Skip to content

compress temporary *.npy files with gzip to give *.npy.gz files #1171

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
erikvansebille merged 3 commits into from
May 16, 2022
Merged

compress temporary *.npy files with gzip to give *.npy.gz files #1171

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
199e39c
compress temporary *.npy files with gzip to give *.npy.gz files
JamiePringle May 14, 2022
be82536
Fixing PEP8 errors
erikvansebille May 16, 2022
2005e70
Fixing small bug in reading gzipped files
erikvansebille May 16, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 5 additions & 4 deletions parcels/particlefile/baseparticlefile.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
import string
from abc import ABC
from abc import abstractmethod
import gzip

import numpy as np

Expand Down Expand Up @@ -235,14 +236,14 @@ def dump_dict_to_npy(self, data_dict, data_dict_once):
os.makedirs(self.tempwritedir)

if len(data_dict) > 0:
tmpfilename = os.path.join(self.tempwritedir, str(len(self.file_list)) + ".npy")
with open(tmpfilename, 'wb') as f:
tmpfilename = os.path.join(self.tempwritedir, str(len(self.file_list)) + ".npy.gz")
with gzip.open(tmpfilename, 'wb') as f:
np.save(f, data_dict)
self.file_list.append(tmpfilename)

if len(data_dict_once) > 0:
tmpfilename = os.path.join(self.tempwritedir, str(len(self.file_list)) + '_once.npy')
with open(tmpfilename, 'wb') as f:
tmpfilename = os.path.join(self.tempwritedir, str(len(self.file_list)) + '_once.npy.gz')
with gzip.open(tmpfilename, 'wb') as f:
np.save(f, data_dict_once)
self.file_list_once.append(tmpfilename)

Expand Down
7 changes: 5 additions & 2 deletions parcels/particlefile/particlefileaos.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
from glob import glob
import numpy as np
import xarray as xr
import gzip

try:
from mpi4py import MPI
Expand Down Expand Up @@ -85,7 +86,8 @@ def read_from_npy(self, file_list, n_timesteps, var, dtype):
# loop over all files
for npyfile in file_list:
try:
data_dict = np.load(npyfile, allow_pickle=True).item()
with gzip.open(npyfile, 'rb') as f:
data_dict = np.load(f, allow_pickle=True).item()
except NameError:
raise RuntimeError('Cannot combine npy files into netcdf file because your ParticleFile is '
'still open on interpreter shutdown.\nYou can use '
Expand Down Expand Up @@ -138,7 +140,8 @@ def export(self):
if os.path.exists(tempwritedir):
pset_info_local = np.load(os.path.join(tempwritedir, 'pset_info.npy'), allow_pickle=True).item()
for npyfile in pset_info_local['file_list']:
tmp_dict = np.load(npyfile, allow_pickle=True).item()
with gzip.open(npyfile, 'rb') as f:
tmp_dict = np.load(f, allow_pickle=True).item()
for i in tmp_dict['id']:
if i in n_timesteps:
n_timesteps[i] += 1
Expand Down
7 changes: 5 additions & 2 deletions parcels/particlefile/particlefilesoa.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
from glob import glob
import numpy as np
import xarray as xr
import gzip

try:
from mpi4py import MPI
Expand Down Expand Up @@ -85,7 +86,8 @@ def read_from_npy(self, file_list, n_timesteps, var, dtype):
# loop over all files
for npyfile in file_list:
try:
data_dict = np.load(npyfile, allow_pickle=True).item()
with gzip.open(npyfile, 'rb') as f:
data_dict = np.load(f, allow_pickle=True).item()
except NameError:
raise RuntimeError('Cannot combine npy files into netcdf file because your ParticleFile is '
'still open on interpreter shutdown.\nYou can use '
Expand Down Expand Up @@ -139,7 +141,8 @@ def export(self):
if os.path.exists(tempwritedir):
pset_info_local = np.load(os.path.join(tempwritedir, 'pset_info.npy'), allow_pickle=True).item()
for npyfile in pset_info_local['file_list']:
tmp_dict = np.load(npyfile, allow_pickle=True).item()
with gzip.open(npyfile, 'rb') as f:
tmp_dict = np.load(f, allow_pickle=True).item()
for i in tmp_dict['id']:
if i in n_timesteps:
n_timesteps[i] += 1
Expand Down