Created
December 31, 2024 21:57
-
-
Save beatzxbt/fd202184e03fa8a05a7d8ab1ff3c7531 to your computer and use it in GitHub Desktop.
uber fast list[list[str]] -> np.ndarray[np.double]
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| cimport numpy as np | |
| from libc.stdint cimport uint16_t | |
| from libc.stdlib cimport strtod | |
| from cpython.unicode cimport PyUnicode_AsUTF8 | |
| cpdef np.ndarray[np.double_t, ndim=2] parse_list_list_str_to_floats(list[list[str]] data): | |
| """ | |
| Parses a list of lists of strings into a NumPy array of floats. | |
| Parameters: | |
| data (list of lists of strings): Input data, where each inner list contains strings. | |
| Returns: | |
| np.ndarray : NumPy array of shape (n, m) with dtype float64. | |
| """ | |
| cdef uint16_t i, j | |
| cdef uint16_t n = len(data) | |
| cdef uint16_t m = len(data[0]) | |
| cdef np.ndarray[np.double_t, ndim=2] result = np.empty((n, m), dtype=np.double) | |
| cdef list[str] row | |
| cdef double value | |
| cdef str item | |
| cdef const char* s | |
| cdef char* endptr | |
| if n == 0: | |
| return np.empty((0, 0), dtype=np.float64) | |
| for i in range(n): | |
| row = data[i] | |
| if len(row) != m: | |
| raise ValueError("All inner lists must have the same length.") | |
| for j in range(m): | |
| item = row[j] | |
| s = PyUnicode_AsUTF8(item) | |
| value = strtod(s, &endptr) | |
| if endptr == s: | |
| raise ValueError(f"Invalid float value: '{item}' at position ({i}, {j}).") | |
| result[i, j] = value | |
| return result |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment