Coverage for /var/srv/projects/api.amasfac.comuna18.com/tmp/venv/lib/python3.9/site-packages/pandas/core/arrays/numeric.py: 22%

1from __future__ import annotations 

2 

3import numbers 

4from typing import ( 

5 TYPE_CHECKING, 

6 Any, 

7 Callable, 

8 Mapping, 

9 TypeVar, 

10) 

11 

12import numpy as np 

13 

14from pandas._libs import ( 

15 lib, 

16 missing as libmissing, 

17) 

18from pandas._typing import ( 

19 Dtype, 

20 DtypeObj, 

21 npt, 

22) 

23from pandas.errors import AbstractMethodError 

24from pandas.util._decorators import cache_readonly 

25 

26from pandas.core.dtypes.common import ( 

27 is_bool_dtype, 

28 is_float_dtype, 

29 is_integer_dtype, 

30 is_object_dtype, 

31 is_string_dtype, 

32 pandas_dtype, 

33) 

34 

35from pandas.core.arrays.masked import ( 

36 BaseMaskedArray, 

37 BaseMaskedDtype, 

38) 

39 

40if TYPE_CHECKING: 40 ↛ 41line 40 didn't jump to line 41, because the condition on line 40 was never true

41 import pyarrow 

42 

43 

44T = TypeVar("T", bound="NumericArray") 

45 

46 

47class NumericDtype(BaseMaskedDtype): 

48 _default_np_dtype: np.dtype 

49 _checker: Callable[[Any], bool] # is_foo_dtype 

50 

51 def __repr__(self) -> str: 

52 return f"{self.name}Dtype()" 

53 

54 @cache_readonly 

55 def is_signed_integer(self) -> bool: 

56 return self.kind == "i" 

57 

58 @cache_readonly 

59 def is_unsigned_integer(self) -> bool: 

60 return self.kind == "u" 

61 

62 @property 

63 def _is_numeric(self) -> bool: 

64 return True 

65 

66 def __from_arrow__( 

67 self, array: pyarrow.Array | pyarrow.ChunkedArray 

68 ) -> BaseMaskedArray: 

69 """ 

70 Construct IntegerArray/FloatingArray from pyarrow Array/ChunkedArray. 

71 """ 

72 import pyarrow 

73 

74 from pandas.core.arrays.arrow._arrow_utils import ( 

75 pyarrow_array_to_numpy_and_mask, 

76 ) 

77 

78 array_class = self.construct_array_type() 

79 

80 pyarrow_type = pyarrow.from_numpy_dtype(self.type) 

81 if not array.type.equals(pyarrow_type): 

82 # test_from_arrow_type_error raise for string, but allow 

83 # through itemsize conversion GH#31896 

84 rt_dtype = pandas_dtype(array.type.to_pandas_dtype()) 

85 if rt_dtype.kind not in ["i", "u", "f"]: 

86 # Could allow "c" or potentially disallow float<->int conversion, 

87 # but at the moment we specifically test that uint<->int works 

88 raise TypeError( 

89 f"Expected array of {self} type, got {array.type} instead" 

90 ) 

91 

92 array = array.cast(pyarrow_type) 

93 

94 if isinstance(array, pyarrow.Array): 

95 chunks = [array] 

96 else: 

97 # pyarrow.ChunkedArray 

98 chunks = array.chunks 

99 

100 results = [] 

101 for arr in chunks: 

102 data, mask = pyarrow_array_to_numpy_and_mask(arr, dtype=self.numpy_dtype) 

103 num_arr = array_class(data.copy(), ~mask, copy=False) 

104 results.append(num_arr) 

105 

106 if not results: 

107 return array_class( 

108 np.array([], dtype=self.numpy_dtype), np.array([], dtype=np.bool_) 

109 ) 

110 elif len(results) == 1: 

111 # avoid additional copy in _concat_same_type 

112 return results[0] 

113 else: 

114 return array_class._concat_same_type(results) 

115 

116 @classmethod 

117 def _str_to_dtype_mapping(cls) -> Mapping[str, NumericDtype]: 

118 raise AbstractMethodError(cls) 

119 

120 @classmethod 

121 def _standardize_dtype(cls, dtype: NumericDtype | str | np.dtype) -> NumericDtype: 

122 """ 

123 Convert a string representation or a numpy dtype to NumericDtype. 

124 """ 

125 if isinstance(dtype, str) and (dtype.startswith(("Int", "UInt", "Float"))): 

126 # Avoid DeprecationWarning from NumPy about np.dtype("Int64") 

127 # https://github.com/numpy/numpy/pull/7476 

128 dtype = dtype.lower() 

129 

130 if not isinstance(dtype, NumericDtype): 

131 mapping = cls._str_to_dtype_mapping() 

132 try: 

133 dtype = mapping[str(np.dtype(dtype))] 

134 except KeyError as err: 

135 raise ValueError(f"invalid dtype specified {dtype}") from err 

136 return dtype 

137 

138 @classmethod 

139 def _safe_cast(cls, values: np.ndarray, dtype: np.dtype, copy: bool) -> np.ndarray: 

140 """ 

141 Safely cast the values to the given dtype. 

142 

143 "safe" in this context means the casting is lossless. 

144 """ 

145 raise AbstractMethodError(cls) 

146 

147 

148def _coerce_to_data_and_mask(values, mask, dtype, copy, dtype_cls, default_dtype): 

149 checker = dtype_cls._checker 

150 

151 inferred_type = None 

152 

153 if dtype is None and hasattr(values, "dtype"): 

154 if checker(values.dtype): 

155 dtype = values.dtype 

156 

157 if dtype is not None: 

158 dtype = dtype_cls._standardize_dtype(dtype) 

159 

160 cls = dtype_cls.construct_array_type() 

161 if isinstance(values, cls): 

162 values, mask = values._data, values._mask 

163 if dtype is not None: 

164 values = values.astype(dtype.numpy_dtype, copy=False) 

165 

166 if copy: 

167 values = values.copy() 

168 mask = mask.copy() 

169 return values, mask, dtype, inferred_type 

170 

171 values = np.array(values, copy=copy) 

172 inferred_type = None 

173 if is_object_dtype(values.dtype) or is_string_dtype(values.dtype): 

174 inferred_type = lib.infer_dtype(values, skipna=True) 

175 if inferred_type == "empty": 

176 pass 

177 elif inferred_type == "boolean": 

178 name = dtype_cls.__name__.strip("_") 

179 raise TypeError(f"{values.dtype} cannot be converted to {name}") 

180 

181 elif is_bool_dtype(values) and checker(dtype): 

182 values = np.array(values, dtype=default_dtype, copy=copy) 

183 

184 elif not (is_integer_dtype(values) or is_float_dtype(values)): 

185 name = dtype_cls.__name__.strip("_") 

186 raise TypeError(f"{values.dtype} cannot be converted to {name}") 

187 

188 if values.ndim != 1: 

189 raise TypeError("values must be a 1D list-like") 

190 

191 if mask is None: 

192 mask = libmissing.is_numeric_na(values) 

193 else: 

194 assert len(mask) == len(values) 

195 

196 if mask.ndim != 1: 

197 raise TypeError("mask must be a 1D list-like") 

198 

199 # infer dtype if needed 

200 if dtype is None: 

201 dtype = default_dtype 

202 else: 

203 dtype = dtype.type 

204 

205 # we copy as need to coerce here 

206 if mask.any(): 

207 values = values.copy() 

208 values[mask] = cls._internal_fill_value 

209 if inferred_type in ("string", "unicode"): 

210 # casts from str are always safe since they raise 

211 # a ValueError if the str cannot be parsed into a float 

212 values = values.astype(dtype, copy=copy) 

213 else: 

214 values = dtype_cls._safe_cast(values, dtype, copy=False) 

215 

216 return values, mask, dtype, inferred_type 

217 

218 

219class NumericArray(BaseMaskedArray): 

220 """ 

221 Base class for IntegerArray and FloatingArray. 

222 """ 

223 

224 _dtype_cls: type[NumericDtype] 

225 

226 def __init__( 

227 self, values: np.ndarray, mask: npt.NDArray[np.bool_], copy: bool = False 

228 ) -> None: 

229 checker = self._dtype_cls._checker 

230 if not (isinstance(values, np.ndarray) and checker(values.dtype)): 

231 descr = ( 

232 "floating" 

233 if self._dtype_cls.kind == "f" # type: ignore[comparison-overlap] 

234 else "integer" 

235 ) 

236 raise TypeError( 

237 f"values should be {descr} numpy array. Use " 

238 "the 'pd.array' function instead" 

239 ) 

240 if values.dtype == np.float16: 

241 # If we don't raise here, then accessing self.dtype would raise 

242 raise TypeError("FloatingArray does not support np.float16 dtype.") 

243 

244 super().__init__(values, mask, copy=copy) 

245 

246 @cache_readonly 

247 def dtype(self) -> NumericDtype: 

248 mapping = self._dtype_cls._str_to_dtype_mapping() 

249 return mapping[str(self._data.dtype)] 

250 

251 @classmethod 

252 def _coerce_to_array( 

253 cls, value, *, dtype: DtypeObj, copy: bool = False 

254 ) -> tuple[np.ndarray, np.ndarray]: 

255 dtype_cls = cls._dtype_cls 

256 default_dtype = dtype_cls._default_np_dtype 

257 mask = None 

258 values, mask, _, _ = _coerce_to_data_and_mask( 

259 value, mask, dtype, copy, dtype_cls, default_dtype 

260 ) 

261 return values, mask 

262 

263 @classmethod 

264 def _from_sequence_of_strings( 

265 cls: type[T], strings, *, dtype: Dtype | None = None, copy: bool = False 

266 ) -> T: 

267 from pandas.core.tools.numeric import to_numeric 

268 

269 scalars = to_numeric(strings, errors="raise") 

270 return cls._from_sequence(scalars, dtype=dtype, copy=copy) 

271 

272 _HANDLED_TYPES = (np.ndarray, numbers.Number)