python - 如何从数据文件中读取指定间隔的行？

Question

我需要读取一个测试文件并以新的 HDF5 文件格式存储数据。到目前为止，我已经成功地完成了这项工作，但现在我需要将数据拆分为不同的组。让我解释。数据文件如下所示:

Generated by trjconv : P/L=1/400 t=   0.00000
11214
    1P1     aP1    1  80.48  35.36   4.25
    2P1     aP1    2  37.45   3.92   3.96
    3P2     aP2    3  18.53  -9.69   4.68
    4P2     aP2    4  55.39  74.34   4.60
    5P3     aP3    5  22.11  68.71   3.85
    6P3     aP3    6  -4.13  24.04   3.73
    7P4     aP4    7  40.16   6.39   4.73
    8P4     aP4    8  -5.40  35.73   4.85
    9P5     aP5    9  36.67  22.45   4.08
   10P5     aP5   10  -3.68 -10.66   4.18
   11P6     aP6   11  35.95  36.43   5.15
   12P6     aP6   12  57.17   3.88   5.08
   13P7     aP7   13 -23.64  50.44   4.32
   14P7     aP7   14   6.78   8.24   4.36
   15LI     aLI   15  21.34  50.63   5.21
   16LI     aLI   16  16.29  -1.34   5.28
   17LI     aLI   17  22.26  71.25   5.40
   18LI     aLI   18  19.76  10.38   5.34
   19LI     aLI   19  78.62  11.13   5.69
   20LI     aLI   20  22.14  59.70   4.92
   21LI     aLI   21  15.65  47.28   5.22
   22LI     aLI   22  82.41   2.09   5.24
   23LI     aLI   23  16.87 -11.68   5.35

您可以从第一列看到每一行都有其唯一的 id 。到目前为止，我一直在考虑将它作为一个数据集，但现在我需要将行拆分为 id * 电话 和 ID 李分成不同的组。我有整个数据集的运行代码，但我不确定是否可以修改以解决当前问题。代码

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import struct
import numpy as np
import h5py
import re

csv_file = 'com'
fmtstring = '7s 8s 5s 7s 7s 7s'
fieldstruct = struct.Struct(fmtstring)
parse = fieldstruct.unpack_from
# Format for footer
fmtstring1 = '10s 10s 10s'
fieldstruct1 = struct.Struct(fmtstring1)
parse1 = fieldstruct1.unpack_from

with open(csv_file, 'r') as f, \
    h5py.File('test.h5', 'w') as hdf:
    ## Particles group with the attributes
    particles_grp = hdf.require_group('particles/lipids/box')
    particles_grp.attrs['dimension'] = 3
    particles_grp.attrs['boundary'] = ['periodic', 'periodic', 'periodic']
    pos_grp = particles_grp.require_group('positions')
    edge_grp = particles_grp.require_group('edges')
    ## h5md group with the attributes
    h5md_grp = hdf.require_group('h5md')
    h5md_grp.attrs['version'] = 1.0
    author_grp = h5md_grp.require_group('author')
    author_grp.attrs['author'] = 'foo', 'email=foo@googlemail.com'
    creator_grp = h5md_grp.require_group('creator')
    creator_grp.attrs['name'] = 'foo'
    creator_grp.attrs['version'] = 1.0
    # datasets with known sizes
    ds_time = pos_grp.create_dataset('time', dtype="f", shape=(0,),
                                           maxshape=(None,), compression='gzip', 
                                           shuffle=True)
    ds_step = pos_grp.create_dataset('step', dtype=np.uint64, shape=(0,),
                                           maxshape=(None,), compression='gzip',
                                           shuffle=True)
    ds_protein = None
    ds_lipid = None
    # datasets in edge group
    edge_ds_time = edge_grp.create_dataset('time', dtype="f", shape=(0,),
                                           maxshape=(None,), compression='gzip', 
                                           shuffle=True)
    edge_ds_step = edge_grp.create_dataset('step', dtype="f", shape=(0,),
                                           maxshape=(None,), compression='gzip', 
                                           shuffle=True)
    edge_ds_value = None

    edge_data = edge_grp.require_dataset('box_size', dtype=np.float32, shape=(0,3),
                                              maxshape=(None,3), compression='gzip', 
                                              shuffle=True)
    
    step = 0
    while True:
        header = f.readline()
        m = re.search("t= *(.*)$", header)
        if m:
            time = float(m.group(1))
        else:
            print("End Of File")
            break

        # get number of data rows, i.e., number of particles
        nparticles = int(f.readline())
        # read data lines and store in array
        arr = np.empty(shape=(nparticles, 3), dtype=np.float32)
        for row in range(nparticles):
            fields = parse( f.readline().encode('utf-8') )
            arr[row] = np.array((float(fields[3]), float(fields[4]), float(fields[5])))
        if nparticles > 0:
            # create a resizable dataset upon the first iteration
            if not ds_lipid:
## It is reading the whole dataset
                ds_protein = pos_grp.create_dataset('lipid', dtype=np.float32,
                                                        shape=(0, nparticles, 3), maxshape=(None, nparticles, 3),
                                                        chunks=(1, nparticles, 3), compression='gzip', shuffle=True)
                edge_ds_value = edge_grp.create_dataset('value', dtype=np.float32,
                                                        shape=(0, 3), maxshape=(None, 3),chunks=(1, 3), compression='gzip', shuffle=True)
            # append this sample to the datasets
            ds_time.resize(step + 1, axis=0)
            ds_step.resize(step + 1, axis=0)
            ds_protein.resize(step + 1, axis=0)
            # append the datasets in edge group
            edge_ds_time.resize(step + 1, axis=0)
            edge_ds_step.resize(step + 1, axis=0)
            edge_ds_value.resize(step + 1, axis=0)
            
            ds_time[step] = time
            ds_step[step] = step
            ds_protein[step] = arr
            edge_ds_time[step] = time
            edge_ds_step[step] = step

        footer = parse1( f.readline().encode('utf-8') )
        dat = np.array(footer).astype(float).reshape(1,3)
        new_size = edge_data.shape[0] + 1
        edge_data.resize(new_size, axis=0)
        edge_data[new_size-1 : new_size, :] = dat
        step += 1
        #=============================================================================

让我稍微解释一下代码。 n粒子逐行读取整个文件并将它们存储在 中ds_蛋白质 .一帧中的总行数为 11214，然后在 10 帧中重复，这里我没有显示。准确地说，我只想要带有 的行电话 要在 中读取的 ID ds_蛋白质 ，在一个数据集中只有 14 个，在 中剩下 11200 个ds_lipid .有什么方法可以使用索引或任何条件来做到这一点，因为我不想拆分文本文件？

Answer 1

首先，警告...你定义了 ds_protein = None在第 45 行，然后在第 81 行创建数据集时重新定义(对于 ds_lipid = None 也是如此)。不确定这会如您所愿。请参阅稍后有关检查数据集是否存在的评论。
当前您将所有数据添加到数组 arr ，然后加载 ds_蛋白质从那个数组。由于没有保存第一列数据，所以需要使用@white's建议:检查fields[0]中的值当你阅读每一行时。代码中的第 75 行将数据解析为 fields多变的。每行的第一列变为 fields[0] .检查该值。如果它有'P'，则将它添加到 的数组中。 ds_蛋白质数据集。如果它有 'LI'，则为 添加一个数组ds_lipid 数据集。
获得蛋白质和脂质数据后，您需要修改方法以创建数据集。现在您使用 .create_dataset()在 while 循环中，它将通过循环第二次发出错误。为了避免这种情况，我在适当的组中添加了对每个数据集名称的检查。
修改后的代码如下。

    # get number of data rows, i.e., number of particles
    nparticles = int(f.readline())
    # read data lines and store in array
    arr_protein = np.empty(shape=(nparticles, 3), dtype=np.float32)
    arr_lipid = np.empty(shape=(nparticles, 3), dtype=np.float32)
    protein_cnt, lipid_cnt = 0, 0
    for row in range(nparticles):
        fields = parse( f.readline().encode('utf-8') )
        if 'P' in str(fields[0]):
            arr_protein[protein_cnt] = np.array((float(fields[3]), float(fields[4]), float(fields[5])))
            protein_cnt += 1
        elif 'LI' in str(fields[0]):
            arr_lipid[lipid_cnt] = np.array((float(fields[3]), float(fields[4]), float(fields[5])))
            lipid_cnt += 1

    arr_protein = arr_protein[:protein_cnt,:]  ## New    
    arr_lipid = arr_lipid[:lipid_cnt,:]        ## New      

    if nparticles > 0:
        # create resizable datasets upon the first iteration
        if 'protein' not in pos_grp.keys():
            ds_protein = pos_grp.create_dataset('protein', dtype=np.float32,
                                                    shape=(0, protein_cnt, 3), maxshape=(None, protein_cnt, 3),
                                                    chunks=(1, protein_cnt, 3), compression='gzip', shuffle=True)
        if 'lipid' not in pos_grp.keys():
            ds_lipid   = pos_grp.create_dataset('lipid', dtype=np.float32,
                                                    shape=(0, lipid_cnt, 3), maxshape=(None, lipid_cnt, 3),                                                        
                                                    chunks=(1, lipid_cnt, 3), compression='gzip', shuffle=True)
        if 'value' not in edge_grp.keys():
             edge_ds_value = edge_grp.create_dataset('value', dtype=np.float32,
                                                    shape=(0, 3), maxshape=(None, 3),
                                                    chunks=(1, 3), compression='gzip', shuffle=True)
        # append this sample to the datasets
        ds_time.resize(step + 1, axis=0)
        ds_step.resize(step + 1, axis=0)
        ds_protein.resize(step + 1, axis=0) ## Modified
        ds_lipid.resize(step + 1, axis=0)   ## Modified
        # append the datasets in edge group
        edge_ds_time.resize(step + 1, axis=0)
        edge_ds_step.resize(step + 1, axis=0)
        edge_ds_value.resize(step + 1, axis=0)
        
        ds_time[step] = time
        ds_step[step] = step
        ds_protein[step] = arr_protein ## Modified
        ds_lipid[step] = arr_lipid     ## Modified
        edge_ds_time[step] = time
        edge_ds_step[step] = step