如果事先知道大小，将矩阵从 CSV 文件读取到 NumPy 的快速方法是什么？

问：

我厌倦了在使用 .在另一个 SO 问题之后，我执行了 perfplot 测试，同时包括一些其他方法。结果（源代码在末尾）：csvnumpy.genfromtxt

最大输入大小的结果显示最佳方法是 ，即：read_csv

def load_read_csv(path: str):
    with open(path, 'r') as csv_file:
        reader = csv.reader(csv_file)
        matrix = None
        first_row = True
        for row_index, row in enumerate(reader):
            if first_row:
                size = len(row)
                matrix = np.zeros((size, size), dtype=int)
                first_row = False
            matrix[row_index] = row

    return matrix

现在我怀疑逐行读取文件，将其转换为字符串列表，然后调用列表中的每个项目并将其添加到 NumPy 矩阵中是最好的方法。int()

这个函数可以进一步优化吗，或者是否有一些用于 CSV 加载的快速库（如 Java 中的 Univocity 解析器），或者可能只是一个专用的 NumPy 函数？

测试源代码：

import perfplot
import csv
import numpy as np
import pandas as pd


def load_read_csv(path: str):
    with open(path, 'r') as csv_file:
        reader = csv.reader(csv_file)
        matrix = None
        first_row = True
        for row_index, row in enumerate(reader):
            if first_row:
                size = len(row)
                matrix = np.zeros((size, size), dtype=int)
                first_row = False
            # matrix[row_index] = [int(item) for item in row]
            matrix[row_index] = row

    return matrix


def load_loadtxt(path: str):
    matrix = np.loadtxt(path, dtype=int, comments=None, delimiter=",", encoding="utf-8")
    return matrix


def load_genfromtxt(path: str):
    matrix = np.genfromtxt(path, dtype=int, comments=None, delimiter=",", deletechars=None, replace_space=None, encoding="utf-8")
    return matrix


def load_pandas(path: str):
    df = pd.read_csv(path, header=None, dtype=np.int32)
    return df.values


def load_pandas_engine_pyarrow(path: str):
    df = pd.read_csv(path, header=None, dtype=np.int32, engine='pyarrow')
    return df.values


def load_pandas_engine_python(path: str):
    df = pd.read_csv(path, header=None, dtype=np.int32, engine='python')
    return df.values


def setup(n):
    matrix = np.random.randint(0, 10000, size=(n, n), dtype=int)
    filename = f"square_matrix_of_size_{n}.csv"
    np.savetxt(filename, matrix, fmt="%d", delimiter=",")
    return filename


b = perfplot.bench(
    setup=setup,  # or setup=np.random.rand
    kernels=[
        load_read_csv,
        load_loadtxt,
        load_genfromtxt,
        load_pandas,
        load_pandas_engine_pyarrow,
        load_pandas_engine_python
    ],
    n_range=[2 ** k for k in range(15)]
)
b.save("out.png")
b.show()