Last active
January 3, 2018 21:42
-
-
Save rsignell-usgs/1009ac7fd4193a56ddd581cf11701688 to your computer and use it in GitHub Desktop.
This file contains 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
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"# Convert NetCDF4 file to HSDS, with custom chunking" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Read netcdf4 files using xarray, so that we can read the attributes" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"import xarray as xr\n", | |
"import numpy as np\n", | |
"import h5pyd as h5py" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"infile = '/notebooks/rsignell/data/CFSR/tmp2m_2months.nc'\n", | |
"outfile = '/home/rsignell/tmp2m_2months_rechunked.nc'\n", | |
"#outfile = '/notebooks/rsignell/data/CFSR/foo.nc'" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"ds = xr.open_dataset(infile, decode_cf=False)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"Frozen(OrderedDict([('latitude', <xarray.IndexVariable 'latitude' (latitude: 880)>\n", | |
"array([-89.843515, -89.640798, -89.436886, ..., 89.436886, 89.640798,\n", | |
" 89.843515])\n", | |
"Attributes:\n", | |
" units: degrees_north\n", | |
" long_name: latitude), ('longitude', <xarray.IndexVariable 'longitude' (longitude: 1760)>\n", | |
"array([ 0.000000e+00, 2.045452e-01, 4.090904e-01, ..., 3.593859e+02,\n", | |
" 3.595905e+02, 3.597950e+02])\n", | |
"Attributes:\n", | |
" units: degrees_east\n", | |
" long_name: longitude), ('time', <xarray.IndexVariable 'time' (time: 1416)>\n", | |
"array([ 1.483232e+09, 1.483236e+09, 1.483240e+09, ..., 1.488319e+09,\n", | |
" 1.488323e+09, 1.488326e+09])\n", | |
"Attributes:\n", | |
" units: seconds since 1970-01-01 00:00:00.0 0:00\n", | |
" long_name: verification time generated by wgrib2 functi...\n", | |
" reference_time: 1483228800.0\n", | |
" reference_time_type: 0\n", | |
" reference_date: 2017.01.01 00:00:00 UTC\n", | |
" reference_time_description: kind of product unclear, reference date is v...\n", | |
" time_step_setting: auto\n", | |
" time_step: 3600.0), ('TMP_2maboveground', <xarray.Variable (time: 1416, latitude: 880, longitude: 1760)>\n", | |
"[2193100800 values with dtype=float32]\n", | |
"Attributes:\n", | |
" _FillValue: 9.999e+20\n", | |
" short_name: TMP_2maboveground\n", | |
" long_name: Temperature\n", | |
" level: 2 m above ground\n", | |
" units: K)]))" | |
] | |
}, | |
"execution_count": 4, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"ds.variables" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"f = h5py.File(outfile, 'w')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"for key, val in ds.attrs.items():\n", | |
" if isinstance(val,str):\n", | |
" f.attrs[key]=val\n", | |
" else:\n", | |
" f.attrs.create(key, val, (), dtype=val.dtype)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 7, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"'COARDS'" | |
] | |
}, | |
"execution_count": 7, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"f.attrs['Conventions']" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 8, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"(880,)" | |
] | |
}, | |
"execution_count": 8, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"ds['latitude'].data.shape" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 9, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"dtype('float64')" | |
] | |
}, | |
"execution_count": 9, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"ds['latitude'].data.dtype" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 10, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"latitude (880,) None\n", | |
"longitude (1760,) None\n", | |
"time (1416,) None\n", | |
"TMP_2maboveground (1416, 880, 1760) None\n" | |
] | |
} | |
], | |
"source": [ | |
"for key, val in ds.variables.items():\n", | |
" print(key, val.shape, val.chunks)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Just specify the chunk sizes for those vars that need rechunking" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"ds['TMP_2maboveground'].attrs['chunks'] = (4, 220, 440)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"latitude\n", | |
"units degrees_north\n", | |
"long_name latitude\n", | |
"longitude\n", | |
"units degrees_east\n", | |
"long_name longitude\n", | |
"time\n", | |
"units seconds since 1970-01-01 00:00:00.0 0:00\n", | |
"long_name verification time generated by wgrib2 function verftime()\n", | |
"reference_time 1483228800.0\n", | |
"reference_time_type 0\n", | |
"reference_date 2017.01.01 00:00:00 UTC\n", | |
"reference_time_description kind of product unclear, reference date is variable, min found reference date is given\n", | |
"time_step_setting auto\n", | |
"time_step 3600.0\n", | |
"TMP_2maboveground\n" | |
] | |
} | |
], | |
"source": [ | |
"for key, val in ds.variables.items():\n", | |
" print(key)\n", | |
" dset = f.create_dataset(key, data=val.data, chunks=val.chunks)\n", | |
" for k,v in val.attrs.items():\n", | |
" print(k,v)\n", | |
" if isinstance(v,str):\n", | |
" dset.attrs[k] = v\n", | |
" else:\n", | |
" dset.attrs.create(k, np.array(v))" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Creating dimension scales\n", | |
"dset.dims.set_scale(f['/latitude'])\n", | |
"dset.dims.set_scale(f['/time'])\n", | |
"dset.dims.set_scale(f['/longitude'])\n", | |
"\n", | |
"# Attaching dimension scales to dataset: /TMP_2maboveground\n", | |
"f['/TMP_2maboveground'].dims[0].attach_scale(f['/time'])\n", | |
"f['/TMP_2maboveground'].dims[1].attach_scale(f['/latitude'])\n", | |
"f['/TMP_2maboveground'].dims[2].attach_scale(f['/longitude'])\n", | |
"\n", | |
"f.close()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python [conda env:h5pyd]", | |
"language": "python", | |
"name": "conda-env-h5pyd-py" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.6.3" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment