mirror of
https://github.com/chanzuckerberg/cellxgene.git
synced 2026-09-17 05:47:58 +08:00
b90447c387
* first flatbuffer schema * do not lint auto-generated files * add flatbuffers package * add flatbuffer module * wire up /data/X/T route * use flatbuffers for matrix data fetc * clarity and comments * add flatbuffer layout route * clean up obsolete code * fix tests * move flake8 config to setup.cfg * add comments * lint * rework layout routes for fbs * add more type support to fbs * lint * add flatbuffer support for annotations * function name improvements * fix botched merge with master * remove unused import * route cleanup for flatbuffers * rename function for clarity * add missing globals to Jest tests * fix client JS tests * fix routes for Python tests * comments for clarity * non-finite floating point hardening * more non-finite number handling * lint * fix tests for summarizeAnnotations * harden diffexp calculation against FP errors * cleanup unused code * lint * add encoding tests for flatbuffers * application type specified as strings * fix spelling error * improve variable names * add note about documentation gap * rename FBS DataFrame to Matrix
70 lines
2.2 KiB
Python
70 lines
2.2 KiB
Python
|
|
"""
|
|
Code to decode, for testing purposes, the flatbuffer encoded blobs.
|
|
This code will need to be updated if fbs/matrix.fbs changes.
|
|
|
|
For more information, see fbs/matrix.fbs and server/app/util/fbs/
|
|
"""
|
|
import json
|
|
|
|
import server.app.util.fbs.NetEncoding.TypedArray as TypedArray
|
|
import server.app.util.fbs.NetEncoding.Matrix as Matrix
|
|
import server.app.util.fbs.NetEncoding.Int32Array as Int32Array
|
|
import server.app.util.fbs.NetEncoding.Uint32Array as Uint32Array
|
|
import server.app.util.fbs.NetEncoding.Float32Array as Float32Array
|
|
import server.app.util.fbs.NetEncoding.Float64Array as Float64Array
|
|
import server.app.util.fbs.NetEncoding.JSONEncodedArray as JSONEncodedArray
|
|
|
|
|
|
def decode_typed_array(tarr):
|
|
type_map = {
|
|
TypedArray.TypedArray.Uint32Array: Uint32Array.Uint32Array,
|
|
TypedArray.TypedArray.Int32Array: Int32Array.Int32Array,
|
|
TypedArray.TypedArray.Float32Array: Float32Array.Float32Array,
|
|
TypedArray.TypedArray.Float64Array: Float64Array.Float64Array,
|
|
TypedArray.TypedArray.JSONEncodedArray: JSONEncodedArray.JSONEncodedArray
|
|
}
|
|
(u_type, u) = tarr
|
|
if u_type == TypedArray.TypedArray.NONE:
|
|
return None
|
|
|
|
TarType = type_map.get(u_type, None)
|
|
assert(TarType is not None)
|
|
|
|
arr = TarType()
|
|
arr.Init(u.Bytes, u.Pos)
|
|
narr = arr.DataAsNumpy()
|
|
if u_type == TypedArray.TypedArray.JSONEncodedArray:
|
|
narr = json.loads(narr.tostring().decode('utf-8'))
|
|
return narr
|
|
|
|
|
|
def decode_matrix_FBS(buf):
|
|
"""
|
|
Given a FBS Matrix, return an decoded Python dict containing
|
|
same info in native format.
|
|
|
|
NOTE / TODO: row_idx not currently implemented
|
|
"""
|
|
df = Matrix.Matrix.GetRootAsMatrix(buf, 0)
|
|
n_rows = df.NRows()
|
|
n_cols = df.NCols()
|
|
|
|
columns_length = df.ColumnsLength()
|
|
|
|
decoded_columns = []
|
|
for col_idx in range(0, columns_length):
|
|
col = df.Columns(col_idx)
|
|
tarr = (col.UType(), col.U())
|
|
decoded_columns.append(decode_typed_array(tarr))
|
|
|
|
cidx = decode_typed_array((df.ColIndexType(), df.ColIndex()))
|
|
|
|
return {
|
|
"n_rows": n_rows,
|
|
"n_cols": n_cols,
|
|
"columns": decoded_columns,
|
|
"col_idx": cidx,
|
|
"row_idx": None
|
|
}
|