binary wire format with flatbuffers (#509)

* 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
This commit is contained in:
Bruce Martin
2019-01-09 14:26:05 -08:00
committed by GitHub
parent 42e25a1a1f
commit b90447c387
41 changed files with 2317 additions and 266 deletions
+69
View File
@@ -0,0 +1,69 @@
"""
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
}
+94 -1
View File
@@ -5,6 +5,8 @@ import time
import requests
import decode_fbs
LOCAL_URL = "http://127.0.0.1:5005/"
VERSION = "v0.2"
URL_BASE = f"{LOCAL_URL}api/{VERSION}/"
@@ -40,6 +42,7 @@ class EndPoints(unittest.TestCase):
url = f"{URL_BASE}{endpoint}"
result = self.session.get(url)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(result_data["schema"]["dataframe"]["nObs"], 2638)
self.assertEqual(len(result_data["schema"]["annotations"]["obs"]), 5)
@@ -49,6 +52,7 @@ class EndPoints(unittest.TestCase):
url = f"{URL_BASE}{endpoint}"
result = self.session.get(url)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(result_data["config"]["displayNames"]["dataset"], "pbmc3k")
self.assertEqual(len(result_data["config"]["features"]), 4)
@@ -58,10 +62,26 @@ class EndPoints(unittest.TestCase):
url = f"{URL_BASE}{endpoint}"
result = self.session.get(url)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(result_data["layout"]["ndims"], 2)
self.assertEqual(len(result_data["layout"]["coordinates"]), 2638)
def test_get_layout_fbs(self):
endpoint = "layout/obs"
url = f"{URL_BASE}{endpoint}"
header = {"Accept": "application/octet-stream"}
result = self.session.get(url, headers=header)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/octet-stream")
df = decode_fbs.decode_matrix_FBS(result.content)
self.assertEqual(df['n_rows'], 2638)
self.assertEqual(df['n_cols'], 2)
self.assertIsNotNone(df['columns'])
self.assertIsNone(df['col_idx'])
self.assertIsNone(df['row_idx'])
self.assertEqual(len(df['columns']), df['n_cols'])
# def test_put_layout(self):
# endpoint = "layout/obs"
# url = f"{URL_BASE}{endpoint}"
@@ -93,6 +113,7 @@ class EndPoints(unittest.TestCase):
url = f"{URL_BASE}{endpoint}"
result = self.session.get(url)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(result_data["names"], ["name", "n_genes", "percent_mito", "n_counts", "louvain"])
self.assertEqual(len(result_data["data"]), 2638)
@@ -103,11 +124,28 @@ class EndPoints(unittest.TestCase):
query = "annotation-name=n_genes&annotation-name=percent_mito"
url = f"{URL_BASE}{endpoint}?{query}"
result = self.session.get(url)
self.assertEqual(result.headers["Content-Type"], "application/json")
self.assertEqual(result.status_code, HTTPStatus.OK)
result_data = result.json()
self.assertEqual(result_data["names"], ["n_genes", "percent_mito"])
self.assertEqual(len(result_data["data"][0]), 3)
def test_get_annotations_obs_fbs(self):
endpoint = "annotations/obs"
url = f"{URL_BASE}{endpoint}"
header = {"Accept": "application/octet-stream"}
result = self.session.get(url, headers=header)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/octet-stream")
df = decode_fbs.decode_matrix_FBS(result.content)
self.assertEqual(df['n_rows'], 2638)
self.assertEqual(df['n_cols'], 5)
self.assertIsNotNone(df['columns'])
self.assertIsNotNone(df['col_idx'])
self.assertIsNone(df['row_idx'])
self.assertEqual(len(df['columns']), df['n_cols'])
self.assertListEqual(df['col_idx'], ['name', 'n_genes', 'percent_mito', 'n_counts', 'louvain'])
def test_get_annotations_obs_error(self):
endpoint = "annotations/obs"
query = "annotation-name=notakey"
@@ -131,6 +169,7 @@ class EndPoints(unittest.TestCase):
}
result = self.session.put(url, json=obs_filter)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(result_data["names"], ["name", "n_genes", "percent_mito", "n_counts", "louvain"])
self.assertEqual(len(result_data["data"]), 15)
@@ -152,6 +191,7 @@ class EndPoints(unittest.TestCase):
}
result = self.session.put(url, json=obs_filter)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(result_data["names"], ["n_genes", "percent_mito"])
self.assertEqual(len(result_data["data"][0]), 3)
@@ -168,6 +208,7 @@ class EndPoints(unittest.TestCase):
}
result = self.session.post(url, json=params)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(len(result_data), 7)
@@ -182,6 +223,7 @@ class EndPoints(unittest.TestCase):
}
result = self.session.post(url, json=params)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(len(result_data), 10)
@@ -190,6 +232,7 @@ class EndPoints(unittest.TestCase):
url = f"{URL_BASE}{endpoint}"
result = self.session.get(url)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(result_data["names"], ["name", "n_cells"])
self.assertEqual(len(result_data["data"]), 1838)
@@ -201,10 +244,27 @@ class EndPoints(unittest.TestCase):
url = f"{URL_BASE}{endpoint}?{query}"
result = self.session.get(url)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(result_data["names"], ["n_cells"])
self.assertEqual(len(result_data["data"][0]), 2)
def test_get_annotations_var_fbs(self):
endpoint = "annotations/var"
url = f"{URL_BASE}{endpoint}"
header = {"Accept": "application/octet-stream"}
result = self.session.get(url, headers=header)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/octet-stream")
df = decode_fbs.decode_matrix_FBS(result.content)
self.assertEqual(df['n_rows'], 1838)
self.assertEqual(df['n_cols'], 2)
self.assertIsNotNone(df['columns'])
self.assertIsNotNone(df['col_idx'])
self.assertIsNone(df['row_idx'])
self.assertEqual(len(df['columns']), df['n_cols'])
self.assertListEqual(df['col_idx'], ['name', 'n_cells'])
def test_get_annotations_var_error(self):
endpoint = "annotations/var"
query = "annotation-name=notakey"
@@ -218,6 +278,7 @@ class EndPoints(unittest.TestCase):
var_filter = {"filter": {"var": {"annotation_value": [{"name": "name", "values": ["ATAD3C", "RER1"]}]}}}
result = self.session.put(url, json=var_filter)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(result_data["names"], ["name", "n_cells"])
self.assertEqual(len(result_data["data"]), 2)
@@ -229,6 +290,7 @@ class EndPoints(unittest.TestCase):
var_filter = {"filter": {"var": {"annotation_value": [{"name": "name", "values": ["ATAD3C", "RER1"]}]}}}
result = self.session.put(url, json=var_filter)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(result_data["names"], ["n_cells"])
self.assertEqual(len(result_data["data"][0]), 2)
@@ -241,6 +303,7 @@ class EndPoints(unittest.TestCase):
url = f"{URL_BASE}{endpoint}?{query}"
result = self.session.get(url)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(len(result_data["obs"]), 2638)
@@ -262,6 +325,7 @@ class EndPoints(unittest.TestCase):
url = f"{URL_BASE}{endpoint}"
result = self.session.get(url)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
def test_data_filter(self):
for axis in ["obs", "var"]:
@@ -270,10 +334,11 @@ class EndPoints(unittest.TestCase):
url = f"{URL_BASE}{endpoint}?{query}"
result = self.session.get(url)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(len(result_data["obs"]), 38)
def test_data_put(self):
def test_data_json_put(self):
for axis in ["obs", "var"]:
endpoint = f"data/{axis}"
url = f"{URL_BASE}{endpoint}"
@@ -291,9 +356,33 @@ class EndPoints(unittest.TestCase):
}
result = self.session.put(url, headers=header, json=obs_filter)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
self.assertEqual(len(result_data["obs"]), 15)
def test_data_put_fbs(self):
endpoint = f"data/var"
url = f"{URL_BASE}{endpoint}"
header = {"Accept": "application/octet-stream"}
filter = {
"filter": {
"var": {
"index": [0, 1, 4]
}
}
}
result = self.session.put(url, headers=header, json=filter)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/octet-stream")
df = decode_fbs.decode_matrix_FBS(result.content)
self.assertEqual(df['n_rows'], 2638)
self.assertEqual(df['n_cols'], 3)
self.assertIsNotNone(df['columns'])
self.assertIsNotNone(df['col_idx'])
self.assertIsNone(df['row_idx'])
self.assertEqual(len(df['columns']), df['n_cols'])
self.assertListEqual(df['col_idx'].tolist(), [0, 1, 4])
def test_data_put_single_var(self):
for axis in ["obs", "var"]:
endpoint = f"data/{axis}"
@@ -302,6 +391,7 @@ class EndPoints(unittest.TestCase):
var_filter = {"filter": {"var": {"annotation_value": [{"name": "name", "values": ["RER1"]}]}}}
result = self.session.put(url, headers=header, json=var_filter)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data = result.json()
if axis == "obs":
self.assertEqual(len(result_data["obs"][0]), 2)
@@ -338,6 +428,7 @@ class EndPoints(unittest.TestCase):
}
result = self.session.put(url, json=f1)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data1 = result.json()
f2 = {
"filter": {
@@ -353,6 +444,7 @@ class EndPoints(unittest.TestCase):
}
result = self.session.put(url, json=f2)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data2 = result.json()
self.assertNotEqual(result_data1, result_data2)
@@ -377,6 +469,7 @@ class EndPoints(unittest.TestCase):
}
result = self.session.put(url, json=f2)
self.assertEqual(result.status_code, HTTPStatus.OK)
self.assertEqual(result.headers["Content-Type"], "application/json")
result_data2 = result.json()
self.assertNotEqual(result_data1, result_data2)