`
-Unlike other similar packages in python that just mimic the piping sign, ``datar`` follows the API designs from the original packages as much as possible. So that minimal effort is needed for those who are familar with those R packages to transition to python.
+Unlike other similar packages in python that just mimic the piping syntax, ``datar`` follows the API designs from the original packages as much as possible. So that minimal effort is needed for those who are familar with those R packages to transition to python.
Installtion
-----------
diff --git a/datar/__init__.py b/datar/__init__.py
index cf4b4936..c74573d6 100644
--- a/datar/__init__.py
+++ b/datar/__init__.py
@@ -4,4 +4,4 @@
from .core import frame_format_patch as _
from .core.defaults import f
-__version__ = '0.2.3'
+__version__ = '0.3.0'
diff --git a/datar/base/seq.py b/datar/base/seq.py
index 94959478..cd6bf7e5 100644
--- a/datar/base/seq.py
+++ b/datar/base/seq.py
@@ -17,37 +17,37 @@
@register_func(None, context=Context.EVAL)
def seq_along(
along_with: Iterable[Any],
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> ArrayLikeType:
"""Generate sequences along an iterable
Args:
along_with: An iterable to seq along with
- _base0: Whether the generated sequence should be 0-based.
+ base0_: Whether the generated sequence should be 0-based.
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
The generated sequence.
"""
- _base0 = get_option('index.base.0', _base0)
- return Array(range(len(along_with))) + int(not _base0)
+ base0_ = get_option('index.base.0', base0_)
+ return Array(range(len(along_with))) + int(not base0_)
@register_func(None, context=Context.EVAL)
def seq_len(
length_out: IntOrIter,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> ArrayLikeType:
"""Generate sequences with the length"""
- _base0 = get_option('index.base.0', _base0)
+ base0_ = get_option('index.base.0', base0_)
if is_scalar(length_out):
- return Array(range(int(length_out))) + int(not _base0)
+ return 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 Array(range(length_out)) + int(not _base0)
+ return Array(range(length_out)) + int(not base0_)
@register_func(None, context=Context.EVAL)
@@ -57,7 +57,7 @@ def seq(
by: IntType = None,
length_out: IntType = None,
along_with: IntType = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
) -> ArrayLikeType:
"""Generate a sequence
@@ -65,15 +65,15 @@ def seq(
Note that this API is consistent with r-base's seq. 1-based and inclusive.
"""
- _base0 = get_option('index.base.0', _base0)
+ base0_ = get_option('index.base.0', base0_)
if along_with is not None:
- return seq_along(along_with, _base0)
+ return seq_along(along_with, base0_)
if from_ is not None and not is_scalar(from_):
- return seq_along(from_, _base0)
+ 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)
+ base = int(not base0_)
if from_ is None:
from_ = base
diff --git a/datar/base/string.py b/datar/base/string.py
index ccb211d2..4376b73f 100644
--- a/datar/base/string.py
+++ b/datar/base/string.py
@@ -72,7 +72,7 @@ def grep(
value: bool = False,
fixed: bool = False,
invert: bool = False,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> Iterable[Union[int, str]]:
"""R's grep, get the element in x matching the pattern
@@ -83,7 +83,7 @@ def grep(
value: Return values instead of indices?
fixed: Fixed matching (instead of regex matching)?
invert: Return elements thata don't match instead?
- _base0: When return indices, whether return 0-based indices?
+ base0_: When return indices, whether return 0-based indices?
If not set, will use `datar.base.get_option('which.base.0')`
Returns:
@@ -104,8 +104,8 @@ def grep(
if value:
return x[matched]
- _base0 = get_option('which.base.0', _base0)
- return numpy.flatnonzero(matched) + int(not _base0)
+ base0_ = get_option('which.base.0', base0_)
+ return numpy.flatnonzero(matched) + int(not base0_)
@register_func(None, context=Context.EVAL)
def grepl(
@@ -439,7 +439,7 @@ def substr(
x: StringOrIter,
start: IntOrIter,
stop: IntOrIter,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> StringOrIter:
"""Extract substrings in strings.
@@ -447,7 +447,7 @@ def substr(
x: The strings
start: The start positions to extract
stop: The stop positions to extract
- _base0: Whether `start` and `stop` are 0-based
+ base0_: Whether `start` and `stop` are 0-based
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -456,15 +456,15 @@ def substr(
if is_scalar(x) and is_scalar(start) and is_scalar(stop):
if is_null(x):
return NA
- _base0 = get_option('index.base.0', _base0)
+ base0_ = get_option('index.base.0', base0_)
x = as_character(x)
lenx = len(x)
# int() converts numpy.int64 to int
- start0 = position_at(int(start), lenx, base0=_base0)
+ start0 = position_at(int(start), lenx, base0=base0_)
stop0 = position_at(
- min(int(stop), lenx - int(_base0)),
+ min(int(stop), lenx - int(base0_)),
lenx,
- base0=_base0
+ base0=base0_
)
return x[start0:stop0+1]
@@ -479,7 +479,7 @@ def substr(
start = recycle_value(start, maxlen)
stop = recycle_value(stop, maxlen)
out = [
- substr(elem, start_, stop_, _base0)
+ substr(elem, start_, stop_, base0_)
for elem, start_, stop_ in zip(x, start, stop)
]
if is_null(out).any():
@@ -491,7 +491,7 @@ def substring(
x: StringOrIter,
first: IntOrIter,
last: IntOrIter = 1000000,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> StringOrIter:
"""Extract substrings in strings.
@@ -499,13 +499,13 @@ def substring(
x: The strings
start: The start positions to extract
stop: The stop positions to extract
- _base0: Whether `start` and `stop` are 0-based
+ base0_: Whether `start` and `stop` are 0-based
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
The substrings from `x`
"""
- return substr(x, first, last, _base0)
+ return substr(x, first, last, base0_)
# strsplit --------------------------------
diff --git a/datar/base/which.py b/datar/base/which.py
index 2dc8a44f..61a03b4c 100644
--- a/datar/base/which.py
+++ b/datar/base/which.py
@@ -8,48 +8,48 @@
from ..core.contexts import Context
@register_func(None, context=Context.EVAL)
-def which(x: Iterable[bool], _base0: Optional[bool] = None) -> Iterable[int]:
+def which(x: Iterable[bool], base0_: Optional[bool] = None) -> Iterable[int]:
"""Convert a bool iterable to indexes
Args:
x: An iterable of bools.
Note that non-bool values will be converted into
- _base0: Whether the returned indexes are 0-based.
+ base0_: Whether the returned indexes are 0-based.
Controlled by `get_option('which.base.0')` if not provided
Returns:
The indexes
"""
- return numpy.flatnonzero(x) + int(not get_option('which.base.0', _base0))
+ return numpy.flatnonzero(x) + int(not get_option('which.base.0', base0_))
@register_func(None)
-def which_min(x: Iterable, _base0: Optional[bool] = None) -> int:
+def which_min(x: Iterable, base0_: Optional[bool] = None) -> int:
"""R's `which.min()`
Get the index of the element with the maximum value
Args:
x: The iterable
- _base0: Whether the index to return is 0-based or not.
+ base0_: Whether the index to return is 0-based or not.
Controlled by `get_option('which.base.0')` if not provided
Returns:
The index of the element with the maximum value
"""
- return numpy.argmin(x) + int(not get_option('which.base.0', _base0))
+ return numpy.argmin(x) + int(not get_option('which.base.0', base0_))
@register_func(None)
-def which_max(x: Iterable, _base0: bool = True) -> int:
+def which_max(x: Iterable, base0_: bool = True) -> int:
"""R's `which.max()`
Get the index of the element with the minimum value
Args:
x: The iterable
- _base0: Whether the index to return is 0-based or not
+ base0_: Whether the index to return is 0-based or not
Not that this is not controlled by `get_option('index.base.0')`
Returns:
The index of the element with the minimum value
"""
- return numpy.argmax(x) + int(not get_option('which.base.0', _base0))
+ return numpy.argmax(x) + int(not get_option('which.base.0', base0_))
diff --git a/datar/core/collections.py b/datar/core/collections.py
index dc22ca2a..369f1a7e 100644
--- a/datar/core/collections.py
+++ b/datar/core/collections.py
@@ -36,12 +36,11 @@ def __init__(
def _pipda_eval(
self,
data: Any,
- context: ContextAnnoType,
- level: int = 0
+ context: ContextAnnoType
) -> Any:
"""Defines how the object should be evaluated when evaluated by
pipda's evaluation"""
- self.elems = evaluate_args(self.elems, data, context, level)
+ self.elems = evaluate_args(self.elems, data, context)
return self
@abstractmethod
@@ -60,9 +59,9 @@ class Collection(CollectionBase, list):
convert them into 0-based finally
The Inverted, Negated and slice objects will be expanded immediately. This
- means there is no chance to apply `_base0` that is received later on. So
+ means there is no chance to apply `base0_` that is received later on. So
the original elements are stored in `self.elems` to wait for a second
- evaluation with the correct `_base0`.
+ evaluation with the correct `base0_`.
Args:
*args: The elements
diff --git a/datar/core/names.py b/datar/core/names.py
index d0dbbe25..5ec675fc 100644
--- a/datar/core/names.py
+++ b/datar/core/names.py
@@ -26,10 +26,10 @@ def _repair_names_unique(
names: Iterable[str],
quiet: bool = False,
sanitizer: Optional[Callable[[str], str]] = None,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> List[str]:
"""Make sure names are unique"""
- base = int(not _base0)
+ base = int(not base0_)
min_names = _repair_names_minimal(names)
neat_names = [
re.sub(r'(?:(? List[str]:
"""Make sure names are safely to be used as variable or attribute"""
min_names = _repair_names_minimal(names)
@@ -66,7 +66,7 @@ def _repair_names_universal(
if keyword.iskeyword(name) or (name and name[0].isdigit())
else name
),
- _base0=_base0
+ base0_=base0_
)
if not quiet:
changed_names = [
@@ -100,7 +100,7 @@ def _repair_names_check_unique(names: Iterable[str]) -> Iterable[str]:
def repair_names(
names: Iterable[str],
repair: Union[str, Callable],
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> List[str]:
"""Repair names based on the method
@@ -118,7 +118,7 @@ def repair_names(
- A function, accepts either a list of names or a single name.
Function accepts a list of names must annotate the first
argument with `typing.Iterable` or `typing.Sequence`.
- _base0: Whether the numeric suffix starts from 0 or not.
+ base0_: Whether the numeric suffix starts from 0 or not.
If not specified, will use `datar.base.get_option('index.base.0')`.
Examples:
@@ -141,7 +141,7 @@ def repair_names(
NameNonUniqueError: when check_unique fails
"""
from .utils import get_option
- _base0 = get_option('index.base.0', _base0)
+ base0_ = get_option('index.base.0', base0_)
if isinstance(repair, str):
repair = BUILTIN_REPAIR_METHODS[repair]
elif is_iterable(repair) and all(isinstance(elem, str) for elem in repair):
@@ -156,15 +156,15 @@ def repair_names(
annotation._name not in ('Iterable', 'Sequence')
): # scalar input
return [
- repair(name, _base0=_base0)
- if '_base0' in parameters
+ repair(name, base0_=base0_)
+ if 'base0_' in parameters
else repair(name)
for name in names
]
names = list(names)
return (
- repair(names, _base0=_base0)
- if '_base0' in parameters
+ repair(names, base0_=base0_)
+ if 'base0_' in parameters
else repair(names)
)
diff --git a/datar/core/operator.py b/datar/core/operator.py
index 83e2e5d9..1cd44935 100644
--- a/datar/core/operator.py
+++ b/datar/core/operator.py
@@ -1,12 +1,11 @@
"""Operators for datar"""
-from typing import Any, Optional, Tuple
+from typing import Any, Tuple
from functools import partial
import operator
import numpy
from pandas import Series
from pipda import register_operator, Operator
-from pipda.context import ContextBase
from .utils import length_of, recycle_value
from .collections import Collection, Inverted, Negated, Intersect
@@ -30,7 +29,7 @@ def _arithmetize2(self, left: Any, right: Any, op: str) -> Any:
left, right = _recycle_left_right(left, right)
return op_func(left, right)
- def invert(self, operand: Any, _context: Optional[ContextBase]) -> Any:
+ def invert(self, operand: Any) -> Any:
"""Interpretation for ~x"""
if isinstance(operand, (slice, str, list, tuple, Collection)):
return Inverted(operand)
diff --git a/datar/dplyr/across.py b/datar/dplyr/across.py
index a7545cb0..305f1070 100644
--- a/datar/dplyr/across.py
+++ b/datar/dplyr/across.py
@@ -8,7 +8,7 @@
import numpy
from pandas import DataFrame, Series
from pipda import register_func, evaluate_expr, evaluate_args, evaluate_kwargs
-from pipda.utils import functype
+from pipda.utils import functype, PipingEnvs
from pipda.context import ContextBase
from pipda.symbolic import DirectRefAttr
@@ -105,7 +105,7 @@ def evaluate(
DirectRefAttr(self.data, column),
*args,
**kwargs,
- _env='piping'
+ _env=PipingEnvs.PIPING
)._pipda_eval(self.data, context)
if ret is None:
@@ -157,7 +157,7 @@ def across(
*args: Any,
_names: Optional[str] = None,
_fn_context: Optional[Union[Context, ContextBase]] = Context.EVAL,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> DataFrame:
"""Apply the same transformation to multiple columns
@@ -178,7 +178,7 @@ def across(
single function case and `{_col}_{_fn}` for the case where
a list is used for _fns. In such a case, `{_fn}` is 0-based.
To use 1-based index, use `{_fn1}`
- _base0: Indicating whether the columns are 0-based if selected
+ base0_: Indicating whether the columns are 0-based if selected
by indexes. if not provided, will use
`datar.base.get_option('index.base.0')`.
_fn_context: Defines the context to evaluate the arguments for functions
@@ -197,21 +197,21 @@ def across(
_cols = evaluate_expr(_cols, _data, Context.SELECT)
return Across(
- _data, _cols, _fns, _names, _base0, args, kwargs
+ _data, _cols, _fns, _names, base0_, args, kwargs
).evaluate(_fn_context)
@register_func(context=Context.SELECT, verb_arg_only=True)
def c_across(
_data: DataFrame,
_cols: Optional[Iterable[str]] = None,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> Series:
"""Apply the same transformation to multiple columns rowwisely
Args:
_data: The dataframe
_cols: The columns
- _base0: Indicating whether the columns are 0-based if selected
+ base0_: Indicating whether the columns are 0-based if selected
by indexes. if not provided, will use
`datar.base.get_option('index.base.0')`.
@@ -221,7 +221,7 @@ def c_across(
if not _cols:
_cols = everything(_data)
- _cols = vars_select(_data.columns.tolist(), _cols, base0=_base0)
+ _cols = vars_select(_data.columns.tolist(), _cols, base0=base0_)
series = [_data.iloc[:, col] for col in _cols]
return numpy.concatenate(series)
@@ -237,7 +237,7 @@ def if_any(
*args: Any,
_names: Optional[str] = None,
_context: Optional[ContextBase] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> Iterable[bool]:
"""Apply the same predicate function to a selection of columns and combine
@@ -253,7 +253,7 @@ def if_any(
_cols, _fns, *args = args
return IfAny(
- _data, _cols, _fns, _names, _base0, args, kwargs
+ _data, _cols, _fns, _names, base0_, args, kwargs
).evaluate(_context)
@@ -270,7 +270,7 @@ def if_all(
*args: Any,
_names: Optional[str] = None,
_context: Optional[ContextBase] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> Iterable[bool]:
"""Apply the same predicate function to a selection of columns and combine
@@ -286,5 +286,5 @@ def if_all(
_cols, _fns, *args = args
return IfAll(
- _data, _cols, _fns, _names, _base0, args, kwargs
+ _data, _cols, _fns, _names, base0_, args, kwargs
).evaluate(_context)
diff --git a/datar/dplyr/bind.py b/datar/dplyr/bind.py
index 9bdecbb3..6a94100b 100644
--- a/datar/dplyr/bind.py
+++ b/datar/dplyr/bind.py
@@ -24,7 +24,7 @@ def bind_rows(
_data: Optional[Union[DataFrame, list, dict]],
*datas: Optional[Union[DataFrame, dict]],
_id: Optional[str] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
_copy: bool = True,
**kwargs: Union[DataFrame, dict]
) -> DataFrame:
@@ -38,8 +38,8 @@ def bind_rows(
Could be a dict or a list, keys/indexes will be used for _id col
*datas: Other dataframes to combine
_id: The name of the id columns
- _base0: Whether `_id` starts from 0 or not, if no keys are provided.
- If `_base0` is not provided, will use
+ base0_: Whether `_id` starts from 0 or not, if no keys are provided.
+ If `base0_` is not provided, will use
`datar.base.get_option('index.base.0')`
_copy: If `False`, do not copy data unnecessarily.
Original API does not support this. This argument will be
@@ -49,7 +49,7 @@ def bind_rows(
Returns:
The combined dataframe
"""
- base = int(not get_option('index.base.0', _base0))
+ base = int(not get_option('index.base.0', base0_))
if _id is not None and not isinstance(_id, str):
raise ValueError("`_id` must be a scalar string.")
@@ -130,9 +130,9 @@ def _(
@register_verb((DataFrame, dict, NoneType), context=Context.EVAL)
def bind_cols(
_data: Optional[Union[DataFrame, dict]],
- *datas: Optional[Union[DataFrame, dict]],
+ *datas: Union[DataFrame, dict],
_name_repair: Union[str, Callable] = "unique",
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
_copy: bool = True
) -> DataFrame:
"""Bind columns of give dataframes
@@ -151,7 +151,7 @@ def bind_cols(
but check they are unique,
- "universal": Make the names unique and syntactic
- a function: apply custom name repair
- _base0: Whether the numeric suffix starts from 0 or not.
+ base0_: Whether the numeric suffix starts from 0 or not.
If not specified, will use `datar.base.get_option('index.base.0')`.
_copy: If `False`, do not copy data unnecessarily.
Original API does not support this. This argument will be
@@ -176,6 +176,6 @@ def bind_cols(
ret.columns = repair_names(
ret.columns.tolist(),
repair=_name_repair,
- _base0=_base0
+ base0_=base0_
)
return ret
diff --git a/datar/dplyr/dslice.py b/datar/dplyr/dslice.py
index b08c75e1..7468df40 100644
--- a/datar/dplyr/dslice.py
+++ b/datar/dplyr/dslice.py
@@ -22,7 +22,7 @@ def slice( # pylint: disable=redefined-builtin
_data: DataFrame,
*rows: Any,
_preserve: bool = False,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Index rows by their (integer) locations
@@ -47,7 +47,7 @@ def slice( # pylint: disable=redefined-builtin
If _preserve = FALSE (the default), the grouping structure is
recalculated based on the resulting data,
otherwise the grouping is kept as is.
- _base0: If rows are selected by indexes, whether they are 0-based.
+ base0_: If rows are selected by indexes, whether they are 0-based.
If not provided, `datar.base.get_option('index.base.0')` is used.
Returns:
@@ -56,7 +56,7 @@ def slice( # pylint: disable=redefined-builtin
if not rows:
return _data
- rows = _sanitize_rows(rows, _data.shape[0], _base0)
+ rows = _sanitize_rows(rows, _data.shape[0], base0_)
out = _data.iloc[rows, :]
if isinstance(_data.index, RangeIndex):
out.reset_index(drop=True, inplace=True)
@@ -68,11 +68,11 @@ def _(
_data: DataFrameGroupBy,
*rows: Any,
_preserve: bool = False,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrameGroupBy:
"""Slice on grouped dataframe"""
out = _data.datar_apply(
- lambda df: slice(df, *rows, _base0=_base0)
+ lambda df: slice(df, *rows, base0_=base0_)
)
out = reconstruct_tibble(_data, out, keep_rowwise=True)
gdata = _filter_groups(out, _data)
@@ -106,7 +106,7 @@ def slice_head(
The sliced dataframe
"""
n = _n_from_prop(_data.shape[0], n, prop)
- return slice(_data, builtins.slice(None, n), _base0=True)
+ return slice(_data, builtins.slice(None, n), base0_=True)
@slice_head.register(DataFrameGroupBy, context=Context.PENDING)
def _(
@@ -132,7 +132,7 @@ def slice_tail(
[`slice_head()`](datar.dplyr.slice.slice_head)
"""
n = _n_from_prop(_data.shape[0], n, prop)
- return slice(_data, builtins.slice(-n, None), _base0=True)
+ return slice(_data, builtins.slice(-n, None), base0_=True)
@slice_tail.register(DataFrameGroupBy, context=Context.PENDING)
def _(
diff --git a/datar/dplyr/funs.py b/datar/dplyr/funs.py
index 76c72959..4c2b08c0 100644
--- a/datar/dplyr/funs.py
+++ b/datar/dplyr/funs.py
@@ -157,7 +157,7 @@ def nth(
n: int,
order_by: Optional[Iterable[Any]] = None,
default: Any = NA,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> Any:
"""Get the nth element of x
@@ -169,7 +169,7 @@ def nth(
order_by: An optional vector used to determine the order
default: A default value to use if the position does not exist
in the input.
- _base0: Whether `n` is 0-based or not.
+ base0_: Whether `n` is 0-based or not.
Returns:
A single element of x at `n'th`
@@ -182,7 +182,7 @@ def nth(
raise TypeError("`nth` expects `n` to be an integer")
try:
- return x[position_at(n, len(x), base0=_base0)]
+ return x[position_at(n, len(x), base0=base0_)]
except (ValueError, IndexError, TypeError):
return default
diff --git a/datar/dplyr/group_by.py b/datar/dplyr/group_by.py
index 806e3589..07db1415 100644
--- a/datar/dplyr/group_by.py
+++ b/datar/dplyr/group_by.py
@@ -21,6 +21,8 @@
from .group_data import group_vars
+# pylint: disable=unused-argument
+
@register_verb(DataFrame, context=Context.PENDING)
def group_by(
_data: DataFrame,
@@ -49,7 +51,7 @@ def group_by(
*args: variables or computations to group by.
Note that columns here cannot be selected by indexes. As they are
treated as computations to be added as new columns.
- So no `_base0` argument is supported.
+ So no `base0_` argument is supported.
**kwargs: Extra variables to group the dataframe
Return:
@@ -71,7 +73,7 @@ def group_by(
def rowwise(
_data: DataFrame,
*columns: Union[str, int],
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrameRowwise:
"""Compute on a data frame a row-at-a-time
@@ -82,14 +84,14 @@ def rowwise(
*columns: Variables to be preserved when calling summarise().
This is typically a set of variables whose combination
uniquely identify each row.
- _base0: Whether indexes are 0-based if columns are selected by indexes.
+ base0_: Whether indexes are 0-based if columns are selected by indexes.
If not given, will use `datar.base.get_option('index.base.0')`
Returns:
A row-wise data frame
"""
check_column_uniqueness(_data)
- idxes = vars_select(_data.columns, *columns, base0=_base0)
+ idxes = vars_select(_data.columns, *columns, base0=base0_)
if len(idxes) == 0:
return DataFrameRowwise(_data)
return DataFrameRowwise(_data, _group_vars=_data.columns[idxes].tolist())
@@ -98,7 +100,7 @@ def rowwise(
def _(
_data: DataFrameGroupBy,
*columns: str,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrameRowwise:
# grouped dataframe's columns are unique already
if columns:
@@ -114,9 +116,9 @@ def _(
def _(
_data: DataFrameRowwise,
*columns: str,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrameRowwise:
- idxes = vars_select(_data.columns, *columns, base0=_base0)
+ idxes = vars_select(_data.columns, *columns, base0=base0_)
if len(idxes) == 0:
# copy_attrs?
return DataFrameRowwise(_data)
@@ -127,7 +129,7 @@ def _(
def ungroup(
x: DataFrame,
*cols: Union[str, int],
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Ungroup a grouped data
@@ -136,7 +138,7 @@ def ungroup(
Args:
x: The data frame
*cols: Variables to remove from the grouping variables.
- _base0: If columns are selected with indexes, whether they are 0-based.
+ base0_: If columns are selected with indexes, whether they are 0-based.
If not given, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -150,12 +152,12 @@ def ungroup(
def _(
x: DataFrameGroupBy,
*cols: Union[str, int],
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
if not cols:
return DataFrame(x, index=x.index)
old_groups = group_vars(x)
- to_remove = vars_select(x.columns, *cols, base0=_base0)
+ to_remove = vars_select(x.columns, *cols, base0=base0_)
new_groups = setdiff(old_groups, x.columns[to_remove])
return group_by(x, *new_groups)
@@ -164,7 +166,7 @@ def _(
def _(
x: DataFrameRowwise,
*cols: Union[str, int],
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
if cols:
raise ValueError('`*cols` is not empty.')
diff --git a/datar/dplyr/group_iter.py b/datar/dplyr/group_iter.py
index 92f6a5f7..f8d5e3c1 100644
--- a/datar/dplyr/group_iter.py
+++ b/datar/dplyr/group_iter.py
@@ -33,7 +33,7 @@ def group_map(
*args: Any,
_keep: bool = False,
**kwargs: Any,
-) -> List[Any]:
+) -> Iterable:
"""A generator to map function to data in each group"""
keys = group_keys(_data) if nargs(_f) > 1 else None
for i, chunk in enumerate(group_split(_data, _keep=_keep)):
@@ -42,9 +42,20 @@ def group_map(
else:
yield _f(chunk, keys.iloc[[i], :], *args, **kwargs)
-group_map.list = register_verb(DataFrame, context=Context.PENDING)(
- lambda *args, **kwargs: list(group_map(*args, **kwargs))
-)
+def _group_map_list(
+ _data: DataFrame,
+ _f: Callable,
+ *args: Any,
+ _keep: bool = False,
+ **kwargs: Any
+) -> List:
+ """List version of group_map"""
+ return list(_data >> group_map(_f, *args, _keep=_keep, **kwargs))
+
+group_map.list = register_verb(
+ DataFrame,
+ context=Context.PENDING
+)(_group_map_list)
@register_verb(DataFrame, context=Context.EVAL)
def group_modify(
@@ -204,9 +215,19 @@ def _(
return group_split_impl(_data, _keep=True)
-group_split.list = register_verb(DataFrame, context=Context.PENDING)(
- lambda *args, **kwargs: list(group_split(*args, **kwargs))
-)
+def _group_split_list(
+ _data: DataFrame,
+ *args: Any,
+ _keep: bool = True,
+ **kwargs: Any
+) -> Iterable[DataFrame]:
+ """List version of group_split"""
+ return list(_data >> group_split(*args, _keep=_keep, **kwargs))
+
+group_split.list = register_verb(
+ DataFrame,
+ context=Context.PENDING
+)(_group_split_list)
def group_split_impl(data: DataFrame, _keep: bool):
"""Implement splitting data frame by groups"""
diff --git a/datar/dplyr/mutate.py b/datar/dplyr/mutate.py
index 0c50c3e3..eb785515 100644
--- a/datar/dplyr/mutate.py
+++ b/datar/dplyr/mutate.py
@@ -30,7 +30,7 @@ def mutate(
_keep: str = 'all',
_before: Optional[Union[int, str]] = None,
_after: Optional[Union[int, str]] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> DataFrame:
# pylint: disable=too-many-branches
@@ -54,7 +54,7 @@ def mutate(
_after: Optionally, control where new columns should appear
(the default is to add to the right hand side).
See relocate() for more details.
- _base0: Whether `_before` and `_after` are 0-based if given by indexes.
+ base0_: Whether `_before` and `_after` are 0-based if given by indexes.
If not provided, will use `datar.base.get_option('index.base.0')`
*args: and
**kwargs: Name-value pairs. The name gives the name of the column
@@ -97,7 +97,7 @@ def mutate(
out = out[setdiff(out.columns, removed)]
if _before is not None or _after is not None:
new = setdiff(cols.columns, _data.columns)
- out = relocate(out, *new, _before=_before, _after=_after, _base0=_base0)
+ out = relocate(out, *new, _before=_before, _after=_after, base0_=base0_)
if keep == 'all':
keep = out.columns
@@ -130,7 +130,7 @@ def _(
_keep: str = 'all',
_before: Optional[str] = None,
_after: Optional[str] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> DataFrameGroupBy:
"""Mutate on DataFrameGroupBy object"""
@@ -143,7 +143,7 @@ def apply_func(df):
_keep=_keep,
_before=_before,
_after=_after,
- _base0=_base0,
+ base0_=base0_,
**kwargs
)
ret.index = rows
@@ -175,7 +175,7 @@ def transmute(
*args: Any,
_before: Optional[Union[int, str]] = None,
_after: Optional[Union[int, str]] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> DataFrame:
"""Mutate with _keep='none'
@@ -188,7 +188,7 @@ def transmute(
_keep='none',
_before=_before,
_after=_after,
- _base0=_base0,
+ base0_=base0_,
**kwargs
)
diff --git a/datar/dplyr/pull.py b/datar/dplyr/pull.py
index 61ef8e33..ad9b226b 100644
--- a/datar/dplyr/pull.py
+++ b/datar/dplyr/pull.py
@@ -22,7 +22,7 @@ def pull(
var: Union[int, str] = -1,
name: Optional[StringOrIter] = None,
to: Optional[str] = None,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> Union[DataFrame, ArrayLikeType, Mapping[str, ArrayLikeType]]:
# pylint: disable=too-many-branches
"""Pull a series or a dataframe from a dataframe
@@ -52,7 +52,7 @@ def pull(
- If not provided: `series` when pulled data has only one columns.
`dict` if `name` provided and has the same length as the pulled
single column. Otherwise `frame`.
- _base0: Whether `var` is 0-based if given by index
+ base0_: Whether `var` is 0-based if given by index
If not provided, `datar.base.get_option('index.base.0')` is used.
Returns:
@@ -66,7 +66,7 @@ def pull(
name = [name]
if isinstance(var, int):
- var = position_at(var, _data.shape[1], base0=_base0)
+ var = position_at(var, _data.shape[1], base0=base0_)
var = _data.columns[var]
var = var.split('$', 1)[0]
diff --git a/datar/dplyr/recode.py b/datar/dplyr/recode.py
index eec32c2a..60f2895b 100644
--- a/datar/dplyr/recode.py
+++ b/datar/dplyr/recode.py
@@ -29,13 +29,13 @@ def _args_to_recodings(
**kwargs: Any
) -> Mapping[Any, Any]:
"""Convert arguments to replaceable"""
- _base0 = get_option('index.base.0')
+ base0_ = get_option('index.base.0')
values = {}
for i, arg in enumerate(args):
if isinstance(arg, dict):
values.update(arg)
else:
- values[i + int(not _base0)] = arg
+ values[i + int(not base0_)] = arg
values.update(kwargs)
if _force_index:
diff --git a/datar/dplyr/relocate.py b/datar/dplyr/relocate.py
index 37f2a25b..c0bae1da 100644
--- a/datar/dplyr/relocate.py
+++ b/datar/dplyr/relocate.py
@@ -15,7 +15,7 @@ def relocate(
*args: Any,
_before: Optional[Union[int, str]] = None,
_after: Optional[Union[int, str]] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> DataFrame:
"""change column positions
@@ -30,7 +30,7 @@ def relocate(
_before: and
_after: Destination. Supplying neither will move columns to
the left-hand side; specifying both is an error.
- _base0: Whether `_before` and `_after` are 0-based if given by indexes.
+ base0_: Whether `_before` and `_after` are 0-based if given by indexes.
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -48,7 +48,7 @@ def relocate(
all_columns,
*args,
**kwargs,
- _base0=_base0,
+ base0_=base0_,
_group_vars=gvars
)
if _before is not None and _after is not None:
@@ -59,14 +59,14 @@ def relocate(
# length = len(all_columns)
if _before is not None:
where = min(_eval_select(
- all_columns, _before, _group_vars=[], _base0=_base0
+ all_columns, _before, _group_vars=[], base0_=base0_
)[0])
if where not in to_move:
to_move.append(where)
elif _after is not None:
where = max(_eval_select(
- all_columns, _after, _group_vars=[], _base0=_base0
+ all_columns, _after, _group_vars=[], base0_=base0_
)[0])
if where not in to_move:
to_move.insert(0, where)
diff --git a/datar/dplyr/rename.py b/datar/dplyr/rename.py
index 108c0799..855c95f2 100644
--- a/datar/dplyr/rename.py
+++ b/datar/dplyr/rename.py
@@ -16,7 +16,7 @@
@register_verb(DataFrame, context=Context.SELECT)
def rename(
_data: DataFrame,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: str
) -> DataFrame:
"""Changes the names of individual variables using new_name = old_name
@@ -25,7 +25,7 @@ def rename(
Args:
_data: The dataframe
**kwargs: The new_name = old_name pairs
- _base0: Whether the old_name is 0-based if given by indexes.
+ base0_: Whether the old_name is 0-based if given by indexes.
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -36,7 +36,7 @@ def rename(
selected, new_names = _eval_select(
all_columns,
_group_vars=gvars,
- _base0=_base0,
+ base0_=base0_,
**kwargs,
)
@@ -61,7 +61,7 @@ def rename_with(
_data: DataFrame,
_fn: Callable[[str], str],
*args: Any,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> DataFrame:
"""Renames columns using a function.
@@ -74,7 +74,7 @@ def rename_with(
no non-keyword arguments are allowed to pass to the function, use
keyword arguments instead.
**kwargs: keyword arguments for `_fn`
- _base0: Whether the old_name is 0-based if given by indexes.
+ base0_: Whether the old_name is 0-based if given by indexes.
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -86,6 +86,6 @@ def rename_with(
cols = args[0]
args = args[1:]
- cols = _data.columns[vars_select(_data.columns, cols, base0=_base0)]
+ cols = _data.columns[vars_select(_data.columns, cols, base0=base0_)]
new_columns = {_fn(col, *args, **kwargs): col for col in cols}
- return rename(_data, **new_columns, _base0=True)
+ return rename(_data, **new_columns, base0_=True)
diff --git a/datar/dplyr/rows.py b/datar/dplyr/rows.py
index 867fdc58..47ae5ccb 100644
--- a/datar/dplyr/rows.py
+++ b/datar/dplyr/rows.py
@@ -274,4 +274,5 @@ def _rows_match(x: DataFrame, y: DataFrame) -> numpy.ndarray:
"""Mimic vctrs::vec_match"""
id_col = '__id__'
y_with_id = rownames_to_column(y, var=id_col)
- return left_join(x, y_with_id)[id_col].values
+ # pylint: disable=no-value-for-parameter
+ return (x >> left_join(y_with_id))[id_col].values
diff --git a/datar/dplyr/select.py b/datar/dplyr/select.py
index 371df317..180b54f6 100644
--- a/datar/dplyr/select.py
+++ b/datar/dplyr/select.py
@@ -20,7 +20,7 @@
def select(
_data: DataFrame,
*args: Union[StringOrIter, Inverted],
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Mapping[str, str]
) -> DataFrame:
"""Select (and optionally rename) variables in a data frame
@@ -37,7 +37,7 @@ def select(
Args:
*columns: The columns to select
**renamings: The columns to rename and select in new => old column way.
- _base0: Whether the columns are 0-based if given by indexes
+ base0_: Whether the columns are 0-based if given by indexes
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -50,7 +50,7 @@ def select(
*args,
**kwargs,
_group_vars=gvars,
- _base0=_base0
+ base0_=base0_
)
out = _data.iloc[:, selected].copy()
@@ -73,7 +73,7 @@ def _eval_select(
_all_columns: Index,
*args: Any,
_group_vars: Iterable[str],
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> Tuple[List[int], Mapping[str, str]]:
"""Evaluate selections to get locations
@@ -81,7 +81,7 @@ def _eval_select(
Returns:
A tuple of (selected columns, dict of old-to-new renaming columns)
"""
- selected = vars_select(_all_columns, *args, *kwargs.values(), base0=_base0)
+ selected = vars_select(_all_columns, *args, *kwargs.values(), base0=base0_)
missing = setdiff(_group_vars, _all_columns[selected])
if missing:
logger.info(
@@ -110,7 +110,7 @@ def _eval_select(
# try:
# If out of bounds, it should be raised at getting missing
val = _all_columns[
- position_at(val, len(_all_columns), base0=_base0)
+ position_at(val, len(_all_columns), base0=base0_)
]
# except IndexError:
# raise ColumnNotExistingError(
diff --git a/datar/dplyr/tidyselect.py b/datar/dplyr/tidyselect.py
index b92cce58..18324ec8 100644
--- a/datar/dplyr/tidyselect.py
+++ b/datar/dplyr/tidyselect.py
@@ -189,7 +189,7 @@ def matches(
def all_of(
_data: DataFrame,
x: Iterable[Union[int, str]],
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> List[str]:
"""For strict selection.
@@ -199,7 +199,7 @@ def all_of(
Args:
_data: The data piped in
x: A set of variables to match the columns
- _base0: Whether `x` is 0-based or not.
+ base0_: Whether `x` is 0-based or not.
if not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -210,7 +210,7 @@ def all_of(
in `_data` columns
"""
all_columns = _data.columns
- x = all_columns[vars_select(all_columns, x, base0=_base0)]
+ x = all_columns[vars_select(all_columns, x, base0=base0_)]
# where do errors raise?
# nonexists = setdiff(x, all_columns)
@@ -228,7 +228,7 @@ def any_of(
x: Iterable[Union[int, str]],
# pylint: disable=redefined-builtin
vars: Optional[Iterable[str]] = None,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> List[str]:
"""Select but doesn't check for missing variables.
@@ -238,14 +238,14 @@ def any_of(
Args:
_data: The data piped in
x: A set of variables to match the columns
- _base0: Whether `x` is 0-based or not.
+ base0_: Whether `x` is 0-based or not.
if not provided, will use `datar.base.get_option('index.base.0')`
Returns:
The matched column names
"""
vars = vars or _data.columns
- x = vars_select(vars, x, raise_nonexists=False, base0=_base0)
+ x = vars_select(vars, x, raise_nonexists=False, base0=base0_)
# exists = []
# for idx in x:
# try:
@@ -260,7 +260,7 @@ def num_range(
prefix: str,
range: Iterable[int], # pylint: disable=redefined-builtin
width: Optional[int] = None,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> List[str]:
"""Matches a numerical range like x01, x02, x03.
@@ -270,16 +270,16 @@ def num_range(
range_: A sequence of integers, like `range(3)` (produces `0,1,2`).
width: Optionally, the "width" of the numeric range.
For example, a range of 2 gives "01", a range of three "001", etc.
- _base0: Whether it is 0-based
+ base0_: Whether it is 0-based
Returns:
A list of ranges with prefix.
"""
- _base0 = get_option('index.base.0', _base0)
+ base0_ = get_option('index.base.0', base0_)
zfill = lambda elem: (
- elem + int(not _base0)
+ elem + int(not base0_)
if not width
- else str(elem + int(not _base0)).zfill(width)
+ else str(elem + int(not base0_)).zfill(width)
)
return Array([
f"{prefix}{zfill(elem)}"
diff --git a/datar/tibble/tibble.py b/datar/tibble/tibble.py
index e15cdce5..32512ff4 100644
--- a/datar/tibble/tibble.py
+++ b/datar/tibble/tibble.py
@@ -25,7 +25,7 @@ def tibble(
*args: Any,
_name_repair: Union[str, Callable] = 'check_unique',
_rows: Optional[int] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
_dtypes: Optional[Union[Dtype, Mapping[str, Dtype]]] = None,
**kwargs: Any
) -> DataFrame:
@@ -43,7 +43,7 @@ def tibble(
- a function: apply custom name repair
_rows: Number of rows of a 0-col dataframe when args and kwargs are
not provided. When args or kwargs are provided, this is ignored.
- _base0: Whether the suffixes of repaired names should be 0-based.
+ base0_: Whether the suffixes of repaired names should be 0-based.
If not provided, will use `datar.base.get_option('index.base.0')`.
Returns:
@@ -84,7 +84,7 @@ def tibble(
names,
values,
_name_repair=_name_repair,
- _base0=_base0,
+ base0_=base0_,
_dtypes=_dtypes
)
@@ -101,7 +101,7 @@ def tibble(
def tibble_row(
*args: Any,
_name_repair: Union[str, Callable] = 'check_unique',
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
_dtypes: Optional[Union[Dtype, Mapping[str, Dtype]]] = None,
**kwargs: Any
) -> DataFrame:
@@ -119,7 +119,7 @@ def tibble_row(
but check they are unique,
- "universal": Make the names unique and syntactic
- a function: apply custom name repair
- _base0: Whether the suffixes of repaired names should be 0-based.
+ base0_: Whether the suffixes of repaired names should be 0-based.
If not provided, will use `datar.base.get_option('index.base.0')`.
Returns:
@@ -128,7 +128,7 @@ def tibble_row(
if not args and not kwargs:
df = DataFrame(index=[0]) # still one row
else:
- df = tibble(*args, **kwargs, _name_repair=_name_repair, _base0=_base0)
+ df = tibble(*args, **kwargs, _name_repair=_name_repair, base0_=base0_)
if df.shape[0] > 1:
raise ValueError("All arguments must be size one, use `[]` to wrap.")
@@ -144,7 +144,7 @@ def tibble_row(
def fibble(
*args: Any,
_name_repair: Union[str, Callable] = 'check_unique',
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
_rows: Optional[int] = None,
_dtypes: Optional[Union[Dtype, Mapping[str, Dtype]]] = None,
**kwargs: Any
@@ -170,14 +170,14 @@ def fibble(
*args, **kwargs,
_name_repair=_name_repair,
_rows=_rows,
- _base0=_base0,
+ base0_=base0_,
_dtypes=_dtypes
)
def tribble(
*dummies: Any,
_name_repair: Union[str, Callable] = 'minimal',
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
_dtypes: Optional[Union[Dtype, Mapping[str, Dtype]]] = None
) -> DataFrame:
"""Create dataframe using an easier to read row-by-row layout
@@ -226,7 +226,7 @@ def tribble(
columns,
[[]]*len(columns),
_name_repair=_name_repair,
- _base0=_base0,
+ base0_=base0_,
_dtypes=_dtypes
)
@@ -241,7 +241,7 @@ def tribble(
columns,
list(zip(*data)),
_name_repair=_name_repair,
- _base0=_base0,
+ base0_=base0_,
_dtypes=_dtypes
)
@@ -249,7 +249,7 @@ def zibble(
names: Iterable[Optional[str]],
values: Iterable,
_name_repair: Union[str, Callable] = 'minimal',
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
_dtypes: Optional[Union[Dtype, Mapping[str, Dtype]]] = None
) -> DataFrame:
"""Zip version of tibble, where names specify together and so do values.
@@ -275,7 +275,7 @@ def zibble(
but check they are unique,
- "universal": Make the names unique and syntactic
- a function: apply custom name repair
- _base0: Whether the suffixes of repaired names should be 0-based.
+ base0_: Whether the suffixes of repaired names should be 0-based.
If not provided, will use `datar.base.get_option('index.base.0')`.
Returns:
@@ -321,7 +321,7 @@ def zibble(
if out is None:
out = DataFrame()
- names = repair_names(out.columns.tolist(), _name_repair, _base0)
+ names = repair_names(out.columns.tolist(), _name_repair, base0_)
out.columns = names
apply_dtypes(out, _dtypes)
diff --git a/datar/tibble/verbs.py b/datar/tibble/verbs.py
index b3f9755c..698ddb7b 100644
--- a/datar/tibble/verbs.py
+++ b/datar/tibble/verbs.py
@@ -19,7 +19,7 @@ def enframe(
x: Optional[Union[Iterable, Mapping]],
name: Optional[str] = "name",
value: str = "value",
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Converts mappings or lists to one- or two-column data frames.
@@ -29,7 +29,7 @@ def enframe(
value: value Names of the columns that store the names and values.
If `None`, a one-column dataframe is returned.
`value` cannot be `None`
- _base0: Whether the indexes for lists converted to name are 0-based
+ base0_: Whether the indexes for lists converted to name are 0-based
or not.
Returns:
@@ -54,8 +54,8 @@ def enframe(
elif name:
if not isinstance(x, dict):
- _base0 = get_option('index.base.0', _base0)
- names = (i + int(not _base0) for i in range(len(x)))
+ base0_ = get_option('index.base.0', base0_)
+ names = (i + int(not base0_) for i in range(len(x)))
values = x
else:
names = x.keys()
@@ -95,7 +95,7 @@ def add_row(
*args: Any,
_before: Optional[int] = None,
_after: Optional[int] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> DataFrame:
"""Add one or more rows of data to an existing data frame.
@@ -109,7 +109,7 @@ def add_row(
_before: and
_after: row index where to add the new rows.
(default to add after the last row)
- _base0: Whether `_before` and `_after` are 0-based or not.
+ base0_: Whether `_before` and `_after` are 0-based or not.
Returns:
The dataframe with the added rows
@@ -133,7 +133,7 @@ def add_row(
if extra_vars:
raise ValueError(f"New rows can't add columns: {extra_vars}")
- pos = _pos_from_before_after(_before, _after, _data.shape[0], _base0)
+ pos = _pos_from_before_after(_before, _after, _data.shape[0], base0_)
out = _rbind_at(_data, df, pos)
if isinstance(_data, DataFrameRowwise):
@@ -155,7 +155,7 @@ def add_column(
_before: Optional[Union[str, int]] = None,
_after: Optional[Union[str, int]] = None,
_name_repair: Union[str, Callable] = 'check_unique',
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
_dtypes: Optional[Union[Dtype, Mapping[str, Dtype]]] = None,
**kwargs: Any
) -> DataFrame:
@@ -168,7 +168,7 @@ def add_column(
_before: and
_after: Column index or name where to add the new columns
(default to add after the last column)
- _base0: Whether `_before` and `_after` are 0-based if they are index.
+ base0_: Whether `_before` and `_after` are 0-based if they are index.
if not given, will be determined by `get_option('index_base_0')`,
which is `False` by default.
_dtypes: The dtypes for the new columns, either a uniform dtype or a
@@ -187,7 +187,7 @@ def add_column(
_before,
_after,
_data.columns.tolist(),
- _base0
+ base0_
)
out = _cbind_at(_data, df, pos, _name_repair)
@@ -255,7 +255,7 @@ def rownames_to_column(_data: DataFrame, var="rowname") -> DataFrame:
def rowid_to_column(
_data: DataFrame,
var="rowid",
- _base0: bool = False
+ base0_: bool = False
) -> DataFrame:
"""Add rownames as a column
@@ -271,7 +271,7 @@ def rowid_to_column(
raise ValueError(f"Column name `{var}` must not be duplicated.")
from ..dplyr.mutate import mutate
- base = int(not _base0)
+ base = int(not base0_)
return remove_rownames(mutate(
_data,
**{var: range(base, _data.shape[0] + base)},
@@ -348,7 +348,7 @@ def _cbind_at(
from ..dplyr import bind_cols
part1 = data.iloc[:, :pos]
part2 = data.iloc[:, pos:]
- return bind_cols(part1, df, part2, _name_repair=_name_repair)
+ return part1 >> bind_cols(df, part2, _name_repair=_name_repair)
def _pos_from_before_after(
before: Optional[int],
diff --git a/datar/tidyr/chop.py b/datar/tidyr/chop.py
index 91906057..efdee1e5 100644
--- a/datar/tidyr/chop.py
+++ b/datar/tidyr/chop.py
@@ -29,7 +29,7 @@
def chop(
data: DataFrame,
cols: Optional[Union[IntOrIter, StringOrIter]] = None,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Makes data frame shorter by converting rows within each group
into list-columns.
@@ -37,7 +37,7 @@ def chop(
Args:
data: A data frame
cols: Columns to chop
- _base0: Whether `cols` are 0-based
+ base0_: Whether `cols` are 0-based
if not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -47,7 +47,7 @@ def chop(
return data.copy()
all_columns = data.columns
- cols = vars_select(all_columns, cols, base0=_base0)
+ cols = vars_select(all_columns, cols, base0=base0_)
cols = all_columns[cols]
# when cols is empty
# order may change for all_columns.difference([])
@@ -75,7 +75,7 @@ def chop(
else:
vals = pandas.concat(compacted, ignore_index=True)
- out = bind_cols(split_key, vals)
+ out = split_key >> bind_cols(vals)
return reconstruct_tibble(data, out, keep_rowwise=True)
@register_verb(DataFrame, context=Context.SELECT)
@@ -83,8 +83,8 @@ def unchop(
data: DataFrame,
cols: Optional[Union[IntOrIter, StringOrIter]] = None,
keep_empty: bool = False,
- dtypes: Optional[Union[Dtype, Mapping[str, Dtype]]] = None,
- _base0: Optional[bool] = None
+ ptype: Optional[Union[Dtype, Mapping[str, Dtype]]] = None,
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Makes df longer by expanding list-columns so that each element
of the list-column gets its own row in the output.
@@ -108,21 +108,21 @@ def unchop(
dropped from the output.
If you want to preserve all rows, use `keep_empty` = `True` to
replace size-0 elements with a single row of missing values.
- dtypes: NOT `ptype`. Providing the dtypes for the output columns.
+ ptype: Providing the dtypes for the output columns.
Could be a single dtype, which will be applied to all columns, or
a dictionary of dtypes with keys for the columns and values the
dtypes.
For nested data frames, we need to specify `col$a` as key. If `col`
is used as key, all columns of the nested data frames will be casted
into that dtype.
- _base0: Whether `cols` are 0-based
+ base0_: Whether `cols` are 0-based
if not provided, will use `datar.base.get_option('index.base.0')`
Returns:
A data frame with selected columns unchopped.
"""
all_columns = data.columns
- cols = vars_select(all_columns, cols, base0=_base0)
+ cols = vars_select(all_columns, cols, base0=base0_)
if len(cols) == 0 or data.shape[0] == 0:
return data.copy()
@@ -131,7 +131,7 @@ def unchop(
key_cols = all_columns.difference(cols).tolist()
out = _unchopping(data, cols, key_cols, keep_empty)
- apply_dtypes(out, dtypes)
+ apply_dtypes(out, ptype)
return reconstruct_tibble(data, out, keep_rowwise=True)
def _vec_split(
@@ -148,7 +148,7 @@ def _vec_split(
if isinstance(by, Series): # pragma: no cover, always a data frame?
by = by.to_frame()
- df = bind_cols(x, by)
+ df = x >> bind_cols(by)
if df.shape[0] == 0:
return DataFrame(columns=['key', 'val'])
df = df >> group_by(*by.columns)
@@ -213,7 +213,7 @@ def _unchopping(
# say y$a, then ['y'] will not select it
out = keep_column_order(DataFrame(key_data), data.columns)
if not keep_empty:
- out = drop_na(out, *val_data, how='all')
+ out = drop_na(out, *val_data, how_='all')
apply_dtypes(out, dtypes)
copy_attrs(out, data)
return out
diff --git a/datar/tidyr/drop_na.py b/datar/tidyr/drop_na.py
index 61af591d..108e856d 100644
--- a/datar/tidyr/drop_na.py
+++ b/datar/tidyr/drop_na.py
@@ -14,8 +14,8 @@
def drop_na(
_data: DataFrame,
*columns: str,
- how: str = 'any',
- _base0: Optional[bool] = None
+ how_: str = 'any',
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Drop rows containing missing values
@@ -24,23 +24,23 @@ def drop_na(
Args:
data: A data frame.
*columns: Columns to inspect for missing values.
- how: How to select the rows to drop
+ how_: How to select the rows to drop
- all: All columns of `columns` to be `NA`s
- any: Any columns of `columns` to be `NA`s
(tidyr doesn't support this argument)
- _base0: Whether `*columns` are 0-based if given by indexes
+ base0_: Whether `*columns` are 0-based if given by indexes
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
Dataframe with rows with NAs dropped and indexes dropped
"""
- arg_match(how, 'how', ['any', 'all'])
+ arg_match(how_, 'how_', ['any', 'all'])
all_columns = _data.columns
if columns:
- columns = vars_select(all_columns, *columns, base0=_base0)
+ columns = vars_select(all_columns, *columns, base0=base0_)
columns = all_columns[columns]
- out = _data.dropna(subset=columns, how=how).reset_index(drop=True)
+ out = _data.dropna(subset=columns, how=how_).reset_index(drop=True)
else:
- out = _data.dropna(how=how).reset_index(drop=True)
+ out = _data.dropna(how=how_).reset_index(drop=True)
return reconstruct_tibble(_data, out, keep_rowwise=True)
diff --git a/datar/tidyr/expand.py b/datar/tidyr/expand.py
index 202c6f31..97f96014 100644
--- a/datar/tidyr/expand.py
+++ b/datar/tidyr/expand.py
@@ -27,7 +27,7 @@
def expand_grid(
*args: Iterable[Any],
_name_repair: Union[str, Callable] = 'check_unique',
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Iterable[Any]
) -> DataFrame:
"""Create a tibble from all combinations of inputs
@@ -44,7 +44,7 @@ def expand_grid(
but check they are unique,
- "universal": Make the names unique and syntactic
- a function: apply custom name repair
- _base0: Whether the suffixes of repaired names should be 0-based.
+ base0_: Whether the suffixes of repaired names should be 0-based.
If not provided, will use `datar.base.get_option('index.base.0')`.
Returns:
@@ -84,15 +84,15 @@ def expand_grid(
## tibble will somehow flatten the nested dataframes into fake nested df.
## do it inside _flatten_nested
- # out = tibble(out, _name_repair=_name_repair, _base0=_base0)
- return _flatten_nested(out, named, _name_repair, _base0)
+ # out = tibble(out, _name_repair=_name_repair, base0_=base0_)
+ return _flatten_nested(out, named, _name_repair, base0_)
@register_verb(DataFrame, context=Context.EVAL)
def expand(
data: DataFrame,
*args: Union[Series, DataFrame],
_name_repair: Union[str, Callable] = "check_unique",
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Union[Series, DataFrame]
) -> DataFrame:
"""Generates all combination of variables found in a dataset.
@@ -117,7 +117,7 @@ def expand(
but check they are unique,
- "universal": Make the names unique and syntactic
- a function: apply custom name repair
- _base0: Whether the suffixes of repaired names should be 0-based.
+ base0_: Whether the suffixes of repaired names should be 0-based.
If not provided, will use `datar.base.get_option('index.base.0')`.
Returns:
@@ -129,8 +129,8 @@ def expand(
key: _sorted_unique(val) for key, val in cols.items()
}
- out = expand_grid(**cols, _name_repair=_name_repair, _base0=_base0)
- out = _flatten_nested(out, named, _name_repair, _base0)
+ out = expand_grid(**cols, _name_repair=_name_repair, base0_=base0_)
+ out = _flatten_nested(out, named, _name_repair, base0_)
copy_attrs(out, data)
return out
@@ -140,7 +140,7 @@ def _(
data: DataFrameGroupBy,
*args: Union[Series, DataFrame],
_name_repair: Union[str, Callable] = "check_unique",
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Union[Series, DataFrame]
) -> DataFrameGroupBy:
"""Expand on grouped data frame"""
@@ -149,7 +149,7 @@ def apply_func(df):
df,
*args,
_name_repair=_name_repair,
- _base0=_base0,
+ base0_=base0_,
**kwargs
)
@@ -161,7 +161,7 @@ def _(
data: DataFrameRowwise,
*args: Union[Series, DataFrame],
_name_repair: Union[str, Callable] = "check_unique",
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Union[Series, DataFrame]
) -> DataFrame:
"""Expand on rowwise dataframe"""
@@ -169,7 +169,7 @@ def _(
data,
*args,
_name_repair=_name_repair,
- _base0=_base0,
+ base0_=base0_,
**kwargs
)
@@ -177,7 +177,7 @@ def _(
def nesting(
*args: Any,
_name_repair: Union[str, Callable] = "check_unique",
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> DataFrame:
"""A helper that only finds combinations already present in the data.
@@ -201,7 +201,7 @@ def nesting(
but check they are unique,
- "universal": Make the names unique and syntactic
- a function: apply custom name repair
- _base0: Whether the suffixes of repaired names should be 0-based.
+ base0_: Whether the suffixes of repaired names should be 0-based.
If not provided, will use `datar.base.get_option('index.base.0')`.
Returns:
@@ -210,16 +210,16 @@ def nesting(
cols = _dots_cols(*args, **kwargs)
named = cols.pop('__named__')
out = _sorted_unique(
- tibble(**cols, _name_repair=_name_repair, _base0=_base0)
+ tibble(**cols, _name_repair=_name_repair, base0_=base0_)
)
- return _flatten_nested(out, named, _name_repair, _base0)
+ return _flatten_nested(out, named, _name_repair, base0_)
@register_func(None, context=Context.EVAL)
def crossing(
*args: Any,
_name_repair: Union[str, Callable] = "check_unique",
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**kwargs: Any
) -> DataFrame:
"""A wrapper around `expand_grid()` that de-duplicates and sorts its inputs
@@ -245,7 +245,7 @@ def crossing(
but check they are unique,
- "universal": Make the names unique and syntactic
- a function: apply custom name repair
- _base0: Whether the suffixes of repaired names should be 0-based.
+ base0_: Whether the suffixes of repaired names should be 0-based.
If not provided, will use `datar.base.get_option('index.base.0')`.
Returns:
@@ -258,8 +258,8 @@ def crossing(
for key, val in cols.items()
}
- out = expand_grid(**out, _name_repair=_name_repair, _base0=_base0)
- return _flatten_nested(out, named, _name_repair, _base0)
+ out = expand_grid(**out, _name_repair=_name_repair, base0_=base0_)
+ return _flatten_nested(out, named, _name_repair, base0_)
@@ -332,7 +332,7 @@ def _flatten_nested(
for key, val in x.items()
}
out = _flatten_at(x, to_flatten)
- return tibble(**out, _name_repair=name_repair, _base0=base0)
+ return tibble(**out, _name_repair=name_repair, base0_=base0)
def _flatten_at(
x: Mapping[str, Iterable[Any]],
diff --git a/datar/tidyr/extract.py b/datar/tidyr/extract.py
index 0d3494ae..863db859 100644
--- a/datar/tidyr/extract.py
+++ b/datar/tidyr/extract.py
@@ -23,7 +23,7 @@ def extract(
regex: str = r'(\w+)',
remove: bool = True,
convert: Union[bool, Dtype, Mapping[str, Dtype]] = False,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Given a regular expression with capturing groups, extract() turns each
group into a new column. If the groups don't match, or the input is NA,
@@ -41,7 +41,7 @@ def extract(
remove: If TRUE, remove input column from output data frame.
convert: The universal type for the extracted columns or a dict for
individual ones
- _base0: Whether `col` is 0-based when given by index
+ base0_: Whether `col` is 0-based when given by index
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -51,7 +51,7 @@ def extract(
into = [into]
all_columns = data.columns
- col = vars_select(all_columns, col, base0=_base0)
+ col = vars_select(all_columns, col, base0=base0_)
col = all_columns[col[0]]
outcols = {}
diff --git a/datar/tidyr/fill.py b/datar/tidyr/fill.py
index 3b1e126d..eabb68f3 100644
--- a/datar/tidyr/fill.py
+++ b/datar/tidyr/fill.py
@@ -21,7 +21,7 @@ def fill(
_data: DataFrame,
*columns: Union[str, int],
_direction: str = "down",
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Fills missing values in selected columns using the next or
previous entry.
@@ -35,7 +35,7 @@ def fill(
Currently either "down" (the default), "up",
"downup" (i.e. first down and then up) or
"updown" (first up and then down).
- _base0: Whether `*columns` are 0-based if given by indexes
+ base0_: Whether `*columns` are 0-based if given by indexes
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -51,7 +51,7 @@ def fill(
method='ffill' if _direction.endswith('down') else 'bfill',
)
else:
- colidx = vars_select(data.columns, *columns, base0=_base0)
+ colidx = vars_select(data.columns, *columns, base0=base0_)
data.iloc[:, colidx] = fill(data.iloc[:, colidx], _direction=_direction)
return data
diff --git a/datar/tidyr/nest.py b/datar/tidyr/nest.py
index aaed353c..78c36689 100644
--- a/datar/tidyr/nest.py
+++ b/datar/tidyr/nest.py
@@ -24,7 +24,7 @@
def nest(
_data: DataFrame,
_names_sep: Optional[str] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**cols: Union[str, int]
) -> DataFrame:
"""Nesting creates a list-column of data frames
@@ -38,7 +38,7 @@ def nest(
The names of the new outer columns will be formed by pasting
together the outer and the inner column names, separated by
`_names_sep`.
- _base0: Whether `**cols` are 0-based
+ base0_: Whether `**cols` are 0-based
if not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -51,7 +51,7 @@ def nest(
colgroups = {}
usedcols = set()
for group, columns in cols.items():
- oldcols = all_columns[vars_select(all_columns, columns, base0=_base0)]
+ oldcols = all_columns[vars_select(all_columns, columns, base0=base0_)]
usedcols = usedcols.union(oldcols)
newcols = (
oldcols if _names_sep is None else
@@ -83,20 +83,20 @@ def nest(
out.columns = list(colgroups)
if u_keys.shape[1] == 0:
return out if isinstance(out, DataFrame) else out.to_frame()
- return bind_cols(u_keys, recycle_value(out, u_keys.shape[0]))
+ return u_keys >> bind_cols(recycle_value(out, u_keys.shape[0]))
@nest.register(DataFrameGroupBy, context=Context.SELECT)
def _(
_data: DataFrameGroupBy,
_names_sep: Optional[str] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**cols: Mapping[str, Union[str, int]]
) -> DataFrameGroupBy:
"""Nesting grouped dataframe"""
if not cols:
cols = {'data': setdiff(_data.columns, group_vars(_data))}
out = nest.dispatch(DataFrame)(
- _data, **cols, _names_sep=_names_sep, _base0=_base0
+ _data, **cols, _names_sep=_names_sep, base0_=base0_
)
return reconstruct_tibble(_data, out, keep_rowwise=True)
@@ -105,10 +105,10 @@ def unnest(
data: DataFrame,
*cols: Union[str, int],
keep_empty: bool = False,
- dtypes: Optional[Union[Dtype, Mapping[str, Dtype]]] = None,
+ ptype: Optional[Union[Dtype, Mapping[str, Dtype]]] = None,
names_sep: Optional[str] = None,
names_repair: Union[str, Callable] = 'check_unique',
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Flattens list-column of data frames back out into regular columns.
@@ -122,7 +122,7 @@ def unnest(
dropped from the output.
If you want to preserve all rows, use `keep_empty` = `True` to
replace size-0 elements with a single row of missing values.
- dtypes: NOT `ptype`. Providing the dtypes for the output columns.
+ ptype: Providing the dtypes for the output columns.
Could be a single dtype, which will be applied to all columns, or
a dictionary of dtypes with keys for the columns and values the
dtypes.
@@ -139,7 +139,7 @@ def unnest(
but check they are unique,
- "universal": Make the names unique and syntactic
- a function: apply custom name repair
- _base0: Whether `cols` are 0-based
+ base0_: Whether `cols` are 0-based
if not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -149,7 +149,7 @@ def unnest(
raise ValueError("`*cols` is required when using unnest().")
all_columns = data.columns
- cols = vars_select(all_columns, cols, base0=_base0)
+ cols = vars_select(all_columns, cols, base0=base0_)
cols = all_columns[cols]
out = data.copy()
@@ -158,7 +158,7 @@ def unnest(
out = unchop(
out, cols,
- keep_empty=keep_empty, dtypes=dtypes, _base0=_base0
+ keep_empty=keep_empty, ptype=ptype, base0_=base0_
)
return unpack(
out, cols,
@@ -170,19 +170,19 @@ def _(
data: DataFrameRowwise,
*cols: Union[str, int],
keep_empty: bool = False,
- dtypes: Optional[Union[Dtype, Mapping[str, Dtype]]] = None,
+ ptype: Optional[Union[Dtype, Mapping[str, Dtype]]] = None,
names_sep: Optional[str] = None,
names_repair: Union[str, Callable] = 'check_unique',
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Unnest rowwise dataframe"""
out = unnest.dispatch(DataFrame)(
data, *cols,
keep_empty=keep_empty,
- dtypes=dtypes,
+ ptype=ptype,
names_sep=names_sep,
names_repair=names_repair,
- _base0=_base0
+ base0_=base0_
)
return DataFrameGroupBy(
out,
diff --git a/datar/tidyr/pack.py b/datar/tidyr/pack.py
index dd3341f1..477f8850 100644
--- a/datar/tidyr/pack.py
+++ b/datar/tidyr/pack.py
@@ -19,7 +19,7 @@
def pack(
_data: DataFrame,
_names_sep: Optional[str] = None,
- _base0: Optional[bool] = None,
+ base0_: Optional[bool] = None,
**cols: Union[str, int]
) -> DataFrame:
"""Makes df narrow by collapsing a set of columns into a single df-column.
@@ -33,7 +33,7 @@ def pack(
The names of the new outer columns will be formed by pasting
together the outer and the inner column names, separated by
`_names_sep`.
- _base0: Whether `**cols` are 0-based
+ base0_: Whether `**cols` are 0-based
if not provided, will use `datar.base.get_option('index.base.0')`
"""
if not cols:
@@ -44,7 +44,7 @@ def pack(
colgroups = {}
usedcols = set()
for group, columns in cols.items():
- oldcols = all_columns[vars_select(all_columns, columns, base0=_base0)]
+ oldcols = all_columns[vars_select(all_columns, columns, base0=base0_)]
usedcols = usedcols.union(oldcols)
newcols = (
oldcols if _names_sep is None else
@@ -58,7 +58,7 @@ def pack(
cols[f'{group}${newcol}'] = _data[oldcol]
asis = setdiff(_data.columns, usedcols)
- out = bind_cols(_data[asis], DataFrame(cols))
+ out = _data[asis] >> bind_cols(DataFrame(cols))
return reconstruct_tibble(_data, out, keep_rowwise=True)
@register_verb(DataFrame, context=Context.SELECT)
@@ -67,7 +67,7 @@ def unpack(
cols: Union[StringOrIter, IntOrIter],
names_sep: Optional[str] = None,
names_repair: Union[str, Callable] = "check_unique",
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Makes df wider by expanding df-columns back out into individual columns.
@@ -89,7 +89,7 @@ def unpack(
but check they are unique,
- "universal": Make the names unique and syntactic
- a function: apply custom name repair
- _base0: Whether `cols` are 0-based
+ base0_: Whether `cols` are 0-based
if not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -101,7 +101,7 @@ def unpack(
all_columns = data.columns
cols = _check_present(
data, cols, all_columns,
- base0=_base0,
+ base0=base0_,
)
out = data.copy()
@@ -120,7 +120,7 @@ def unpack(
else:
new_cols.append(col)
- new_cols = repair_names(new_cols, names_repair, _base0)
+ new_cols = repair_names(new_cols, names_repair, base0_)
out.columns = new_cols
copy_attrs(out, data)
diff --git a/datar/tidyr/pivot_long.py b/datar/tidyr/pivot_long.py
index d07ed505..16aa55ca 100644
--- a/datar/tidyr/pivot_long.py
+++ b/datar/tidyr/pivot_long.py
@@ -48,7 +48,7 @@ def pivot_longer(
values_transform: Optional[
Union[Callable, Mapping[str, Callable]]
] = None,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
):
""""lengthens" data, increasing the number of rows and
decreasing the number of columns.
@@ -133,7 +133,7 @@ def pivot_longer(
but check they are unique,
- "universal": Make the names unique and syntactic
- a function: apply custom name repair
- _base0: Whether `cols` are 0-based if given by indexes
+ base0_: Whether `cols` are 0-based if given by indexes
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -142,7 +142,7 @@ def pivot_longer(
rowid_column = '_PIVOT_ROWID_'
ret = _data.assign(**{rowid_column: range(_data.shape[0])})
all_columns = ret.columns
- columns = _data.columns[vars_select(_data.columns, cols, base0=_base0)]
+ columns = _data.columns[vars_select(_data.columns, cols, base0=base0_)]
id_columns = all_columns.difference(columns)
if is_scalar(names_to):
@@ -203,7 +203,7 @@ def pivot_longer(
sep=names_sep
)
# extract/separate puts `into` last
- ret = relocate(ret, values_to, _after=-1, _base0=True)
+ ret = relocate(ret, values_to, _after=-1, base0_=True)
if '.value' in names_to:
@@ -258,7 +258,7 @@ def pivot_longer(
elif name in values_transform:
ret[name] = ret[name].apply(values_transform[name])
- names = repair_names(ret.columns.tolist(), names_repair, _base0=_base0)
+ names = repair_names(ret.columns.tolist(), names_repair, base0_=base0_)
ret.columns = names
return reconstruct_tibble(_data, ret)
diff --git a/datar/tidyr/pivot_wide.py b/datar/tidyr/pivot_wide.py
index f6bb9222..80fc3f79 100644
--- a/datar/tidyr/pivot_wide.py
+++ b/datar/tidyr/pivot_wide.py
@@ -31,7 +31,7 @@ def pivot_wider(
values_from: StringOrIter = "value",
values_fill: Any = None,
values_fn: Union[Callable, Mapping[str, Callable]] = identity,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
""""widens" data, increasing the number of columns and decreasing
the number of rows.
@@ -65,7 +65,7 @@ def pivot_wider(
This can be a dict you want to apply different aggregations to
different value columns.
If not specified, will be `numpy.mean`
- _base0: Whether `id_cols`, `names_from` and `values_from`
+ base0_: Whether `id_cols`, `names_from` and `values_from`
are 0-based if given by indexes.
If not provided, will use `datar.base.get_option('index.base.0')`
@@ -81,7 +81,7 @@ def pivot_wider(
if id_cols is None:
all_cols = _data.columns
- names_from = all_cols[vars_select(all_cols, names_from, base0=_base0)]
+ names_from = all_cols[vars_select(all_cols, names_from, base0=base0_)]
# values_from could be a df-column
new_values_from = []
for value_from in values_from:
@@ -95,7 +95,7 @@ def pivot_wider(
else:
new_values_from.append(value_from)
values_from = all_cols[
- vars_select(all_cols, *new_values_from, base0=_base0)
+ vars_select(all_cols, *new_values_from, base0=base0_)
]
id_cols = (
all_cols
diff --git a/datar/tidyr/separate.py b/datar/tidyr/separate.py
index b2570c45..10560ba2 100644
--- a/datar/tidyr/separate.py
+++ b/datar/tidyr/separate.py
@@ -31,7 +31,7 @@ def separate(
convert: Union[bool, Dtype, Mapping[str, Dtype]] = False,
extra: str = "warn",
fill: str = "warn",
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Given either a regular expression or a vector of character positions,
turns a single character column into multiple columns.
@@ -62,7 +62,7 @@ def separate(
- "warn" (the default): emit a warning and fill from the right
- "right": fill with missing values on the right
- "left": fill with missing values on the left
- _base0: Whether `col` is 0-based when given by index and Whether `sep`
+ base0_: Whether `col` is 0-based when given by index and Whether `sep`
is 0-based if given by position
If not provided, will use `datar.base.get_option('index.base.0')`
@@ -76,7 +76,7 @@ def separate(
raise ValueError("`into` must be a string or a list of strings.")
all_columns = data.columns
- col = vars_select(all_columns, col, base0=_base0)
+ col = vars_select(all_columns, col, base0=base0_)
col = all_columns[col[0]]
colindex = [
@@ -96,7 +96,7 @@ def separate(
sep=sep,
extra=extra,
fill=fill,
- base0=_base0,
+ base0=base0_,
extra_warns=extra_warns,
missing_warns=missing_warns
)
@@ -133,7 +133,7 @@ def separate_rows(
*columns: str,
sep: str = r'[^0-9A-Za-z]+',
convert: Union[bool, Dtype, Mapping[str, Dtype]] = False,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Separates the values and places each one in its own row.
@@ -143,14 +143,14 @@ def separate_rows(
sep: Separator between columns.
convert: The universal type for the extracted columns or a dict for
individual ones
- _base0: Whether `columns` is 0-based when given by index
+ base0_: Whether `columns` is 0-based when given by index
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
Dataframe with rows separated and repeated.
"""
all_columns = data.columns
- selected = all_columns[vars_select(all_columns, *columns, base0=_base0)]
+ selected = all_columns[vars_select(all_columns, *columns, base0=base0_)]
out = data.copy()
for sel in selected:
out[sel] = out[sel].apply(
@@ -159,12 +159,12 @@ def separate_rows(
sep=sep,
extra="merge",
fill="right",
- base0=_base0,
+ base0=base0_,
extra_warns=[],
missing_warns=[]
)
- out = unchop(out, selected, keep_empty=True, dtypes=convert, _base0=_base0)
+ out = unchop(out, selected, keep_empty=True, ptype=convert, base0_=base0_)
return reconstruct_tibble(out, ungroup(out), selected, keep_rowwise=True)
def _separate_col(
diff --git a/datar/tidyr/uncount.py b/datar/tidyr/uncount.py
index 5fb22be3..b03dfe7b 100644
--- a/datar/tidyr/uncount.py
+++ b/datar/tidyr/uncount.py
@@ -20,7 +20,7 @@ def uncount(
weights: IntOrIter,
_remove: bool = True,
_id: Optional[str] = None,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Duplicating rows according to a weighting variable
@@ -31,7 +31,7 @@ def uncount(
then this column is removed.
_id: Supply a string to create a new variable which gives a
unique identifier for each created row (0-based).
- _base0: Whether the generated `_id` columns are 0-based.
+ base0_: Whether the generated `_id` columns are 0-based.
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -60,7 +60,7 @@ def uncount(
out.reset_index(drop=True, inplace=True)
if _id:
- base = int(not get_option('index.base.0', _base0))
+ base = int(not get_option('index.base.0', base0_))
# pylint: disable=no-value-for-parameter
out = (
out >>
diff --git a/datar/tidyr/unite.py b/datar/tidyr/unite.py
index 781d143f..f36bcf2e 100644
--- a/datar/tidyr/unite.py
+++ b/datar/tidyr/unite.py
@@ -19,7 +19,7 @@ def unite(
sep: str = '_',
remove: bool = True,
na_rm: bool = False,
- _base0: Optional[bool] = None
+ base0_: Optional[bool] = None
) -> DataFrame:
"""Unite multiple columns into one by pasting strings together
@@ -31,7 +31,7 @@ def unite(
remove: If True, remove input columns from output data frame.
na_rm: If True, missing values will be remove prior to uniting
each value.
- _base0: Whether `columns` is 0-based when given by index
+ base0_: Whether `columns` is 0-based when given by index
If not provided, will use `datar.base.get_option('index.base.0')`
Returns:
@@ -41,7 +41,7 @@ def unite(
if not columns:
columns = all_columns
else:
- columns = all_columns[vars_select(all_columns, *columns, base0=_base0)]
+ columns = all_columns[vars_select(all_columns, *columns, base0=base0_)]
out = data.copy()
diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md
index a5df6d91..65b6ac35 100644
--- a/docs/CHANGELOG.md
+++ b/docs/CHANGELOG.md
@@ -1,3 +1,12 @@
+## 0.3.0
+- Adopt `pipda` v0.3.0
+
+Breaking changes:
+
+- Rename argument `dtypes` of `unchop` and `unnest` back to `ptype`
+- Change all `_base0` to `base0_`
+- Change argument `how` of `tidyr.drop_na` to `how_`
+
## 0.2.3
- Fix compatibility with `pandas` `v1.2.0~4` (#20, thanks to @antonio-yu)
- Fix base.table when inputs are factors and exclude is NA;
@@ -63,7 +72,7 @@ Changed:
## 0.0.6
- Add `options`, `get_option` and `options_context` to `datar.base` to allow set/get global options
- Add options: `dplyr.summarise.inform`
-- Add `_base0` argument to all related APIs
+- Add `base0_` argument to all related APIs
- Add `nycflights13` datasets
- Support slice_head/slice_tail for grouped data
diff --git a/docs/TODO.md b/docs/TODO.md
deleted file mode 100644
index 8c5afd0a..00000000
--- a/docs/TODO.md
+++ /dev/null
@@ -1,10 +0,0 @@
-
-- [x] Add tests for tidyr from original tidyverse/tidyr cases
-- [x] Add more tests for base/core
-- [ ] Port more functions from `r-base`, `r-stats`, etc
-- [ ] Port more datasets from `r-datasets` namespace
-- [x] Add more detailed documentations
-- [x] Add reference maps to compare to the references from the original packages.
-- [x] Add `_base0` argument to APIs with index involved
-- [x] Add `options` for `index_base`, `dplyr.summarise.inform`, etc
-- [x] Rename `base.context` to `base.data_context`
diff --git a/docs/advanced.md b/docs/advanced.md
new file mode 100644
index 00000000..091fd574
--- /dev/null
+++ b/docs/advanced.md
@@ -0,0 +1,68 @@
+## Register your own verb
+
+Verbs are registered by `register_verb()` from [`pipda`][1].
+
+The full signature of `register_verb()` is as follows:
+
+```python
+register_verb(
+ types: Union[function, Type, Iterable[Type]] = Try this notebook on binder.
"
+ "text/html": [
+ "Try this notebook on binder.
"
+ ],
+ "text/plain": [
+ "\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" name height mass hair_color skin_color eye_color \\\n",
"0 Luke Skywalker 172.0 77.0 blond fair blue \n",
@@ -100,11 +309,11 @@
"5 57.0 male masculine Stewjon Human \n",
"6 41.9 male masculine Tatooine Human \n",
"7 64.0 male masculine Eriadu Human "
- ],
- "text/html": "| \n", + " | name | \n", + "height | \n", + "mass | \n", + "hair_color | \n", + "skin_color | \n", + "eye_color | \n", + "birth_year | \n", + "sex | \n", + "gender | \n", + "homeworld | \n", + "species | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "Luke Skywalker | \n", + "172.0 | \n", + "77.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "19.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 1 | \n", + "C-3PO | \n", + "167.0 | \n", + "75.0 | \n", + "NaN | \n", + "gold | \n", + "yellow | \n", + "112.0 | \n", + "none | \n", + "masculine | \n", + "Tatooine | \n", + "Droid | \n", + "
| 2 | \n", + "R2-D2 | \n", + "96.0 | \n", + "32.0 | \n", + "NaN | \n", + "white, blue | \n", + "red | \n", + "33.0 | \n", + "none | \n", + "masculine | \n", + "Naboo | \n", + "Droid | \n", + "
| 3 | \n", + "Darth Vader | \n", + "202.0 | \n", + "136.0 | \n", + "none | \n", + "white | \n", + "yellow | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 4 | \n", + "Biggs Darklighter | \n", + "183.0 | \n", + "84.0 | \n", + "black | \n", + "light | \n", + "brown | \n", + "24.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 5 | \n", + "Obi-Wan Kenobi | \n", + "182.0 | \n", + "77.0 | \n", + "auburn, white | \n", + "fair | \n", + "blue-gray | \n", + "57.0 | \n", + "male | \n", + "masculine | \n", + "Stewjon | \n", + "Human | \n", + "
| 6 | \n", + "Anakin Skywalker | \n", + "188.0 | \n", + "84.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 7 | \n", + "Wilhuff Tarkin | \n", + "180.0 | \n", + "NaN | \n", + "auburn, grey | \n", + "fair | \n", + "blue | \n", + "64.0 | \n", + "male | \n", + "masculine | \n", + "Eriadu | \n", + "Human | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 2,
"metadata": {},
- "execution_count": 2
+ "output_type": "execute_result"
}
],
"source": [
@@ -116,12 +325,160 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | name | \nheight | \nmass | \nhair_color | \nskin_color | \neye_color | \nbirth_year | \nsex | \ngender | \nhomeworld | \nspecies | \n
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \nLuke Skywalker | \n172.0 | \n77.0 | \nblond | \nfair | \nblue | \n19.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 1 | \nC-3PO | \n167.0 | \n75.0 | \nNaN | \ngold | \nyellow | \n112.0 | \nnone | \nmasculine | \nTatooine | \nDroid | \n
| 2 | \nR2-D2 | \n96.0 | \n32.0 | \nNaN | \nwhite, blue | \nred | \n33.0 | \nnone | \nmasculine | \nNaboo | \nDroid | \n
| 3 | \nDarth Vader | \n202.0 | \n136.0 | \nnone | \nwhite | \nyellow | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 4 | \nBiggs Darklighter | \n183.0 | \n84.0 | \nblack | \nlight | \nbrown | \n24.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 5 | \nObi-Wan Kenobi | \n182.0 | \n77.0 | \nauburn, white | \nfair | \nblue-gray | \n57.0 | \nmale | \nmasculine | \nStewjon | \nHuman | \n
| 6 | \nAnakin Skywalker | \n188.0 | \n84.0 | \nblond | \nfair | \nblue | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 7 | \nWilhuff Tarkin | \n180.0 | \nNaN | \nauburn, grey | \nfair | \nblue | \n64.0 | \nmale | \nmasculine | \nEriadu | \nHuman | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" name height mass hair_color skin_color eye_color \\\n",
"0 Luke Skywalker 172.0 77.0 blond fair blue \n",
@@ -142,11 +499,11 @@
"5 57.0 male masculine Stewjon Human \n",
"6 41.9 male masculine Tatooine Human \n",
"7 64.0 male masculine Eriadu Human "
- ],
- "text/html": "| \n", + " | name | \n", + "height | \n", + "mass | \n", + "hair_color | \n", + "skin_color | \n", + "eye_color | \n", + "birth_year | \n", + "sex | \n", + "gender | \n", + "homeworld | \n", + "species | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "Luke Skywalker | \n", + "172.0 | \n", + "77.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "19.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 1 | \n", + "C-3PO | \n", + "167.0 | \n", + "75.0 | \n", + "NaN | \n", + "gold | \n", + "yellow | \n", + "112.0 | \n", + "none | \n", + "masculine | \n", + "Tatooine | \n", + "Droid | \n", + "
| 2 | \n", + "R2-D2 | \n", + "96.0 | \n", + "32.0 | \n", + "NaN | \n", + "white, blue | \n", + "red | \n", + "33.0 | \n", + "none | \n", + "masculine | \n", + "Naboo | \n", + "Droid | \n", + "
| 3 | \n", + "Darth Vader | \n", + "202.0 | \n", + "136.0 | \n", + "none | \n", + "white | \n", + "yellow | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 4 | \n", + "Biggs Darklighter | \n", + "183.0 | \n", + "84.0 | \n", + "black | \n", + "light | \n", + "brown | \n", + "24.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 5 | \n", + "Obi-Wan Kenobi | \n", + "182.0 | \n", + "77.0 | \n", + "auburn, white | \n", + "fair | \n", + "blue-gray | \n", + "57.0 | \n", + "male | \n", + "masculine | \n", + "Stewjon | \n", + "Human | \n", + "
| 6 | \n", + "Anakin Skywalker | \n", + "188.0 | \n", + "84.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 7 | \n", + "Wilhuff Tarkin | \n", + "180.0 | \n", + "NaN | \n", + "auburn, grey | \n", + "fair | \n", + "blue | \n", + "64.0 | \n", + "male | \n", + "masculine | \n", + "Eriadu | \n", + "Human | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 3,
"metadata": {},
- "execution_count": 3
+ "output_type": "execute_result"
}
],
"source": [
@@ -155,12 +512,272 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | name | \nheight | \nmass | \nhair_color | \nskin_color | \neye_color | \nbirth_year | \nsex | \ngender | \nhomeworld | \nspecies | \n
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \nLuke Skywalker | \n172.0 | \n77.0 | \nblond | \nfair | \nblue | \n19.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 1 | \nC-3PO | \n167.0 | \n75.0 | \nNaN | \ngold | \nyellow | \n112.0 | \nnone | \nmasculine | \nTatooine | \nDroid | \n
| 2 | \nR2-D2 | \n96.0 | \n32.0 | \nNaN | \nwhite, blue | \nred | \n33.0 | \nnone | \nmasculine | \nNaboo | \nDroid | \n
| 3 | \nDarth Vader | \n202.0 | \n136.0 | \nnone | \nwhite | \nyellow | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 4 | \nBiggs Darklighter | \n183.0 | \n84.0 | \nblack | \nlight | \nbrown | \n24.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 5 | \nObi-Wan Kenobi | \n182.0 | \n77.0 | \nauburn, white | \nfair | \nblue-gray | \n57.0 | \nmale | \nmasculine | \nStewjon | \nHuman | \n
| 6 | \nAnakin Skywalker | \n188.0 | \n84.0 | \nblond | \nfair | \nblue | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 7 | \nWilhuff Tarkin | \n180.0 | \nNaN | \nauburn, grey | \nfair | \nblue | \n64.0 | \nmale | \nmasculine | \nEriadu | \nHuman | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" name height mass hair_color skin_color eye_color \\\n",
"0 Luke Skywalker 172.0 77.0 blond fair blue \n",
@@ -197,11 +814,11 @@
"13 112.0 none masculine Tatooine Droid \n",
"14 33.0 none masculine Naboo Droid \n",
"15 41.9 male masculine Tatooine Human "
- ],
- "text/html": "| \n", + " | name | \n", + "height | \n", + "mass | \n", + "hair_color | \n", + "skin_color | \n", + "eye_color | \n", + "birth_year | \n", + "sex | \n", + "gender | \n", + "homeworld | \n", + "species | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "Luke Skywalker | \n", + "172.0 | \n", + "77.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "19.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 1 | \n", + "C-3PO | \n", + "167.0 | \n", + "75.0 | \n", + "NaN | \n", + "gold | \n", + "yellow | \n", + "112.0 | \n", + "none | \n", + "masculine | \n", + "Tatooine | \n", + "Droid | \n", + "
| 2 | \n", + "R2-D2 | \n", + "96.0 | \n", + "32.0 | \n", + "NaN | \n", + "white, blue | \n", + "red | \n", + "33.0 | \n", + "none | \n", + "masculine | \n", + "Naboo | \n", + "Droid | \n", + "
| 3 | \n", + "Darth Vader | \n", + "202.0 | \n", + "136.0 | \n", + "none | \n", + "white | \n", + "yellow | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 4 | \n", + "Biggs Darklighter | \n", + "183.0 | \n", + "84.0 | \n", + "black | \n", + "light | \n", + "brown | \n", + "24.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 5 | \n", + "Obi-Wan Kenobi | \n", + "182.0 | \n", + "77.0 | \n", + "auburn, white | \n", + "fair | \n", + "blue-gray | \n", + "57.0 | \n", + "male | \n", + "masculine | \n", + "Stewjon | \n", + "Human | \n", + "
| 6 | \n", + "Anakin Skywalker | \n", + "188.0 | \n", + "84.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 7 | \n", + "Wilhuff Tarkin | \n", + "180.0 | \n", + "NaN | \n", + "auburn, grey | \n", + "fair | \n", + "blue | \n", + "64.0 | \n", + "male | \n", + "masculine | \n", + "Eriadu | \n", + "Human | \n", + "
| 8 | \n", + "Biggs Darklighter | \n", + "183.0 | \n", + "84.0 | \n", + "black | \n", + "light | \n", + "brown | \n", + "24.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 9 | \n", + "Obi-Wan Kenobi | \n", + "182.0 | \n", + "77.0 | \n", + "auburn, white | \n", + "fair | \n", + "blue-gray | \n", + "57.0 | \n", + "male | \n", + "masculine | \n", + "Stewjon | \n", + "Human | \n", + "
| 10 | \n", + "Anakin Skywalker | \n", + "188.0 | \n", + "84.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 11 | \n", + "Wilhuff Tarkin | \n", + "180.0 | \n", + "NaN | \n", + "auburn, grey | \n", + "fair | \n", + "blue | \n", + "64.0 | \n", + "male | \n", + "masculine | \n", + "Eriadu | \n", + "Human | \n", + "
| 12 | \n", + "Luke Skywalker | \n", + "172.0 | \n", + "77.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "19.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 13 | \n", + "C-3PO | \n", + "167.0 | \n", + "75.0 | \n", + "NaN | \n", + "gold | \n", + "yellow | \n", + "112.0 | \n", + "none | \n", + "masculine | \n", + "Tatooine | \n", + "Droid | \n", + "
| 14 | \n", + "R2-D2 | \n", + "96.0 | \n", + "32.0 | \n", + "NaN | \n", + "white, blue | \n", + "red | \n", + "33.0 | \n", + "none | \n", + "masculine | \n", + "Naboo | \n", + "Droid | \n", + "
| 15 | \n", + "Darth Vader | \n", + "202.0 | \n", + "136.0 | \n", + "none | \n", + "white | \n", + "yellow | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 4,
"metadata": {},
- "execution_count": 4
+ "output_type": "execute_result"
}
],
"source": [
@@ -210,8 +827,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
- "id": "entire-overall",
+ "execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2021-04-17T00:51:37.403386Z",
@@ -222,17 +838,54 @@
},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | name | \nheight | \nmass | \nhair_color | \nskin_color | \neye_color | \nbirth_year | \nsex | \ngender | \nhomeworld | \nspecies | \n
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \nLuke Skywalker | \n172.0 | \n77.0 | \nblond | \nfair | \nblue | \n19.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 1 | \nC-3PO | \n167.0 | \n75.0 | \nNaN | \ngold | \nyellow | \n112.0 | \nnone | \nmasculine | \nTatooine | \nDroid | \n
| 2 | \nR2-D2 | \n96.0 | \n32.0 | \nNaN | \nwhite, blue | \nred | \n33.0 | \nnone | \nmasculine | \nNaboo | \nDroid | \n
| 3 | \nDarth Vader | \n202.0 | \n136.0 | \nnone | \nwhite | \nyellow | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 4 | \nBiggs Darklighter | \n183.0 | \n84.0 | \nblack | \nlight | \nbrown | \n24.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 5 | \nObi-Wan Kenobi | \n182.0 | \n77.0 | \nauburn, white | \nfair | \nblue-gray | \n57.0 | \nmale | \nmasculine | \nStewjon | \nHuman | \n
| 6 | \nAnakin Skywalker | \n188.0 | \n84.0 | \nblond | \nfair | \nblue | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 7 | \nWilhuff Tarkin | \n180.0 | \nNaN | \nauburn, grey | \nfair | \nblue | \n64.0 | \nmale | \nmasculine | \nEriadu | \nHuman | \n
| 8 | \nBiggs Darklighter | \n183.0 | \n84.0 | \nblack | \nlight | \nbrown | \n24.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 9 | \nObi-Wan Kenobi | \n182.0 | \n77.0 | \nauburn, white | \nfair | \nblue-gray | \n57.0 | \nmale | \nmasculine | \nStewjon | \nHuman | \n
| 10 | \nAnakin Skywalker | \n188.0 | \n84.0 | \nblond | \nfair | \nblue | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 11 | \nWilhuff Tarkin | \n180.0 | \nNaN | \nauburn, grey | \nfair | \nblue | \n64.0 | \nmale | \nmasculine | \nEriadu | \nHuman | \n
| 12 | \nLuke Skywalker | \n172.0 | \n77.0 | \nblond | \nfair | \nblue | \n19.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 13 | \nC-3PO | \n167.0 | \n75.0 | \nNaN | \ngold | \nyellow | \n112.0 | \nnone | \nmasculine | \nTatooine | \nDroid | \n
| 14 | \nR2-D2 | \n96.0 | \n32.0 | \nNaN | \nwhite, blue | \nred | \n33.0 | \nnone | \nmasculine | \nNaboo | \nDroid | \n
| 15 | \nDarth Vader | \n202.0 | \n136.0 | \nnone | \nwhite | \nyellow | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" a b\n",
"0 1 2\n",
"1 3 4"
- ],
- "text/html": "| \n", + " | a | \n", + "b | \n", + "
|---|---|---|
| 0 | \n", + "1 | \n", + "2 | \n", + "
| 1 | \n", + "3 | \n", + "4 | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 5,
"metadata": {},
- "execution_count": 5
+ "output_type": "execute_result"
}
],
"source": [
@@ -241,8 +894,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
- "id": "primary-convertible",
+ "execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2021-04-17T00:51:37.522360Z",
@@ -253,19 +905,66 @@
},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | a | \nb | \n
|---|---|---|
| 0 | \n1 | \n2 | \n
| 1 | \n3 | \n4 | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" a b\n",
"0 1 2\n",
"1 3 5\n",
"2 4 6\n",
"3 7 8"
- ],
- "text/html": "| \n", + " | a | \n", + "b | \n", + "
|---|---|---|
| 0 | \n", + "1 | \n", + "2 | \n", + "
| 1 | \n", + "3 | \n", + "5 | \n", + "
| 2 | \n", + "4 | \n", + "6 | \n", + "
| 3 | \n", + "7 | \n", + "8 | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 6,
"metadata": {},
- "execution_count": 6
+ "output_type": "execute_result"
}
],
"source": [
@@ -277,12 +976,169 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | a | \nb | \n
|---|---|---|
| 0 | \n1 | \n2 | \n
| 1 | \n3 | \n5 | \n
| 2 | \n4 | \n6 | \n
| 3 | \n7 | \n8 | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" id name height mass hair_color skin_color \\\n",
"0 1 Luke Skywalker 172.0 77.0 blond fair \n",
@@ -303,11 +1159,11 @@
"5 blue-gray 57.0 male masculine Stewjon Human \n",
"6 blue 41.9 male masculine Tatooine Human \n",
"7 blue 64.0 male masculine Eriadu Human "
- ],
- "text/html": "| \n", + " | id | \n", + "name | \n", + "height | \n", + "mass | \n", + "hair_color | \n", + "skin_color | \n", + "eye_color | \n", + "birth_year | \n", + "sex | \n", + "gender | \n", + "homeworld | \n", + "species | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "1 | \n", + "Luke Skywalker | \n", + "172.0 | \n", + "77.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "19.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 1 | \n", + "1 | \n", + "C-3PO | \n", + "167.0 | \n", + "75.0 | \n", + "NaN | \n", + "gold | \n", + "yellow | \n", + "112.0 | \n", + "none | \n", + "masculine | \n", + "Tatooine | \n", + "Droid | \n", + "
| 2 | \n", + "1 | \n", + "R2-D2 | \n", + "96.0 | \n", + "32.0 | \n", + "NaN | \n", + "white, blue | \n", + "red | \n", + "33.0 | \n", + "none | \n", + "masculine | \n", + "Naboo | \n", + "Droid | \n", + "
| 3 | \n", + "1 | \n", + "Darth Vader | \n", + "202.0 | \n", + "136.0 | \n", + "none | \n", + "white | \n", + "yellow | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 4 | \n", + "2 | \n", + "Biggs Darklighter | \n", + "183.0 | \n", + "84.0 | \n", + "black | \n", + "light | \n", + "brown | \n", + "24.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 5 | \n", + "2 | \n", + "Obi-Wan Kenobi | \n", + "182.0 | \n", + "77.0 | \n", + "auburn, white | \n", + "fair | \n", + "blue-gray | \n", + "57.0 | \n", + "male | \n", + "masculine | \n", + "Stewjon | \n", + "Human | \n", + "
| 6 | \n", + "2 | \n", + "Anakin Skywalker | \n", + "188.0 | \n", + "84.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 7 | \n", + "2 | \n", + "Wilhuff Tarkin | \n", + "180.0 | \n", + "NaN | \n", + "auburn, grey | \n", + "fair | \n", + "blue | \n", + "64.0 | \n", + "male | \n", + "masculine | \n", + "Eriadu | \n", + "Human | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 7,
"metadata": {},
- "execution_count": 7
+ "output_type": "execute_result"
}
],
"source": [
@@ -316,12 +1172,169 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | id | \nname | \nheight | \nmass | \nhair_color | \nskin_color | \neye_color | \nbirth_year | \nsex | \ngender | \nhomeworld | \nspecies | \n
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n1 | \nLuke Skywalker | \n172.0 | \n77.0 | \nblond | \nfair | \nblue | \n19.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 1 | \n1 | \nC-3PO | \n167.0 | \n75.0 | \nNaN | \ngold | \nyellow | \n112.0 | \nnone | \nmasculine | \nTatooine | \nDroid | \n
| 2 | \n1 | \nR2-D2 | \n96.0 | \n32.0 | \nNaN | \nwhite, blue | \nred | \n33.0 | \nnone | \nmasculine | \nNaboo | \nDroid | \n
| 3 | \n1 | \nDarth Vader | \n202.0 | \n136.0 | \nnone | \nwhite | \nyellow | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 4 | \n2 | \nBiggs Darklighter | \n183.0 | \n84.0 | \nblack | \nlight | \nbrown | \n24.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 5 | \n2 | \nObi-Wan Kenobi | \n182.0 | \n77.0 | \nauburn, white | \nfair | \nblue-gray | \n57.0 | \nmale | \nmasculine | \nStewjon | \nHuman | \n
| 6 | \n2 | \nAnakin Skywalker | \n188.0 | \n84.0 | \nblond | \nfair | \nblue | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 7 | \n2 | \nWilhuff Tarkin | \n180.0 | \nNaN | \nauburn, grey | \nfair | \nblue | \n64.0 | \nmale | \nmasculine | \nEriadu | \nHuman | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" id name height mass hair_color skin_color \\\n",
"0 0 Luke Skywalker 172.0 77.0 blond fair \n",
@@ -342,25 +1355,182 @@
"5 blue-gray 57.0 male masculine Stewjon Human \n",
"6 blue 41.9 male masculine Tatooine Human \n",
"7 blue 64.0 male masculine Eriadu Human "
- ],
- "text/html": "| \n", + " | id | \n", + "name | \n", + "height | \n", + "mass | \n", + "hair_color | \n", + "skin_color | \n", + "eye_color | \n", + "birth_year | \n", + "sex | \n", + "gender | \n", + "homeworld | \n", + "species | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "0 | \n", + "Luke Skywalker | \n", + "172.0 | \n", + "77.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "19.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 1 | \n", + "0 | \n", + "C-3PO | \n", + "167.0 | \n", + "75.0 | \n", + "NaN | \n", + "gold | \n", + "yellow | \n", + "112.0 | \n", + "none | \n", + "masculine | \n", + "Tatooine | \n", + "Droid | \n", + "
| 2 | \n", + "0 | \n", + "R2-D2 | \n", + "96.0 | \n", + "32.0 | \n", + "NaN | \n", + "white, blue | \n", + "red | \n", + "33.0 | \n", + "none | \n", + "masculine | \n", + "Naboo | \n", + "Droid | \n", + "
| 3 | \n", + "0 | \n", + "Darth Vader | \n", + "202.0 | \n", + "136.0 | \n", + "none | \n", + "white | \n", + "yellow | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 4 | \n", + "1 | \n", + "Biggs Darklighter | \n", + "183.0 | \n", + "84.0 | \n", + "black | \n", + "light | \n", + "brown | \n", + "24.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 5 | \n", + "1 | \n", + "Obi-Wan Kenobi | \n", + "182.0 | \n", + "77.0 | \n", + "auburn, white | \n", + "fair | \n", + "blue-gray | \n", + "57.0 | \n", + "male | \n", + "masculine | \n", + "Stewjon | \n", + "Human | \n", + "
| 6 | \n", + "1 | \n", + "Anakin Skywalker | \n", + "188.0 | \n", + "84.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 7 | \n", + "1 | \n", + "Wilhuff Tarkin | \n", + "180.0 | \n", + "NaN | \n", + "auburn, grey | \n", + "fair | \n", + "blue | \n", + "64.0 | \n", + "male | \n", + "masculine | \n", + "Eriadu | \n", + "Human | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 8,
"metadata": {},
- "execution_count": 8
+ "output_type": "execute_result"
}
],
"source": [
- "bind_rows([one, two], _id = \"id\", _base0=True) # 0-based id"
+ "bind_rows([one, two], _id = \"id\", base0_=True) # 0-based id"
]
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | id | \nname | \nheight | \nmass | \nhair_color | \nskin_color | \neye_color | \nbirth_year | \nsex | \ngender | \nhomeworld | \nspecies | \n
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n0 | \nLuke Skywalker | \n172.0 | \n77.0 | \nblond | \nfair | \nblue | \n19.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 1 | \n0 | \nC-3PO | \n167.0 | \n75.0 | \nNaN | \ngold | \nyellow | \n112.0 | \nnone | \nmasculine | \nTatooine | \nDroid | \n
| 2 | \n0 | \nR2-D2 | \n96.0 | \n32.0 | \nNaN | \nwhite, blue | \nred | \n33.0 | \nnone | \nmasculine | \nNaboo | \nDroid | \n
| 3 | \n0 | \nDarth Vader | \n202.0 | \n136.0 | \nnone | \nwhite | \nyellow | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 4 | \n1 | \nBiggs Darklighter | \n183.0 | \n84.0 | \nblack | \nlight | \nbrown | \n24.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 5 | \n1 | \nObi-Wan Kenobi | \n182.0 | \n77.0 | \nauburn, white | \nfair | \nblue-gray | \n57.0 | \nmale | \nmasculine | \nStewjon | \nHuman | \n
| 6 | \n1 | \nAnakin Skywalker | \n188.0 | \n84.0 | \nblond | \nfair | \nblue | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 7 | \n1 | \nWilhuff Tarkin | \n180.0 | \nNaN | \nauburn, grey | \nfair | \nblue | \n64.0 | \nmale | \nmasculine | \nEriadu | \nHuman | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" id name height mass hair_color skin_color eye_color \\\n",
"0 a Luke Skywalker 172.0 77.0 blond fair blue \n",
@@ -381,11 +1551,11 @@
"5 57.0 male masculine Stewjon Human \n",
"6 41.9 male masculine Tatooine Human \n",
"7 64.0 male masculine Eriadu Human "
- ],
- "text/html": "| \n", + " | id | \n", + "name | \n", + "height | \n", + "mass | \n", + "hair_color | \n", + "skin_color | \n", + "eye_color | \n", + "birth_year | \n", + "sex | \n", + "gender | \n", + "homeworld | \n", + "species | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "a | \n", + "Luke Skywalker | \n", + "172.0 | \n", + "77.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "19.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 1 | \n", + "a | \n", + "C-3PO | \n", + "167.0 | \n", + "75.0 | \n", + "NaN | \n", + "gold | \n", + "yellow | \n", + "112.0 | \n", + "none | \n", + "masculine | \n", + "Tatooine | \n", + "Droid | \n", + "
| 2 | \n", + "a | \n", + "R2-D2 | \n", + "96.0 | \n", + "32.0 | \n", + "NaN | \n", + "white, blue | \n", + "red | \n", + "33.0 | \n", + "none | \n", + "masculine | \n", + "Naboo | \n", + "Droid | \n", + "
| 3 | \n", + "a | \n", + "Darth Vader | \n", + "202.0 | \n", + "136.0 | \n", + "none | \n", + "white | \n", + "yellow | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 4 | \n", + "b | \n", + "Biggs Darklighter | \n", + "183.0 | \n", + "84.0 | \n", + "black | \n", + "light | \n", + "brown | \n", + "24.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 5 | \n", + "b | \n", + "Obi-Wan Kenobi | \n", + "182.0 | \n", + "77.0 | \n", + "auburn, white | \n", + "fair | \n", + "blue-gray | \n", + "57.0 | \n", + "male | \n", + "masculine | \n", + "Stewjon | \n", + "Human | \n", + "
| 6 | \n", + "b | \n", + "Anakin Skywalker | \n", + "188.0 | \n", + "84.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 7 | \n", + "b | \n", + "Wilhuff Tarkin | \n", + "180.0 | \n", + "NaN | \n", + "auburn, grey | \n", + "fair | \n", + "blue | \n", + "64.0 | \n", + "male | \n", + "masculine | \n", + "Eriadu | \n", + "Human | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 9,
"metadata": {},
- "execution_count": 9
+ "output_type": "execute_result"
}
],
"source": [
@@ -395,12 +1565,169 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | id | \nname | \nheight | \nmass | \nhair_color | \nskin_color | \neye_color | \nbirth_year | \nsex | \ngender | \nhomeworld | \nspecies | \n
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \na | \nLuke Skywalker | \n172.0 | \n77.0 | \nblond | \nfair | \nblue | \n19.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 1 | \na | \nC-3PO | \n167.0 | \n75.0 | \nNaN | \ngold | \nyellow | \n112.0 | \nnone | \nmasculine | \nTatooine | \nDroid | \n
| 2 | \na | \nR2-D2 | \n96.0 | \n32.0 | \nNaN | \nwhite, blue | \nred | \n33.0 | \nnone | \nmasculine | \nNaboo | \nDroid | \n
| 3 | \na | \nDarth Vader | \n202.0 | \n136.0 | \nnone | \nwhite | \nyellow | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 4 | \nb | \nBiggs Darklighter | \n183.0 | \n84.0 | \nblack | \nlight | \nbrown | \n24.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 5 | \nb | \nObi-Wan Kenobi | \n182.0 | \n77.0 | \nauburn, white | \nfair | \nblue-gray | \n57.0 | \nmale | \nmasculine | \nStewjon | \nHuman | \n
| 6 | \nb | \nAnakin Skywalker | \n188.0 | \n84.0 | \nblond | \nfair | \nblue | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 7 | \nb | \nWilhuff Tarkin | \n180.0 | \nNaN | \nauburn, grey | \nfair | \nblue | \n64.0 | \nmale | \nmasculine | \nEriadu | \nHuman | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" groups name height mass hair_color skin_color \\\n",
"0 group 1 Luke Skywalker 172.0 77.0 blond fair \n",
@@ -421,11 +1748,11 @@
"5 blue-gray 57.0 male masculine Stewjon Human \n",
"6 blue 41.9 male masculine Tatooine Human \n",
"7 blue 64.0 male masculine Eriadu Human "
- ],
- "text/html": "| \n", + " | groups | \n", + "name | \n", + "height | \n", + "mass | \n", + "hair_color | \n", + "skin_color | \n", + "eye_color | \n", + "birth_year | \n", + "sex | \n", + "gender | \n", + "homeworld | \n", + "species | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "group 1 | \n", + "Luke Skywalker | \n", + "172.0 | \n", + "77.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "19.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 1 | \n", + "group 1 | \n", + "C-3PO | \n", + "167.0 | \n", + "75.0 | \n", + "NaN | \n", + "gold | \n", + "yellow | \n", + "112.0 | \n", + "none | \n", + "masculine | \n", + "Tatooine | \n", + "Droid | \n", + "
| 2 | \n", + "group 1 | \n", + "R2-D2 | \n", + "96.0 | \n", + "32.0 | \n", + "NaN | \n", + "white, blue | \n", + "red | \n", + "33.0 | \n", + "none | \n", + "masculine | \n", + "Naboo | \n", + "Droid | \n", + "
| 3 | \n", + "group 1 | \n", + "Darth Vader | \n", + "202.0 | \n", + "136.0 | \n", + "none | \n", + "white | \n", + "yellow | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 4 | \n", + "group 2 | \n", + "Biggs Darklighter | \n", + "183.0 | \n", + "84.0 | \n", + "black | \n", + "light | \n", + "brown | \n", + "24.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 5 | \n", + "group 2 | \n", + "Obi-Wan Kenobi | \n", + "182.0 | \n", + "77.0 | \n", + "auburn, white | \n", + "fair | \n", + "blue-gray | \n", + "57.0 | \n", + "male | \n", + "masculine | \n", + "Stewjon | \n", + "Human | \n", + "
| 6 | \n", + "group 2 | \n", + "Anakin Skywalker | \n", + "188.0 | \n", + "84.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 7 | \n", + "group 2 | \n", + "Wilhuff Tarkin | \n", + "180.0 | \n", + "NaN | \n", + "auburn, grey | \n", + "fair | \n", + "blue | \n", + "64.0 | \n", + "male | \n", + "masculine | \n", + "Eriadu | \n", + "Human | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 10,
"metadata": {},
- "execution_count": 10
+ "output_type": "execute_result"
}
],
"source": [
@@ -434,8 +1761,7 @@
},
{
"cell_type": "code",
- "execution_count": 11,
- "id": "aggressive-pilot",
+ "execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2021-04-17T00:51:37.538541Z",
@@ -446,8 +1772,70 @@
},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | groups | \nname | \nheight | \nmass | \nhair_color | \nskin_color | \neye_color | \nbirth_year | \nsex | \ngender | \nhomeworld | \nspecies | \n
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \ngroup 1 | \nLuke Skywalker | \n172.0 | \n77.0 | \nblond | \nfair | \nblue | \n19.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 1 | \ngroup 1 | \nC-3PO | \n167.0 | \n75.0 | \nNaN | \ngold | \nyellow | \n112.0 | \nnone | \nmasculine | \nTatooine | \nDroid | \n
| 2 | \ngroup 1 | \nR2-D2 | \n96.0 | \n32.0 | \nNaN | \nwhite, blue | \nred | \n33.0 | \nnone | \nmasculine | \nNaboo | \nDroid | \n
| 3 | \ngroup 1 | \nDarth Vader | \n202.0 | \n136.0 | \nnone | \nwhite | \nyellow | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 4 | \ngroup 2 | \nBiggs Darklighter | \n183.0 | \n84.0 | \nblack | \nlight | \nbrown | \n24.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 5 | \ngroup 2 | \nObi-Wan Kenobi | \n182.0 | \n77.0 | \nauburn, white | \nfair | \nblue-gray | \n57.0 | \nmale | \nmasculine | \nStewjon | \nHuman | \n
| 6 | \ngroup 2 | \nAnakin Skywalker | \n188.0 | \n84.0 | \nblond | \nfair | \nblue | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 7 | \ngroup 2 | \nWilhuff Tarkin | \n180.0 | \nNaN | \nauburn, grey | \nfair | \nblue | \n64.0 | \nmale | \nmasculine | \nEriadu | \nHuman | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" x y\n",
"0 0.0 NaN\n",
@@ -457,11 +1845,11 @@
"4 NaN 1.0\n",
"5 NaN 2.0\n",
"6 NaN 3.0"
- ],
- "text/html": "| \n", + " | x | \n", + "y | \n", + "
|---|---|---|
| 0 | \n", + "0.0 | \n", + "NaN | \n", + "
| 1 | \n", + "1.0 | \n", + "NaN | \n", + "
| 2 | \n", + "2.0 | \n", + "NaN | \n", + "
| 3 | \n", + "NaN | \n", + "0.0 | \n", + "
| 4 | \n", + "NaN | \n", + "1.0 | \n", + "
| 5 | \n", + "NaN | \n", + "2.0 | \n", + "
| 6 | \n", + "NaN | \n", + "3.0 | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 11,
"metadata": {},
- "execution_count": 11
+ "output_type": "execute_result"
}
],
"source": [
@@ -472,8 +1860,7 @@
},
{
"cell_type": "code",
- "execution_count": 12,
- "id": "sexual-memphis",
+ "execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2021-04-17T00:51:37.571552Z",
@@ -484,18 +1871,60 @@
},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | x | \ny | \n
|---|---|---|
| 0 | \n0.0 | \nNaN | \n
| 1 | \n1.0 | \nNaN | \n
| 2 | \n2.0 | \nNaN | \n
| 3 | \nNaN | \n0.0 | \n
| 4 | \nNaN | \n1.0 | \n
| 5 | \nNaN | \n2.0 | \n
| 6 | \nNaN | \n3.0 | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" x y\n",
"0 0 0.0\n",
"1 1 1.0\n",
"2 2 NaN"
- ],
- "text/html": "| \n", + " | x | \n", + "y | \n", + "
|---|---|---|
| 0 | \n", + "0 | \n", + "0.0 | \n", + "
| 1 | \n", + "1 | \n", + "1.0 | \n", + "
| 2 | \n", + "2 | \n", + "NaN | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 12,
"metadata": {},
- "execution_count": 12
+ "output_type": "execute_result"
}
],
"source": [
@@ -507,32 +1936,69 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | x | \ny | \n
|---|---|---|
| 0 | \n0 | \n0.0 | \n
| 1 | \n1 | \n1.0 | \n
| 2 | \n2 | \nNaN | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" x\n",
"0 0\n",
"1 1\n",
"2 2"
- ],
- "text/html": "| \n", + " | x | \n", + "
|---|---|
| 0 | \n", + "0 | \n", + "
| 1 | \n", + "1 | \n", + "
| 2 | \n", + "2 | \n", + "
\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 13,
"metadata": {},
- "execution_count": 13
+ "output_type": "execute_result"
}
],
"source": [
- "bind_cols(tibble(x = range(3)), tibble())"
+ "tibble(x = range(3)) >> bind_cols(tibble())"
]
},
{
"cell_type": "code",
- "execution_count": 14,
- "id": "amateur-interaction",
+ "execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2021-04-17T00:51:37.605622Z",
@@ -543,8 +2009,8 @@
},
"outputs": [
{
- "output_type": "stream",
"name": "stderr",
+ "output_type": "stream",
"text": [
"[2021-05-24 17:52:22][datar][WARNING] New names:\n",
"[2021-05-24 17:52:22][datar][WARNING] * 'name' -> 'name__1'\n",
@@ -572,8 +2038,151 @@
]
},
{
- "output_type": "execute_result",
"data": {
+ "text/html": [
+ "| \n | x | \n
|---|---|
| 0 | \n0 | \n
| 1 | \n1 | \n
| 2 | \n2 | \n
\n",
+ "\n",
+ "\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
"text/plain": [
" name__1 height__2 mass__3 hair_color__4 skin_color__5 \\\n",
"0 Luke Skywalker 172.0 77.0 blond fair \n",
@@ -600,11 +2209,11 @@
"3 male masculine Eriadu Human \n",
"\n",
"[4 rows x 22 columns]"
- ],
- "text/html": "| \n", + " | name__1 | \n", + "height__2 | \n", + "mass__3 | \n", + "hair_color__4 | \n", + "skin_color__5 | \n", + "eye_color__6 | \n", + "birth_year__7 | \n", + "sex__8 | \n", + "gender__9 | \n", + "homeworld__10 | \n", + "... | \n", + "height__13 | \n", + "mass__14 | \n", + "hair_color__15 | \n", + "skin_color__16 | \n", + "eye_color__17 | \n", + "birth_year__18 | \n", + "sex__19 | \n", + "gender__20 | \n", + "homeworld__21 | \n", + "species__22 | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "Luke Skywalker | \n", + "172.0 | \n", + "77.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "19.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "... | \n", + "183.0 | \n", + "84.0 | \n", + "black | \n", + "light | \n", + "brown | \n", + "24.0 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 1 | \n", + "C-3PO | \n", + "167.0 | \n", + "75.0 | \n", + "NaN | \n", + "gold | \n", + "yellow | \n", + "112.0 | \n", + "none | \n", + "masculine | \n", + "Tatooine | \n", + "... | \n", + "182.0 | \n", + "77.0 | \n", + "auburn, white | \n", + "fair | \n", + "blue-gray | \n", + "57.0 | \n", + "male | \n", + "masculine | \n", + "Stewjon | \n", + "Human | \n", + "
| 2 | \n", + "R2-D2 | \n", + "96.0 | \n", + "32.0 | \n", + "NaN | \n", + "white, blue | \n", + "red | \n", + "33.0 | \n", + "none | \n", + "masculine | \n", + "Naboo | \n", + "... | \n", + "188.0 | \n", + "84.0 | \n", + "blond | \n", + "fair | \n", + "blue | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "Human | \n", + "
| 3 | \n", + "Darth Vader | \n", + "202.0 | \n", + "136.0 | \n", + "none | \n", + "white | \n", + "yellow | \n", + "41.9 | \n", + "male | \n", + "masculine | \n", + "Tatooine | \n", + "... | \n", + "180.0 | \n", + "NaN | \n", + "auburn, grey | \n", + "fair | \n", + "blue | \n", + "64.0 | \n", + "male | \n", + "masculine | \n", + "Eriadu | \n", + "Human | \n", + "
4 rows × 22 columns
\n", + "\n\n\n \n
\n
"
+ ]
},
+ "execution_count": 14,
"metadata": {},
- "execution_count": 14
+ "output_type": "execute_result"
}
],
"source": [
@@ -613,22 +2222,16 @@
}
],
"metadata": {
+ "interpreter": {
+ "hash": "c4cc73b080e063fcebb9afb794613be7caf4b26129562cba1382945a18cc49cc"
+ },
"kernelspec": {
- "display_name": "Python 3",
- "language": "python",
+ "display_name": "Python 3.7.8 64-bit ('base': conda)",
"name": "python3"
},
"language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
"name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.7.8"
+ "version": ""
}
},
"nbformat": 4,
diff --git a/docs/notebooks/chop.ipynb b/docs/notebooks/chop.ipynb
index ccbd67a3..f2d33714 100644
--- a/docs/notebooks/chop.ipynb
+++ b/docs/notebooks/chop.ipynb
@@ -1,25 +1,4 @@
{
- "metadata": {
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.7.8"
- },
- "orig_nbformat": 2,
- "kernelspec": {
- "name": "python378jvsc74a57bd0c4cc73b080e063fcebb9afb794613be7caf4b26129562cba1382945a18cc49cc",
- "display_name": "Python 3.7.8 64-bit ('base': conda)"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 2,
"cells": [
{
"cell_type": "code",
@@ -27,44 +6,125 @@
"metadata": {},
"outputs": [
{
- "output_type": "display_data",
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "[2021-06-29 16:34:36][datar][WARNING] Builtin name \"min\" has been overriden by datar.\n",
+ "[2021-06-29 16:34:36][datar][WARNING] Builtin name \"max\" has been overriden by datar.\n",
+ "[2021-06-29 16:34:36][datar][WARNING] Builtin name \"sum\" has been overriden by datar.\n",
+ "[2021-06-29 16:34:36][datar][WARNING] Builtin name \"abs\" has been overriden by datar.\n",
+ "[2021-06-29 16:34:36][datar][WARNING] Builtin name \"round\" has been overriden by datar.\n",
+ "[2021-06-29 16:34:36][datar][WARNING] Builtin name \"all\" has been overriden by datar.\n",
+ "[2021-06-29 16:34:36][datar][WARNING] Builtin name \"any\" has been overriden by datar.\n",
+ "[2021-06-29 16:34:36][datar][WARNING] Builtin name \"re\" has been overriden by datar.\n",
+ "[2021-06-29 16:34:36][datar][WARNING] Builtin name \"filter\" has been overriden by datar.\n",
+ "[2021-06-29 16:34:36][datar][WARNING] Builtin name \"slice\" has been overriden by datar.\n"
+ ]
+ },
+ {
"data": {
- "text/plain": "| \n | name__1 | \nheight__2 | \nmass__3 | \nhair_color__4 | \nskin_color__5 | \neye_color__6 | \nbirth_year__7 | \nsex__8 | \ngender__9 | \nhomeworld__10 | \n... | \nheight__13 | \nmass__14 | \nhair_color__15 | \nskin_color__16 | \neye_color__17 | \nbirth_year__18 | \nsex__19 | \ngender__20 | \nhomeworld__21 | \nspecies__22 | \n
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \nLuke Skywalker | \n172.0 | \n77.0 | \nblond | \nfair | \nblue | \n19.0 | \nmale | \nmasculine | \nTatooine | \n... | \n183.0 | \n84.0 | \nblack | \nlight | \nbrown | \n24.0 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 1 | \nC-3PO | \n167.0 | \n75.0 | \nNaN | \ngold | \nyellow | \n112.0 | \nnone | \nmasculine | \nTatooine | \n... | \n182.0 | \n77.0 | \nauburn, white | \nfair | \nblue-gray | \n57.0 | \nmale | \nmasculine | \nStewjon | \nHuman | \n
| 2 | \nR2-D2 | \n96.0 | \n32.0 | \nNaN | \nwhite, blue | \nred | \n33.0 | \nnone | \nmasculine | \nNaboo | \n... | \n188.0 | \n84.0 | \nblond | \nfair | \nblue | \n41.9 | \nmale | \nmasculine | \nTatooine | \nHuman | \n
| 3 | \nDarth Vader | \n202.0 | \n136.0 | \nnone | \nwhite | \nyellow | \n41.9 | \nmale | \nmasculine | \nTatooine | \n... | \n180.0 | \nNaN | \nauburn, grey | \nfair | \nblue | \n64.0 | \nmale | \nmasculine | \nEriadu | \nHuman | \n
4 rows × 22 columns
\nTry this notebook on binder.
"
+ "text/html": [
+ "Try this notebook on binder.
"
+ ],
+ "text/plain": [
+ "| \n", + " | x | \n", + "data | \n", + "
|---|---|---|
| \n", + " | <int64> | \n", + "<object> | \n", + "
| 0 | \n", + "1 | \n", + "<DF 3x2> | \n", + "
| 1 | \n", + "2 | \n", + "<DF 2x2> | \n", + "
| 2 | \n", + "3 | \n", + "<DF 1x2> | \n", + "
\n\n\n \n
\n
"
+ "text/plain": [
+ " x data\n",
+ " | \n | x | \ndata | \n
|---|---|---|
| 0 | \n1 | \ny z\n0 1 6\n1 2 5\n2 3 4 | \n
| 1 | \n2 | \ny z\n3 4 3\n4 5 2 | \n
| 2 | \n3 | \ny z\n5 6 1 | \n