{"id":292496,"date":"2024-05-20T14:20:26","date_gmt":"2024-05-20T06:20:26","guid":{"rendered":""},"modified":"2024-05-20T14:20:37","modified_gmt":"2024-05-20T06:20:37","slug":"h5py-%e5%a6%82%e4%bd%95%e5%ad%98%e5%82%a8%e5%ad%97%e7%ac%a6%e4%b8%b2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/292496.html","title":{"rendered":"h5py \u5982\u4f55\u5b58\u50a8\u5b57\u7b26\u4e32"},"content":{"rendered":"

\"h5py<\/p>\n

H5PY\u53ef\u4ee5\u901a\u8fc7\u521b\u5efa\u6570\u636e\u96c6\uff08Dataset\uff09\u6765\u5b58\u50a8\u5b57\u7b26\u4e32\u3002\u5b58\u50a8\u5b57\u7b26\u4e32\u6709\u4e24\u79cd\u7c7b\u578b\uff1a\u53ef\u53d8\u957f\u5ea6\u5b57\u7b26\u4e32\u548c\u56fa\u5b9a\u957f\u5ea6\u5b57\u7b26\u4e32\u3002\u53ef\u53d8\u957f\u5ea6\u5b57\u7b26\u4e32\u4f7f\u7528H5T_VARIABLE\uff0c\u9002\u7528\u4e8e\u5b58\u50a8\u957f\u5ea6\u4e0d\u540c\u7684\u5b57\u7b26\u4e32\uff1b\u56fa\u5b9a\u957f\u5ea6\u5b57\u7b26\u4e32\u5219\u9884\u5b9a\u4e49\u4e00\u4e2a\u6700\u5927\u957f\u5ea6\uff0c\u9002\u7528\u4e8e\u5b58\u50a8\u957f\u5ea6\u76f8\u8fd1\u7684\u5b57\u7b26\u4e32<\/strong>\u3002\u8981\u5b58\u50a8\u53ef\u53d8\u957f\u5ea6\u7684\u5b57\u7b26\u4e32\u6570\u636e\uff0c\u4f60\u9700\u8981\u521b\u5efa\u4e00\u4e2a\u7279\u6b8a\u7684\u6570\u636e\u7c7b\u578b\uff0c\u7136\u540e\u5c06\u8fd9\u4e2a\u7c7b\u578b\u7528\u4f5c\u521b\u5efa\u6570\u636e\u96c6\u7684\u6570\u636e\u7c7b\u578b\u3002\u8fd9\u6837\u505a\u7684\u597d\u5904\u662fHDF5\u4f1a\u52a8\u6001\u7ba1\u7406\u6570\u636e\u6240\u9700\u7684\u7a7a\u95f4\uff0c\u9002\u5408\u4e8e\u5b57\u7b26\u4e32\u957f\u5ea6\u5dee\u5f02\u8f83\u5927\u7684\u60c5\u51b5\u3002<\/p>\n<\/p>\n

\u63a5\u4e0b\u6765\uff0c\u5c06\u8be6\u7ec6\u63cf\u8ff0\u5982\u4f55\u521b\u5efa\u8fd9\u4e24\u79cd\u7c7b\u578b\u7684\u5b57\u7b26\u4e32\u6570\u636e\u96c6\u548c\u4e00\u4e9b\u7279\u522b\u6ce8\u610f\u7684\u4e8b\u9879\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u521b\u5efa\u5b58\u50a8\u5b57\u7b26\u4e32\u7684\u6570\u636e\u96c6<\/h3>\n<\/p>\n

\u53ef\u53d8\u957f\u5ea6\u5b57\u7b26\u4e32\u6570\u636e\u96c6<\/h4>\n<\/p>\n
    \n
  1. \n

    \u5bfc\u5165h5py\u5e93\u548c\u521b\u5efa\u6587\u4ef6<\/strong>\uff1a<\/p>\n

    \u9996\u5148\uff0c\u4f60\u9700\u8981\u5bfc\u5165h5py\u5e93\u5e76\u521b\u5efa\u4e00\u4e2a\u65b0\u7684HDF5\u6587\u4ef6\u3002<\/p>\n<\/p>\n

    import h5py<\/p>\n
    \u521b\u5efa\u65b0\u7684HDF5\u6587\u4ef6<\/strong><\/h2>\n
    with h5py.File('strings.h5', 'w') as hdf_file:<\/p>\n
        # \u63a5\u4e0b\u6765\u7684\u6b65\u9aa4\u5c06\u5728\u6b64\u8fdb\u884c<\/p>\n
    <\/code><\/pre>\n<\/p>\n<\/li>\n
  2. \n
    \u5b9a\u4e49\u6570\u636e\u7c7b\u578b\u5e76\u521b\u5efa\u6570\u636e\u96c6<\/strong>\uff1a<\/p>\n
    \u4f7f\u7528h5py.special_dtype\u521b\u5efa\u4e00\u4e2a\u53ef\u53d8\u957f\u5ea6\u7684\u5b57\u7b26\u4e32\u6570\u636e\u7c7b\u578b\uff0c\u7136\u540e\u4f7f\u7528\u8fd9\u4e2a\u6570\u636e\u7c7b\u578b\u521b\u5efa\u65b0\u7684\u6570\u636e\u96c6\u3002<\/p>\n<\/p>\n
    # \u5b9a\u4e49\u53ef\u53d8\u957f\u5ea6\u7684\u5b57\u7b26\u4e32\u7c7b\u578b<\/p>\n
    dtype = h5py.special_dtype(vlen=str)<\/p>\n
    \u521b\u5efa\u6570\u636e\u96c6<\/strong><\/h2>\n
    dataset = hdf_file.create_dataset('variable_length_strings', (100,), dtype=dtype)<\/p>\n
    \u5b58\u50a8\u6570\u636e<\/strong><\/h2>\n
    dataset[0] = 'hello'<\/p>\n
    dataset[1] = 'world'<\/p>\n
    <\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n
    \u56fa\u5b9a\u957f\u5ea6\u5b57\u7b26\u4e32\u6570\u636e\u96c6<\/h4>\n<\/p>\n
      \n
    1. \n
      \u5b9a\u4e49\u56fa\u5b9a\u957f\u5ea6\u7684\u5b57\u7b26\u4e32\u7c7b\u578b<\/strong>\uff1a<\/p>\n
      \u76f4\u63a5\u4f7f\u7528numpy\u5e93\u5b9a\u4e49\u4e00\u4e2a\u56fa\u5b9a\u7684\u957f\u5ea6\uff0c\u598220\u4e2a\u5b57\u7b26\uff0c\u9009\u62e9numpy.dtype<\/code>\u4e3a'|S20'<\/code>\u3002<\/p>\n<\/p>\n
      import numpy as np<\/p>\n
      \u5b9a\u4e49\u56fa\u5b9a\u957f\u5ea6\u7684\u5b57\u7b26\u4e32\u7c7b\u578b\uff0c\u8fd9\u91cc\u8bbe\u7f6e\u4e3a20<\/strong><\/h2>\n
      dtype = np.dtype('|S20')<\/p>\n
      <\/code><\/pre>\n<\/p>\n<\/li>\n
    2. \n
      \u521b\u5efa\u6570\u636e\u96c6<\/strong>\uff1a<\/p>\n
      \u7528\u5b9a\u4e49\u597d\u7684\u56fa\u5b9a\u957f\u5ea6\u5b57\u7b26\u4e32\u7c7b\u578b\u4f5c\u4e3a\u6570\u636e\u7c7b\u578b\u53c2\u6570\u521b\u5efa\u6570\u636e\u96c6\uff0c\u5e76\u5b58\u50a8\u6570\u636e\u3002<\/p>\n<\/p>\n
      # \u521b\u5efa\u56fa\u5b9a\u957f\u5ea6\u7684\u5b57\u7b26\u4e32\u6570\u636e\u96c6<\/p>\n
      dataset = hdf_file.create_dataset('fixed_length_strings', (100,), dtype=dtype)<\/p>\n
      \u5b58\u50a8\u6570\u636e\uff0c\u8d85\u51fa\u90e8\u5206\u5c06\u88ab\u622a\u65ad<\/strong><\/h2>\n
      dataset[0] = 'hello'<\/p>\n
      dataset[1] = 'world'<\/p>\n
      <\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n
      \u4e8c\u3001\u5b58\u50a8\u548c\u8bfb\u53d6\u5b57\u7b26\u4e32<\/h3>\n<\/p>\n
      \u5b58\u50a8\u5b57\u7b26\u4e32<\/h4>\n<\/p>\n
      \u5728\u521b\u5efa\u5408\u9002\u7684\u5b57\u7b26\u4e32\u6570\u636e\u96c6\u4e4b\u540e\uff0c\u4f7f\u7528\u6570\u636e\u96c6\u5bf9\u8c61\u7684\u7d22\u5f15\u6216\u5207\u7247\u5c06\u5b57\u7b26\u4e32\u5199\u5165\u6570\u636e\u96c6\u4e2d\u3002<\/p>\n<\/p>\n
      # \u5b58\u50a8\u5355\u4e2a\u5b57\u7b26\u4e32<\/p>\n
      dataset[0] = 'example string'<\/p>\n
      \u5b58\u50a8\u591a\u4e2a\u5b57\u7b26\u4e32<\/strong><\/h2>\n
      strs = ['string1', 'string2', 'string3']<\/p>\n
      dataset[1:4] = strs<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      \u8bfb\u53d6\u5b57\u7b26\u4e32<\/h4>\n<\/p>\n
      \u8bfb\u53d6\u5b57\u7b26\u4e32\u65f6\uff0cH5PY\u5c06\u81ea\u52a8\u5904\u7406\u5b57\u7b26\u4e32\u7684\u7f16\u7801\u548c\u89e3\u7801\u3002<\/p>\n<\/p>\n
      # \u8bfb\u53d6\u5355\u4e2a\u5b57\u7b26\u4e32<\/p>\n
      str_value = dataset[0]<\/p>\n
      \u8bfb\u53d6\u4e00\u7cfb\u5217\u5b57\u7b26\u4e32<\/strong><\/h2>\n
      str_values = dataset[1:4]<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      \u4e09\u3001\u6ce8\u610f\u4e8b\u9879\u548c\u6700\u4f73\u5b9e\u8df5<\/h3>\n<\/p>\n
      \u5b57\u7b26\u4e32\u7f16\u7801<\/h4>\n<\/p>\n
      HDF5\u5e76\u4e0d\u76f4\u63a5\u652f\u6301Python\u7684unicode\u5b57\u7b26\u4e32\u7c7b\u578b\u3002\u56e0\u6b64\uff0c\u5728\u5b58\u50a8\u65f6\uff0c\u901a\u5e38\u9700\u8981\u5bf9\u5b57\u7b26\u4e32\u8fdb\u884c\u7f16\u7801\u8f6c\u6362\u4e3a\u5b57\u8282\u4e32\u3002<\/p>\n<\/p>\n
      unicode_string = '\u4f60\u597d\u4e16\u754c'<\/p>\n
      encoded_string = unicode_string.encode('utf-8')<\/p>\n
      dataset[0] = encoded_string<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      \u5b57\u7b26\u4e32\u6570\u636e\u96c6\u5c5e\u6027<\/h4>\n<\/p>\n
      \u5728\u521b\u5efa\u5b57\u7b26\u4e32\u6570\u636e\u96c6\u65f6\uff0c\u53ef\u4ee5\u8bbe\u5b9a\u6570\u636e\u96c6\u7684\u5c5e\u6027\uff0c\u4f8b\u5982\u538b\u7f29\u7ea7\u522b\u3001\u5757\u5927\u5c0f\u7b49\u3002<\/p>\n<\/p>\n
      # \u521b\u5efa\u5177\u6709\u538b\u7f29\u5c5e\u6027\u7684\u6570\u636e\u96c6<\/p>\n
      dataset = hdf_file.create_dataset(<\/p>\n
          'compressed_strings', <\/p>\n
          (100,), <\/p>\n
          dtype=dtype, <\/p>\n
          compression='gzip', <\/p>\n
          compression_opts=9<\/p>\n
      )<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      \u6027\u80fd\u8003\u8651<\/h4>\n<\/p>\n
      \u53ef\u53d8\u957f\u5ea6\u7684\u5b57\u7b26\u4e32\u6570\u636e\u96c6\u53ef\u80fd\u5728\u5b58\u50a8\u548c\u68c0\u7d22\u65f6\u6548\u7387\u8f83\u4f4e\u3002\u5982\u679c\u5b57\u7b26\u4e32\u957f\u5ea6\u8f83\u4e3a\u4e00\u81f4\uff0c\u8003\u8651\u4f7f\u7528\u56fa\u5b9a\u957f\u5ea6\u7684\u5b57\u7b26\u4e32\u6570\u636e\u96c6\u6765\u63d0\u5347\u6027\u80fd\u3002<\/p>\n<\/p>\n
      \u5bb9\u9519\u548c\u5f02\u5e38\u5904\u7406<\/h4>\n<\/p>\n
      \u64cd\u4f5cHDF5\u6587\u4ef6\u65f6\uff0c\u8981\u59a5\u5584\u5904\u7406\u5f02\u5e38\u548c\u9519\u8bef\u3002<\/p>\n<\/p>\n
      try:<\/p>\n
          # \u4f60\u7684\u64cd\u4f5c\u4ee3\u7801<\/p>\n
      except Exception as e:<\/p>\n
          print('An error occurred:', e)<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      \u5927\u6570\u636e\u91cf\u5904\u7406<\/h4>\n<\/p>\n
      \u82e5\u5b57\u7b26\u4e32\u6570\u636e\u91cf\u6781\u5927\uff0c\u8003\u8651\u4f7f\u7528\u5206\u5757\u5b58\u50a8\uff08chunking\uff09\u548c\u6570\u636e\u538b\u7f29\u3002\u8fd9\u6837\u53ef\u4ee5\u5728\u78c1\u76d8\u7a7a\u95f4\u548c\u8bfb\u5199\u6027\u80fd\u4e4b\u95f4\u53d6\u5f97\u5e73\u8861\u3002\u540c\u65f6\uff0c\u4e5f\u8981\u6ce8\u610f\u5185\u5b58\u7684\u4f7f\u7528\u60c5\u51b5\uff0c\u907f\u514d\u4e00\u6b21\u6027\u52a0\u8f7d\u8fc7\u5927\u6570\u636e\u96c6\u5bfc\u81f4\u5185\u5b58\u6ea2\u51fa\u3002<\/p>\n<\/p>\n
      \u7efc\u4e0a\u6240\u8ff0\uff0c\u901a\u8fc7\u7406\u89e3HDF5\u6587\u4ef6\u683c\u5f0f\u53cah5py\u5e93\u7684\u529f\u80fd\uff0c\u6211\u4eec\u53ef\u4ee5\u6709\u6548\u5730\u5b58\u50a8\u548c\u7ba1\u7406\u5927\u91cf\u7684\u5b57\u7b26\u4e32\u7c7b\u578b\u6570\u636e\u3002\u6839\u636e\u5b9e\u9645\u9700\u6c42\uff0c\u9009\u62e9\u53ef\u53d8\u957f\u5ea6\u6216\u56fa\u5b9a\u957f\u5ea6\u5b57\u7b26\u4e32\u6570\u636e\u96c6\uff0c\u5408\u7406\u8bbe\u7f6e\u6570\u636e\u96c6\u5c5e\u6027\uff0c\u5e76\u6ce8\u610f\u5f02\u5e38\u5904\u7406\uff0c\u90fd\u662f\u786e\u4fdd\u6570\u636e\u5b58\u50a8\u9ad8\u6548\u4e14\u9c81\u68d2\u6027\u597d\u7684\u5173\u952e\u3002<\/p>\n<\/p>\n
      \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
      1. \u5982\u4f55\u5728h5py\u4e2d\u5b58\u50a8\u5b57\u7b26\u4e32\u6570\u636e\uff1f<\/strong>
      \n\u5728h5py\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528create_dataset<\/code>\u51fd\u6570\u6765\u521b\u5efa\u4e00\u4e2a\u6570\u636e\u96c6\u6765\u5b58\u50a8\u5b57\u7b26\u4e32\u3002\u7136\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528write<\/code>\u51fd\u6570\u5c06\u5b57\u7b26\u4e32\u5199\u5165\u6570\u636e\u96c6\u4e2d\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u5b57\u7b26\u4e32\u5fc5\u987b\u5148\u8f6c\u6362\u6210\u5b57\u8282\u6570\u7ec4\uff0c\u7136\u540e\u518d\u5199\u5165\u6570\u636e\u96c6\u3002\u4f8b\u5982\uff1a<\/p>\n
      import h5py\n\n# \u521b\u5efa\u4e00\u4e2aHDF5\u6587\u4ef6\nfile = h5py.File("data.h5", "w")\n\n# \u521b\u5efa\u4e00\u4e2a\u6570\u636e\u96c6\u6765\u5b58\u50a8\u5b57\u7b26\u4e32\ndataset = file.create_dataset("str_data", shape=(1,), dtype=h5py.special_dtype(vlen=str))\n\n# \u5c06\u5b57\u7b26\u4e32\u5199\u5165\u6570\u636e\u96c6\u4e2d\nstr_data = "Hello, World!"\ndataset.write(np.array([str_data], dtype=h5py.special_dtype(vlen=str)))\n\n# \u5173\u95ed\u6587\u4ef6\nfile.close()\n<\/code><\/pre>\n
      2. \u5982\u4f55\u5c06\u591a\u4e2a\u5b57\u7b26\u4e32\u5b58\u50a8\u5230\u4e00\u4e2a\u6570\u636e\u96c6\u4e2d\uff1f<\/strong>
      \n\u5982\u679c\u8981\u5b58\u50a8\u591a\u4e2a\u5b57\u7b26\u4e32\uff0c\u53ef\u4ee5\u5c06\u591a\u4e2a\u5b57\u7b26\u4e32\u7ec4\u5408\u6210\u4e00\u4e2a\u5217\u8868\uff0c\u7136\u540e\u4e00\u6b21\u6027\u5199\u5165\u6570\u636e\u96c6\u4e2d\u3002\u4f8b\u5982\uff1a<\/p>\n
      import h5py\n\n# \u521b\u5efa\u4e00\u4e2aHDF5\u6587\u4ef6\nfile = h5py.File("data.h5", "w")\n\n# \u521b\u5efa\u4e00\u4e2a\u6570\u636e\u96c6\u6765\u5b58\u50a8\u5b57\u7b26\u4e32\ndataset = file.create_dataset("str_data", shape=(3,), dtype=h5py.special_dtype(vlen=str))\n\n# \u5c06\u591a\u4e2a\u5b57\u7b26\u4e32\u5199\u5165\u6570\u636e\u96c6\u4e2d\nstr_data = ["Hello", "World", "H5py"]\ndataset.write(np.array(str_data, dtype=h5py.special_dtype(vlen=str)))\n\n# \u5173\u95ed\u6587\u4ef6\nfile.close()\n<\/code><\/pre>\n
      3. \u5982\u4f55\u4eceh5py\u6570\u636e\u96c6\u4e2d\u8bfb\u53d6\u5b57\u7b26\u4e32\u6570\u636e\uff1f<\/strong>
      \n\u8981\u4eceh5py\u6570\u636e\u96c6\u4e2d\u8bfb\u53d6\u5b57\u7b26\u4e32\u6570\u636e\uff0c\u53ef\u4ee5\u4f7f\u7528read<\/code>\u51fd\u6570\u6765\u8bfb\u53d6\u6570\u636e\u96c6\u4e2d\u7684\u5185\u5bb9\u3002\u7136\u540e\uff0c\u53ef\u4ee5\u5c06\u5b57\u8282\u6570\u7ec4\u8f6c\u6362\u56de\u5b57\u7b26\u4e32\u3002\u4f8b\u5982\uff1a<\/p>\n
      import h5py\n\n# \u6253\u5f00HDF5\u6587\u4ef6\nfile = h5py.File("data.h5", "r")\n\n# \u8bfb\u53d6\u6570\u636e\u96c6\u4e2d\u7684\u5b57\u7b26\u4e32\u6570\u636e\ndataset = file["str_data"]\nstr_data = dataset[()]\n\n# \u5c06\u5b57\u8282\u6570\u7ec4\u8f6c\u6362\u4e3a\u5b57\u7b26\u4e32\nstr_data = str_data.astype(str)\n\n# \u6253\u5370\u5b57\u7b26\u4e32\u6570\u636e\nprint(str_data)\n\n# \u5173\u95ed\u6587\u4ef6\nfile.close()\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"H5PY\u53ef\u4ee5\u901a\u8fc7\u521b\u5efa\u6570\u636e\u96c6\uff08Dataset\uff09\u6765\u5b58\u50a8\u5b57\u7b26\u4e32\u3002\u5b58\u50a8\u5b57\u7b26\u4e32\u6709\u4e24\u79cd\u7c7b\u578b\uff1a\u53ef\u53d8\u957f\u5ea6\u5b57\u7b26\u4e32\u548c\u56fa\u5b9a\u957f\u5ea6\u5b57\u7b26\u4e32 […]","protected":false},"author":3,"featured_media":292514,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/292496"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=292496"}],"version-history":[{"count":0,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/292496\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/292514"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=292496"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=292496"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=292496"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}