Merge pull request #6 from pwwang/dev

0.0.4

.pre-commit-config.yaml

@@ -4,9 +4,11 @@ repos:
     rev: 5df1a4bf6f04a1ed3a643167b38d502575e29aef
     hooks:
     -   id: trailing-whitespace
-        exclude: 'docs/'
+        exclude: 'docs/|README\.rst'
     -   id: end-of-file-fixer
+        exclude: 'docs/|README\.rst'
     -   id: check-yaml
+        exclude: 'mkdocs.yml'
 -   repo: local
     hooks:
     -   id: masterpylintrc

README.md

@@ -1,19 +1,22 @@
 # datar
 
-Port of R data packages (especially from tidyverse): [tidyr][1], [dplyr][2], [tibble][4] and so on in python, using [pipda][3].
+Port of [dplyr][2] and other related R packages in python, using [pipda][3].
 
 Unlike other similar packages in python that just mimic the piping sign, `datar` follows the API designs from the original packages as possible. So that nearly no extra effort is needed for those who are familar with those R packages to transition to python.
 
 <!-- badges -->
+[![Pypi][6]][7] [![Github][8]][9] ![Building][10] [![Docs and API][11]][5] [![Codacy][12]][13] [![Codacy coverage][14]][13]
 
-[Documentation][5]
+[Documentation][5] | [Reference Maps][15] | [Notebook Examples][16] | [API][17]
 
 ## Installtion
 
 ```shell
 pip install -U datar
 ```
 
+`datar` requires python 3.7.1+ and is backended by `pandas (1.2+)`.
+
 ## Example usage
 
 ```python
@@ -92,3 +95,15 @@ iris >> pull(f.Sepal_Length) >> dist_plot()
 [3]: https://github.com/pwwang/pipda
 [4]: https://tibble.tidyverse.org/index.html
 [5]: https://pwwang.github.io/datar/
+[6]: https://img.shields.io/pypi/v/datar?style=flat-square
+[7]: https://pypi.org/project/datar/
+[8]: https://img.shields.io/github/v/tag/pwwang/datar?style=flat-square
+[9]: https://github.com/pwwang/datar
+[10]: https://img.shields.io/github/workflow/status/pwwang/datar/Build%20and%20Deploy?style=flat-square
+[11]: https://img.shields.io/github/workflow/status/pwwang/datar/Build%20Docs?label=Docs&style=flat-square
+[12]: https://img.shields.io/codacy/grade/3d9bdff4d7a34bdfb9cd9e254184cb35?style=flat-square
+[13]: https://app.codacy.com/gh/pwwang/datar
+[14]: https://img.shields.io/codacy/coverage/3d9bdff4d7a34bdfb9cd9e254184cb35?style=flat-square
+[15]: https://pwwang.github.io/datar/reference_maps/ALL/
+[16]: https://pwwang.github.io/datar/notebooks/across/
+[17]: https://pwwang.github.io/datar/api/datar/

README.rst

@@ -0,0 +1,130 @@
+.. role:: raw-html-m2r(raw)
+   :format: html
+
+
+datar
+=====
+
+Port of `dplyr <https://dplyr.tidyverse.org/index.html>`_ and other related R packages in python, using `pipda <https://github.com/pwwang/pipda>`_.
+
+Unlike other similar packages in python that just mimic the piping sign, ``datar`` follows the API designs from the original packages as possible. So that nearly no extra effort is needed for those who are familar with those R packages to transition to python.
+
+:raw-html-m2r:`<!-- badges -->`
+`
+.. image:: https://img.shields.io/pypi/v/datar?style=flat-square
+   :target: https://img.shields.io/pypi/v/datar?style=flat-square
+   :alt: Pypi
+ <https://pypi.org/project/datar/>`_ `
+.. image:: https://img.shields.io/github/v/tag/pwwang/datar?style=flat-square
+   :target: https://img.shields.io/github/v/tag/pwwang/datar?style=flat-square
+   :alt: Github
+ <https://github.com/pwwang/datar>`_ 
+.. image:: https://img.shields.io/github/workflow/status/pwwang/datar/Build%20and%20Deploy?style=flat-square
+   :target: https://img.shields.io/github/workflow/status/pwwang/datar/Build%20and%20Deploy?style=flat-square
+   :alt: Building
+ `
+.. image:: https://img.shields.io/github/workflow/status/pwwang/datar/Build%20Docs?label=Docs&style=flat-square
+   :target: https://img.shields.io/github/workflow/status/pwwang/datar/Build%20Docs?label=Docs&style=flat-square
+   :alt: Docs and API
+ <https://pwwang.github.io/datar/>`_ `
+.. image:: https://img.shields.io/codacy/grade/3d9bdff4d7a34bdfb9cd9e254184cb35?style=flat-square
+   :target: https://img.shields.io/codacy/grade/3d9bdff4d7a34bdfb9cd9e254184cb35?style=flat-square
+   :alt: Codacy
+ <https://app.codacy.com/gh/pwwang/datar>`_ `
+.. image:: https://img.shields.io/codacy/coverage/3d9bdff4d7a34bdfb9cd9e254184cb35?style=flat-square
+   :target: https://img.shields.io/codacy/coverage/3d9bdff4d7a34bdfb9cd9e254184cb35?style=flat-square
+   :alt: Codacy coverage
+ <https://app.codacy.com/gh/pwwang/datar>`_
+
+`Documentation <https://pwwang.github.io/datar/>`_ | `Reference Maps <https://pwwang.github.io/datar/reference_maps/ALL/>`_ | `Notebook Examples <https://pwwang.github.io/datar/notebooks/across/>`_ | `API <https://pwwang.github.io/datar/api/datar/>`_
+
+Installtion
+-----------
+
+.. code-block:: shell
+
+   pip install -U datar
+
+``datar`` requires python 3.7.1+ and is backended by ``pandas (1.2+)``.
+
+Example usage
+-------------
+
+.. code-block:: python
+
+   from datar import f
+   from datar.dplyr import mutate, filter, if_else
+   from datar.tibble import tibble
+
+   df = tibble(
+       x=range(4),
+       y=['zero', 'one', 'two', 'three']
+   )
+   df >> mutate(z=f.x)
+   """# output
+      x      y  z
+   0  0   zero  0
+   1  1    one  1
+   2  2    two  2
+   3  3  three  3
+   """
+
+   df >> mutate(z=if_else(f.x>1, 1, 0))
+   """# output:
+      x      y  z
+   0  0   zero  0
+   1  1    one  0
+   2  2    two  1
+   3  3  three  1
+   """
+
+   df >> filter(f.x>1)
+   """# output:
+      x      y
+   0  2    two
+   1  3  three
+   """
+
+   df >> mutate(z=if_else(f.x>1, 1, 0)) >> filter(f.z==1)
+   """# output:
+      x      y  z
+   0  2    two  1
+   1  3  three  1
+   """
+
+.. code-block:: python
+
+   # works with plotnine
+   import numpy
+   from datar.base import sin, pi
+   from plotnine import ggplot, aes, geom_line, theme_classic
+
+   df = tibble(x=numpy.linspace(0, 2*pi, 500))
+   (df >>
+      mutate(y=sin(f.x), sign=if_else(f.y>=0, "positive", "negative")) >>
+      ggplot(aes(x='x', y='y')) + theme_classic()
+   ) + geom_line(aes(color='sign'), size=1.2)
+
+
+.. image:: ./example.png
+   :target: ./example.png
+   :alt: example
+
+
+.. code-block:: python
+
+   # very easy to integrate with other libraries
+   # for example: klib
+   import klib
+   from pipda import register_verb
+   from datar.datasets import iris
+   from datar.dplyr import pull
+
+   dist_plot = register_verb(func=klib.dist_plot)
+   iris >> pull(f.Sepal_Length) >> dist_plot()
+
+
+.. image:: ./example2.png
+   :target: ./example2.png
+   :alt: example
+

datar/__init__.py

@@ -3,4 +3,4 @@
 from .core import operator as _datar_operator
 from .core.defaults import f
 
-__version__ = '0.0.3'
+__version__ = '0.0.4'

datar/base/funcs.py

@@ -397,22 +397,25 @@ def c(*elems: Any) -> Collection:
     return Collection(*elems)
 
 @register_func(None, context=Context.EVAL)
-def seq_along(along_with: Iterable[Any]) -> SeriesLikeType:
+def seq_along(
+        along_with: Iterable[Any],
+        _base0: bool = False
+) -> SeriesLikeType:
     """Generate sequences along an iterable"""
-    return numpy.array(range(len(along_with))) + 1
+    return numpy.array(range(len(along_with))) + int(not _base0)
 
 @register_func(None, context=Context.EVAL)
-def seq_len(length_out: IntOrIter) -> SeriesLikeType:
+def seq_len(length_out: IntOrIter, _base0: bool = False) -> SeriesLikeType:
     """Generate sequences with the length"""
     if is_scalar(length_out):
-        return numpy.array(range(int(length_out)))
+        return numpy.array(range(int(length_out))) + int(not _base0)
     if len(length_out) > 1:
         logger.warning(
             "In seq_len(%r) : first element used of 'length_out' argument",
             length_out
         )
     length_out = int(list(length_out)[0])
-    return numpy.array(range(length_out))
+    return numpy.array(range(length_out)) + int(not _base0)
 
 
 @register_func(None, context=Context.EVAL)
@@ -421,7 +424,8 @@ def seq(
         to: IntType = None,
         by: IntType = None,
         length_out: IntType = None,
-        along_with: IntType = None
+        along_with: IntType = None,
+        _base0: bool = False
 ) -> SeriesLikeType:
     """Generate a sequence
 
@@ -431,24 +435,27 @@ def seq(
         This API is consistent with r-base's seq. 1-based and inclusive.
     """
     if along_with is not None:
-        return seq_along(along_with)
+        return seq_along(along_with, _base0)
     if from_ is not None and not is_scalar(from_):
-        return seq_along(from_)
+        return seq_along(from_, _base0)
     if length_out is not None and from_ is None and to is None:
         return seq_len(length_out)
 
+    base = int(not _base0)
+
     if from_ is None:
-        from_ = 1
+        from_ = base
     elif to is None:
-        from_, to = 1, from_
+        from_, to = base, from_
 
     if length_out is not None:
         by = (float(to) - float(from_)) / float(length_out - 1)
+
     elif by is None:
         by = 1 if to > from_ else -1
-        length_out = to - from_ + 1 if to > from_ else from_ - to + 1
+        length_out = to - from_ + base if to > from_ else from_ - to + base
     else:
-        length_out = (to - from_ + 1.1 * by) // by
+        length_out = (to - from_ + .1 * by + float(base) * by) // by
     return numpy.array([from_ + n * by for n in range(int(length_out))])
 
 @register_func(None, context=Context.EVAL)

datar/dplyr/bind.py

@@ -77,7 +77,7 @@ def data_to_df(data):
             if col in dat and not dat[col].isna().all()
         ]
         all_categorical = [
-            is_categorical(ser) for ser in all_series
+            is_categorical(ser) or all(pandas.isna(ser)) for ser in all_series
         ]
         if all(all_categorical):
             union_cat = union_categoricals(all_series)
@@ -98,6 +98,7 @@ def data_to_df(data):
             keys=key_data.keys(),
             names=[_id, None]
         ).reset_index(level=0).reset_index(drop=True)
+
     return pandas.concat(key_data.values()).reset_index(drop=True)
 
 @bind_rows.register(DataFrameGroupBy, context=Context.PENDING)

datar/tibble/__init__.py

@@ -1,3 +1,10 @@
 """APIs for R-tibble"""
 
-from .funcs import tibble, tribble, fibble
+from .funcs import (
+    tibble, tibble_row, tribble, fibble,
+    enframe, deframe,
+    add_row, add_case, add_column,
+    has_rownames, has_index, remove_index, remove_rownames, drop_index,
+    rownames_to_column, index_to_column, rowid_to_column,
+    column_to_rownames, column_to_index,
+)