def get(self, model_id, prediction_id):
req_format = request.args.get('format', 'geojson')
req_inferences = request.args.get('inferences', 'all')
req_threshold = request.args.get('threshold', '0')
req_threshold = float(req_threshold)
stream = PredictionService.export(prediction_id)
inferences = PredictionService.inferences(prediction_id)
pred = PredictionService.get_prediction_by_id(prediction_id)
first = False
if req_inferences != 'all':
inferences = [ req_inferences ]
def generate_npz():
nonlocal req_threshold
labels_dict ={}
for row in stream:
if req_inferences != 'all' and row[3].get(req_inferences) is None:
continue
if req_inferences != 'all' and row[3].get(req_inferences) <= req_threshold:
continue
if row[4]:
i_lst = pred.inf_list.split(",")
#convert raw predictions into 0 or 1 based on threshold
raw_pred = []
for num, inference in enumerate(i_lst):
raw_pred.append(row[3][inference])
if req_inferences == 'all':
req_threshold = request.args.get('threshold', '0.5')
req_threshold = float(req_threshold)
l = [1 if score >= req_threshold else 0 for score in raw_pred]
#convert quadkey to x-y-z
t = '-'.join([str(i) for i in mercantile.quadkey_to_tile(row[1])])
# special case for binary
if (pred.inf_binary) and (len(i_lst) != 2):
return err(400, "binary models must have two catagories"), 400
if (len(i_lst) == 2) and (pred.inf_binary):
if list(row[4].values())[0]: #validated and true, keep original
labels_dict.update({t:l})
else:
if l == [1, 0]:
l = [0, 1]
else:
l = [1, 0]
labels_dict.update({t:l})
else:
# for multi-label
for key in list(row[4].keys()):
i = i_lst.index(key)
if not row[4][key]:
if l[i] == 0:
l[i] = 1
else:
l[i] = 0
labels_dict.update({t:l})
if not labels_dict:
raise NoValid
bytestream = io.BytesIO()
np.savez(bytestream, **labels_dict)
return bytestream.getvalue()
def generate():
nonlocal first
if req_format == "geojson":
yield '{ "type": "FeatureCollection", "features": ['
elif req_format == "csv":
output = io.StringIO()
rowdata = ["ID", "QuadKey", "QuadKeyGeom"]
rowdata.extend(inferences)
csv.writer(output, quoting=csv.QUOTE_NONNUMERIC).writerow(rowdata)
yield output.getvalue()
for row in stream:
if req_inferences != 'all' and row[3].get(req_inferences) is None:
continue
if req_inferences != 'all' and row[3].get(req_inferences) <= req_threshold:
continue
if req_format == "geojson" or req_format == "geojsonld":
properties_dict = {}
if row[4]:
properties_dict = row[3]
valid_dict = {}
valid_dict.update({'validity': row[4]})
properties_dict.update(valid_dict)
else:
properties_dict = row[3]
feat = {
"id": row[0],
"quadkey": row[1],
"type": "Feature",
"properties": properties_dict,
"geometry": json.loads(row[2])
}
if req_format == "geojsonld":
yield json.dumps(feat) + '\n'
elif req_format == "geojson":
if first == False:
first = True
yield '\n' + json.dumps(feat)
else:
yield ',\n' + json.dumps(feat)
elif req_format == "csv":
output = io.StringIO()
rowdata = [ row[0], row[1], row[2]]
for inf in inferences:
rowdata.append(row[3].get(inf, 0.0))
csv.writer(output, quoting=csv.QUOTE_NONNUMERIC).writerow(rowdata)
yield output.getvalue()
else:
return err(501, "not a valid export type, valid export types are: geojson, csv, and npz"), 501
if req_format == "geojson":
yield ']}'
if req_format == "csv":
mime = "text/csv"
elif req_format == "geojson":
mime = "application/geo+json"
elif req_format == "geojsonld":
mime = "application/geo+json-seq"
elif req_format == "npz":
mime = "application/npz"
if req_format == "npz":
try:
npz = generate_npz()
return Response(
response = generate_npz(),
mimetype = mime,
status = 200,
headers = {
"Content-Disposition": 'attachment; filename="export.' + req_format + '"'
}
)
except NoValid:
return err(400, "Can only return npz if predictions are validated. Currently there are no valid predictions"), 400
else:
return Response(
generate(),
mimetype = mime,
status = 200,
headers = {
"Content-Disposition": 'attachment; filename="export.' + req_format + '"'
}
)
def payload(integration_id: int, payload: dict):
integration = IntegrationService.get_secrets(integration_id)
if integration is None:
raise IntegrationNotFound("Integration Not Found")
if integration.integration != "maproulette":
raise Exception("Only MapRoulette Integrations supported")
for ele in [
"prediction",
"project",
"project_desc",
"challenge",
"challenge_instr",
"threshold",
"inferences",
]:
if payload.get(ele) is None:
raise Exception("Missing " + ele + " key in body")
auth = integration.auth
if payload.get("auth") is not None:
auth = payload.get("auth")
parsed = urlparse(integration.url)
config = maproulette.Configuration(api_key=auth,
hostname=parsed.netloc,
protocol=parsed.scheme)
project_api = maproulette.Project(config)
challenge_api = maproulette.Challenge(config)
try:
project = project_api.get_project_by_name(
project_name=payload.get("project"))
except Exception:
project = project_api.create_project(
data={
"name": payload.get("project"),
"display_name": payload.get("project"),
"description": payload.get("project_desc"),
"enabled": True,
})
try:
challenge = challenge_api.create_challenge(
data={
"name": payload.get("challenge"),
"parent": project["data"]["id"],
"instruction": payload.get("challenge_instr"),
})
except Exception as e:
raise e
req_inferences = payload.get("inferences", "all")
req_threshold = float(payload.get("threshold", "0"))
stream = PredictionService.export(int(payload.get("prediction")))
feats = {"type": "FeatureCollection", "features": []}
for row in stream:
if req_inferences != "all" and row[3].get(req_inferences) is None:
continue
if req_inferences != "all" and row[3].get(
req_inferences) <= req_threshold:
continue
properties_dict = row[3]
if row[4]:
valid_dict = {}
valid_dict.update({"validity": row[4]})
properties_dict.update(valid_dict)
properties_dict["mle:id"] = row[0]
feat = {
"quadkey": row[1],
"type": "Feature",
"properties": properties_dict,
"geometry": json.loads(row[2]),
}
feats["features"].append(feat)
challenge_api.add_tasks_to_challenge(
challenge_id=challenge["data"]["id"], data=feats)
return {
"project": project["data"]["id"],
"challenge": challenge["data"]["id"]
}
def payload(integration_id: int, payload: dict):
integration = IntegrationService.get_secrets(integration_id)
if integration is None:
raise IntegrationNotFound('Integration Not Found')
if integration.integration != "maproulette":
raise Exception("Only MapRoulette Integrations supported");
for ele in ['prediction', 'project', 'project_desc', 'challenge', 'challenge_instr', 'threshold', 'inferences']:
if payload.get(ele) is None:
raise Exception('Missing ' + ele + ' key in body')
auth = integration.auth
if payload.get('auth') is not None:
auth = payload.get('auth')
parsed = urlparse(integration.url)
config = maproulette.Configuration(
api_key=auth,
hostname=parsed.netloc,
protocol=parsed.scheme
)
project_api = maproulette.Project(config)
challenge_api = maproulette.Challenge(config)
try:
project = project_api.get_project_by_name(
project_name=payload.get('project')
)
except:
project = project_api.create_project(
data={
"name": payload.get('project'),
"display_name": payload.get('project'),
"description": payload.get('project_desc'),
"enabled": True
}
)
try:
challenge = challenge_api.create_challenge(
data={
'name': payload.get('challenge'),
'parent': project['data']['id'],
'instruction': payload.get('challenge_instr')
}
)
except Exception as e:
raise e
req_inferences = payload.get('inferences', 'all')
req_threshold = float(payload.get('threshold', '0'))
stream = PredictionService.export(int(payload.get('prediction')))
inferences = PredictionService.inferences(int(payload.get('prediction')))
pred = PredictionService.get_prediction_by_id(int(payload.get('prediction')))
if req_inferences != 'all':
inferences = [ req_inferences ]
fc = {
'type': 'FeatureCollection',
'features': []
}
for row in stream:
if req_inferences != 'all' and row[3].get(req_inferences) is None:
continue
if req_inferences != 'all' and row[3].get(req_inferences) <= req_threshold:
continue
properties_dict = {}
if row[4]:
properties_dict = row[3]
valid_dict = {}
valid_dict.update({'validity': row[4]})
properties_dict.update(valid_dict)
feat = {
"id": row[0],
"quadkey": row[1],
"type": "Feature",
"properties": properties_dict,
"geometry": json.loads(row[2])
}
fc['features'].append(feat)
challenge_api.add_tasks_to_challenge(
challenge_id=challenge['data']['id'],
data=fc
)
return {
"project": project['data']['id'],
"challenge": challenge['data']['id']
}
def get(self, project_id, prediction_id):
"""
Export Geospatial Predictions
---
parameters:
- name: project_id
in: path
schema:
type: integer
minimum: 0
description: The ID of the Project
- name: prediction_id
in: path
schema:
type: integer
minimum: 0
description: The ID of the Project
- name: format
in: query
schema:
type: string
default: geojson
enum:
- geojson
- geojsonseq
- csv
description: The format to provide records in
- name: inferences
in: query
schema:
type: string
default: all
description: Return all inferences or only a single inference
- name: threshold
in: query
schema:
type: integer
default: 0
minimum: 0
maximum: 1
description: The confidence threshold to apply to exported inferences
responses:
200:
description: Exported Data
"""
req_format = request.args.get("format", "geojson")
req_inferences = request.args.get("inferences", "all")
req_threshold = request.args.get("threshold", "0")
req_threshold = float(req_threshold)
stream = PredictionService.export(prediction_id)
inferences = PredictionService.inferences(prediction_id)
pred = PredictionService.get_prediction_by_id(prediction_id)
hint = pred.hint
z = pred.tile_zoom
i_info = ImageryService.get(pred.imagery_id)
c_list = ImageryService.get(pred.imagery_id)
first = False
if req_inferences != "all":
inferences = [req_inferences]
def generate_npz():
nonlocal req_threshold
nonlocal hint
nonlocal z
nonlocal i_info
nonlocal c_list
# get chip list csv as dataframe to match up chip-lst name + geometry with geometry in the predictions database
labels_dict = {}
for row in stream:
if req_inferences != "all" and row[3].get(req_inferences) is None:
continue
if (
req_inferences != "all"
and row[3].get(req_inferences) <= req_threshold
):
continue
# set labels.npz key to be x-y-z tile either from quadkey or wkt geometry
if i_info["fmt"] == "wms":
if row[1]:
t = "-".join(
[str(i) for i in mercantile.quadkey_to_tile(row[1])]
)
else:
s = shape(json.loads(row[2])).centroid
t = "-".join([str(i) for i in mercantile.tile(s.x, s.y, z)])
if i_info["fmt"] == "list":
r = requests.get(c_list["url"])
df = pd.read_csv(io.StringIO(r.text))
df["c"] = df["bounds"].apply(
lambda x: box(*[float(n) for n in x.split(",")])
)
gdf = gpd.GeoDataFrame(df, crs="EPSG:4326", geometry=df["c"])
# get tile name that where chip-list geom and geom in prediction row match
gdf_2 = gpd.GeoDataFrame(
{"geometry": [shape(json.loads(row[2]))]}, crs="EPSG:4326"
)
# To-DO account for no overlap case
i = gpd.overlay(gdf, gdf_2, how="intersection")
tiles_intersection = i["name"].tolist()
# convert raw predictions into 0 or 1 based on threshold
raw_pred = []
i_lst = pred.inf_list.split(",")
for num, inference in enumerate(i_lst):
raw_pred.append(row[3][inference])
if req_inferences == "all":
req_threshold = request.args.get("threshold", "0.5")
req_threshold = float(req_threshold)
binary_pred_list = [1 if score >= req_threshold else 0 for score in raw_pred]
# special case for training and not predictions
if hint == "training":
if i_info["fmt"] == "list":
for chip_name in tiles_intersection:
labels_dict.update({chip_name: binary_pred_list})
else:
labels_dict.update({t: binary_pred_list})
elif row[4]:
t = "-".join([str(i) for i in mercantile.quadkey_to_tile(row[1])])
# special case for binary
if pred.inf_binary and len(i_lst) != 2:
return err(400, "binary models must have two catagories"), 400
if len(i_lst) == 2 and pred.inf_binary:
if list(row[4].values())[
0
]: # validated and true, keep original
labels_dict.update({t: binary_pred_list})
else:
if binary_pred_list == [1, 0]:
binary_pred_list = [0, 1]
else:
binary_pred_list = [1, 0]
labels_dict.update({t: binary_pred_list})
else:
# for multi-label
for key in list(row[4].keys()):
i = i_lst.index(key)
if not row[4][key]:
if binary_pred_list[i] == 0:
binary_pred_list[i] = 1
else:
binary_pred_list[i] = 0
labels_dict.update({t: binary_pred_list})
if not labels_dict:
raise NoValid
bytestream = io.BytesIO()
np.savez(bytestream, **labels_dict)
return bytestream.getvalue()
def generate():
nonlocal first
if req_format == "geojson":
yield '{ "type": "FeatureCollection", "features": ['
elif req_format == "csv":
output = io.StringIO()
rowdata = ["ID", "QuadKey", "QuadKeyGeom"]
rowdata.extend(inferences)
csv.writer(output, quoting=csv.QUOTE_NONNUMERIC).writerow(rowdata)
yield output.getvalue()
for row in stream:
if req_inferences != "all" and row[3].get(req_inferences) is None:
continue
if (
req_inferences != "all"
and row[3].get(req_inferences) <= req_threshold
):
continue
if req_format == "geojson" or req_format == "geojsonld":
properties_dict = {}
if row[4]:
properties_dict = row[3]
valid_dict = {}
valid_dict.update({"validity": row[4]})
properties_dict.update(valid_dict)
else:
properties_dict = row[3]
feat = {
"id": row[0],
"quadkey": row[1],
"type": "Feature",
"properties": properties_dict,
"geometry": json.loads(row[2]),
}
if req_format == "geojsonld":
yield json.dumps(feat) + "\n"
elif req_format == "geojson":
if first is False:
first = True
yield "\n" + json.dumps(feat)
else:
yield ",\n" + json.dumps(feat)
elif req_format == "csv":
output = io.StringIO()
rowdata = [row[0], row[1], row[2]]
for inf in inferences:
rowdata.append(row[3].get(inf, 0.0))
csv.writer(output, quoting=csv.QUOTE_NONNUMERIC).writerow(rowdata)
yield output.getvalue()
else:
return (
err(
501,
"not a valid export type, valid export types are: geojson, csv, and npz",
),
501,
)
if req_format == "geojson":
yield "]}"
if req_format == "csv":
mime = "text/csv"
elif req_format == "geojson":
mime = "application/geo+json"
elif req_format == "geojsonld":
mime = "application/geo+json-seq"
elif req_format == "npz":
mime = "application/npz"
if req_format == "npz":
try:
return Response(
response=generate_npz(),
mimetype=mime,
status=200,
headers={
"Content-Disposition": 'attachment; filename="export.'
+ req_format
+ '"'
},
)
except NoValid:
return (
err(
400,
"Can only return npz if predictions are validated. Currently there are no valid predictions",
),
400,
)
else:
return Response(
generate(),
mimetype=mime,
status=200,
headers={
"Content-Disposition": 'attachment; filename="export.'
+ req_format
+ '"'
},
)