import numpy as np import pandas as pd def read_asc(filepath): usecols = [0, 4] # 仅读取第0列和第4列 chunksize = 100000 # 每次读取100000行数据 for chunk in pd.read_csv(filepath, skiprows=4, encoding="gbk", engine='python', sep=' ', delimiter=None, index_col=False, header=None, skipinitialspace=True, usecols=usecols, chunksize=chunksize): file = np.array(chunk) data = read_message(file) filter_step_size(data) def read_message(file): mask = file[:, 1] == "107" data = file[mask] return data def filter_step_size(data): diff = np.diff(data[:, 0].astype(float)) # 将第0列转换为浮点数类型 mask = np.logical_and(0.090 < diff, diff < 0.110) success_sum = np.count_nonzero(mask) fail_sum = len(mask) - success_sum result = np.column_stack((data[:-1, 0], data[1:, 0], diff)) result = result[~mask] print("报文通过数: {}".format(success_sum)) print("报文未通过数: {}".format(fail_sum)) print("未通过前一项值：未通过后一项值：差值：") print(result) if __name__ == '__main__': read_asc("E:\\package\\107(2).asc") 增加条件，在读取asc文件后，读取第四列="Rx",第五列="1a7"的第一列数据

你可以在`read_message`函数中添加一个条件来筛选第四列为"Rx"和第五列为"1a7"的数据。修改后的代码如下：

def read_message(file):
    mask = np.logical_and(file[:, 3] == "Rx", file[:, 4] == "1a7")
    data = file[mask]
    return data

这样，`read_message`函数将会返回第四列为"Rx"和第五列为"1a7"的数据。

相关问题

import numpy as np import pandas as pd def read_asc(filepath): usecols = [0, 4] # 仅读取第0列和第4列 chunksize = 100000 # 每次读取100000行数据 for chunk in pd.read_csv(filepath, skiprows=4, encoding="gbk", engine='python', sep=' ', delimiter=None, index_col=False, header=None, skipinitialspace=True, usecols=usecols, chunksize=chunksize): file = np.array(chunk) data = read_message(file) filter_step_size(data) def read_message(file): mask = file[:, 1] == "107" data = file[mask] return data def filter_step_size(data): diff = np.diff(data[:, 0].astype(float)) # 将第0列转换为浮点数类型 mask = np.logical_and(0.090 < diff, diff < 0.110) success_sum = np.count_nonzero(mask) fail_sum = len(mask) - success_sum result = np.column_stack((data[:-1, 0], data[1:, 0], diff)) result = result[~mask] print("报文通过数: {}".format(success_sum)) print("报文未通过数: {}".format(fail_sum)) print("未通过前一项值：未通过后一项值：差值：") print(result) if __name__ == '__main__': read_asc("E:\\package\\107(2).asc") 增加条件，将读取第0列和第四列，并读取第四列值为107的数据。改为读取第0列，第三列和第四列，并读取第三列为Rx且第四列为107的数据

修改后的代码如下：

import numpy as np
import pandas as pd


def read_asc(filepath):
    usecols = [0, 3, 4]  # 仅读取第0列、第3列和第4列
    chunksize = 100000  # 每次读取100000行数据

    for chunk in pd.read_csv(filepath, skiprows=4, encoding="gbk", engine='python', sep=' ', delimiter=None,
                             index_col=False, header=None, skipinitialspace=True, usecols=usecols, chunksize=chunksize):
        file = np.array(chunk)

        data = read_message(file)
        filter_step_size(data)


def read_message(file):
    mask = np.logical_and(file[:, 2] == "Rx", file[:, 3] == "107")  # 第三列为Rx且第四列为107
    data = file[mask]
    return data


def filter_step_size(data):
    diff = np.diff(data[:, 0].astype(float))  # 将第0列转换为浮点数类型
    mask = np.logical_and(0.090 < diff, diff < 0.110)
    success_sum = np.count_nonzero(mask)
    fail_sum = len(mask) - success_sum

    result = np.column_stack((data[:-1, 0], data[1:, 0], diff))
    result = result[~mask]

    print("报文通过数: {}".format(success_sum))
    print("报文未通过数: {}".format(fail_sum))
    print("未通过前一项值：未通过后一项值：差值：")
    print(result)


if __name__ == '__main__':
    read_asc("E:\\package\\107(2).asc")

这样修改后的代码会读取第0列、第3列和第4列，并且只读取第三列为"Rx"且第四列为"107"的数据。

import numpy as np import pandas as pd def read_asc(filepath): usecols = [0, 3, 4] # 仅读取第0列和第4列 chunksize = 100000 # 每次读取100000行数据 for chunk in pd.read_csv(filepath, skiprows=4, encoding="gbk", engine='python', sep=' ', delimiter=None, index_col=False, header=None, skipinitialspace=True, usecols=usecols, chunksize=chunksize): file = np.array(chunk) data = read_message(file) filter_step_size(data) def read_message(file): mask = np.logical_and(file[:, 3] == "Rx", file[:, 4] == "1a7") data = file[mask] return data def filter_step_size(data): diff = np.diff(data[:, 0].astype(float)) # 将第0列转换为浮点数类型 mask = np.logical_and(0.090 < diff, diff < 0.110) success_sum = np.count_nonzero(mask) fail_sum = len(mask) - success_sum result = np.column_stack((data[:-1, 0], data[1:, 0], diff)) result = result[~mask] print("报文通过数: {}".format(success_sum)) print("报文未通过数: {}".format(fail_sum)) print("未通过前一项值：未通过后一项值：差值：") print(result) if __name__ == '__main__': read_asc("E:\\package\\107(2).asc") 这段代码报错”index 3 is out of bounds for axis 1 with size 3“，修改优化

这个错误是因为你尝试访问一个超出数组索引范围的列。根据你的代码，`usecols`列表中只包含了0、3、4三个列的索引，但是`file`数组中的列索引是从0开始的，所以你需要将`usecols`中的索引值减去1。

修改后的代码如下：

def read_asc(filepath):
    usecols = [1, 4, 5]  # 仅读取第0列和第4列
    chunksize = 100000  # 每次读取100000行数据

    for chunk in pd.read_csv(filepath, skiprows=4, encoding="gbk", engine='python', sep=' ', delimiter=None,
                             index_col=False, header=None, skipinitialspace=True, usecols=usecols, chunksize=chunksize):
        file = np.array(chunk)

        data = read_message(file)
        filter_step_size(data)

这样修改后，`usecols`列表中的索引值就与实际的列索引对应了。