%matplotlib inline
import pandas as pd
import socket
host = socket.getfqdn()
from core import load, zoom, calc, save,plots,monitor
#reload funcs after updating ./core/*.py
import importlib
importlib.reload(load)
importlib.reload(zoom)
importlib.reload(calc)
importlib.reload(save)
importlib.reload(plots)
importlib.reload(monitor)
<module 'core.monitor' from '/ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/monitor.py'>
# 'month': = 'JOBID' almost month but not really,
# If you submit the job with job scheduler, above
#below are list of enviroment variable one can pass
#%env local='2"
# local : if True run dask local cluster, if not true, put number of workers
# setted in the 'local'
# if no 'local ' given, local will be setted automatically to 'True'
#%env ychunk='2'
#%env tchunk='2'
# controls chunk. 'False' sets no modification from original netcdf file's chunk.
# ychunk=10 will group the original netcdf file to 10 by 10
# tchunk=1 will chunk the time coordinate one by one
#%env control=Ints_monitor
# name of control file to be used for computation/plots/save/
#%env file_exp=
# 'file_exp': Which 'experiment' name is it?
#. this corresopnds to intake catalog name without path and .yaml
#%env year=
# for Validation, this correspoinds to path/year/month 's year
# for monitoring, this corresponids to 'date' having * means do all files in the monitoring directory
# setting it as *0[0-9] &*1[0-9]& *[2-3][0-9], the job can be separated in three lots.
#%env month=
# for monitoring this corresponds to file path path-XIOS.{month}/
#
#%env save= proceed saving? True or False , Default is setted as True
#%env plot= proceed plotting? True or False , Default is setted as True
#%env calc= proceed computation? or just load computed result? True or False , Default is setted as True
%%time
# 'savefig': Do we save output in html? or not. keep it true.
savefig=True
client,cluster,control,catalog_url,month,year,daskreport,outputpath = load.set_control(host)
!mkdir -p $outputpath
!mkdir -p $daskreport
client
local True using host= irene5170.c-irene.mg1.tgcc.ccc.cea.fr starting dask cluster on local= True workers 16 10000000000 False not local in tgcc rome local cluster starting This code is running on irene5170.c-irene.mg1.tgcc.ccc.cea.fr using SEDNA_ALPHA_MONITOR file experiment, read from ../lib/SEDNA_ALPHA_MONITOR.yaml on year= * on month= 22 outputpath= ../results/rome_SEDNA_ALPHA_MONITOR/22/ daskreport= ../results/dask/2501644irene5170.c-irene.mg1.tgcc.ccc.cea.fr_SEDNA_ALPHA_MONITOR_22section_moni_FramS/ CPU times: user 373 ms, sys: 254 ms, total: 627 ms Wall time: 10.6 s
Client
|
Cluster
|
df=load.controlfile(control)
#Take out 'later' tagged computations
df=df[~df['Value'].str.contains('later')]
df
Value | Inputs | Equation | Zone | Plot | Colourmap | MinMax | Unit | Oldname | Unnamed: 10 | |
---|---|---|---|---|---|---|---|---|---|---|
3_Section | gridS.vosaline,gridT.votemper,gridV.vomecrty,p... | data.drop_vars('vozocrtx') | FramS | section | None | {'vosaline': (33,36.2), 'votemper': (-2,6), 'v... | None | S-1 |
Each computation consists of
%%time
#todo add 'year' here.
data=load.datas(catalog_url,df.Inputs,month,year,daskreport)
#print('#1 Data: created:')
#print('# if we raed too much file, we can do sel to take out some dates here')
data
../lib/SEDNA_ALPHA_MONITOR.yaml using param_xios reading ../lib/SEDNA_ALPHA_MONITOR.yaml using param_xios reading <bound method DataSourceBase.describe of sources: param_xios: args: combine: by_coords concat_dim: y urlpath: /ccc/work/cont003/gen7420/odakatin/CONFIGS/SEDNA/SEDNA-I/SEDNA_Domain_cfg_Tgt_20210423_tsh10m_L1/param/x_*.nc xarray_kwargs: compat: override coords: minimal data_vars: minimal parallel: true description: SEDNA NEMO parameters from MPI output nav_lon lat fails driver: intake_xarray.netcdf.NetCDFSource metadata: catalog_dir: /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/../lib/ > {'name': 'param_xios', 'container': 'xarray', 'plugin': ['netcdf'], 'driver': ['netcdf'], 'description': 'SEDNA NEMO parameters from MPI output nav_lon lat fails', 'direct_access': 'forbid', 'user_parameters': [{'name': 'path', 'description': 'file coordinate', 'type': 'str', 'default': '/ccc/work/cont003/gen7420/odakatin/CONFIGS/SEDNA/MESH/SEDNA_mesh_mask_Tgt_20210423_tsh10m_L1/param'}], 'metadata': {}, 'args': {'urlpath': '/ccc/work/cont003/gen7420/odakatin/CONFIGS/SEDNA/SEDNA-I/SEDNA_Domain_cfg_Tgt_20210423_tsh10m_L1/param/x_*.nc', 'combine': 'by_coords', 'concat_dim': 'y'}} 0 read gridS ['vosaline'] using load_data_xios reading gridS using load_data_xios reading <bound method DataSourceBase.describe of sources: data_xios: args: combine: by_coords concat_dim: time_counter,x,y urlpath: /ccc/scratch/cont003/gen7420/talandel/ONGOING-RUNS/SEDNA-ALPHA-XIOS.22/SEDNA-ALPHA_1d_gridS_*_0[0-5][0-9][0-9].nc xarray_kwargs: compat: override coords: minimal data_vars: minimal drop_variables: !!set deptht_bounds: null depthu_bounds: null nav_lat: null nav_lon: null time_centerd: null time_centered_bounds: null time_counter_bounds: null parallel: true preprocess: !!python/name:core.load.prep '' description: SEDNA NEMO outputs from different xios server driver: intake_xarray.netcdf.NetCDFSource metadata: catalog_dir: /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/../lib/ > took 136.26106762886047 seconds 0 merging gridS ['vosaline'] 1 read gridT ['votemper'] using load_data_xios reading gridT using load_data_xios reading <bound method DataSourceBase.describe of sources: data_xios: args: combine: by_coords concat_dim: time_counter,x,y urlpath: /ccc/scratch/cont003/gen7420/talandel/ONGOING-RUNS/SEDNA-ALPHA-XIOS.22/SEDNA-ALPHA_1d_gridT_*_0[0-5][0-9][0-9].nc xarray_kwargs: compat: override coords: minimal data_vars: minimal drop_variables: !!set deptht_bounds: null depthu_bounds: null nav_lat: null nav_lon: null time_centerd: null time_centered_bounds: null time_counter_bounds: null parallel: true preprocess: !!python/name:core.load.prep '' description: SEDNA NEMO outputs from different xios server driver: intake_xarray.netcdf.NetCDFSource metadata: catalog_dir: /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/../lib/ > took 61.24652886390686 seconds 1 merging gridT ['votemper'] took 0.3305366039276123 seconds 2 read gridV ['vomecrty'] using load_data_xios reading gridV using load_data_xios reading <bound method DataSourceBase.describe of sources: data_xios: args: combine: by_coords concat_dim: time_counter,x,y urlpath: /ccc/scratch/cont003/gen7420/talandel/ONGOING-RUNS/SEDNA-ALPHA-XIOS.22/SEDNA-ALPHA_1d_gridV_*_0[0-5][0-9][0-9].nc xarray_kwargs: compat: override coords: minimal data_vars: minimal drop_variables: !!set deptht_bounds: null depthu_bounds: null nav_lat: null nav_lon: null time_centerd: null time_centered_bounds: null time_counter_bounds: null parallel: true preprocess: !!python/name:core.load.prep '' description: SEDNA NEMO outputs from different xios server driver: intake_xarray.netcdf.NetCDFSource metadata: catalog_dir: /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/../lib/ > took 69.81649827957153 seconds 2 merging gridV ['vomecrty'] took 0.35733699798583984 seconds param nav_lon will be included in data param mask2d will be included in data param nav_lat will be included in data param depth will be included in data param mask will be included in data sum_num (13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12) start rechunking with (372, 360, 360, 360, 360, 360, 360, 360, 360, 360, 360, 360, 360, 360, 360, 360, 360, 360, 48) end of y_rechunk CPU times: user 2min 11s, sys: 24 s, total: 2min 35s Wall time: 4min 46s
<xarray.Dataset> Dimensions: (t: 15, x: 6560, y: 6540, z: 150) Coordinates: * t (t) object 2004-06-16 12:00:00 ... 2004-06-30 12:00:00 * y (y) int64 1 2 3 4 5 6 7 8 ... 6534 6535 6536 6537 6538 6539 6540 * x (x) int64 1 2 3 4 5 6 7 8 ... 6554 6555 6556 6557 6558 6559 6560 * z (z) int64 1 2 3 4 5 6 7 8 9 ... 143 144 145 146 147 148 149 150 nav_lon (y, x) float32 dask.array<chunksize=(372, 6560), meta=np.ndarray> mask2d (y, x) bool dask.array<chunksize=(372, 6560), meta=np.ndarray> nav_lat (y, x) float32 dask.array<chunksize=(372, 6560), meta=np.ndarray> depth (z, y, x) float64 dask.array<chunksize=(150, 372, 6560), meta=np.ndarray> mask (z, y, x) bool dask.array<chunksize=(150, 372, 6560), meta=np.ndarray> Data variables: vosaline (t, z, y, x) float32 dask.array<chunksize=(1, 150, 372, 6560), meta=np.ndarray> votemper (t, z, y, x) float32 dask.array<chunksize=(1, 150, 372, 6560), meta=np.ndarray> vomecrty (t, z, y, x) float32 dask.array<chunksize=(1, 150, 372, 6560), meta=np.ndarray>
array([cftime.DatetimeNoLeap(2004, 6, 16, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 17, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 18, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 19, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 20, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 21, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 22, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 23, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 24, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 25, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 26, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 27, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 28, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 29, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 30, 12, 0, 0, 0)], dtype=object)
array([ 1, 2, 3, ..., 6538, 6539, 6540])
array([ 1, 2, 3, ..., 6558, 6559, 6560])
array([ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150])
|
|
|
|
|
|
|
|
%%time
monitor.auto(df,data,savefig,daskreport,outputpath,file_exp='SEDNA'
)
switch:calcswitch,saveswitch,plotswitch True False True data= zoom.FramS(data) #2 Zooming Data
<xarray.Dataset> Dimensions: (t: 15, x: 554, z: 103) Coordinates: * t (t) object 2004-06-16 12:00:00 ... 2004-06-30 12:00:00 y int64 2609 * x (x) int64 3749 3750 3751 3752 3753 ... 4298 4299 4300 4301 4302 * z (z) int64 1 2 3 4 5 6 7 8 9 10 ... 95 96 97 98 99 100 101 102 103 nav_lon (x) float32 dask.array<chunksize=(554,), meta=np.ndarray> mask2d (x) bool dask.array<chunksize=(554,), meta=np.ndarray> nav_lat (x) float32 dask.array<chunksize=(554,), meta=np.ndarray> depth (z, x) float64 dask.array<chunksize=(103, 554), meta=np.ndarray> mask (z, x) bool dask.array<chunksize=(103, 554), meta=np.ndarray> Data variables: vosaline (t, z, x) float32 dask.array<chunksize=(1, 103, 554), meta=np.ndarray> votemper (t, z, x) float32 dask.array<chunksize=(1, 103, 554), meta=np.ndarray> vomecrty (t, z, x) float32 dask.array<chunksize=(1, 103, 554), meta=np.ndarray>
array([cftime.DatetimeNoLeap(2004, 6, 16, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 17, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 18, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 19, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 20, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 21, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 22, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 23, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 24, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 25, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 26, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 27, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 28, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 29, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 6, 30, 12, 0, 0, 0)], dtype=object)
array(2609)
array([3749, 3750, 3751, ..., 4300, 4301, 4302])
array([ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103])
|
|
|
|
|
|
|
|
dtaa= data.drop_vars('vozocrtx') #3 Start computing count: <xarray.Dataset> Dimensions: () Coordinates: y int64 2609 Data variables: vosaline int64 dask.array<chunksize=(), meta=np.ndarray> votemper int64 dask.array<chunksize=(), meta=np.ndarray> vomecrty int64 dask.array<chunksize=(), meta=np.ndarray>
<xarray.Dataset> Dimensions: () Coordinates: y int64 2609 Data variables: vosaline int64 dask.array<chunksize=(), meta=np.ndarray> votemper int64 dask.array<chunksize=(), meta=np.ndarray> vomecrty int64 dask.array<chunksize=(), meta=np.ndarray>
array(2609)
|
|
|
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) <timed eval> in <module> /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/monitor.py in auto(df, val, savefig, daskreport, outputpath, file_exp) 37 print('count:',data.count()) 38 display(data.count()) ---> 39 data=eval(command) 40 print('nbytes:',data.nbytes) 41 print('count:',data.count()) /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/monitor.py in <module> ~/monitor/lib/python3.7/site-packages/xarray/core/dataset.py in drop_vars(self, names, errors) 3896 names = set(names) 3897 if errors == "raise": -> 3898 self._assert_all_in_dataset(names) 3899 3900 variables = {k: v for k, v in self._variables.items() if k not in names} ~/monitor/lib/python3.7/site-packages/xarray/core/dataset.py in _assert_all_in_dataset(self, names, virtual_okay) 3867 if bad_names: 3868 raise ValueError( -> 3869 "One or more of the specified variables " 3870 "cannot be found in this dataset" 3871 ) ValueError: One or more of the specified variables cannot be found in this dataset