import zarr
import numpy as np
from matplotlib import pyplot as plt
import moraine.cli as mc
import moraine as mrpc
Point Cloud data manipulation
gix2bool
gix2bool (gix:str, is_pc:str, shape:tuple[int], chunks:tuple[int]=(1000, 1000))
Convert pc grid index to bool 2d array
| Type | Default | Details | |
|---|---|---|---|
| gix | str | point cloud grid index | |
| is_pc | str | output, output bool array | |
| shape | tuple | shape of one image (nlines,width) | |
| chunks | tuple | (1000, 1000) | output chunk size |
bool2gix
bool2gix (is_pc:str, gix:str, chunks:int=100000)
Convert bool 2d array to grid index
| Type | Default | Details | |
|---|---|---|---|
| is_pc | str | input bool array | |
| gix | str | output, point cloud grid index | |
| chunks | int | 100000 | output point chunk size |
ras2pc
ras2pc (idx:str, ras:str|list, pc:str|list, chunks:int=None, processes=False, n_workers=1, threads_per_worker=1, **dask_cluster_arg)
Convert raster data to point cloud data
| Type | Default | Details | |
|---|---|---|---|
| idx | str | point cloud grid index or hillbert index | |
| ras | str | list | path (in string) or list of path for raster data | |
| pc | str | list | output, path (in string) or list of path for point cloud data | |
| chunks | int | None | output point chunk size, same as gix by default |
| processes | bool | False | use process for dask worker or thread |
| n_workers | int | 1 | number of dask worker |
| threads_per_worker | int | 1 | number of threads per dask worker |
| dask_cluster_arg |
Usage:
logger = mc.get_logger()ras_data1 = np.random.rand(100,100).astype(np.float32)
ras_data2 = np.random.rand(100,100,3).astype(np.float32)+1j*np.random.rand(100,100,3).astype(np.float32)
gix = np.random.choice(np.arange(100*100,dtype=np.int32),size=1000,replace=False)
gix.sort()
gix = np.stack(np.unravel_index(gix,shape=(100,100)),axis=-1).astype(np.int32)
pc_data1 = ras_data1[gix[:,0],gix[:,1]]
pc_data2 = ras_data2[gix[:,0],gix[:,1]]
gix_zarr = zarr.open('pc/gix.zarr','w',shape=gix.shape,dtype=gix.dtype,chunks=(200,1))
ras_zarr1 = zarr.open('pc/ras1.zarr','w',shape=ras_data1.shape,dtype=ras_data1.dtype,chunks=(20,100))
ras_zarr2 = zarr.open('pc/ras2.zarr','w',shape=ras_data2.shape,dtype=ras_data2.dtype,chunks=(20,100,1))
gix_zarr[:] = gix
ras_zarr1[:] = ras_data1
ras_zarr2[:] = ras_data2ras2pc('pc/gix.zarr','pc/ras1.zarr','pc/pc1.zarr')
pc_zarr1 = zarr.open('pc/pc1.zarr','r')
np.testing.assert_array_equal(pc_data1,pc_zarr1[:])
ras2pc('pc/gix.zarr',ras=['pc/ras1.zarr','pc/ras2.zarr'],pc=['pc/pc1.zarr','pc/pc2.zarr'])
pc_zarr1 = zarr.open('pc/pc1.zarr','r')
pc_zarr2 = zarr.open('pc/pc2.zarr','r')
np.testing.assert_array_equal(pc_data1,pc_zarr1[:])
np.testing.assert_array_equal(pc_data2,pc_zarr2[:])2024-08-14 17:15:41 - log_args - INFO - running function: ras2pc
2024-08-14 17:15:41 - log_args - INFO - fetching args:
2024-08-14 17:15:41 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:15:41 - log_args - INFO - ras = 'pc/ras1.zarr'
2024-08-14 17:15:41 - log_args - INFO - pc = 'pc/pc1.zarr'
2024-08-14 17:15:41 - log_args - INFO - chunks = None
2024-08-14 17:15:41 - log_args - INFO - processes = False
2024-08-14 17:15:41 - log_args - INFO - n_workers = 1
2024-08-14 17:15:41 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:41 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:41 - log_args - INFO - fetching args done.
2024-08-14 17:15:41 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:15:41 - ras2pc - INFO - loading gix into memory.
2024-08-14 17:15:41 - ras2pc - INFO - starting dask local cluster.
2024-08-14 17:15:41 - ras2pc - INFO - dask local cluster started.
2024-08-14 17:15:41 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:41 - ras2pc - INFO - start to slice on pc/ras1.zarr
2024-08-14 17:15:41 - zarr_info - INFO - pc/ras1.zarr zarray shape, chunks, dtype: (100, 100), (20, 100), float32
2024-08-14 17:15:41 - darr_info - INFO - ras dask array shape, chunksize, dtype: (100, 100), (100, 100), float32
2024-08-14 17:15:41 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:15:41 - ras2pc - INFO - saving to pc/pc1.zarr.
2024-08-14 17:15:41 - zarr_info - INFO - pc/pc1.zarr zarray shape, chunks, dtype: (1000,), (200,), float32
2024-08-14 17:15:41 - ras2pc - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:42 - ras2pc - INFO - computing finished.ed | 0.1s
2024-08-14 17:15:42 - ras2pc - INFO - dask cluster closed.
2024-08-14 17:15:42 - log_args - INFO - running function: ras2pc
2024-08-14 17:15:42 - log_args - INFO - fetching args:
2024-08-14 17:15:42 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:15:42 - log_args - INFO - ras = ['pc/ras1.zarr', 'pc/ras2.zarr']
2024-08-14 17:15:42 - log_args - INFO - pc = ['pc/pc1.zarr', 'pc/pc2.zarr']
2024-08-14 17:15:42 - log_args - INFO - chunks = None
2024-08-14 17:15:42 - log_args - INFO - processes = False
2024-08-14 17:15:42 - log_args - INFO - n_workers = 1
2024-08-14 17:15:42 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:42 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:42 - log_args - INFO - fetching args done.
2024-08-14 17:15:42 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:15:42 - ras2pc - INFO - loading gix into memory.
2024-08-14 17:15:42 - ras2pc - INFO - starting dask local cluster.
2024-08-14 17:15:42 - ras2pc - INFO - dask local cluster started.
2024-08-14 17:15:42 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:42 - ras2pc - INFO - start to slice on pc/ras1.zarr
2024-08-14 17:15:42 - zarr_info - INFO - pc/ras1.zarr zarray shape, chunks, dtype: (100, 100), (20, 100), float32
2024-08-14 17:15:42 - darr_info - INFO - ras dask array shape, chunksize, dtype: (100, 100), (100, 100), float32
2024-08-14 17:15:42 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:15:42 - ras2pc - INFO - saving to pc/pc1.zarr.
2024-08-14 17:15:42 - zarr_info - INFO - pc/pc1.zarr zarray shape, chunks, dtype: (1000,), (200,), float32
2024-08-14 17:15:42 - ras2pc - INFO - start to slice on pc/ras2.zarr
2024-08-14 17:15:42 - zarr_info - INFO - pc/ras2.zarr zarray shape, chunks, dtype: (100, 100, 3), (20, 100, 1), complex64
2024-08-14 17:15:42 - darr_info - INFO - ras dask array shape, chunksize, dtype: (100, 100, 3), (100, 100, 1), complex64
2024-08-14 17:15:42 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000, 3), (1000, 1), complex64
2024-08-14 17:15:42 - ras2pc - INFO - saving to pc/pc2.zarr.
2024-08-14 17:15:42 - zarr_info - INFO - pc/pc2.zarr zarray shape, chunks, dtype: (1000, 3), (200, 1), complex64
2024-08-14 17:15:42 - ras2pc - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:42 - ras2pc - INFO - computing finished.ed | 0.1s
2024-08-14 17:15:42 - ras2pc - INFO - dask cluster closed.pc_concat
pc_concat (pcs:list|str, pc:list|str, key:list|str=None, chunks:int=None, processes=False, n_workers=1, threads_per_worker=1, **dask_cluster_arg)
concatenate (and sort) point cloud dataset.
| Type | Default | Details | |
|---|---|---|---|
| pcs | list | str | list of path to pc or directory that hold one pc, or a list of that | |
| pc | list | str | output, path of output or a list of that | |
| key | list | str | None | keys that sort the pc data, no sort by default |
| chunks | int | None | pc chunk size in output data, optional, same as first pc in pcs by default |
| processes | bool | False | use process for dask worker or thread |
| n_workers | int | 1 | number of dask worker |
| threads_per_worker | int | 1 | number of threads per dask worker |
| dask_cluster_arg |
pc_data = np.random.rand(1000,3).astype(np.float32)+1j*np.random.rand(1000,3).astype(np.float32)
pc1_zarr = zarr.open('pc/pc1.zarr','w',shape=(300,3),dtype=pc_data.dtype,chunks=(300,1))
pc2_zarr = zarr.open('pc/pc2.zarr','w',shape=(700,3),dtype=pc_data.dtype,chunks=(700,1))
pc1_zarr[:] = pc_data[:300]
pc2_zarr[:] = pc_data[300:]pc_concat(['pc/pc1.zarr','pc/pc2.zarr'],'pc/pc.zarr',chunks=500)
np.testing.assert_array_equal(zarr.open('pc/pc.zarr','r')[:],pc_data)2024-08-14 17:15:42 - log_args - INFO - running function: pc_concat
2024-08-14 17:15:42 - log_args - INFO - fetching args:
2024-08-14 17:15:42 - log_args - INFO - pcs = ['pc/pc1.zarr', 'pc/pc2.zarr']
2024-08-14 17:15:42 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:15:42 - log_args - INFO - key = None
2024-08-14 17:15:42 - log_args - INFO - chunks = 500
2024-08-14 17:15:42 - log_args - INFO - processes = False
2024-08-14 17:15:42 - log_args - INFO - n_workers = 1
2024-08-14 17:15:42 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:42 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:42 - log_args - INFO - fetching args done.
2024-08-14 17:15:42 - pc_concat - INFO - input pcs: [['pc/pc1.zarr', 'pc/pc2.zarr']]
2024-08-14 17:15:42 - pc_concat - INFO - output pc: ['pc/pc.zarr']
2024-08-14 17:15:42 - pc_concat - INFO - starting dask local cluster.
2024-08-14 17:15:42 - pc_concat - INFO - dask local cluster started.
2024-08-14 17:15:42 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:42 - pc_concat - INFO - read pc from ['pc/pc1.zarr', 'pc/pc2.zarr']
2024-08-14 17:15:42 - darr_info - INFO - concatenated pc dask array shape, chunksize, dtype: (1000, 3), (1000, 1), complex64
2024-08-14 17:15:42 - pc_concat - INFO - save pc to pc/pc.zarr
2024-08-14 17:15:42 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (1000, 3), (500, 1), complex64
2024-08-14 17:15:42 - pc_concat - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:42 - pc_concat - INFO - computing finished.| 0.1s
2024-08-14 17:15:42 - pc_concat - INFO - dask cluster closed.ras2pc_ras_chunk
ras2pc_ras_chunk (gix:str, ras:str|list, pc:str|list, key:str, chunks:tuple=None, processes=False, n_workers=1, threads_per_worker=1, **dask_cluster_arg)
Convert raster data to point cloud data that sorted by ras chunk
| Type | Default | Details | |
|---|---|---|---|
| gix | str | point cloud grid index | |
| ras | str | list | path (in string) or list of path for raster data | |
| pc | str | list | output, path (directory) or list of path for point cloud data | |
| key | str | output, path for the key to sort generated pc in the directory back to gix order | |
| chunks | tuple | None | ras chunks, same as the first ras by default |
| processes | bool | False | use process for dask worker or thread |
| n_workers | int | 1 | number of dask worker |
| threads_per_worker | int | 1 | number of threads per dask worker |
| dask_cluster_arg |
ras2pc_ras_chunk('pc/gix.zarr','pc/ras1.zarr','pc/pc1',key='pc/key.zarr')
pc_concat('pc/pc1','pc/pc1.zarr',key='pc/key.zarr',chunks=200)
pc_zarr1 = zarr.open('pc/pc1.zarr','r')
np.testing.assert_array_equal(pc_data1,pc_zarr1[:])
ras2pc_ras_chunk('pc/gix.zarr',ras=['pc/ras1.zarr','pc/ras2.zarr'],pc=['pc/pc1','pc/pc2'],key='pc/key.zarr')
pc_concat('pc/pc1','pc/pc1.zarr',key='pc/key.zarr',chunks=200)
pc_concat('pc/pc2','pc/pc2.zarr',key='pc/key.zarr',chunks=200)
pc_zarr1 = zarr.open('pc/pc1.zarr','r')
pc_zarr2 = zarr.open('pc/pc2.zarr','r')
np.testing.assert_array_equal(pc_data1,pc_zarr1[:])
np.testing.assert_array_equal(pc_data2,pc_zarr2[:])2024-08-14 17:15:43 - log_args - INFO - running function: ras2pc_ras_chunk
2024-08-14 17:15:43 - log_args - INFO - fetching args:
2024-08-14 17:15:43 - log_args - INFO - gix = 'pc/gix.zarr'
2024-08-14 17:15:43 - log_args - INFO - ras = 'pc/ras1.zarr'
2024-08-14 17:15:43 - log_args - INFO - pc = 'pc/pc1'
2024-08-14 17:15:43 - log_args - INFO - key = 'pc/key.zarr'
2024-08-14 17:15:43 - log_args - INFO - chunks = None
2024-08-14 17:15:43 - log_args - INFO - processes = False
2024-08-14 17:15:43 - log_args - INFO - n_workers = 1
2024-08-14 17:15:43 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:43 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:43 - log_args - INFO - fetching args done.
2024-08-14 17:15:43 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:15:43 - ras2pc_ras_chunk - INFO - loading gix into memory.
2024-08-14 17:15:43 - ras2pc_ras_chunk - INFO - convert gix to the order of ras chunk
2024-08-14 17:15:50 - ras2pc_ras_chunk - INFO - save key
2024-08-14 17:15:50 - ras2pc_ras_chunk - INFO - starting dask local cluster.
2024-08-14 17:15:50 - ras2pc_ras_chunk - INFO - dask local cluster started.
2024-08-14 17:15:50 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:50 - ras2pc_ras_chunk - INFO - start to slice on pc/ras1.zarr
2024-08-14 17:15:50 - zarr_info - INFO - pc/ras1.zarr zarray shape, chunks, dtype: (100, 100), (20, 20), float32
2024-08-14 17:15:50 - darr_info - INFO - ras dask array shape, chunksize, dtype: (100, 100), (20, 20), float32
2024-08-14 17:15:50 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000,), (50,), float32
2024-08-14 17:15:50 - ras2pc_ras_chunk - INFO - saving to pc/pc1.
2024-08-14 17:15:50 - ras2pc_ras_chunk - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - computing finished.
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - dask cluster closed.
2024-08-14 17:15:51 - log_args - INFO - running function: pc_concat
2024-08-14 17:15:51 - log_args - INFO - fetching args:
2024-08-14 17:15:51 - log_args - INFO - pcs = 'pc/pc1'
2024-08-14 17:15:51 - log_args - INFO - pc = 'pc/pc1.zarr'
2024-08-14 17:15:51 - log_args - INFO - key = 'pc/key.zarr'
2024-08-14 17:15:51 - log_args - INFO - chunks = 200
2024-08-14 17:15:51 - log_args - INFO - processes = False
2024-08-14 17:15:51 - log_args - INFO - n_workers = 1
2024-08-14 17:15:51 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:51 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:51 - log_args - INFO - fetching args done.
2024-08-14 17:15:51 - pc_concat - INFO - input pcs: [[Path('pc/pc1/0.zarr'), Path('pc/pc1/1.zarr'), Path('pc/pc1/2.zarr'), Path('pc/pc1/3.zarr'), Path('pc/pc1/4.zarr'), Path('pc/pc1/5.zarr'), Path('pc/pc1/6.zarr'), Path('pc/pc1/7.zarr'), Path('pc/pc1/8.zarr'), Path('pc/pc1/9.zarr'), Path('pc/pc1/10.zarr'), Path('pc/pc1/11.zarr'), Path('pc/pc1/12.zarr'), Path('pc/pc1/13.zarr'), Path('pc/pc1/14.zarr'), Path('pc/pc1/15.zarr'), Path('pc/pc1/16.zarr'), Path('pc/pc1/17.zarr'), Path('pc/pc1/18.zarr'), Path('pc/pc1/19.zarr'), Path('pc/pc1/20.zarr'), Path('pc/pc1/21.zarr'), Path('pc/pc1/22.zarr'), Path('pc/pc1/23.zarr'), Path('pc/pc1/24.zarr')]]
2024-08-14 17:15:51 - pc_concat - INFO - output pc: ['pc/pc1.zarr']
2024-08-14 17:15:51 - pc_concat - INFO - load key
2024-08-14 17:15:51 - zarr_info - INFO - pc/key.zarr zarray shape, chunks, dtype: (1000,), (200,), int64
2024-08-14 17:15:51 - pc_concat - INFO - starting dask local cluster.
2024-08-14 17:15:51 - pc_concat - INFO - dask local cluster started.
2024-08-14 17:15:51 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:51 - pc_concat - INFO - read pc from [Path('pc/pc1/0.zarr'), Path('pc/pc1/1.zarr'), Path('pc/pc1/2.zarr'), Path('pc/pc1/3.zarr'), Path('pc/pc1/4.zarr'), Path('pc/pc1/5.zarr'), Path('pc/pc1/6.zarr'), Path('pc/pc1/7.zarr'), Path('pc/pc1/8.zarr'), Path('pc/pc1/9.zarr'), Path('pc/pc1/10.zarr'), Path('pc/pc1/11.zarr'), Path('pc/pc1/12.zarr'), Path('pc/pc1/13.zarr'), Path('pc/pc1/14.zarr'), Path('pc/pc1/15.zarr'), Path('pc/pc1/16.zarr'), Path('pc/pc1/17.zarr'), Path('pc/pc1/18.zarr'), Path('pc/pc1/19.zarr'), Path('pc/pc1/20.zarr'), Path('pc/pc1/21.zarr'), Path('pc/pc1/22.zarr'), Path('pc/pc1/23.zarr'), Path('pc/pc1/24.zarr')]
2024-08-14 17:15:51 - darr_info - INFO - concatenated pc dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:15:51 - pc_concat - INFO - sort pc according to key
2024-08-14 17:15:51 - darr_info - INFO - sorted pc dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:15:51 - pc_concat - INFO - save pc to pc/pc1.zarr
2024-08-14 17:15:51 - zarr_info - INFO - pc/pc1.zarr zarray shape, chunks, dtype: (1000,), (200,), float32
2024-08-14 17:15:51 - pc_concat - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:51 - pc_concat - INFO - computing finished.| 0.1s
2024-08-14 17:15:51 - pc_concat - INFO - dask cluster closed.
2024-08-14 17:15:51 - log_args - INFO - running function: ras2pc_ras_chunk
2024-08-14 17:15:51 - log_args - INFO - fetching args:
2024-08-14 17:15:51 - log_args - INFO - gix = 'pc/gix.zarr'
2024-08-14 17:15:51 - log_args - INFO - ras = ['pc/ras1.zarr', 'pc/ras2.zarr']
2024-08-14 17:15:51 - log_args - INFO - pc = ['pc/pc1', 'pc/pc2']
2024-08-14 17:15:51 - log_args - INFO - key = 'pc/key.zarr'
2024-08-14 17:15:51 - log_args - INFO - chunks = None
2024-08-14 17:15:51 - log_args - INFO - processes = False
2024-08-14 17:15:51 - log_args - INFO - n_workers = 1
2024-08-14 17:15:51 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:51 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:51 - log_args - INFO - fetching args done.
2024-08-14 17:15:51 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - loading gix into memory.
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - convert gix to the order of ras chunk
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - save key
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - starting dask local cluster.
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - dask local cluster started.
2024-08-14 17:15:51 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - start to slice on pc/ras1.zarr
2024-08-14 17:15:51 - zarr_info - INFO - pc/ras1.zarr zarray shape, chunks, dtype: (100, 100), (20, 20), float32
2024-08-14 17:15:51 - darr_info - INFO - ras dask array shape, chunksize, dtype: (100, 100), (20, 20), float32
2024-08-14 17:15:51 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000,), (50,), float32
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - saving to pc/pc1.
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - start to slice on pc/ras2.zarr
2024-08-14 17:15:51 - zarr_info - INFO - pc/ras2.zarr zarray shape, chunks, dtype: (100, 100, 3), (20, 20, 1), complex64
2024-08-14 17:15:51 - darr_info - INFO - ras dask array shape, chunksize, dtype: (100, 100, 3), (20, 20, 3), complex64
2024-08-14 17:15:51 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000, 3), (50, 3), complex64
2024-08-14 17:15:51 - ras2pc_ras_chunk - INFO - saving to pc/pc2.
2024-08-14 17:15:52 - ras2pc_ras_chunk - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:53 - ras2pc_ras_chunk - INFO - computing finished.
2024-08-14 17:15:53 - ras2pc_ras_chunk - INFO - dask cluster closed.
2024-08-14 17:15:53 - log_args - INFO - running function: pc_concat
2024-08-14 17:15:53 - log_args - INFO - fetching args:
2024-08-14 17:15:53 - log_args - INFO - pcs = 'pc/pc1'
2024-08-14 17:15:53 - log_args - INFO - pc = 'pc/pc1.zarr'
2024-08-14 17:15:53 - log_args - INFO - key = 'pc/key.zarr'
2024-08-14 17:15:53 - log_args - INFO - chunks = 200
2024-08-14 17:15:53 - log_args - INFO - processes = False
2024-08-14 17:15:53 - log_args - INFO - n_workers = 1
2024-08-14 17:15:53 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:53 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:53 - log_args - INFO - fetching args done.
2024-08-14 17:15:53 - pc_concat - INFO - input pcs: [[Path('pc/pc1/0.zarr'), Path('pc/pc1/1.zarr'), Path('pc/pc1/2.zarr'), Path('pc/pc1/3.zarr'), Path('pc/pc1/4.zarr'), Path('pc/pc1/5.zarr'), Path('pc/pc1/6.zarr'), Path('pc/pc1/7.zarr'), Path('pc/pc1/8.zarr'), Path('pc/pc1/9.zarr'), Path('pc/pc1/10.zarr'), Path('pc/pc1/11.zarr'), Path('pc/pc1/12.zarr'), Path('pc/pc1/13.zarr'), Path('pc/pc1/14.zarr'), Path('pc/pc1/15.zarr'), Path('pc/pc1/16.zarr'), Path('pc/pc1/17.zarr'), Path('pc/pc1/18.zarr'), Path('pc/pc1/19.zarr'), Path('pc/pc1/20.zarr'), Path('pc/pc1/21.zarr'), Path('pc/pc1/22.zarr'), Path('pc/pc1/23.zarr'), Path('pc/pc1/24.zarr')]]
2024-08-14 17:15:53 - pc_concat - INFO - output pc: ['pc/pc1.zarr']
2024-08-14 17:15:53 - pc_concat - INFO - load key
2024-08-14 17:15:53 - zarr_info - INFO - pc/key.zarr zarray shape, chunks, dtype: (1000,), (200,), int64
2024-08-14 17:15:53 - pc_concat - INFO - starting dask local cluster.
2024-08-14 17:15:53 - pc_concat - INFO - dask local cluster started.
2024-08-14 17:15:53 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:53 - pc_concat - INFO - read pc from [Path('pc/pc1/0.zarr'), Path('pc/pc1/1.zarr'), Path('pc/pc1/2.zarr'), Path('pc/pc1/3.zarr'), Path('pc/pc1/4.zarr'), Path('pc/pc1/5.zarr'), Path('pc/pc1/6.zarr'), Path('pc/pc1/7.zarr'), Path('pc/pc1/8.zarr'), Path('pc/pc1/9.zarr'), Path('pc/pc1/10.zarr'), Path('pc/pc1/11.zarr'), Path('pc/pc1/12.zarr'), Path('pc/pc1/13.zarr'), Path('pc/pc1/14.zarr'), Path('pc/pc1/15.zarr'), Path('pc/pc1/16.zarr'), Path('pc/pc1/17.zarr'), Path('pc/pc1/18.zarr'), Path('pc/pc1/19.zarr'), Path('pc/pc1/20.zarr'), Path('pc/pc1/21.zarr'), Path('pc/pc1/22.zarr'), Path('pc/pc1/23.zarr'), Path('pc/pc1/24.zarr')]
2024-08-14 17:15:53 - darr_info - INFO - concatenated pc dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:15:53 - pc_concat - INFO - sort pc according to key
2024-08-14 17:15:53 - darr_info - INFO - sorted pc dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:15:53 - pc_concat - INFO - save pc to pc/pc1.zarr
2024-08-14 17:15:53 - zarr_info - INFO - pc/pc1.zarr zarray shape, chunks, dtype: (1000,), (200,), float32
2024-08-14 17:15:53 - pc_concat - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:53 - pc_concat - INFO - computing finished.| 0.1s
2024-08-14 17:15:53 - pc_concat - INFO - dask cluster closed.
2024-08-14 17:15:53 - log_args - INFO - running function: pc_concat
2024-08-14 17:15:53 - log_args - INFO - fetching args:
2024-08-14 17:15:53 - log_args - INFO - pcs = 'pc/pc2'
2024-08-14 17:15:53 - log_args - INFO - pc = 'pc/pc2.zarr'
2024-08-14 17:15:53 - log_args - INFO - key = 'pc/key.zarr'
2024-08-14 17:15:53 - log_args - INFO - chunks = 200
2024-08-14 17:15:53 - log_args - INFO - processes = False
2024-08-14 17:15:53 - log_args - INFO - n_workers = 1
2024-08-14 17:15:53 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:53 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:53 - log_args - INFO - fetching args done.
2024-08-14 17:15:53 - pc_concat - INFO - input pcs: [[Path('pc/pc2/0.zarr'), Path('pc/pc2/1.zarr'), Path('pc/pc2/2.zarr'), Path('pc/pc2/3.zarr'), Path('pc/pc2/4.zarr'), Path('pc/pc2/5.zarr'), Path('pc/pc2/6.zarr'), Path('pc/pc2/7.zarr'), Path('pc/pc2/8.zarr'), Path('pc/pc2/9.zarr'), Path('pc/pc2/10.zarr'), Path('pc/pc2/11.zarr'), Path('pc/pc2/12.zarr'), Path('pc/pc2/13.zarr'), Path('pc/pc2/14.zarr'), Path('pc/pc2/15.zarr'), Path('pc/pc2/16.zarr'), Path('pc/pc2/17.zarr'), Path('pc/pc2/18.zarr'), Path('pc/pc2/19.zarr'), Path('pc/pc2/20.zarr'), Path('pc/pc2/21.zarr'), Path('pc/pc2/22.zarr'), Path('pc/pc2/23.zarr'), Path('pc/pc2/24.zarr')]]
2024-08-14 17:15:53 - pc_concat - INFO - output pc: ['pc/pc2.zarr']
2024-08-14 17:15:53 - pc_concat - INFO - load key
2024-08-14 17:15:53 - zarr_info - INFO - pc/key.zarr zarray shape, chunks, dtype: (1000,), (200,), int64
2024-08-14 17:15:53 - pc_concat - INFO - starting dask local cluster.
2024-08-14 17:15:53 - pc_concat - INFO - dask local cluster started.
2024-08-14 17:15:53 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:53 - pc_concat - INFO - read pc from [Path('pc/pc2/0.zarr'), Path('pc/pc2/1.zarr'), Path('pc/pc2/2.zarr'), Path('pc/pc2/3.zarr'), Path('pc/pc2/4.zarr'), Path('pc/pc2/5.zarr'), Path('pc/pc2/6.zarr'), Path('pc/pc2/7.zarr'), Path('pc/pc2/8.zarr'), Path('pc/pc2/9.zarr'), Path('pc/pc2/10.zarr'), Path('pc/pc2/11.zarr'), Path('pc/pc2/12.zarr'), Path('pc/pc2/13.zarr'), Path('pc/pc2/14.zarr'), Path('pc/pc2/15.zarr'), Path('pc/pc2/16.zarr'), Path('pc/pc2/17.zarr'), Path('pc/pc2/18.zarr'), Path('pc/pc2/19.zarr'), Path('pc/pc2/20.zarr'), Path('pc/pc2/21.zarr'), Path('pc/pc2/22.zarr'), Path('pc/pc2/23.zarr'), Path('pc/pc2/24.zarr')]
2024-08-14 17:15:53 - darr_info - INFO - concatenated pc dask array shape, chunksize, dtype: (1000, 3), (1000, 1), complex64
2024-08-14 17:15:53 - pc_concat - INFO - sort pc according to key
2024-08-14 17:15:53 - darr_info - INFO - sorted pc dask array shape, chunksize, dtype: (1000, 3), (1000, 1), complex64
2024-08-14 17:15:53 - pc_concat - INFO - save pc to pc/pc2.zarr
2024-08-14 17:15:53 - zarr_info - INFO - pc/pc2.zarr zarray shape, chunks, dtype: (1000, 3), (200, 1), complex64
2024-08-14 17:15:53 - pc_concat - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:53 - pc_concat - INFO - computing finished.| 0.2s
2024-08-14 17:15:53 - pc_concat - INFO - dask cluster closed.pc2ras
pc2ras (idx:str, pc:str|list, ras:str|list, shape:tuple[int], chunks:tuple[int]=(1000, 1000), processes=False, n_workers=1, threads_per_worker=1, **dask_cluster_arg)
Convert point cloud data to raster data, filled with nan
| Type | Default | Details | |
|---|---|---|---|
| idx | str | point cloud grid index or hillbert index | |
| pc | str | list | path (in string) or list of path for point cloud data | |
| ras | str | list | output, path (in string) or list of path for raster data | |
| shape | tuple | shape of one image (nlines,width) | |
| chunks | tuple | (1000, 1000) | output chunk size |
| processes | bool | False | use process for dask worker or thread |
| n_workers | int | 1 | number of dask worker |
| threads_per_worker | int | 1 | number of threads per dask worker |
| dask_cluster_arg |
Usage:
pc_data1 = np.random.rand(1000).astype(np.float32)
pc_data2 = np.random.rand(1000,3).astype(np.float32)+1j*np.random.rand(1000,3).astype(np.float32)
gix = np.random.choice(np.arange(100*100,dtype=np.int32),size=1000,replace=False)
gix.sort()
gix = np.stack(np.unravel_index(gix,shape=(100,100)),axis=-1).astype(np.int32)
ras_data1 = np.zeros((100,100),dtype=np.float32)
ras_data2 = np.zeros((100,100,3),dtype=np.complex64)
ras_data1[:] = np.nan
ras_data2[:] = np.nan
ras_data1[gix[:,0],gix[:,1]] = pc_data1
ras_data2[gix[:,0],gix[:,1]] = pc_data2
gix_zarr = zarr.open('pc/gix.zarr','w',shape=gix.shape,dtype=gix.dtype,chunks=(200,1))
pc_zarr1 = zarr.open('pc/pc1.zarr','w',shape=pc_data1.shape,dtype=pc_data1.dtype,chunks=(200,))
pc_zarr2 = zarr.open('pc/pc2.zarr','w',shape=pc_data2.shape,dtype=pc_data2.dtype,chunks=(200,1))
gix_zarr[:] = gix
pc_zarr1[:] = pc_data1
pc_zarr2[:] = pc_data2pc2ras('pc/gix.zarr','pc/pc1.zarr','pc/ras1.zarr',shape=(100,100),chunks=(20,100))
ras_zarr1 = zarr.open('pc/ras1.zarr','r')
np.testing.assert_array_equal(ras_data1,ras_zarr1[:])
pc2ras('pc/gix.zarr',['pc/pc1.zarr','pc/pc2.zarr'],['pc/ras1.zarr','pc/ras2.zarr'],shape=(100,100),chunks=(20,100))
ras_zarr1 = zarr.open('pc/ras1.zarr','r')
ras_zarr2 = zarr.open('pc/ras2.zarr','r')
np.testing.assert_array_equal(ras_data1,ras_zarr1[:])
np.testing.assert_array_equal(ras_data2,ras_zarr2[:])2024-08-14 17:15:54 - log_args - INFO - running function: pc2ras
2024-08-14 17:15:54 - log_args - INFO - fetching args:
2024-08-14 17:15:54 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:15:54 - log_args - INFO - pc = 'pc/pc1.zarr'
2024-08-14 17:15:54 - log_args - INFO - ras = 'pc/ras1.zarr'
2024-08-14 17:15:54 - log_args - INFO - shape = (100, 100)
2024-08-14 17:15:54 - log_args - INFO - chunks = (20, 100)
2024-08-14 17:15:54 - log_args - INFO - processes = False
2024-08-14 17:15:54 - log_args - INFO - n_workers = 1
2024-08-14 17:15:54 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:54 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:54 - log_args - INFO - fetching args done.
2024-08-14 17:15:54 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:15:54 - pc2ras - INFO - loading gix into memory.
2024-08-14 17:15:54 - pc2ras - INFO - starting dask local cluster.
2024-08-14 17:15:55 - pc2ras - INFO - dask local cluster started.
2024-08-14 17:15:55 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:55 - pc2ras - INFO - start to work on pc/pc1.zarr
2024-08-14 17:15:55 - zarr_info - INFO - pc/pc1.zarr zarray shape, chunks, dtype: (1000,), (200,), float32
2024-08-14 17:15:55 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:15:55 - pc2ras - INFO - create ras dask array
2024-08-14 17:15:55 - darr_info - INFO - ras dask array shape, chunksize, dtype: (100, 100), (100, 100), float32
2024-08-14 17:15:55 - pc2ras - INFO - save ras to pc/ras1.zarr
2024-08-14 17:15:55 - zarr_info - INFO - pc/ras1.zarr zarray shape, chunks, dtype: (100, 100), (20, 100), float32
2024-08-14 17:15:55 - pc2ras - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:55 - pc2ras - INFO - computing finished.ed | 0.2s
2024-08-14 17:15:55 - pc2ras - INFO - dask cluster closed.
2024-08-14 17:15:55 - log_args - INFO - running function: pc2ras
2024-08-14 17:15:55 - log_args - INFO - fetching args:
2024-08-14 17:15:55 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:15:55 - log_args - INFO - pc = ['pc/pc1.zarr', 'pc/pc2.zarr']
2024-08-14 17:15:55 - log_args - INFO - ras = ['pc/ras1.zarr', 'pc/ras2.zarr']
2024-08-14 17:15:55 - log_args - INFO - shape = (100, 100)
2024-08-14 17:15:55 - log_args - INFO - chunks = (20, 100)
2024-08-14 17:15:55 - log_args - INFO - processes = False
2024-08-14 17:15:55 - log_args - INFO - n_workers = 1
2024-08-14 17:15:55 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:55 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:55 - log_args - INFO - fetching args done.
2024-08-14 17:15:55 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:15:55 - pc2ras - INFO - loading gix into memory.
2024-08-14 17:15:55 - pc2ras - INFO - starting dask local cluster.
2024-08-14 17:15:55 - pc2ras - INFO - dask local cluster started.
2024-08-14 17:15:55 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:55 - pc2ras - INFO - start to work on pc/pc1.zarr
2024-08-14 17:15:55 - zarr_info - INFO - pc/pc1.zarr zarray shape, chunks, dtype: (1000,), (200,), float32
2024-08-14 17:15:55 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:15:55 - pc2ras - INFO - create ras dask array
2024-08-14 17:15:55 - darr_info - INFO - ras dask array shape, chunksize, dtype: (100, 100), (100, 100), float32
2024-08-14 17:15:55 - pc2ras - INFO - save ras to pc/ras1.zarr
2024-08-14 17:15:55 - zarr_info - INFO - pc/ras1.zarr zarray shape, chunks, dtype: (100, 100), (20, 100), float32
2024-08-14 17:15:55 - pc2ras - INFO - start to work on pc/pc2.zarr
2024-08-14 17:15:55 - zarr_info - INFO - pc/pc2.zarr zarray shape, chunks, dtype: (1000, 3), (200, 1), complex64
2024-08-14 17:15:55 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000, 3), (1000, 1), complex64
2024-08-14 17:15:55 - pc2ras - INFO - create ras dask array
2024-08-14 17:15:55 - darr_info - INFO - ras dask array shape, chunksize, dtype: (100, 100, 3), (100, 100, 1), complex64
2024-08-14 17:15:55 - pc2ras - INFO - save ras to pc/ras2.zarr
2024-08-14 17:15:55 - zarr_info - INFO - pc/ras2.zarr zarray shape, chunks, dtype: (100, 100, 3), (20, 100, 1), complex64
2024-08-14 17:15:55 - pc2ras - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:55 - pc2ras - INFO - computing finished.ed | 0.1s
2024-08-14 17:15:55 - pc2ras - INFO - dask cluster closed.pc_hix
pc_hix (gix:str, hix:str, shape:tuple)
Compute the hillbert index from grid index for point cloud data.
| Type | Details | |
|---|---|---|
| gix | str | grid index |
| hix | str | output, path |
| shape | tuple | (nlines, width) |
Usage:
bbox = [0,0,100,100]
gix = np.random.choice(np.arange(100*100,dtype=np.int32),size=1000,replace=False)
gix.sort()
gix = np.stack(np.unravel_index(gix,shape=(100,100)),axis=-1).astype(np.int32)
gix_zarr = zarr.open('pc/gix.zarr','w',shape=gix.shape, chunks=(100,1),dtype=gix.dtype)
gix_zarr[:] = gixpc_hix('pc/gix.zarr', 'pc/hix.zarr',shape=(100,100))2024-08-14 17:15:56 - log_args - INFO - running function: pc_hix
2024-08-14 17:15:56 - log_args - INFO - fetching args:
2024-08-14 17:15:56 - log_args - INFO - gix = 'pc/gix.zarr'
2024-08-14 17:15:56 - log_args - INFO - hix = 'pc/hix.zarr'
2024-08-14 17:15:56 - log_args - INFO - shape = (100, 100)
2024-08-14 17:15:56 - log_args - INFO - fetching args done.
2024-08-14 17:15:56 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (1000, 2), (100, 1), int32
2024-08-14 17:15:56 - zarr_info - INFO - pc/hix.zarr zarray shape, chunks, dtype: (1000,), (100,), int64
2024-08-14 17:15:56 - pc_hix - INFO - calculating the hillbert index based on grid index
2024-08-14 17:15:57 - pc_hix - INFO - writing the hillbert index
2024-08-14 17:15:57 - pc_hix - INFO - done.hix = zarr.open('pc/hix.zarr','r')[:]
plt.scatter(gix[:,1], gix[:,0], c=hix)
plt.colorbar()
plt.show()
pc_gix
pc_gix (hix:str, gix:str, shape:tuple)
Compute the hillbert index from grid index for point cloud data.
| Type | Details | |
|---|---|---|
| hix | str | grid index |
| gix | str | output, path |
| shape | tuple | (nlines, width) |
bbox = [0,0,100,100]
gix = np.random.choice(np.arange(100*100,dtype=np.int32),size=1000,replace=False)
gix.sort()
gix = np.stack(np.unravel_index(gix,shape=(100,100)),axis=-1).astype(np.int32)
gix_zarr = zarr.open('pc/gix.zarr','w',shape=gix.shape, chunks=(100,1),dtype=gix.dtype)
gix_zarr[:] = gix
pc_hix('pc/gix.zarr', 'pc/hix.zarr',shape=(100,100))
pc_gix('pc/hix.zarr','pc/gix_.zarr', (100,100))
np.testing.assert_array_equal(zarr.open('pc/gix_.zarr','r')[:], gix)2024-08-14 17:15:57 - log_args - INFO - running function: pc_hix
2024-08-14 17:15:57 - log_args - INFO - fetching args:
2024-08-14 17:15:57 - log_args - INFO - gix = 'pc/gix.zarr'
2024-08-14 17:15:57 - log_args - INFO - hix = 'pc/hix.zarr'
2024-08-14 17:15:57 - log_args - INFO - shape = (100, 100)
2024-08-14 17:15:57 - log_args - INFO - fetching args done.
2024-08-14 17:15:57 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (1000, 2), (100, 1), int32
2024-08-14 17:15:57 - zarr_info - INFO - pc/hix.zarr zarray shape, chunks, dtype: (1000,), (100,), int64
2024-08-14 17:15:58 - pc_hix - INFO - calculating the hillbert index based on grid index
2024-08-14 17:15:58 - pc_hix - INFO - writing the hillbert index
2024-08-14 17:15:58 - pc_hix - INFO - done.
2024-08-14 17:15:58 - log_args - INFO - running function: pc_gix
2024-08-14 17:15:58 - log_args - INFO - fetching args:
2024-08-14 17:15:58 - log_args - INFO - hix = 'pc/hix.zarr'
2024-08-14 17:15:58 - log_args - INFO - gix = 'pc/gix_.zarr'
2024-08-14 17:15:58 - log_args - INFO - shape = (100, 100)
2024-08-14 17:15:58 - log_args - INFO - fetching args done.
2024-08-14 17:15:58 - zarr_info - INFO - pc/hix.zarr zarray shape, chunks, dtype: (1000,), (100,), int64
2024-08-14 17:15:58 - zarr_info - INFO - pc/gix_.zarr zarray shape, chunks, dtype: (1000, 2), (100, 1), int32
2024-08-14 17:15:58 - pc_gix - INFO - calculating the grid index from hillbert index
2024-08-14 17:15:59 - pc_gix - INFO - writing the grid index
2024-08-14 17:15:59 - pc_gix - INFO - done.pc_sort
pc_sort (idx_in:str, idx:str, pc_in:str|list=None, pc:str|list=None, shape:tuple=None, chunks:int=None, key:str=None, processes=False, n_workers=1, threads_per_worker=1, **dask_cluster_arg)
Sort point cloud data according to the indices that sort idx_in.
| Type | Default | Details | |
|---|---|---|---|
| idx_in | str | the unsorted grid index or hillbert index of the input data | |
| idx | str | output, the sorted grid index or hillbert index | |
| pc_in | str | list | None | path (in string) or list of path for the input point cloud data |
| pc | str | list | None | output, path (in string) or list of path for the output point cloud data |
| shape | tuple | None | (nline, width), faster if provided for grid index input |
| chunks | int | None | chunk size in output data, same as idx_in by default |
| key | str | None | output, path (in string) for the key of sorting |
| processes | bool | False | use process for dask worker or thread |
| n_workers | int | 1 | number of dask worker |
| threads_per_worker | int | 1 | number of threads per dask worker |
| dask_cluster_arg |
pc_in = np.random.rand(1000).astype(np.float32)
gix_in = np.random.choice(np.arange(100*100,dtype=np.int32),size=1000,replace=False)
gix_in = np.stack(np.unravel_index(gix_in,shape=(100,100)),axis=-1).astype(np.int32)
ind = np.lexsort((gix_in[:,1],gix_in[:,0]))
pc = pc_in[ind]; gix = gix_in[ind]
pc_in_zarr = zarr.open('pc/pc_in.zarr','w',shape=pc_in.shape,dtype=pc_in.dtype,chunks=(100,))
gix_in_zarr = zarr.open('pc/gix_in.zarr','w',shape=gix_in.shape,dtype=gix_in.dtype,chunks=(100,1))
pc_in_zarr[:] = pc_in; gix_in_zarr[:] = gix_inpc_sort('pc/gix_in.zarr','pc/gix.zarr','pc/pc_in.zarr','pc/pc.zarr',shape=(100,100))
pc_zarr = zarr.open('pc/pc.zarr','r'); gix_zarr = zarr.open('pc/gix.zarr','r')
np.testing.assert_array_equal(pc_zarr[:],pc)
np.testing.assert_array_equal(gix_zarr[:],gix)2024-08-14 17:15:59 - log_args - INFO - running function: pc_sort
2024-08-14 17:15:59 - log_args - INFO - fetching args:
2024-08-14 17:15:59 - log_args - INFO - idx_in = 'pc/gix_in.zarr'
2024-08-14 17:15:59 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:15:59 - log_args - INFO - pc_in = 'pc/pc_in.zarr'
2024-08-14 17:15:59 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:15:59 - log_args - INFO - shape = (100, 100)
2024-08-14 17:15:59 - log_args - INFO - chunks = None
2024-08-14 17:15:59 - log_args - INFO - key = None
2024-08-14 17:15:59 - log_args - INFO - processes = False
2024-08-14 17:15:59 - log_args - INFO - n_workers = 1
2024-08-14 17:15:59 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:15:59 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:15:59 - log_args - INFO - fetching args done.
2024-08-14 17:15:59 - zarr_info - INFO - pc/gix_in.zarr zarray shape, chunks, dtype: (1000, 2), (100, 1), int32
2024-08-14 17:15:59 - pc_sort - INFO - loading idx_in and calculate the sorting indices.
2024-08-14 17:15:59 - pc_sort - INFO - output pc chunk size is 100
2024-08-14 17:15:59 - pc_sort - INFO - write idx
2024-08-14 17:15:59 - zarr_info - INFO - idx zarray shape, chunks, dtype: (1000, 2), (100, 1), int32
2024-08-14 17:15:59 - pc_sort - INFO - starting dask local cluster.
2024-08-14 17:15:59 - pc_sort - INFO - dask local cluster started.
2024-08-14 17:15:59 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:15:59 - zarr_info - INFO - pc/pc_in.zarr zarray shape, chunks, dtype: (1000,), (100,), float32
2024-08-14 17:15:59 - darr_info - INFO - pc_in dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:15:59 - pc_sort - INFO - set up sorted pc data dask array.
2024-08-14 17:15:59 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:15:59 - pc_sort - INFO - write pc to pc/pc.zarr
2024-08-14 17:15:59 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (1000,), (100,), float32
2024-08-14 17:15:59 - pc_sort - INFO - computing graph setted. doing all the computing.
2024-08-14 17:15:59 - pc_sort - INFO - computing finished.d | 0.1s
2024-08-14 17:15:59 - pc_sort - INFO - dask cluster closed.pc_in = np.random.rand(1000).astype(np.float32)
hix_in = np.random.choice(np.arange(100*100,dtype=np.int64),size=1000,replace=False)
ind = np.argsort(hix_in,kind='stable')
pc = pc_in[ind]; hix = hix_in[ind]
pc_in_zarr = zarr.open('pc/pc_in.zarr','w',shape=pc_in.shape,dtype=pc_in.dtype,chunks=(100,))
hix_in_zarr = zarr.open('pc/hix_in.zarr','w',shape=hix_in.shape,dtype=hix_in.dtype,chunks=(100,))
pc_in_zarr[:] = pc_in; hix_in_zarr[:] = hix_in
pc_sort('pc/hix_in.zarr','pc/hix.zarr','pc/pc_in.zarr','pc/pc.zarr')
pc_zarr = zarr.open('pc/pc.zarr','r'); hix_zarr = zarr.open('pc/hix.zarr','r')
np.testing.assert_array_equal(pc_zarr[:],pc)
np.testing.assert_array_equal(hix_zarr[:],hix)2024-08-14 17:16:00 - log_args - INFO - running function: pc_sort
2024-08-14 17:16:00 - log_args - INFO - fetching args:
2024-08-14 17:16:00 - log_args - INFO - idx_in = 'pc/hix_in.zarr'
2024-08-14 17:16:00 - log_args - INFO - idx = 'pc/hix.zarr'
2024-08-14 17:16:00 - log_args - INFO - pc_in = 'pc/pc_in.zarr'
2024-08-14 17:16:00 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:16:00 - log_args - INFO - shape = None
2024-08-14 17:16:00 - log_args - INFO - chunks = None
2024-08-14 17:16:00 - log_args - INFO - key = None
2024-08-14 17:16:00 - log_args - INFO - processes = False
2024-08-14 17:16:00 - log_args - INFO - n_workers = 1
2024-08-14 17:16:00 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:00 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:00 - log_args - INFO - fetching args done.
2024-08-14 17:16:00 - zarr_info - INFO - pc/hix_in.zarr zarray shape, chunks, dtype: (1000,), (100,), int64
2024-08-14 17:16:00 - pc_sort - INFO - loading idx_in and calculate the sorting indices.
2024-08-14 17:16:00 - pc_sort - INFO - output pc chunk size is 100
2024-08-14 17:16:00 - pc_sort - INFO - write idx
2024-08-14 17:16:00 - zarr_info - INFO - idx zarray shape, chunks, dtype: (1000,), (100,), int64
2024-08-14 17:16:00 - pc_sort - INFO - starting dask local cluster.
2024-08-14 17:16:00 - pc_sort - INFO - dask local cluster started.
2024-08-14 17:16:00 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:00 - zarr_info - INFO - pc/pc_in.zarr zarray shape, chunks, dtype: (1000,), (100,), float32
2024-08-14 17:16:00 - darr_info - INFO - pc_in dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:16:00 - pc_sort - INFO - set up sorted pc data dask array.
2024-08-14 17:16:00 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:16:00 - pc_sort - INFO - write pc to pc/pc.zarr
2024-08-14 17:16:00 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (1000,), (100,), float32
2024-08-14 17:16:00 - pc_sort - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:00 - pc_sort - INFO - computing finished.d | 0.1s
2024-08-14 17:16:00 - pc_sort - INFO - dask cluster closed.pc_union
pc_union (idx1:str, idx2:str, idx:str, pc1:str|list=None, pc2:str|list=None, pc:str|list=None, shape:tuple=None, chunks:int=None, processes=False, n_workers=1, threads_per_worker=1, **dask_cluster_arg)
Get the union of two point cloud dataset. For points at their intersection, pc_data1 rather than pc_data2 is copied to the result pc_data. pc_chunk_size and n_pc_chunk are used to determine the final pc_chunk_size. If non of them are provided, the pc_chunk_size is setted as it in idx1.
| Type | Default | Details | |
|---|---|---|---|
| idx1 | str | grid index or hillbert index of the first point cloud | |
| idx2 | str | grid index or hillbert index of the second point cloud | |
| idx | str | output, grid index or hillbert index of the union point cloud | |
| pc1 | str | list | None | path (in string) or list of path for the first point cloud data |
| pc2 | str | list | None | path (in string) or list of path for the second point cloud data |
| pc | str | list | None | output, path (in string) or list of path for the union point cloud data |
| shape | tuple | None | image shape, faster if provided for grid index input |
| chunks | int | None | chunk size in output data, same as idx1 by default |
| processes | bool | False | use process for dask worker or thread |
| n_workers | int | 1 | number of dask worker |
| threads_per_worker | int | 1 | number of threads per dask worker |
| dask_cluster_arg |
Usage:
pc_data1 = np.random.rand(1000,3).astype(np.float32)+1j*np.random.rand(1000,3).astype(np.float32)
pc_data2 = np.random.rand(800,3).astype(np.float32)+1j*np.random.rand(800,3).astype(np.float32)
gix1 = np.random.choice(np.arange(100*100,dtype=np.int32),size=1000,replace=False)
gix1.sort()
gix1 = np.stack(np.unravel_index(gix1,shape=(100,100)),axis=-1).astype(np.int32)
gix2 = np.random.choice(np.arange(100*100,dtype=np.int32),size=800,replace=False)
gix2.sort()
gix2 = np.stack(np.unravel_index(gix2,shape=(100,100)),axis=-1).astype(np.int32)
gix, inv_iidx1, inv_iidx2, iidx2 = mr.pc_union(gix1,gix2)
pc_data = np.empty((gix.shape[0],*pc_data1.shape[1:]),dtype=pc_data1.dtype)
pc_data[inv_iidx1] = pc_data1
pc_data[inv_iidx2] = pc_data2[iidx2]
gix1_zarr = zarr.open('pc/gix1.zarr','w',shape=gix1.shape,dtype=gix1.dtype,chunks=(200,1))
gix2_zarr = zarr.open('pc/gix2.zarr','w',shape=gix2.shape,dtype=gix2.dtype,chunks=(200,1))
pc1_zarr = zarr.open('pc/pc1.zarr','w',shape=pc_data1.shape,dtype=pc_data1.dtype,chunks=(200,1))
pc2_zarr = zarr.open('pc/pc2.zarr','w',shape=pc_data2.shape,dtype=pc_data2.dtype,chunks=(200,1))
gix1_zarr[:] = gix1
gix2_zarr[:] = gix2
pc1_zarr[:] = pc_data1
pc2_zarr[:] = pc_data2pc_union('pc/gix1.zarr','pc/gix2.zarr','pc/gix.zarr', shape=(100,100))
pc_union('pc/gix1.zarr','pc/gix2.zarr','pc/gix.zarr','pc/pc1.zarr','pc/pc2.zarr','pc/pc.zarr')
gix_zarr = zarr.open('pc/gix.zarr','r')
pc_zarr = zarr.open('pc/pc.zarr','r')
np.testing.assert_array_equal(gix_zarr[:],gix)
np.testing.assert_array_equal(pc_zarr[:],pc_data)2024-08-14 17:16:01 - log_args - INFO - running function: pc_union
2024-08-14 17:16:01 - log_args - INFO - fetching args:
2024-08-14 17:16:01 - log_args - INFO - idx1 = 'pc/gix1.zarr'
2024-08-14 17:16:01 - log_args - INFO - idx2 = 'pc/gix2.zarr'
2024-08-14 17:16:01 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:16:01 - log_args - INFO - pc1 = None
2024-08-14 17:16:01 - log_args - INFO - pc2 = None
2024-08-14 17:16:01 - log_args - INFO - pc = None
2024-08-14 17:16:01 - log_args - INFO - shape = (100, 100)
2024-08-14 17:16:01 - log_args - INFO - chunks = None
2024-08-14 17:16:01 - log_args - INFO - processes = False
2024-08-14 17:16:01 - log_args - INFO - n_workers = 1
2024-08-14 17:16:01 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:01 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:01 - log_args - INFO - fetching args done.
2024-08-14 17:16:01 - zarr_info - INFO - pc/gix1.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:16:01 - zarr_info - INFO - pc/gix2.zarr zarray shape, chunks, dtype: (800, 2), (200, 1), int32
2024-08-14 17:16:01 - pc_union - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:01 - pc_union - INFO - calculate the union
2024-08-14 17:16:01 - pc_union - INFO - number of points in the union: 1709
2024-08-14 17:16:01 - pc_union - INFO - write union idx
2024-08-14 17:16:01 - pc_union - INFO - write done
2024-08-14 17:16:01 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (1709, 2), (200, 1), int32
2024-08-14 17:16:01 - pc_union - INFO - no point cloud data provided, exit.
2024-08-14 17:16:01 - log_args - INFO - running function: pc_union
2024-08-14 17:16:01 - log_args - INFO - fetching args:
2024-08-14 17:16:01 - log_args - INFO - idx1 = 'pc/gix1.zarr'
2024-08-14 17:16:01 - log_args - INFO - idx2 = 'pc/gix2.zarr'
2024-08-14 17:16:01 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:16:01 - log_args - INFO - pc1 = 'pc/pc1.zarr'
2024-08-14 17:16:01 - log_args - INFO - pc2 = 'pc/pc2.zarr'
2024-08-14 17:16:01 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:16:01 - log_args - INFO - shape = None
2024-08-14 17:16:01 - log_args - INFO - chunks = None
2024-08-14 17:16:01 - log_args - INFO - processes = False
2024-08-14 17:16:01 - log_args - INFO - n_workers = 1
2024-08-14 17:16:01 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:01 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:01 - log_args - INFO - fetching args done.
2024-08-14 17:16:01 - zarr_info - INFO - pc/gix1.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:16:01 - zarr_info - INFO - pc/gix2.zarr zarray shape, chunks, dtype: (800, 2), (200, 1), int32
2024-08-14 17:16:01 - pc_union - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:01 - pc_union - INFO - calculate the union
2024-08-14 17:16:01 - pc_union - INFO - number of points in the union: 1709
2024-08-14 17:16:01 - pc_union - INFO - write union idx
2024-08-14 17:16:01 - pc_union - INFO - write done
2024-08-14 17:16:01 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (1709, 2), (200, 1), int32
2024-08-14 17:16:01 - pc_union - INFO - starting dask local cluster.
2024-08-14 17:16:01 - pc_union - INFO - dask local cluster started.
2024-08-14 17:16:01 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:01 - zarr_info - INFO - pc/pc1.zarr zarray shape, chunks, dtype: (1000, 3), (200, 1), complex64
2024-08-14 17:16:01 - zarr_info - INFO - pc/pc2.zarr zarray shape, chunks, dtype: (800, 3), (200, 1), complex64
2024-08-14 17:16:01 - darr_info - INFO - pc1 dask array shape, chunksize, dtype: (1000, 3), (1000, 1), complex64
2024-08-14 17:16:01 - darr_info - INFO - pc2 dask array shape, chunksize, dtype: (800, 3), (800, 1), complex64
2024-08-14 17:16:01 - pc_union - INFO - set up union pc data dask array.
2024-08-14 17:16:01 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1709, 3), (1709, 1), complex64
2024-08-14 17:16:01 - pc_union - INFO - write pc to pc/pc.zarr
2024-08-14 17:16:01 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (1709, 3), (200, 1), complex64
2024-08-14 17:16:01 - pc_union - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:01 - pc_union - INFO - computing finished. | 0.1s
2024-08-14 17:16:01 - pc_union - INFO - dask cluster closed.pc_data1 = np.random.rand(1000,3).astype(np.float32)+1j*np.random.rand(1000,3).astype(np.float32)
pc_data2 = np.random.rand(800,3).astype(np.float32)+1j*np.random.rand(800,3).astype(np.float32)
hix1 = np.random.choice(np.arange(100*100,dtype=np.int64),size=1000,replace=False)
hix1.sort()
hix2 = np.random.choice(np.arange(100*100,dtype=np.int64),size=800,replace=False)
hix2.sort()
hix, inv_iidx1, inv_iidx2, iidx2 = mr.pc_union(hix1,hix2)
pc_data = np.empty((hix.shape[0],*pc_data1.shape[1:]),dtype=pc_data1.dtype)
pc_data[inv_iidx1] = pc_data1
pc_data[inv_iidx2] = pc_data2[iidx2]
hix1_zarr = zarr.open('pc/hix1.zarr','w',shape=hix1.shape,dtype=hix1.dtype,chunks=(200,))
hix2_zarr = zarr.open('pc/hix2.zarr','w',shape=hix2.shape,dtype=hix2.dtype,chunks=(200,))
pc1_zarr = zarr.open('pc/pc1.zarr','w',shape=pc_data1.shape,dtype=pc_data1.dtype,chunks=(200,1))
pc2_zarr = zarr.open('pc/pc2.zarr','w',shape=pc_data2.shape,dtype=pc_data2.dtype,chunks=(200,1))
hix1_zarr[:] = hix1
hix2_zarr[:] = hix2
pc1_zarr[:] = pc_data1
pc2_zarr[:] = pc_data2pc_union('pc/hix1.zarr','pc/hix2.zarr','pc/hix.zarr')
pc_union('pc/hix1.zarr','pc/hix2.zarr','pc/hix.zarr','pc/pc1.zarr','pc/pc2.zarr','pc/pc.zarr')
hix_zarr = zarr.open('pc/hix.zarr','r')
pc_zarr = zarr.open('pc/pc.zarr','r')
np.testing.assert_array_equal(hix_zarr[:],hix)
np.testing.assert_array_equal(pc_zarr[:],pc_data)2024-08-14 17:16:02 - log_args - INFO - running function: pc_union
2024-08-14 17:16:02 - log_args - INFO - fetching args:
2024-08-14 17:16:02 - log_args - INFO - idx1 = 'pc/hix1.zarr'
2024-08-14 17:16:02 - log_args - INFO - idx2 = 'pc/hix2.zarr'
2024-08-14 17:16:02 - log_args - INFO - idx = 'pc/hix.zarr'
2024-08-14 17:16:02 - log_args - INFO - pc1 = None
2024-08-14 17:16:02 - log_args - INFO - pc2 = None
2024-08-14 17:16:02 - log_args - INFO - pc = None
2024-08-14 17:16:02 - log_args - INFO - shape = None
2024-08-14 17:16:02 - log_args - INFO - chunks = None
2024-08-14 17:16:02 - log_args - INFO - processes = False
2024-08-14 17:16:02 - log_args - INFO - n_workers = 1
2024-08-14 17:16:02 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:02 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:02 - log_args - INFO - fetching args done.
2024-08-14 17:16:02 - zarr_info - INFO - pc/hix1.zarr zarray shape, chunks, dtype: (1000,), (200,), int64
2024-08-14 17:16:02 - zarr_info - INFO - pc/hix2.zarr zarray shape, chunks, dtype: (800,), (200,), int64
2024-08-14 17:16:02 - pc_union - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:02 - pc_union - INFO - calculate the union
2024-08-14 17:16:02 - pc_union - INFO - number of points in the union: 1719
2024-08-14 17:16:02 - pc_union - INFO - write union idx
2024-08-14 17:16:02 - pc_union - INFO - write done
2024-08-14 17:16:02 - zarr_info - INFO - pc/hix.zarr zarray shape, chunks, dtype: (1719,), (200,), int64
2024-08-14 17:16:02 - pc_union - INFO - no point cloud data provided, exit.
2024-08-14 17:16:02 - log_args - INFO - running function: pc_union
2024-08-14 17:16:02 - log_args - INFO - fetching args:
2024-08-14 17:16:02 - log_args - INFO - idx1 = 'pc/hix1.zarr'
2024-08-14 17:16:02 - log_args - INFO - idx2 = 'pc/hix2.zarr'
2024-08-14 17:16:02 - log_args - INFO - idx = 'pc/hix.zarr'
2024-08-14 17:16:02 - log_args - INFO - pc1 = 'pc/pc1.zarr'
2024-08-14 17:16:02 - log_args - INFO - pc2 = 'pc/pc2.zarr'
2024-08-14 17:16:02 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:16:02 - log_args - INFO - shape = None
2024-08-14 17:16:02 - log_args - INFO - chunks = None
2024-08-14 17:16:02 - log_args - INFO - processes = False
2024-08-14 17:16:02 - log_args - INFO - n_workers = 1
2024-08-14 17:16:02 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:02 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:02 - log_args - INFO - fetching args done.
2024-08-14 17:16:02 - zarr_info - INFO - pc/hix1.zarr zarray shape, chunks, dtype: (1000,), (200,), int64
2024-08-14 17:16:02 - zarr_info - INFO - pc/hix2.zarr zarray shape, chunks, dtype: (800,), (200,), int64
2024-08-14 17:16:02 - pc_union - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:02 - pc_union - INFO - calculate the union
2024-08-14 17:16:02 - pc_union - INFO - number of points in the union: 1719
2024-08-14 17:16:02 - pc_union - INFO - write union idx
2024-08-14 17:16:02 - pc_union - INFO - write done
2024-08-14 17:16:02 - zarr_info - INFO - pc/hix.zarr zarray shape, chunks, dtype: (1719,), (200,), int64
2024-08-14 17:16:02 - pc_union - INFO - starting dask local cluster.
2024-08-14 17:16:02 - pc_union - INFO - dask local cluster started.
2024-08-14 17:16:02 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:02 - zarr_info - INFO - pc/pc1.zarr zarray shape, chunks, dtype: (1000, 3), (200, 1), complex64
2024-08-14 17:16:02 - zarr_info - INFO - pc/pc2.zarr zarray shape, chunks, dtype: (800, 3), (200, 1), complex64
2024-08-14 17:16:02 - darr_info - INFO - pc1 dask array shape, chunksize, dtype: (1000, 3), (1000, 1), complex64
2024-08-14 17:16:02 - darr_info - INFO - pc2 dask array shape, chunksize, dtype: (800, 3), (800, 1), complex64
2024-08-14 17:16:02 - pc_union - INFO - set up union pc data dask array.
2024-08-14 17:16:02 - darr_info - INFO - pc dask array shape, chunksize, dtype: (1719, 3), (1719, 1), complex64
2024-08-14 17:16:02 - pc_union - INFO - write pc to pc/pc.zarr
2024-08-14 17:16:02 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (1719, 3), (200, 1), complex64
2024-08-14 17:16:02 - pc_union - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:02 - pc_union - INFO - computing finished. | 0.1s
2024-08-14 17:16:02 - pc_union - INFO - dask cluster closed.pc_intersect
pc_intersect (idx1:str, idx2:str, idx:str, pc1:str|list=None, pc2:str|list=None, pc:str|list=None, shape:tuple=None, chunks:int=None, prefer_1=True, processes=False, n_workers=1, threads_per_worker=1, **dask_cluster_arg)
Get the intersection of two point cloud dataset. pc_chunk_size and n_pc_chunk are used to determine the final pc_chunk_size. If non of them are provided, the n_pc_chunk is set to n_chunk in idx1.
| Type | Default | Details | |
|---|---|---|---|
| idx1 | str | grid index or hillbert index of the first point cloud | |
| idx2 | str | grid index or hillbert index of the second point cloud | |
| idx | str | output, grid index or hillbert index of the union point cloud | |
| pc1 | str | list | None | path (in string) or list of path for the first point cloud data |
| pc2 | str | list | None | path (in string) or list of path for the second point cloud data |
| pc | str | list | None | output, path (in string) or list of path for the union point cloud data |
| shape | tuple | None | image shape, faster if provided for grid index input |
| chunks | int | None | chunk size in output data, same as idx1 by default |
| prefer_1 | bool | True | save pc1 on intersection to output pc dataset by default True. Otherwise, save data from pc2 |
| processes | bool | False | use process for dask worker or thread |
| n_workers | int | 1 | number of dask worker |
| threads_per_worker | int | 1 | number of threads per dask worker |
| dask_cluster_arg |
Usage:
pc_data1 = np.random.rand(1000,3).astype(np.float32)+1j*np.random.rand(1000,3).astype(np.float32)
pc_data2 = np.random.rand(800,3).astype(np.float32)+1j*np.random.rand(800,3).astype(np.float32)
gix1 = np.random.choice(np.arange(100*100,dtype=np.int32),size=1000,replace=False)
gix1.sort()
gix1 = np.stack(np.unravel_index(gix1,shape=(100,100)),axis=-1).astype(np.int32)
gix2 = np.random.choice(np.arange(100*100,dtype=np.int32),size=800,replace=False)
gix2.sort()
gix2 = np.stack(np.unravel_index(gix2,shape=(100,100)),axis=-1).astype(np.int32)
gix, iidx1, iidx2 = mr.pc_intersect(gix1,gix2)
pc_data = np.empty((gix.shape[0],*pc_data1.shape[1:]),dtype=pc_data1.dtype)
pc_data[:] = pc_data2[iidx2]
gix1_zarr = zarr.open('pc/gix1.zarr','w',shape=gix1.shape,dtype=gix1.dtype,chunks=(200,1))
gix2_zarr = zarr.open('pc/gix2.zarr','w',shape=gix2.shape,dtype=gix2.dtype,chunks=(200,1))
pc1_zarr = zarr.open('pc/pc1.zarr','w',shape=pc_data1.shape,dtype=pc_data1.dtype,chunks=(200,1))
pc2_zarr = zarr.open('pc/pc2.zarr','w',shape=pc_data2.shape,dtype=pc_data2.dtype,chunks=(200,1))
gix1_zarr[:] = gix1
gix2_zarr[:] = gix2
pc1_zarr[:] = pc_data1
pc2_zarr[:] = pc_data2pc_intersect('pc/gix1.zarr','pc/gix2.zarr','pc/gix.zarr', shape=(100,100))
pc_intersect('pc/gix1.zarr','pc/gix2.zarr','pc/gix.zarr',pc2='pc/pc2.zarr', pc='pc/pc.zarr',prefer_1=False)
gix_zarr = zarr.open('pc/gix.zarr','r')
pc_zarr = zarr.open('pc/pc.zarr','r')
np.testing.assert_array_equal(gix_zarr[:],gix)
np.testing.assert_array_equal(pc_zarr[:],pc_data)2024-08-14 17:16:02 - log_args - INFO - running function: pc_intersect
2024-08-14 17:16:02 - log_args - INFO - fetching args:
2024-08-14 17:16:02 - log_args - INFO - idx1 = 'pc/gix1.zarr'
2024-08-14 17:16:02 - log_args - INFO - idx2 = 'pc/gix2.zarr'
2024-08-14 17:16:02 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:16:02 - log_args - INFO - pc1 = None
2024-08-14 17:16:02 - log_args - INFO - pc2 = None
2024-08-14 17:16:02 - log_args - INFO - pc = None
2024-08-14 17:16:02 - log_args - INFO - shape = (100, 100)
2024-08-14 17:16:02 - log_args - INFO - chunks = None
2024-08-14 17:16:02 - log_args - INFO - prefer_1 = True
2024-08-14 17:16:02 - log_args - INFO - processes = False
2024-08-14 17:16:02 - log_args - INFO - n_workers = 1
2024-08-14 17:16:02 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:02 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:02 - log_args - INFO - fetching args done.
2024-08-14 17:16:02 - zarr_info - INFO - pc/gix1.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:16:02 - zarr_info - INFO - pc/gix2.zarr zarray shape, chunks, dtype: (800, 2), (200, 1), int32
2024-08-14 17:16:02 - pc_intersect - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:02 - pc_intersect - INFO - calculate the intersection
2024-08-14 17:16:02 - pc_intersect - INFO - number of points in the intersection: 84
2024-08-14 17:16:02 - pc_intersect - INFO - write intersect idx
2024-08-14 17:16:02 - pc_intersect - INFO - write done
2024-08-14 17:16:02 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (84, 2), (200, 1), int32
2024-08-14 17:16:02 - pc_intersect - INFO - no point cloud data provided, exit.
2024-08-14 17:16:02 - log_args - INFO - running function: pc_intersect
2024-08-14 17:16:02 - log_args - INFO - fetching args:
2024-08-14 17:16:02 - log_args - INFO - idx1 = 'pc/gix1.zarr'
2024-08-14 17:16:02 - log_args - INFO - idx2 = 'pc/gix2.zarr'
2024-08-14 17:16:02 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:16:02 - log_args - INFO - pc1 = None
2024-08-14 17:16:02 - log_args - INFO - pc2 = 'pc/pc2.zarr'
2024-08-14 17:16:02 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:16:02 - log_args - INFO - shape = None
2024-08-14 17:16:02 - log_args - INFO - chunks = None
2024-08-14 17:16:02 - log_args - INFO - prefer_1 = False
2024-08-14 17:16:02 - log_args - INFO - processes = False
2024-08-14 17:16:02 - log_args - INFO - n_workers = 1
2024-08-14 17:16:02 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:02 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:02 - log_args - INFO - fetching args done.
2024-08-14 17:16:02 - zarr_info - INFO - pc/gix1.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:16:02 - zarr_info - INFO - pc/gix2.zarr zarray shape, chunks, dtype: (800, 2), (200, 1), int32
2024-08-14 17:16:02 - pc_intersect - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:02 - pc_intersect - INFO - calculate the intersection
2024-08-14 17:16:02 - pc_intersect - INFO - number of points in the intersection: 84
2024-08-14 17:16:02 - pc_intersect - INFO - write intersect idx
2024-08-14 17:16:02 - pc_intersect - INFO - write done
2024-08-14 17:16:02 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (84, 2), (200, 1), int32
2024-08-14 17:16:02 - pc_intersect - INFO - select pc2 as pc_input.
2024-08-14 17:16:02 - pc_intersect - INFO - starting dask local cluster.
2024-08-14 17:16:02 - pc_intersect - INFO - dask local cluster started.
2024-08-14 17:16:02 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:02 - zarr_info - INFO - pc/pc2.zarr zarray shape, chunks, dtype: (800, 3), (200, 1), complex64
2024-08-14 17:16:02 - darr_info - INFO - pc_input dask array shape, chunksize, dtype: (800, 3), (800, 1), complex64
2024-08-14 17:16:02 - pc_intersect - INFO - set up intersect pc data dask array.
2024-08-14 17:16:02 - darr_info - INFO - pc dask array shape, chunksize, dtype: (84, 3), (84, 1), complex64
2024-08-14 17:16:02 - pc_intersect - INFO - write pc to pc/pc.zarr
2024-08-14 17:16:02 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (84, 3), (200, 1), complex64
2024-08-14 17:16:02 - pc_intersect - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:03 - pc_intersect - INFO - computing finished.0.1s
2024-08-14 17:16:03 - pc_intersect - INFO - dask cluster closed.pc_data1 = np.random.rand(1000,3).astype(np.float32)+1j*np.random.rand(1000,3).astype(np.float32)
pc_data2 = np.random.rand(800,3).astype(np.float32)+1j*np.random.rand(800,3).astype(np.float32)
hix1 = np.random.choice(np.arange(100*100,dtype=np.int64),size=1000,replace=False)
hix1.sort()
hix2 = np.random.choice(np.arange(100*100,dtype=np.int64),size=800,replace=False)
hix2.sort()
hix, iidx1, iidx2 = mr.pc_intersect(hix1,hix2)
pc_data = np.empty((hix.shape[-1],*pc_data1.shape[1:]),dtype=pc_data1.dtype)
pc_data[:] = pc_data2[iidx2]
hix1_zarr = zarr.open('pc/hix1.zarr','w',shape=hix1.shape,dtype=hix1.dtype,chunks=(200,))
hix2_zarr = zarr.open('pc/hix2.zarr','w',shape=hix2.shape,dtype=hix2.dtype,chunks=(200,))
pc1_zarr = zarr.open('pc/pc1.zarr','w',shape=pc_data1.shape,dtype=pc_data1.dtype,chunks=(200,1))
pc2_zarr = zarr.open('pc/pc2.zarr','w',shape=pc_data2.shape,dtype=pc_data2.dtype,chunks=(200,1))
hix1_zarr[:] = hix1
hix2_zarr[:] = hix2
pc1_zarr[:] = pc_data1
pc2_zarr[:] = pc_data2pc_intersect('pc/hix1.zarr','pc/hix2.zarr','pc/hix.zarr')
pc_intersect('pc/hix1.zarr','pc/hix2.zarr','pc/hix.zarr',pc2='pc/pc2.zarr', pc='pc/pc.zarr',prefer_1=False)
hix_zarr = zarr.open('pc/hix.zarr','r')
pc_zarr = zarr.open('pc/pc.zarr','r')
np.testing.assert_array_equal(hix_zarr[:],hix)
np.testing.assert_array_equal(pc_zarr[:],pc_data)2024-08-14 17:16:03 - log_args - INFO - running function: pc_intersect
2024-08-14 17:16:03 - log_args - INFO - fetching args:
2024-08-14 17:16:03 - log_args - INFO - idx1 = 'pc/hix1.zarr'
2024-08-14 17:16:03 - log_args - INFO - idx2 = 'pc/hix2.zarr'
2024-08-14 17:16:03 - log_args - INFO - idx = 'pc/hix.zarr'
2024-08-14 17:16:03 - log_args - INFO - pc1 = None
2024-08-14 17:16:03 - log_args - INFO - pc2 = None
2024-08-14 17:16:03 - log_args - INFO - pc = None
2024-08-14 17:16:03 - log_args - INFO - shape = None
2024-08-14 17:16:03 - log_args - INFO - chunks = None
2024-08-14 17:16:03 - log_args - INFO - prefer_1 = True
2024-08-14 17:16:03 - log_args - INFO - processes = False
2024-08-14 17:16:03 - log_args - INFO - n_workers = 1
2024-08-14 17:16:03 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:03 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:03 - log_args - INFO - fetching args done.
2024-08-14 17:16:03 - zarr_info - INFO - pc/hix1.zarr zarray shape, chunks, dtype: (1000,), (200,), int64
2024-08-14 17:16:03 - zarr_info - INFO - pc/hix2.zarr zarray shape, chunks, dtype: (800,), (200,), int64
2024-08-14 17:16:03 - pc_intersect - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:03 - pc_intersect - INFO - calculate the intersection
2024-08-14 17:16:03 - pc_intersect - INFO - number of points in the intersection: 80
2024-08-14 17:16:03 - pc_intersect - INFO - write intersect idx
2024-08-14 17:16:03 - pc_intersect - INFO - write done
2024-08-14 17:16:03 - zarr_info - INFO - pc/hix.zarr zarray shape, chunks, dtype: (80,), (200,), int64
2024-08-14 17:16:03 - pc_intersect - INFO - no point cloud data provided, exit.
2024-08-14 17:16:03 - log_args - INFO - running function: pc_intersect
2024-08-14 17:16:03 - log_args - INFO - fetching args:
2024-08-14 17:16:03 - log_args - INFO - idx1 = 'pc/hix1.zarr'
2024-08-14 17:16:03 - log_args - INFO - idx2 = 'pc/hix2.zarr'
2024-08-14 17:16:03 - log_args - INFO - idx = 'pc/hix.zarr'
2024-08-14 17:16:03 - log_args - INFO - pc1 = None
2024-08-14 17:16:03 - log_args - INFO - pc2 = 'pc/pc2.zarr'
2024-08-14 17:16:03 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:16:03 - log_args - INFO - shape = None
2024-08-14 17:16:03 - log_args - INFO - chunks = None
2024-08-14 17:16:03 - log_args - INFO - prefer_1 = False
2024-08-14 17:16:03 - log_args - INFO - processes = False
2024-08-14 17:16:03 - log_args - INFO - n_workers = 1
2024-08-14 17:16:03 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:03 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:03 - log_args - INFO - fetching args done.
2024-08-14 17:16:03 - zarr_info - INFO - pc/hix1.zarr zarray shape, chunks, dtype: (1000,), (200,), int64
2024-08-14 17:16:03 - zarr_info - INFO - pc/hix2.zarr zarray shape, chunks, dtype: (800,), (200,), int64
2024-08-14 17:16:03 - pc_intersect - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:03 - pc_intersect - INFO - calculate the intersection
2024-08-14 17:16:03 - pc_intersect - INFO - number of points in the intersection: 80
2024-08-14 17:16:03 - pc_intersect - INFO - write intersect idx
2024-08-14 17:16:03 - pc_intersect - INFO - write done
2024-08-14 17:16:03 - zarr_info - INFO - pc/hix.zarr zarray shape, chunks, dtype: (80,), (200,), int64
2024-08-14 17:16:03 - pc_intersect - INFO - select pc2 as pc_input.
2024-08-14 17:16:03 - pc_intersect - INFO - starting dask local cluster.
2024-08-14 17:16:03 - pc_intersect - INFO - dask local cluster started.
2024-08-14 17:16:03 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:03 - zarr_info - INFO - pc/pc2.zarr zarray shape, chunks, dtype: (800, 3), (200, 1), complex64
2024-08-14 17:16:03 - darr_info - INFO - pc_input dask array shape, chunksize, dtype: (800, 3), (800, 1), complex64
2024-08-14 17:16:03 - pc_intersect - INFO - set up intersect pc data dask array.
2024-08-14 17:16:03 - darr_info - INFO - pc dask array shape, chunksize, dtype: (80, 3), (80, 1), complex64
2024-08-14 17:16:03 - pc_intersect - INFO - write pc to pc/pc.zarr
2024-08-14 17:16:03 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (80, 3), (200, 1), complex64
2024-08-14 17:16:03 - pc_intersect - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:03 - pc_intersect - INFO - computing finished.0.1s
2024-08-14 17:16:03 - pc_intersect - INFO - dask cluster closed.pc_diff
pc_diff (idx1:str, idx2:str, idx:str, pc1:str|list=None, pc:str|list=None, shape:tuple=None, chunks:int=None, processes=False, n_workers=1, threads_per_worker=1, **dask_cluster_arg)
Get the point cloud in idx1 that are not in idx2. pc_chunk_size and n_pc_chunk are used to determine the final pc_chunk_size. If non of them are provided, the n_pc_chunk is set to n_chunk in idx1.
| Type | Default | Details | |
|---|---|---|---|
| idx1 | str | grid index or hillbert index of the first point cloud | |
| idx2 | str | grid index or hillbert index of the second point cloud | |
| idx | str | output, grid index or hillbert index of the union point cloud | |
| pc1 | str | list | None | path (in string) or list of path for the first point cloud data |
| pc | str | list | None | output, path (in string) or list of path for the union point cloud data |
| shape | tuple | None | image shape, faster if provided for grid index input |
| chunks | int | None | chunk size in output data,optional |
| processes | bool | False | use process for dask worker or thread |
| n_workers | int | 1 | number of dask worker |
| threads_per_worker | int | 1 | number of threads per dask worker |
| dask_cluster_arg |
Usage:
pc_data1 = np.random.rand(1000,3).astype(np.float32)+1j*np.random.rand(1000,3).astype(np.float32)
gix1 = np.random.choice(np.arange(100*100,dtype=np.int32),size=1000,replace=False)
gix1.sort()
gix1 = np.stack(np.unravel_index(gix1,shape=(100,100)),axis=-1).astype(np.int32)
gix2 = np.random.choice(np.arange(100*100,dtype=np.int32),size=800,replace=False)
gix2.sort()
gix2 = np.stack(np.unravel_index(gix2,shape=(100,100)),axis=-1).astype(np.int32)
gix, iidx1 = mr.pc_diff(gix1,gix2)
pc_data = np.empty((gix.shape[0],*pc_data1.shape[1:]),dtype=pc_data1.dtype)
pc_data[:] = pc_data1[iidx1]
gix1_zarr = zarr.open('pc/gix1.zarr','w',shape=gix1.shape,dtype=gix1.dtype,chunks=(200,1))
gix2_zarr = zarr.open('pc/gix2.zarr','w',shape=gix2.shape,dtype=gix2.dtype,chunks=(200,1))
pc1_zarr = zarr.open('pc/pc1.zarr','w',shape=pc_data1.shape,dtype=pc_data1.dtype,chunks=(200,1))
gix1_zarr[:] = gix1
gix2_zarr[:] = gix2
pc1_zarr[:] = pc_data1pc_diff('pc/gix1.zarr','pc/gix2.zarr','pc/gix.zarr')
pc_diff('pc/gix1.zarr','pc/gix2.zarr','pc/gix.zarr',pc1='pc/pc1.zarr', pc='pc/pc.zarr')
gix_zarr = zarr.open('pc/gix.zarr','r')
pc_zarr = zarr.open('pc/pc.zarr','r')
np.testing.assert_array_equal(gix_zarr[:],gix)
np.testing.assert_array_equal(pc_zarr[:],pc_data)2024-08-14 17:16:03 - log_args - INFO - running function: pc_diff
2024-08-14 17:16:03 - log_args - INFO - fetching args:
2024-08-14 17:16:03 - log_args - INFO - idx1 = 'pc/gix1.zarr'
2024-08-14 17:16:03 - log_args - INFO - idx2 = 'pc/gix2.zarr'
2024-08-14 17:16:03 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:16:03 - log_args - INFO - pc1 = None
2024-08-14 17:16:03 - log_args - INFO - pc = None
2024-08-14 17:16:03 - log_args - INFO - shape = None
2024-08-14 17:16:03 - log_args - INFO - chunks = None
2024-08-14 17:16:03 - log_args - INFO - processes = False
2024-08-14 17:16:03 - log_args - INFO - n_workers = 1
2024-08-14 17:16:03 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:03 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:03 - log_args - INFO - fetching args done.
2024-08-14 17:16:03 - zarr_info - INFO - pc/gix1.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:16:03 - zarr_info - INFO - pc/gix2.zarr zarray shape, chunks, dtype: (800, 2), (200, 1), int32
2024-08-14 17:16:03 - pc_diff - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:03 - pc_diff - INFO - calculate the diff.
2024-08-14 17:16:03 - pc_diff - INFO - number of points in the diff: 933
2024-08-14 17:16:04 - pc_diff - INFO - write intersect idx
2024-08-14 17:16:04 - pc_diff - INFO - write done
2024-08-14 17:16:04 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (933, 2), (200, 1), int32
2024-08-14 17:16:04 - pc_diff - INFO - no point cloud data provided, exit.
2024-08-14 17:16:04 - log_args - INFO - running function: pc_diff
2024-08-14 17:16:04 - log_args - INFO - fetching args:
2024-08-14 17:16:04 - log_args - INFO - idx1 = 'pc/gix1.zarr'
2024-08-14 17:16:04 - log_args - INFO - idx2 = 'pc/gix2.zarr'
2024-08-14 17:16:04 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:16:04 - log_args - INFO - pc1 = 'pc/pc1.zarr'
2024-08-14 17:16:04 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:16:04 - log_args - INFO - shape = None
2024-08-14 17:16:04 - log_args - INFO - chunks = None
2024-08-14 17:16:04 - log_args - INFO - processes = False
2024-08-14 17:16:04 - log_args - INFO - n_workers = 1
2024-08-14 17:16:04 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:04 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:04 - log_args - INFO - fetching args done.
2024-08-14 17:16:04 - zarr_info - INFO - pc/gix1.zarr zarray shape, chunks, dtype: (1000, 2), (200, 1), int32
2024-08-14 17:16:04 - zarr_info - INFO - pc/gix2.zarr zarray shape, chunks, dtype: (800, 2), (200, 1), int32
2024-08-14 17:16:04 - pc_diff - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:04 - pc_diff - INFO - calculate the diff.
2024-08-14 17:16:04 - pc_diff - INFO - number of points in the diff: 933
2024-08-14 17:16:04 - pc_diff - INFO - write intersect idx
2024-08-14 17:16:04 - pc_diff - INFO - write done
2024-08-14 17:16:04 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (933, 2), (200, 1), int32
2024-08-14 17:16:04 - pc_diff - INFO - starting dask local cluster.
2024-08-14 17:16:04 - pc_diff - INFO - dask local cluster started.
2024-08-14 17:16:04 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:04 - zarr_info - INFO - pc/pc1.zarr zarray shape, chunks, dtype: (1000, 3), (200, 1), complex64
2024-08-14 17:16:04 - darr_info - INFO - pc1 dask array shape, chunksize, dtype: (1000, 3), (1000, 1), complex64
2024-08-14 17:16:04 - pc_diff - INFO - set up diff pc data dask array.
2024-08-14 17:16:04 - darr_info - INFO - pc dask array shape, chunksize, dtype: (933, 3), (933, 1), complex64
2024-08-14 17:16:04 - pc_diff - INFO - write pc to pc/pc.zarr
2024-08-14 17:16:04 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (933, 3), (200, 1), complex64
2024-08-14 17:16:04 - pc_diff - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:04 - pc_diff - INFO - computing finished.d | 0.1s
2024-08-14 17:16:04 - pc_diff - INFO - dask cluster closed.pc_data1 = np.random.rand(1000,3).astype(np.float32)+1j*np.random.rand(1000,3).astype(np.float32)
hix1 = np.random.choice(np.arange(100*100,dtype=np.int64),size=1000,replace=False)
hix1.sort()
hix2 = np.random.choice(np.arange(100*100,dtype=np.int64),size=800,replace=False)
hix2.sort()
hix, iidx1 = mr.pc_diff(hix1,hix2)
pc_data = np.empty((hix.shape[-1],*pc_data1.shape[1:]),dtype=pc_data1.dtype)
pc_data[:] = pc_data1[iidx1]
hix1_zarr = zarr.open('pc/hix1.zarr','w',shape=hix1.shape,dtype=hix1.dtype,chunks=(200,))
hix2_zarr = zarr.open('pc/hix2.zarr','w',shape=hix2.shape,dtype=hix2.dtype,chunks=(200,))
pc1_zarr = zarr.open('pc/pc1.zarr','w',shape=pc_data1.shape,dtype=pc_data1.dtype,chunks=(200,1))
hix1_zarr[:] = hix1
hix2_zarr[:] = hix2
pc1_zarr[:] = pc_data1pc_diff('pc/hix1.zarr','pc/hix2.zarr','pc/hix.zarr')
pc_diff('pc/hix1.zarr','pc/hix2.zarr','pc/hix.zarr',pc1='pc/pc1.zarr', pc='pc/pc.zarr')
hix_zarr = zarr.open('pc/hix.zarr','r')
pc_zarr = zarr.open('pc/pc.zarr','r')
np.testing.assert_array_equal(hix_zarr[:],hix)
np.testing.assert_array_equal(pc_zarr[:],pc_data)2024-08-14 17:16:04 - log_args - INFO - running function: pc_diff
2024-08-14 17:16:04 - log_args - INFO - fetching args:
2024-08-14 17:16:04 - log_args - INFO - idx1 = 'pc/hix1.zarr'
2024-08-14 17:16:04 - log_args - INFO - idx2 = 'pc/hix2.zarr'
2024-08-14 17:16:04 - log_args - INFO - idx = 'pc/hix.zarr'
2024-08-14 17:16:04 - log_args - INFO - pc1 = None
2024-08-14 17:16:04 - log_args - INFO - pc = None
2024-08-14 17:16:04 - log_args - INFO - shape = None
2024-08-14 17:16:04 - log_args - INFO - chunks = None
2024-08-14 17:16:04 - log_args - INFO - processes = False
2024-08-14 17:16:04 - log_args - INFO - n_workers = 1
2024-08-14 17:16:04 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:04 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:04 - log_args - INFO - fetching args done.
2024-08-14 17:16:04 - zarr_info - INFO - pc/hix1.zarr zarray shape, chunks, dtype: (1000,), (200,), int64
2024-08-14 17:16:04 - zarr_info - INFO - pc/hix2.zarr zarray shape, chunks, dtype: (800,), (200,), int64
2024-08-14 17:16:04 - pc_diff - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:04 - pc_diff - INFO - calculate the diff.
2024-08-14 17:16:04 - pc_diff - INFO - number of points in the diff: 920
2024-08-14 17:16:04 - pc_diff - INFO - write intersect idx
2024-08-14 17:16:04 - pc_diff - INFO - write done
2024-08-14 17:16:04 - zarr_info - INFO - pc/hix.zarr zarray shape, chunks, dtype: (920,), (200,), int64
2024-08-14 17:16:04 - pc_diff - INFO - no point cloud data provided, exit.
2024-08-14 17:16:04 - log_args - INFO - running function: pc_diff
2024-08-14 17:16:04 - log_args - INFO - fetching args:
2024-08-14 17:16:04 - log_args - INFO - idx1 = 'pc/hix1.zarr'
2024-08-14 17:16:04 - log_args - INFO - idx2 = 'pc/hix2.zarr'
2024-08-14 17:16:04 - log_args - INFO - idx = 'pc/hix.zarr'
2024-08-14 17:16:04 - log_args - INFO - pc1 = 'pc/pc1.zarr'
2024-08-14 17:16:04 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:16:04 - log_args - INFO - shape = None
2024-08-14 17:16:04 - log_args - INFO - chunks = None
2024-08-14 17:16:04 - log_args - INFO - processes = False
2024-08-14 17:16:04 - log_args - INFO - n_workers = 1
2024-08-14 17:16:04 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:04 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:04 - log_args - INFO - fetching args done.
2024-08-14 17:16:04 - zarr_info - INFO - pc/hix1.zarr zarray shape, chunks, dtype: (1000,), (200,), int64
2024-08-14 17:16:04 - zarr_info - INFO - pc/hix2.zarr zarray shape, chunks, dtype: (800,), (200,), int64
2024-08-14 17:16:04 - pc_diff - INFO - loading idx1 and idx2 into memory.
2024-08-14 17:16:04 - pc_diff - INFO - calculate the diff.
2024-08-14 17:16:04 - pc_diff - INFO - number of points in the diff: 920
2024-08-14 17:16:04 - pc_diff - INFO - write intersect idx
2024-08-14 17:16:04 - pc_diff - INFO - write done
2024-08-14 17:16:04 - zarr_info - INFO - pc/hix.zarr zarray shape, chunks, dtype: (920,), (200,), int64
2024-08-14 17:16:04 - pc_diff - INFO - starting dask local cluster.
2024-08-14 17:16:04 - pc_diff - INFO - dask local cluster started.
2024-08-14 17:16:04 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:04 - zarr_info - INFO - pc/pc1.zarr zarray shape, chunks, dtype: (1000, 3), (200, 1), complex64
2024-08-14 17:16:04 - darr_info - INFO - pc1 dask array shape, chunksize, dtype: (1000, 3), (1000, 1), complex64
2024-08-14 17:16:04 - pc_diff - INFO - set up diff pc data dask array.
2024-08-14 17:16:04 - darr_info - INFO - pc dask array shape, chunksize, dtype: (920, 3), (920, 1), complex64
2024-08-14 17:16:04 - pc_diff - INFO - write pc to pc/pc.zarr
2024-08-14 17:16:04 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (920, 3), (200, 1), complex64
2024-08-14 17:16:04 - pc_diff - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:05 - pc_diff - INFO - computing finished.d | 0.2s
2024-08-14 17:16:05 - pc_diff - INFO - dask cluster closed.pc_logic_ras
pc_logic_ras (ras, gix, operation:str, chunks:int=100000)
generate point cloud index based on logical operation of one raster image.
| Type | Default | Details | |
|---|---|---|---|
| ras | the raster image used for thresholding | ||
| gix | output, grid index of selected pixels | ||
| operation | str | logical operation on input ras | |
| chunks | int | 100000 | chunk size in output data, optional |
ras = np.random.rand(100,100).astype(np.float32)
min_thres = 0.1; max_thres=0.5
is_pc = (ras>=min_thres) & (ras<=max_thres)
gix = np.stack(np.where(is_pc),axis=-1).astype(np.int32)
ras_zarr = zarr.open('pc/ras.zarr','rw',shape=ras.shape,dtype=ras.dtype,chunks=(10,100))
ras_zarr[:] = raspc_logic_ras('pc/ras.zarr','pc/gix.zarr',f'(ras>={min_thres})&(ras<={max_thres})')
gix_zarr = zarr.open('pc/gix.zarr','r')
np.testing.assert_array_equal(gix_zarr[:],gix)2024-08-14 17:16:05 - log_args - INFO - running function: pc_logic_ras
2024-08-14 17:16:05 - log_args - INFO - fetching args:
2024-08-14 17:16:05 - log_args - INFO - ras = 'pc/ras.zarr'
2024-08-14 17:16:05 - log_args - INFO - gix = 'pc/gix.zarr'
2024-08-14 17:16:05 - log_args - INFO - operation = '(ras>=0.1)&(ras<=0.5)'
2024-08-14 17:16:05 - log_args - INFO - chunks = 100000
2024-08-14 17:16:05 - log_args - INFO - fetching args done.
2024-08-14 17:16:05 - zarr_info - INFO - pc/ras.zarr zarray shape, chunks, dtype: (100, 100), (10, 100), float32
2024-08-14 17:16:05 - pc_logic_ras - INFO - loading ras into memory.
2024-08-14 17:16:05 - pc_logic_ras - INFO - select pc based on operation: (ras>=0.1)&(ras<=0.5)
2024-08-14 17:16:05 - pc_logic_ras - INFO - number of selected pixels: 3987.
2024-08-14 17:16:05 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (3987, 2), (100000, 1), int32
2024-08-14 17:16:05 - pc_logic_ras - INFO - writing gix.
2024-08-14 17:16:05 - pc_logic_ras - INFO - write done.pc_logic_pc
pc_logic_pc (idx_in:str, pc_in:str, idx:str, operation:str, chunks:int=None)
generate point cloud index and data based on logical operation one point cloud data.
| Type | Default | Details | |
|---|---|---|---|
| idx_in | str | the grid index or hillbert index of input pc data | |
| pc_in | str | the grid index or hillbert index cloud data used for thresholding | |
| idx | str | output, grid index or hillbert index of selected pixels | |
| operation | str | operator | |
| chunks | int | None | chunk size in output data,optional |
Usage:
pc_in = np.random.rand(1000).astype(np.float32)
gix_in = np.random.choice(np.arange(100*100,dtype=np.int32),size=1000,replace=False)
gix_in.sort()
gix_in = np.stack(np.unravel_index(gix_in,shape=(100,100)),axis=-1).astype(np.int32)
min_thres = 0.1; max_thres=0.5
is_pc = (pc_in>=min_thres) & (pc_in<=max_thres)
gix = gix_in[is_pc]
pc_in_zarr = zarr.open('pc/pc_in.zarr','w',shape=pc_in.shape,dtype=pc_in.dtype,chunks=(100,))
gix_in_zarr = zarr.open('pc/gix_in.zarr','w',shape=gix_in.shape,dtype=gix_in.dtype,chunks=(100,1))
pc_in_zarr[:] = pc_in; gix_in_zarr[:] = gix_inpc_logic_pc('pc/gix_in.zarr','pc/pc_in.zarr','pc/gix.zarr',f'(pc_in>={min_thres})&(pc_in<={max_thres})')
gix_zarr = zarr.open('pc/gix.zarr','r')
np.testing.assert_array_equal(gix_zarr[:],gix)2024-08-14 17:16:05 - log_args - INFO - running function: pc_logic_pc
2024-08-14 17:16:05 - log_args - INFO - fetching args:
2024-08-14 17:16:05 - log_args - INFO - idx_in = 'pc/gix_in.zarr'
2024-08-14 17:16:05 - log_args - INFO - pc_in = 'pc/pc_in.zarr'
2024-08-14 17:16:05 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:16:05 - log_args - INFO - operation = '(pc_in>=0.1)&(pc_in<=0.5)'
2024-08-14 17:16:05 - log_args - INFO - chunks = None
2024-08-14 17:16:05 - log_args - INFO - fetching args done.
2024-08-14 17:16:05 - zarr_info - INFO - pc/gix_in.zarr zarray shape, chunks, dtype: (1000, 2), (100, 1), int32
2024-08-14 17:16:05 - zarr_info - INFO - pc/pc_in.zarr zarray shape, chunks, dtype: (1000,), (100,), float32
2024-08-14 17:16:05 - pc_logic_pc - INFO - loading idx_in into memory.
2024-08-14 17:16:05 - pc_logic_pc - INFO - loading pc_in into memory.
2024-08-14 17:16:05 - pc_logic_pc - INFO - select pc based on operation: (pc_in>=0.1)&(pc_in<=0.5)
2024-08-14 17:16:05 - pc_logic_pc - INFO - number of selected pixels: 435.
2024-08-14 17:16:05 - zarr_info - INFO - idx zarray shape, chunks, dtype: (435, 2), (100, 1), int32
2024-08-14 17:16:05 - pc_logic_pc - INFO - writing idx.
2024-08-14 17:16:05 - pc_logic_pc - INFO - write done.pc_in = np.random.rand(1000).astype(np.float32)
hix_in = np.random.choice(np.arange(100*100,dtype=np.int64),size=1000,replace=False)
hix_in.sort()
min_thres = 0.1; max_thres=0.5
is_pc = (pc_in>=min_thres) & (pc_in<=max_thres)
hix = hix_in[is_pc]
pc_in_zarr = zarr.open('pc/pc_in.zarr','w',shape=pc_in.shape,dtype=pc_in.dtype,chunks=(100,))
hix_in_zarr = zarr.open('pc/hix_in.zarr','w',shape=hix_in.shape,dtype=hix_in.dtype,chunks=(100,))
pc_in_zarr[:] = pc_in; hix_in_zarr[:] = hix_in
pc_logic_pc('pc/hix_in.zarr','pc/pc_in.zarr','pc/hix.zarr',f'(pc_in>={min_thres})&(pc_in<={max_thres})')
hix_zarr = zarr.open('pc/hix.zarr','r')
np.testing.assert_array_equal(hix_zarr[:],hix)2024-08-14 17:16:05 - log_args - INFO - running function: pc_logic_pc
2024-08-14 17:16:05 - log_args - INFO - fetching args:
2024-08-14 17:16:05 - log_args - INFO - idx_in = 'pc/hix_in.zarr'
2024-08-14 17:16:05 - log_args - INFO - pc_in = 'pc/pc_in.zarr'
2024-08-14 17:16:05 - log_args - INFO - idx = 'pc/hix.zarr'
2024-08-14 17:16:05 - log_args - INFO - operation = '(pc_in>=0.1)&(pc_in<=0.5)'
2024-08-14 17:16:05 - log_args - INFO - chunks = None
2024-08-14 17:16:05 - log_args - INFO - fetching args done.
2024-08-14 17:16:05 - zarr_info - INFO - pc/hix_in.zarr zarray shape, chunks, dtype: (1000,), (100,), int64
2024-08-14 17:16:05 - zarr_info - INFO - pc/pc_in.zarr zarray shape, chunks, dtype: (1000,), (100,), float32
2024-08-14 17:16:05 - pc_logic_pc - INFO - loading idx_in into memory.
2024-08-14 17:16:05 - pc_logic_pc - INFO - loading pc_in into memory.
2024-08-14 17:16:05 - pc_logic_pc - INFO - select pc based on operation: (pc_in>=0.1)&(pc_in<=0.5)
2024-08-14 17:16:05 - pc_logic_pc - INFO - number of selected pixels: 381.
2024-08-14 17:16:05 - zarr_info - INFO - idx zarray shape, chunks, dtype: (381,), (100,), int64
2024-08-14 17:16:05 - pc_logic_pc - INFO - writing idx.
2024-08-14 17:16:05 - pc_logic_pc - INFO - write done.pc_select_data
pc_select_data (idx_in:str, idx:str, pc_in:str|list, pc:str|list, shape:tuple=None, chunks:int=None, processes=False, n_workers=1, threads_per_worker=1, **dask_cluster_arg)
generate point cloud data based on its index and one point cloud data. The index of generated point cloud data must in the index of the old one.
| Type | Default | Details | |
|---|---|---|---|
| idx_in | str | the grid index or hillbert index of the input data | |
| idx | str | the grid index or hillbert index of the output data | |
| pc_in | str | list | path (in string) or list of path for the input point cloud data | |
| pc | str | list | output, path (in string) or list of path for the output point cloud data | |
| shape | tuple | None | shape of the raster data the point cloud from, must be provided if idx is hix |
| chunks | int | None | chunk size in output data, same as chunks of idx by default |
| processes | bool | False | use process for dask worker or thread |
| n_workers | int | 1 | number of dask worker |
| threads_per_worker | int | 1 | number of threads per dask worker |
| dask_cluster_arg |
pc_in = np.random.rand(1000,4).astype(np.float32)
gix_in = np.random.choice(np.arange(100*100,dtype=np.int32),size=1000,replace=False)
gix_in.sort()
gix_in = np.stack(np.unravel_index(gix_in,shape=(100,100)),axis=-1).astype(np.int32)
iidx_in = np.random.choice(np.arange(1000,dtype=np.int64),size=500,replace=False); iidx_in.sort()
gix = gix_in[iidx_in]
pc = pc_in[iidx_in]
pc_in_zarr = zarr.open('pc/pc_in.zarr','w',shape=pc_in.shape,dtype=pc_in.dtype,chunks=(100,1))
gix_in_zarr = zarr.open('pc/gix_in.zarr','w',shape=gix_in.shape,dtype=gix_in.dtype,chunks=(100,1))
gix_zarr = zarr.open('pc/gix.zarr','w',shape=gix.shape,dtype=gix.dtype,chunks=(100,1))
pc_in_zarr[:] = pc_in; gix_in_zarr[:] = gix_in; gix_zarr[:] = gixpc_select_data('pc/gix_in.zarr','pc/gix.zarr','pc/pc_in.zarr','pc/pc.zarr')
pc_zarr = zarr.open('pc/pc.zarr','r')
np.testing.assert_array_equal(pc_zarr[:],pc)2024-08-14 17:16:06 - log_args - INFO - running function: pc_select_data
2024-08-14 17:16:06 - log_args - INFO - fetching args:
2024-08-14 17:16:06 - log_args - INFO - idx_in = 'pc/gix_in.zarr'
2024-08-14 17:16:06 - log_args - INFO - idx = 'pc/gix.zarr'
2024-08-14 17:16:06 - log_args - INFO - pc_in = 'pc/pc_in.zarr'
2024-08-14 17:16:06 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:16:06 - log_args - INFO - shape = None
2024-08-14 17:16:06 - log_args - INFO - chunks = None
2024-08-14 17:16:06 - log_args - INFO - processes = False
2024-08-14 17:16:06 - log_args - INFO - n_workers = 1
2024-08-14 17:16:06 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:06 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:06 - log_args - INFO - fetching args done.
2024-08-14 17:16:06 - zarr_info - INFO - pc/gix_in.zarr zarray shape, chunks, dtype: (1000, 2), (100, 1), int32
2024-08-14 17:16:06 - zarr_info - INFO - pc/gix.zarr zarray shape, chunks, dtype: (500, 2), (100, 1), int32
2024-08-14 17:16:06 - pc_select_data - INFO - loading idx_in and idx into memory.
2024-08-14 17:16:07 - pc_select_data - INFO - starting dask local cluster.
2024-08-14 17:16:07 - pc_select_data - INFO - dask local cluster started.
2024-08-14 17:16:07 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:07 - zarr_info - INFO - pc/pc_in.zarr zarray shape, chunks, dtype: (1000, 4), (100, 1), float32
2024-08-14 17:16:07 - darr_info - INFO - pc_in dask array shape, chunksize, dtype: (1000, 4), (1000, 1), float32
2024-08-14 17:16:07 - pc_select_data - INFO - set up selected pc data dask array.
2024-08-14 17:16:07 - darr_info - INFO - pc dask array shape, chunksize, dtype: (500, 4), (500, 1), float32
2024-08-14 17:16:07 - pc_select_data - INFO - write pc to pc/pc.zarr
2024-08-14 17:16:07 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (500, 4), (100, 1), float32
2024-08-14 17:16:07 - pc_select_data - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:07 - pc_select_data - INFO - computing finished.1s
2024-08-14 17:16:07 - pc_select_data - INFO - dask cluster closed.pc_in = np.random.rand(1000).astype(np.float32)
hix_in = np.random.choice(np.arange(100*100,dtype=np.int64),size=1000,replace=False)
hix_in.sort()
iidx_in = np.random.choice(np.arange(1000,dtype=np.int64),size=500,replace=False)
iidx_in.sort()
hix = hix_in[iidx_in]
pc = pc_in[iidx_in]
pc_in_zarr = zarr.open('pc/pc_in.zarr','w',shape=pc_in.shape,dtype=pc_in.dtype,chunks=(100,))
hix_in_zarr = zarr.open('pc/hix_in.zarr','w',shape=hix_in.shape,dtype=hix_in.dtype,chunks=(100,))
hix_zarr = zarr.open('pc/hix.zarr','w',shape=hix.shape,dtype=hix.dtype,chunks=(100,))
pc_in_zarr[:] = pc_in; hix_in_zarr[:] = hix_in; hix_zarr[:] = hix
pc_select_data('pc/hix_in.zarr','pc/hix.zarr','pc/pc_in.zarr','pc/pc.zarr')
pc_zarr = zarr.open('pc/pc.zarr','r')
np.testing.assert_array_equal(pc_zarr[:],pc)2024-08-14 17:16:08 - log_args - INFO - running function: pc_select_data
2024-08-14 17:16:08 - log_args - INFO - fetching args:
2024-08-14 17:16:08 - log_args - INFO - idx_in = 'pc/hix_in.zarr'
2024-08-14 17:16:08 - log_args - INFO - idx = 'pc/hix.zarr'
2024-08-14 17:16:08 - log_args - INFO - pc_in = 'pc/pc_in.zarr'
2024-08-14 17:16:08 - log_args - INFO - pc = 'pc/pc.zarr'
2024-08-14 17:16:08 - log_args - INFO - shape = None
2024-08-14 17:16:08 - log_args - INFO - chunks = None
2024-08-14 17:16:08 - log_args - INFO - processes = False
2024-08-14 17:16:08 - log_args - INFO - n_workers = 1
2024-08-14 17:16:08 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:08 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:08 - log_args - INFO - fetching args done.
2024-08-14 17:16:08 - zarr_info - INFO - pc/hix_in.zarr zarray shape, chunks, dtype: (1000,), (100,), int64
2024-08-14 17:16:08 - zarr_info - INFO - pc/hix.zarr zarray shape, chunks, dtype: (500,), (100,), int64
2024-08-14 17:16:08 - pc_select_data - INFO - loading idx_in and idx into memory.
2024-08-14 17:16:08 - pc_select_data - INFO - starting dask local cluster.
2024-08-14 17:16:08 - pc_select_data - INFO - dask local cluster started.
2024-08-14 17:16:08 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:08 - zarr_info - INFO - pc/pc_in.zarr zarray shape, chunks, dtype: (1000,), (100,), float32
2024-08-14 17:16:08 - darr_info - INFO - pc_in dask array shape, chunksize, dtype: (1000,), (1000,), float32
2024-08-14 17:16:08 - pc_select_data - INFO - set up selected pc data dask array.
2024-08-14 17:16:08 - darr_info - INFO - pc dask array shape, chunksize, dtype: (500,), (500,), float32
2024-08-14 17:16:08 - pc_select_data - INFO - write pc to pc/pc.zarr
2024-08-14 17:16:08 - zarr_info - INFO - pc/pc.zarr zarray shape, chunks, dtype: (500,), (100,), float32
2024-08-14 17:16:08 - pc_select_data - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:08 - pc_select_data - INFO - computing finished.1s
2024-08-14 17:16:08 - pc_select_data - INFO - dask cluster closed.data_reduce
data_reduce (data_in:str, out:str, map_func:Callable=None, reduce_func:Callable=<function mean at 0x7f0c9d3883b0>, axis=0, post_map_func:Callable=None, processes=False, n_workers=1, threads_per_worker=1, **dask_cluster_arg)
reduction operation for dataset.
| Type | Default | Details | |
|---|---|---|---|
| data_in | str | path (in string) for the input data | |
| out | str | output, path (in string) for the output data | |
| map_func | Callable | None | elementwise mapping function for input, no mapping by default |
| reduce_func | Callable | mean | reduction function after mapping, np.mean by default |
| axis | int | 0 | axis to be reduced, 0 for point cloud data, (0,1) for raster data |
| post_map_func | Callable | None | post mapping after reduction, no mapping by default |
| processes | bool | False | use process for dask worker or thread |
| n_workers | int | 1 | number of dask worker |
| threads_per_worker | int | 1 | number of threads per dask worker |
| dask_cluster_arg |
pc_in1 = np.random.rand(1000).astype(np.float32)+1j*np.random.rand(1000).astype(np.float32)
pc_in2 = np.random.rand(800,3).astype(np.float32)+1j*np.random.rand(800,3).astype(np.float32)
pc1_zarr = zarr.open('pc/pc_in1.zarr','w',shape=pc_in1.shape,dtype=pc_data1.dtype,chunks=(200))
pc2_zarr = zarr.open('pc/pc_in2.zarr','w',shape=pc_in2.shape,dtype=pc_data2.dtype,chunks=(200,1))
pc1_zarr[:] = pc_in1
pc2_zarr[:] = pc_in2data_reduce('pc/pc_in1.zarr','pc/pc_out1.zarr',map_func=np.abs,reduce_func=np.sum,post_map_func=lambda x: x/1000)
data_reduce('pc/pc_in2.zarr','pc/pc_out2.zarr',map_func=np.abs,reduce_func=np.sum,post_map_func=lambda x: x/800)
np.testing.assert_array_almost_equal(zarr.open('pc/pc_out1.zarr','r')[:][0], np.mean(np.abs(pc_in1),axis=0))
np.testing.assert_array_almost_equal(zarr.open('pc/pc_out2.zarr','r')[:], np.mean(np.abs(pc_in2),axis=0))2024-08-14 17:16:08 - log_args - INFO - running function: data_reduce
2024-08-14 17:16:08 - log_args - INFO - fetching args:
2024-08-14 17:16:08 - log_args - INFO - data_in = 'pc/pc_in1.zarr'
2024-08-14 17:16:08 - log_args - INFO - out = 'pc/pc_out1.zarr'
2024-08-14 17:16:08 - log_args - INFO - map_func = <ufunc 'absolute'>
2024-08-14 17:16:08 - log_args - INFO - reduce_func = <function sum>
2024-08-14 17:16:08 - log_args - INFO - axis = 0
2024-08-14 17:16:08 - log_args - INFO - post_map_func = <function <lambda>>
2024-08-14 17:16:08 - log_args - INFO - processes = False
2024-08-14 17:16:08 - log_args - INFO - n_workers = 1
2024-08-14 17:16:08 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:08 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:08 - log_args - INFO - fetching args done.
2024-08-14 17:16:08 - zarr_info - INFO - pc/pc_in1.zarr zarray shape, chunks, dtype: (1000,), (200,), complex64
2024-08-14 17:16:08 - data_reduce - INFO - starting dask local cluster.
2024-08-14 17:16:08 - data_reduce - INFO - dask local cluster started.
2024-08-14 17:16:08 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:08 - darr_info - INFO - data_in dask array shape, chunksize, dtype: (1000,), (200,), complex64
2024-08-14 17:16:08 - darr_info - INFO - maped_data_in dask array shape, chunksize, dtype: (1000,), (200,), float32
2024-08-14 17:16:08 - darr_info - INFO - reduced data in every chunk dask array shape, chunksize, dtype: (5,), (1,), float32
2024-08-14 17:16:08 - data_reduce - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:09 - data_reduce - INFO - computing finished. 0.1s
2024-08-14 17:16:09 - data_reduce - INFO - dask cluster closed.
2024-08-14 17:16:09 - data_reduce - INFO - continue the reduction on reduced data over every chunk
2024-08-14 17:16:09 - data_reduce - INFO - post mapping
2024-08-14 17:16:09 - data_reduce - INFO - writing output.
2024-08-14 17:16:09 - data_reduce - INFO - done.
2024-08-14 17:16:09 - log_args - INFO - running function: data_reduce
2024-08-14 17:16:09 - log_args - INFO - fetching args:
2024-08-14 17:16:09 - log_args - INFO - data_in = 'pc/pc_in2.zarr'
2024-08-14 17:16:09 - log_args - INFO - out = 'pc/pc_out2.zarr'
2024-08-14 17:16:09 - log_args - INFO - map_func = <ufunc 'absolute'>
2024-08-14 17:16:09 - log_args - INFO - reduce_func = <function sum>
2024-08-14 17:16:09 - log_args - INFO - axis = 0
2024-08-14 17:16:09 - log_args - INFO - post_map_func = <function <lambda>>
2024-08-14 17:16:09 - log_args - INFO - processes = False
2024-08-14 17:16:09 - log_args - INFO - n_workers = 1
2024-08-14 17:16:09 - log_args - INFO - threads_per_worker = 1
2024-08-14 17:16:09 - log_args - INFO - dask_cluster_arg = {}
2024-08-14 17:16:09 - log_args - INFO - fetching args done.
2024-08-14 17:16:09 - zarr_info - INFO - pc/pc_in2.zarr zarray shape, chunks, dtype: (800, 3), (200, 1), complex64
2024-08-14 17:16:09 - data_reduce - INFO - starting dask local cluster.
2024-08-14 17:16:09 - data_reduce - INFO - dask local cluster started.
2024-08-14 17:16:09 - dask_cluster_info - INFO - dask cluster: LocalCluster(dashboard_link='http://10.211.48.16:8787/status', workers=1, threads=1, memory=1.46 TiB)
2024-08-14 17:16:09 - darr_info - INFO - data_in dask array shape, chunksize, dtype: (800, 3), (200, 1), complex64
2024-08-14 17:16:09 - darr_info - INFO - maped_data_in dask array shape, chunksize, dtype: (800, 3), (200, 1), float32
2024-08-14 17:16:09 - darr_info - INFO - reduced data in every chunk dask array shape, chunksize, dtype: (4, 3), (1, 1), float32
2024-08-14 17:16:09 - data_reduce - INFO - computing graph setted. doing all the computing.
2024-08-14 17:16:09 - data_reduce - INFO - computing finished. 0.1s
2024-08-14 17:16:09 - data_reduce - INFO - dask cluster closed.
2024-08-14 17:16:09 - data_reduce - INFO - continue the reduction on reduced data over every chunk
2024-08-14 17:16:09 - data_reduce - INFO - post mapping
2024-08-14 17:16:09 - data_reduce - INFO - writing output.
2024-08-14 17:16:09 - data_reduce - INFO - done.