10138721258

Committed 29 Jul 2024 05:35AM UTC coverage: 93.448% (-0.3%) from 93.797%

Build # 10138721258

Build Type

Pull #681

github

Committed by

web-flow

Commit Message

Merge 7af2bd516 into 3aee19e38

Pull Request Pull Request #681: Enhance cross-platform compatibility for loading PySRRegressor models

Run Details

15 of 17 new or added lines in 2 files covered. (88.24%)

3 existing lines in 1 file now uncovered.

1141 of 1221 relevant lines covered (93.45%)

2.59 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

92.86

/pysr/utils.py

import difflib
import inspect
import os
import pickle as pkl
import re
from pathlib import Path, PurePosixPath, PureWindowsPath
from typing import Any, List, TypeVar, Union

from numpy import ndarray
from sklearn.utils.validation import _check_feature_names_in  # type: ignore

T = TypeVar("T", bound=Any)

ArrayLike = Union[ndarray, List[T]]
PathLike = Union[str, Path]


def _csv_filename_to_pkl_filename(csv_filename: PathLike) -> PathLike:
    if os.path.splitext(csv_filename)[1] == ".pkl":
        return csv_filename

    # Assume that the csv filename is of the form "foo.csv"
    assert str(csv_filename).endswith(".csv")

    dirname = str(os.path.dirname(csv_filename))
    basename = str(os.path.basename(csv_filename))
    base = str(os.path.splitext(basename)[0])

    pkl_basename = base + ".pkl"

    return os.path.join(dirname, pkl_basename)


_regexp_im = re.compile(r"\b(\d+\.\d+)im\b")
_regexp_im_sci = re.compile(r"\b(\d+\.\d+)[eEfF]([+-]?\d+)im\b")
_regexp_sci = re.compile(r"\b(\d+\.\d+)[eEfF]([+-]?\d+)\b")

_apply_regexp_im = lambda x: _regexp_im.sub(r"\1j", x)
_apply_regexp_im_sci = lambda x: _regexp_im_sci.sub(r"\1e\2j", x)
_apply_regexp_sci = lambda x: _regexp_sci.sub(r"\1e\2", x)


def _preprocess_julia_floats(s: str) -> str:
    if isinstance(s, str):
        s = _apply_regexp_im(s)
        s = _apply_regexp_im_sci(s)
        s = _apply_regexp_sci(s)
    return s


def _safe_check_feature_names_in(self, variable_names, generate_names=True):
    """_check_feature_names_in with compat for old versions."""
    try:
        return _check_feature_names_in(
            self, variable_names, generate_names=generate_names
        )
    except TypeError:
        return _check_feature_names_in(self, variable_names)


def _subscriptify(i: int) -> str:
    """Converts integer to subscript text form.

    For example, 123 -> "₁₂₃".
    """
    return "".join([chr(0x2080 + int(c)) for c in str(i)])


def _suggest_keywords(cls, k: str) -> List[str]:
    valid_keywords = [
        param
        for param in inspect.signature(cls.__init__).parameters
        if param not in ["self", "kwargs"]
    ]
    suggestions = difflib.get_close_matches(k, valid_keywords, n=3)
    return suggestions


class _CrossPlatformPathUnpickler(pkl.Unpickler):
    def find_class(self, module, name):
        if module == "pathlib":
            if name == "PosixPath":
                return PurePosixPath
            elif name == "WindowsPath":
                return PureWindowsPath
        return super().find_class(module, name)


def _path_to_str(path):
    if isinstance(path, (PurePosixPath, PureWindowsPath)):
        return str(path)
    return path

1	import difflib	3✔
2	import inspect	3✔
3	import os	3✔
4	import pickle as pkl	3✔
5	import re	3✔
6	from pathlib import Path, PurePosixPath, PureWindowsPath	3✔
7	from typing import Any, List, TypeVar, Union	3✔
8
9	from numpy import ndarray	3✔
10	from sklearn.utils.validation import _check_feature_names_in # type: ignore	3✔
11
12	T = TypeVar("T", bound=Any)	3✔
13
14	ArrayLike = Union[ndarray, List[T]]	3✔
15	PathLike = Union[str, Path]	3✔
16
17
18	def _csv_filename_to_pkl_filename(csv_filename: PathLike) -> PathLike:	3✔
19	if os.path.splitext(csv_filename)[1] == ".pkl":	3✔
20	return csv_filename	3✔
21
22	# Assume that the csv filename is of the form "foo.csv"
23	assert str(csv_filename).endswith(".csv")	3✔
24
25	dirname = str(os.path.dirname(csv_filename))	3✔
26	basename = str(os.path.basename(csv_filename))	3✔
27	base = str(os.path.splitext(basename)[0])	3✔
28
29	pkl_basename = base + ".pkl"	3✔
30
31	return os.path.join(dirname, pkl_basename)	3✔
32
33
34	_regexp_im = re.compile(r"\b(\d+\.\d+)im\b")	3✔
35	_regexp_im_sci = re.compile(r"\b(\d+\.\d+)[eEfF]([+-]?\d+)im\b")	3✔
36	_regexp_sci = re.compile(r"\b(\d+\.\d+)[eEfF]([+-]?\d+)\b")	3✔
37
38	_apply_regexp_im = lambda x: _regexp_im.sub(r"\1j", x)	3✔
39	_apply_regexp_im_sci = lambda x: _regexp_im_sci.sub(r"\1e\2j", x)	3✔
40	_apply_regexp_sci = lambda x: _regexp_sci.sub(r"\1e\2", x)	3✔
41
42
43	def _preprocess_julia_floats(s: str) -> str:	3✔
44	if isinstance(s, str):	3✔
45	s = _apply_regexp_im(s)	3✔
46	s = _apply_regexp_im_sci(s)	3✔
47	s = _apply_regexp_sci(s)	3✔
48	return s	3✔
49
50
51	def _safe_check_feature_names_in(self, variable_names, generate_names=True):	3✔
52	"""_check_feature_names_in with compat for old versions."""
53	try:	3✔
54	return _check_feature_names_in(	3✔
55	self, variable_names, generate_names=generate_names
56	)
57	except TypeError:	×
58	return _check_feature_names_in(self, variable_names)	×
59
60
61	def _subscriptify(i: int) -> str:	3✔
62	"""Converts integer to subscript text form.
63
64	For example, 123 -> "₁₂₃".
65	"""
66	return "".join([chr(0x2080 + int(c)) for c in str(i)])	3✔
67
68
69	def _suggest_keywords(cls, k: str) -> List[str]:	3✔
70	valid_keywords = [	3✔
71	param
72	for param in inspect.signature(cls.__init__).parameters
73	if param not in ["self", "kwargs"]
74	]
75	suggestions = difflib.get_close_matches(k, valid_keywords, n=3)	3✔
76	return suggestions	3✔
77
78
79	class _CrossPlatformPathUnpickler(pkl.Unpickler):	3✔
80	def find_class(self, module, name):	3✔
81	if module == "pathlib":	3✔
82	if name == "PosixPath":	3✔
83	return PurePosixPath	3✔
NEW 84	elif name == "WindowsPath":	×
NEW 85	return PureWindowsPath	×
86	return super().find_class(module, name)	3✔
87
88
89	def _path_to_str(path):	3✔
90	if isinstance(path, (PurePosixPath, PureWindowsPath)):	3✔
91	return str(path)	3✔
92	return path	3✔

MilesCranmer / PySR / 10138721258

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous