we may have had an index set before our coord_df was
         materialized, we'll have to apply it to the newly materialized df
@@ -85,7 +85,7 @@ def _get__coord_df(self):
         return self._coord_df_cache
 
     def _set__coord_df(self, coord_df):
-        """Set the coordinate dataframe wrapped by this _IndexMetadata.
+        """Set the coordinate DataFrame wrapped by this _IndexMetadata.
 
         Sometimes we set the _IndexMetadata's coord_df outside of the
         constructor, generally using fxns like drop(). This produces a modified

modin/dataframe/indexing.py → modin/pandas/indexing.py

@@ -24,7 +24,7 @@
   and perform lookup/item write.
 
 _LocIndexer and _iLocIndexer is responsible for indexer specific logic and
-  lookup computation. Loc will take care of enlarge dataframe. Both indexer
+  lookup computation. Loc will take care of enlarge DataFrame. Both indexer
   will take care of translating pandas's lookup to Ray DataFrame's internal
   lookup.
 
@@ -145,8 +145,8 @@ def __init__(self, ray_df):
     def __getitem__(self, row_lookup, col_lookup, ndim):
         """
         Args:
-            row_lookup: A pandas dataframe, a partial view from row_coord_df
-            col_lookup: A pandas dataframe, a partial view from col_coord_df
+            row_lookup: A pandas DataFrame, a partial view from row_coord_df
+            col_lookup: A pandas DataFrame, a partial view from col_coord_df
             ndim: the dimension of returned data
         """
         if ndim == 2:
@@ -218,8 +218,8 @@ def _generate_view(self, row_lookup, col_lookup):
     def __setitem__(self, row_lookup, col_lookup, item):
         """
         Args:
-            row_lookup: A pandas dataframe, a partial view from row_coord_df
-            col_lookup: A pandas dataframe, a partial view from col_coord_df
+            row_lookup: A pandas DataFrame, a partial view from row_coord_df
+            col_lookup: A pandas DataFrame, a partial view from col_coord_df
             item: The new item needs to be set. It can be any shape that's
                 broadcastable to the product of the lookup tables.
         """

modin/dataframe/test/test_concat.py → modin/pandas/test/test_concat.py

@@ -4,8 +4,8 @@
 
 import pytest
 import pandas
-import modin.dataframe as pd
-from modin.dataframe.utils import (
+import modin.pandas as pd
+from modin.pandas.utils import (
     to_pandas,
     from_pandas
 )

modin/dataframe/test/test_dataframe.py → modin/pandas/test/test_dataframe.py

@@ -7,8 +7,8 @@
 import pandas
 import pandas.util.testing as tm
 from pandas.tests.frame.common import TestData
-import modin.dataframe as pd
-from modin.dataframe.utils import to_pandas
+import modin.pandas as pd
+from modin.pandas.utils import to_pandas
 
 
 @pytest.fixture
@@ -1997,7 +1997,7 @@ def test_infer_objects():
 @pytest.fixture
 def test_info(ray_df):
     info_string = ray_df.info()
-    assert '<class \'modin.dataframe.dataframe.DataFrame\'>\n' in info_string
+    assert '<class \'modin.pandas.dataframe.DataFrame\'>\n' in info_string
     info_string = ray_df.info(memory_usage=True)
     assert 'memory_usage: ' in info_string
 

modin/dataframe/test/test_groupby.py → modin/pandas/test/test_groupby.py

@@ -6,8 +6,8 @@
 import sys
 import pandas
 import numpy as np
-import modin.dataframe as pd
-from modin.dataframe.utils import (
+import modin.pandas as pd
+from modin.pandas.utils import (
     from_pandas,
     to_pandas)
 

modin/dataframe/test/test_io.py → modin/pandas/test/test_io.py

@@ -5,8 +5,8 @@
 import pytest
 import numpy as np
 import pandas
-from modin.dataframe.utils import to_pandas
-import modin.dataframe as pd
+from modin.pandas.utils import to_pandas
+import modin.pandas as pd
 import os
 import sqlite3
 

modin/dataframe/test/test_series.py → modin/pandas/test/test_series.py

@@ -3,7 +3,7 @@
 from __future__ import print_function
 
 import pytest
-import modin.dataframe as pd
+import modin.pandas as pd
 
 
 @pytest.fixture

modin/dataframe/utils.py → modin/pandas/utils.py

@@ -125,11 +125,11 @@ def _get_nan_block_id(n_row=1, n_col=1, transpose=False):
 
 
 def _get_lengths(df):
-    """Gets the length of the dataframe.
+    """Gets the length of the DataFrame.
     Args:
         df: A remote pandas.DataFrame object.
     Returns:
-        Returns an integer length of the dataframe object. If the attempt
+        Returns an integer length of the DataFrame object. If the attempt
             fails, returns 0 as the length.
     """
     try:
@@ -141,11 +141,11 @@ def _get_lengths(df):
 
 
 def _get_widths(df):
-    """Gets the width (number of columns) of the dataframe.
+    """Gets the width (number of columns) of the DataFrame.
     Args:
         df: A remote pandas.DataFrame object.
     Returns:
-        Returns an integer width of the dataframe object. If the attempt
+        Returns an integer width of the DataFrame object. If the attempt
             fails, returns 0 as the length.
     """
     try:
@@ -164,7 +164,7 @@ def _partition_pandas_dataframe(df, num_partitions=None, row_chunksize=None):
             into. Has priority over chunksize.
         row_chunksize (int): The number of rows to put in each partition.
     Returns:
-        [ObjectID]: A list of object IDs corresponding to the dataframe
+        [ObjectID]: A list of object IDs corresponding to the DataFrame
         partitions
     """
     if num_partitions is not None:
@@ -342,7 +342,7 @@ def _build_row_lengths(df_row):
 
 @ray.remote
 def _build_coord_df(lengths, index):
-    """Build the coordinate dataframe over all partitions."""
+    """Build the coordinate DataFrame over all partitions."""
     filtered_lengths = [x for x in lengths if x > 0]
     coords = None
     if len(filtered_lengths) > 0:
@@ -462,7 +462,7 @@ def decorator(cls):
 
 @ray.remote
 def _reindex_helper(old_index, new_index, axis, npartitions, *df):
-    """Reindexes a dataframe to prepare for join/concat.
+    """Reindexes a DataFrame to prepare for join/concat.
 
     Args:
         df: The DataFrame partition