mirror of
https://gitflic.ru/project/openide/openide.git
synced 2026-09-27 10:03:11 +07:00
DS-4878 Pandas-specific-quick-fix-replace-listdf.col.values-to-df.col.tolist
Add new intention and a corresponding quick fix for the usage pd.Series.values property from pandas library. ^DS-4878 Fixed Merge-request: IJ-MR-106089 Merged-by: Natalia Murycheva <natalia.murycheva@jetbrains.com> GitOrigin-RevId: 0c8dc40b09ee2d95ecd8ded532f31f5ef4a7740f
This commit is contained in:
Natalia.Murycheva
committed by
intellij-monorepo-bot
intellij-monorepo-bot
parent
3d5155fe07
commit
0d53aa47df
+14
@@ -0,0 +1,14 @@
|
||||
<html>
|
||||
<body>
|
||||
<p>Reports redundant <code>list</code> in <code>list(Series.values)</code> statement for pandas and polars libraries.
|
||||
Such <code>Series</code> values extraction can be replaced with the <code>to_list()</code> function call.</p>
|
||||
<p><b>Example:</b></p>
|
||||
<pre style="font-family: monospace">
|
||||
list(df['column'].values)
|
||||
</pre>
|
||||
<p>When the quick-fix is applied, the code changes to:</p>
|
||||
<pre style="font-family: monospace">
|
||||
df['column'].to_list()
|
||||
</pre>
|
||||
</body>
|
||||
</html>
|
||||
@@ -1245,3 +1245,7 @@ INSP.class.var.can.not.override.instance.variable=Cannot override instance varia
|
||||
INSP.class.var.can.not.be.used.in.annotations.for.function.parameters='ClassVar' cannot be used in annotations for function parameters
|
||||
INSP.class.var.can.not.be.used.in.annotation.for.function.return.value='ClassVar' cannot be used in annotation for a function return value
|
||||
INSP.class.var.can.not.include.type.variables='ClassVar' parameter cannot include type variables
|
||||
|
||||
# Pandas-Specific inspections and quick fixes
|
||||
INSP.pandas.series.values.replace.with.tolist=Method Series.to_list() is recommended
|
||||
QFIX.pandas.series.values.replace.with.tolist=Replace list(Series.values) with Series.to_list()
|
||||
|
||||
@@ -194,6 +194,9 @@
|
||||
<localInspection language="Python" shortName="PyRelativeImportInspection" suppressId="PyPackages" bundle="messages.PyPsiBundle"
|
||||
key="INSP.NAME.relative.import" groupKey="INSP.GROUP.python" enabledByDefault="true" level="WEAK WARNING"
|
||||
implementationClass="com.jetbrains.python.inspections.PyRelativeImportInspection"/>
|
||||
<localInspection language="Python" shortName="PyPandasSeriesToListInspection" suppressId="PyPackages" bundle="messages.PyPsiBundle"
|
||||
key="INSP.pandas.series.values.replace.with.tolist" enabledByDefault="true" level="WARNING"
|
||||
implementationClass="com.jetbrains.python.inspections.PyPandasSeriesToListInspection"/>
|
||||
|
||||
<defaultLiveTemplates file="liveTemplates/Python.xml"/>
|
||||
<liveTemplateContext contextId="Python"
|
||||
|
||||
@@ -0,0 +1,88 @@
|
||||
// Copyright 2000-2023 JetBrains s.r.o. and contributors. Use of this source code is governed by the Apache 2.0 license.
|
||||
package com.jetbrains.python.inspections
|
||||
|
||||
import com.intellij.codeInspection.LocalInspectionToolSession
|
||||
import com.intellij.codeInspection.LocalQuickFix
|
||||
import com.intellij.codeInspection.ProblemDescriptor
|
||||
import com.intellij.codeInspection.ProblemsHolder
|
||||
import com.intellij.openapi.project.Project
|
||||
import com.intellij.psi.PsiElementVisitor
|
||||
import com.intellij.psi.util.PsiTreeUtil
|
||||
import com.jetbrains.python.PyPsiBundle
|
||||
import com.jetbrains.python.psi.*
|
||||
import com.jetbrains.python.psi.types.PyClassType
|
||||
import com.jetbrains.python.psi.types.PyType
|
||||
import com.jetbrains.python.psi.types.TypeEvalContext
|
||||
|
||||
class PyPandasSeriesToListInspection : PyInspection() {
|
||||
override fun buildVisitor(holder: ProblemsHolder, isOnTheFly: Boolean, session: LocalInspectionToolSession): PsiElementVisitor {
|
||||
return Visitor(holder, PyInspectionVisitor.getContext(session))
|
||||
}
|
||||
|
||||
private class Visitor(holder: ProblemsHolder, context: TypeEvalContext) : PyInspectionVisitor(holder, context) {
|
||||
|
||||
override fun visitPyCallExpression(node: PyCallExpression) {
|
||||
if ((PsiTreeUtil.hasErrorElements(node))) return
|
||||
if (node.callee?.text != "list" || node.arguments.size != 1) return
|
||||
val argument = node.arguments.single()
|
||||
if (argument !is PyQualifiedExpression) return
|
||||
if (argument.referencedName != "values") return
|
||||
|
||||
val qualifier = argument.qualifier ?: return
|
||||
|
||||
if (hasSeriesType(qualifier, myTypeEvalContext)) {
|
||||
registerProblem(node, PyPsiBundle.message("INSP.pandas.series.values.replace.with.tolist"), DSPandasSeriesToListQuickFix())
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks whether expression possibly has type Series.
|
||||
*/
|
||||
private fun hasSeriesType(expression: PyExpression, context: TypeEvalContext): Boolean {
|
||||
if (expression is PySubscriptionExpression) {
|
||||
return context.getType(expression.indexExpression).isPyClassWithName("str")
|
||||
}
|
||||
|
||||
val expressionType = context.getType(expression)
|
||||
if (expressionType.isPyClassWithName("Series")) return true
|
||||
|
||||
if (expressionType != null) return false
|
||||
return isQualifiedDataframeCall(expression, context)
|
||||
}
|
||||
|
||||
private fun isQualifiedDataframeCall(expression: PyExpression, context: TypeEvalContext): Boolean {
|
||||
if (expression !is PyQualifiedExpression) return false
|
||||
return context.getType(expression.qualifier).isPyClassWithName("DataFrame")
|
||||
}
|
||||
}
|
||||
|
||||
private class DSPandasSeriesToListQuickFix : LocalQuickFix {
|
||||
override fun getFamilyName() = PyPsiBundle.message("QFIX.pandas.series.values.replace.with.tolist")
|
||||
|
||||
override fun applyFix(project: Project, descriptor: ProblemDescriptor) {
|
||||
val functionCall = descriptor.psiElement as? PyCallExpression ?: return
|
||||
|
||||
val argument = functionCall.arguments.singleOrNull() as? PyQualifiedExpression ?: return
|
||||
val argumentQualifier = argument.qualifier ?: return
|
||||
|
||||
val toListCallString = argumentQualifier.text + ".to_list()"
|
||||
|
||||
val toListCallStatement = PyElementGenerator.getInstance(project).createFromText(
|
||||
LanguageLevel.forElement(functionCall),
|
||||
PyExpressionStatement::class.java,
|
||||
toListCallString
|
||||
)
|
||||
|
||||
functionCall.replace(toListCallStatement.expression)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private fun PyType?.isPyClassWithName(typeName: String) =
|
||||
this is PyClassType && name == typeName
|
||||
|
||||
|
||||
private fun TypeEvalContext.getType(element: PyTypedElement?): PyType? {
|
||||
if (element == null) return null
|
||||
return getType(element)
|
||||
}
|
||||
@@ -0,0 +1,5 @@
|
||||
import pandas as pd
|
||||
# DataFrame columns case
|
||||
df = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6], "c": [7, 8, 9]})
|
||||
|
||||
<warning descr="Method Series.to_list() is recommended">list<caret>(df.b.values)</warning>
|
||||
@@ -0,0 +1,5 @@
|
||||
import pandas as pd
|
||||
# DataFrame columns case
|
||||
df = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6], "c": [7, 8, 9]})
|
||||
|
||||
df.b.to_list()
|
||||
@@ -0,0 +1,12 @@
|
||||
import pandas as pd
|
||||
# DataFrame columns case
|
||||
df = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6], "c": [7, 8, 9]})
|
||||
|
||||
list(df[['a', 'b']].values)
|
||||
bb = ["a", "b", "c"]
|
||||
list(df[bb].values)
|
||||
|
||||
# with errors
|
||||
list(df.<error descr="Name expected">[</error>'a'].values)
|
||||
|
||||
<warning descr="Method Series.to_list() is recommended">list<caret>(df['a'].values)</warning>
|
||||
@@ -0,0 +1,12 @@
|
||||
import pandas as pd
|
||||
# DataFrame columns case
|
||||
df = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6], "c": [7, 8, 9]})
|
||||
|
||||
list(df[['a', 'b']].values)
|
||||
bb = ["a", "b", "c"]
|
||||
list(df[bb].values)
|
||||
|
||||
# with errors
|
||||
list(df.['a'].values)
|
||||
|
||||
df['a'].to_list()
|
||||
@@ -0,0 +1,2 @@
|
||||
from series import Series
|
||||
from frame import DataFrame
|
||||
@@ -0,0 +1,18 @@
|
||||
from series import Series
|
||||
|
||||
|
||||
class NDFrame:
|
||||
...
|
||||
|
||||
|
||||
class DataFrame:
|
||||
def __getitem__(self, key):
|
||||
if key == "1":
|
||||
return None
|
||||
if key == "2":
|
||||
return Series()
|
||||
if key == "3":
|
||||
return NDFrame()
|
||||
if key == "4":
|
||||
return DataFrame()
|
||||
|
||||
@@ -0,0 +1,292 @@
|
||||
class property(object):
|
||||
"""
|
||||
Property attribute.
|
||||
|
||||
fget
|
||||
function to be used for getting an attribute value
|
||||
fset
|
||||
function to be used for setting an attribute value
|
||||
fdel
|
||||
function to be used for del'ing an attribute
|
||||
doc
|
||||
docstring
|
||||
|
||||
Typical use is to define a managed attribute x:
|
||||
|
||||
class C(object):
|
||||
def getx(self): return self._x
|
||||
def setx(self, value): self._x = value
|
||||
def delx(self): del self._x
|
||||
x = property(getx, setx, delx, "I'm the 'x' property.")
|
||||
|
||||
Decorators make defining new properties or modifying existing ones easy:
|
||||
|
||||
class C(object):
|
||||
@property
|
||||
def x(self):
|
||||
"I am the 'x' property."
|
||||
return self._x
|
||||
@x.setter
|
||||
def x(self, value):
|
||||
self._x = value
|
||||
@x.deleter
|
||||
def x(self):
|
||||
del self._x
|
||||
"""
|
||||
def deleter(self, *args, **kwargs): # real signature unknown
|
||||
""" Descriptor to obtain a copy of the property with a different deleter. """
|
||||
pass
|
||||
|
||||
def getter(self, *args, **kwargs): # real signature unknown
|
||||
""" Descriptor to obtain a copy of the property with a different getter. """
|
||||
pass
|
||||
|
||||
def setter(self, *args, **kwargs): # real signature unknown
|
||||
""" Descriptor to obtain a copy of the property with a different setter. """
|
||||
pass
|
||||
|
||||
def __delete__(self, *args, **kwargs): # real signature unknown
|
||||
""" Delete an attribute of instance. """
|
||||
pass
|
||||
|
||||
def __getattribute__(self, *args, **kwargs): # real signature unknown
|
||||
""" Return getattr(self, name). """
|
||||
pass
|
||||
|
||||
def __get__(self, *args, **kwargs): # real signature unknown
|
||||
""" Return an attribute of instance, which is of type owner. """
|
||||
pass
|
||||
|
||||
def __init__(self, fget=None, fset=None, fdel=None, doc=None): # known special case of property.__init__
|
||||
"""
|
||||
Property attribute.
|
||||
|
||||
fget
|
||||
function to be used for getting an attribute value
|
||||
fset
|
||||
function to be used for setting an attribute value
|
||||
fdel
|
||||
function to be used for del'ing an attribute
|
||||
doc
|
||||
docstring
|
||||
|
||||
Typical use is to define a managed attribute x:
|
||||
|
||||
class C(object):
|
||||
def getx(self): return self._x
|
||||
def setx(self, value): self._x = value
|
||||
def delx(self): del self._x
|
||||
x = property(getx, setx, delx, "I'm the 'x' property.")
|
||||
|
||||
Decorators make defining new properties or modifying existing ones easy:
|
||||
|
||||
class C(object):
|
||||
@property
|
||||
def x(self):
|
||||
"I am the 'x' property."
|
||||
return self._x
|
||||
@x.setter
|
||||
def x(self, value):
|
||||
self._x = value
|
||||
@x.deleter
|
||||
def x(self):
|
||||
del self._x
|
||||
# (copied from class doc)
|
||||
"""
|
||||
pass
|
||||
|
||||
@staticmethod # known case of __new__
|
||||
def __new__(*args, **kwargs): # real signature unknown
|
||||
""" Create and return a new object. See help(type) for accurate signature. """
|
||||
pass
|
||||
|
||||
def __set__(self, *args, **kwargs): # real signature unknown
|
||||
""" Set an attribute of instance to value. """
|
||||
pass
|
||||
|
||||
fdel = property(lambda self: object(), lambda self, v: None, lambda self: None) # default
|
||||
|
||||
fget = property(lambda self: object(), lambda self, v: None, lambda self: None) # default
|
||||
|
||||
fset = property(lambda self: object(), lambda self, v: None, lambda self: None) # default
|
||||
|
||||
__isabstractmethod__ = property(lambda self: object(), lambda self, v: None, lambda self: None) # default
|
||||
|
||||
|
||||
class IndexOpsMixin():
|
||||
"""
|
||||
Common ops mixin to support a unified interface / docs for Series / Index
|
||||
"""
|
||||
def tolist(self):
|
||||
"""
|
||||
Return a list of the values.
|
||||
|
||||
These are each a scalar type, which is a Python scalar
|
||||
(for str, int, float) or a pandas scalar
|
||||
(for Timestamp/Timedelta/Interval/Period)
|
||||
|
||||
Returns
|
||||
-------
|
||||
list
|
||||
|
||||
See Also
|
||||
--------
|
||||
numpy.ndarray.tolist : Return the array as an a.ndim-levels deep
|
||||
nested list of Python scalars.
|
||||
"""
|
||||
# return self._values.tolist()
|
||||
...
|
||||
|
||||
to_list = tolist
|
||||
|
||||
|
||||
class NDFrame:
|
||||
...
|
||||
|
||||
|
||||
class Series(IndexOpsMixin, NDFrame):
|
||||
"""
|
||||
One-dimensional ndarray with axis labels (including time series).
|
||||
|
||||
Labels need not be unique but must be a hashable type. The object
|
||||
supports both integer- and label-based indexing and provides a host of
|
||||
methods for performing operations involving the index. Statistical
|
||||
methods from ndarray have been overridden to automatically exclude
|
||||
missing data (currently represented as NaN).
|
||||
|
||||
Operations between Series (+, -, /, \\*, \\*\\*) align values based on their
|
||||
associated index values-- they need not be the same length. The result
|
||||
index will be the sorted union of the two indexes.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
data : array-like, Iterable, dict, or scalar value
|
||||
Contains data stored in Series. If data is a dict, argument order is
|
||||
maintained.
|
||||
index : array-like or Index (1d)
|
||||
Values must be hashable and have the same length as `data`.
|
||||
Non-unique index values are allowed. Will default to
|
||||
RangeIndex (0, 1, 2, ..., n) if not provided. If data is dict-like
|
||||
and index is None, then the keys in the data are used as the index. If the
|
||||
index is not None, the resulting Series is reindexed with the index values.
|
||||
dtype : str, numpy.dtype, or ExtensionDtype, optional
|
||||
Data type for the output Series. If not specified, this will be
|
||||
inferred from `data`.
|
||||
See the :ref:`user guide <basics.dtypes>` for more usages.
|
||||
name : str, optional
|
||||
The name to give to the Series.
|
||||
copy : bool, default False
|
||||
Copy input data. Only affects Series or 1d ndarray input. See examples.
|
||||
|
||||
Examples
|
||||
--------
|
||||
Constructing Series from a dictionary with an Index specified
|
||||
|
||||
# >>> d = {'a': 1, 'b': 2, 'c': 3}
|
||||
# >>> ser = pd.Series(data=d, index=['a', 'b', 'c'])
|
||||
# >>> ser
|
||||
a 1
|
||||
b 2
|
||||
c 3
|
||||
dtype: int64
|
||||
|
||||
The keys of the dictionary match with the Index values, hence the Index
|
||||
values have no effect.
|
||||
|
||||
# >>> d = {'a': 1, 'b': 2, 'c': 3}
|
||||
# >>> ser = pd.Series(data=d, index=['x', 'y', 'z'])
|
||||
# >>> ser
|
||||
x NaN
|
||||
y NaN
|
||||
z NaN
|
||||
dtype: float64
|
||||
|
||||
Note that the Index is first build with the keys from the dictionary.
|
||||
After this the Series is reindexed with the given Index values, hence we
|
||||
get all NaN as a result.
|
||||
|
||||
Constructing Series from a list with `copy=False`.
|
||||
|
||||
# >>> r = [1, 2]
|
||||
# >>> ser = pd.Series(r, copy=False)
|
||||
# >>> ser.iloc[0] = 999
|
||||
# >>> r
|
||||
[1, 2]
|
||||
# >>> ser
|
||||
0 999
|
||||
1 2
|
||||
dtype: int64
|
||||
|
||||
Due to input data type the Series has a `copy` of
|
||||
the original data even though `copy=False`, so
|
||||
the data is unchanged.
|
||||
|
||||
Constructing Series from a 1d ndarray with `copy=False`.
|
||||
|
||||
# >>> r = np.array([1, 2])
|
||||
# >>> ser = pd.Series(r, copy=False)
|
||||
# >>> ser.iloc[0] = 999
|
||||
# >>> r
|
||||
array([999, 2])
|
||||
# >>> ser
|
||||
0 999
|
||||
1 2
|
||||
dtype: int64
|
||||
|
||||
Due to input data type the Series has a `view` on
|
||||
the original data, so
|
||||
the data is changed as well.
|
||||
"""
|
||||
def __init__(
|
||||
self,
|
||||
data=None,
|
||||
index=None,
|
||||
dtype = None,
|
||||
name=None,
|
||||
copy = False,
|
||||
fastpath = False,
|
||||
):
|
||||
...
|
||||
|
||||
@property
|
||||
def values(self):
|
||||
"""
|
||||
Return Series as ndarray or ndarray-like depending on the dtype.
|
||||
|
||||
.. warning::
|
||||
|
||||
We recommend using :attr:`Series.array` or
|
||||
:meth:`Series.to_numpy`, depending on whether you need
|
||||
a reference to the underlying data or a NumPy array.
|
||||
|
||||
Returns
|
||||
-------
|
||||
numpy.ndarray or ndarray-like
|
||||
|
||||
See Also
|
||||
--------
|
||||
Series.array : Reference to the underlying data.
|
||||
Series.to_numpy : A NumPy array representing the underlying data.
|
||||
|
||||
Examples
|
||||
--------
|
||||
# >>> pd.Series([1, 2, 3]).values
|
||||
array([1, 2, 3])
|
||||
|
||||
# >>> pd.Series(list('aabc')).values
|
||||
array(['a', 'a', 'b', 'c'], dtype=object)
|
||||
|
||||
# >>> pd.Series(list('aabc')).astype('category').values
|
||||
['a', 'a', 'b', 'c']
|
||||
Categories (3, object): ['a', 'b', 'c']
|
||||
|
||||
Timezone aware datetime data is converted to UTC:
|
||||
|
||||
# >>> pd.Series(pd.date_range('20130101', periods=3,
|
||||
... tz='US/Eastern')).values
|
||||
array(['2013-01-01T05:00:00.000000000',
|
||||
'2013-01-02T05:00:00.000000000',
|
||||
'2013-01-03T05:00:00.000000000'], dtype='datetime64[ns]')
|
||||
"""
|
||||
# return self._mgr.external_values()
|
||||
...
|
||||
@@ -0,0 +1,5 @@
|
||||
import pandas as pd
|
||||
# Series case
|
||||
a = pd.Series([1, 2, 3])
|
||||
|
||||
<warning descr="Method Series.to_list() is recommended">list<caret>(a.values)</warning>
|
||||
@@ -0,0 +1,5 @@
|
||||
import pandas as pd
|
||||
# Series case
|
||||
a = pd.Series([1, 2, 3])
|
||||
|
||||
a.to_list()
|
||||
@@ -0,0 +1,29 @@
|
||||
// Copyright 2000-2023 JetBrains s.r.o. and contributors. Use of this source code is governed by the Apache 2.0 license.
|
||||
package com.jetbrains.python.quickFixes
|
||||
|
||||
import com.jetbrains.python.PyPsiBundle
|
||||
import com.jetbrains.python.PyQuickFixTestCase
|
||||
import com.jetbrains.python.inspections.PyPandasSeriesToListInspection
|
||||
|
||||
class PyPandasSeriesToListQuickFixTest : PyQuickFixTestCase() {
|
||||
private val quickFixName = PyPsiBundle.message("QFIX.pandas.series.values.replace.with.tolist")
|
||||
|
||||
@Throws(Exception::class)
|
||||
override fun setUp() {
|
||||
super.setUp()
|
||||
myFixture.copyDirectoryToProject("", "")
|
||||
}
|
||||
|
||||
fun testDataframeGetitem() {
|
||||
doQuickFixTest(PyPandasSeriesToListInspection::class.java, quickFixName)
|
||||
}
|
||||
|
||||
fun testDataframeGetattr() {
|
||||
doQuickFixTest(PyPandasSeriesToListInspection::class.java, quickFixName)
|
||||
}
|
||||
|
||||
|
||||
fun testSeriesSimple() {
|
||||
doQuickFixTest(PyPandasSeriesToListInspection::class.java, quickFixName)
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user