def _count_suburb_by_age_group(tree_data: List[Dict[str, Any]], use_prediction: bool) -> Dict[str, Any]:
counted_trees: Dict[str, int] = {}
for tree in tree_data:
suburb_name = clean_key(tree["geo_info"]["suburb"])
if counted_trees.get(suburb_name) is None:
counted_trees[suburb_name]: Dict[str, Any] = {}
age_group = tree["tree_age"]["age_group_2020"]
if age_group is None:
if use_prediction is True:
try:
if tree["predictions"]["by_radius_prediction"]["age_group"]["probability"] >= MIN_PROBABILITY:
age_group = tree["predictions"]["by_radius_prediction"]["age_group"]["prediction"]
except:
pass
age_group = clean_key(age_group)
if counted_trees[suburb_name].get(age_group) is None:
counted_trees[suburb_name][age_group]: Dict[str, Any] = {
"absolute": 0,
"percentage": 0
}
counted_trees[suburb_name][age_group]["absolute"] += 1
for suburb, suburb_vals in counted_trees.items():
all_suburb_trees = sum([x["absolute"] for x in suburb_vals.values()])
for agegroup, vals in suburb_vals.items():
counted_trees[suburb][agegroup]["percentage"] = round(vals["absolute"]/all_suburb_trees, 2)
return counted_trees
def _count_district_by_genus(tree_data: List[Dict[str, Any]], use_prediction: bool) -> Dict[str, Any]:
counted_trees: Dict[str, int] = {}
for tree in tree_data:
district_name = clean_key(tree["geo_info"]["district"])
if counted_trees.get(district_name) is None:
counted_trees[district_name]: Dict[str, Any] = {}
genus_name = tree["tree_taxonomy"]["genus"]
if genus_name is None:
if use_prediction is True:
try:
if tree["predictions"]["by_radius_prediction"]["genus"]["probability"] >= MIN_PROBABILITY:
genus_name = tree["predictions"]["by_radius_prediction"]["genus"]["prediction"]
except:
pass
genus_name = clean_key(genus_name)
if counted_trees[district_name].get(genus_name) is None:
counted_trees[district_name][genus_name]: Dict[str, Any] = {
"absolute": 0,
"percentage": 0
}
counted_trees[district_name][genus_name]["absolute"] += 1
for district, district_vals in counted_trees.items():
all_district_trees = sum([x["absolute"] for x in district_vals.values()])
for genus, vals in district_vals.items():
counted_trees[district][genus]["percentage"] = round(vals["absolute"]/all_district_trees, 2)
return counted_trees
def _count_object_type_by_suburb(
tree_data: List[Dict[str, Any]]) -> Dict[str, Any]:
counted_trees: Dict[str, int] = {}
for tree in tree_data:
object_type = tree["base_info"]["object_type"]
object_type = clean_key(object_type)
if counted_trees.get(object_type) is None:
counted_trees[object_type]: Dict[str, Any] = {}
suburb_name = clean_key(tree["geo_info"]["suburb"])
if counted_trees[object_type].get(suburb_name) is None:
counted_trees[object_type][suburb_name]: Dict[str, Any] = {
"absolute": 0,
"percentage": 0
}
counted_trees[object_type][suburb_name]["absolute"] += 1
for object_type, object_type_vals in counted_trees.items():
all_object_type_trees = sum(
[x["absolute"] for x in object_type_vals.values()])
for suburb, vals in object_type_vals.items():
counted_trees[object_type][suburb]["percentage"] = round(
vals["absolute"] / all_object_type_trees, 2)
return counted_trees
def _count_trees(tree_data: List[Dict[str, Any]],
use_prediction: bool) -> Dict[str, Any]:
counted_trees: Dict[str, int] = {}
for tree in tree_data:
age_group = tree["tree_age"]["age_group_2020"]
if age_group is None:
if use_prediction is True:
try:
if tree["predictions"]["by_radius_prediction"][
"age_group"]["probability"] >= MIN_PROBABILITY:
age_group = tree["predictions"][
"by_radius_prediction"]["age_group"]["prediction"]
except:
pass
age_group = clean_key(age_group)
if counted_trees.get(age_group) is None:
counted_trees[age_group]: Dict[str, Any] = {
"absolute": 0,
"percentage": 0
}
counted_trees[age_group]["absolute"] += 1
for age_group, vals in counted_trees.items():
counted_trees[age_group]["percentage"] = round(
vals["absolute"] / len(tree_data), 2)
return counted_trees
def _location_type(tree_data: List[Dict[str, Any]]) -> Dict[str, Any]:
location_types_count: Dict[str, int] = {}
for tree in tree_data:
location_types = tree["tree_location_type"]
if location_types is None:
location_type = clean_key(location_types)
if location_types_count.get(location_type) is None:
location_types_count[location_type] = 0
location_types_count[location_type] += 1
continue
is_highway = False
if len(location_types) == 1 and "highway" in location_types:
is_highway = True
use_green_spaces_agriculture = True
if len(
location_types
) > 1 and "green_spaces_leisure" in location_types and "green_spaces_agriculture" in location_types:
use_green_spaces_agriculture = False
for location_type in location_types:
if location_type == "highway" and is_highway is False:
continue
if location_type == "green_spaces_agriculture" and use_green_spaces_agriculture is False:
continue
if location_types_count.get(location_type) is None:
location_types_count[location_type] = 0
location_types_count[location_type] += 1
return location_types_count
def _count_neighbours_radius_50(tree_data: List[Dict[str, Any]]) -> Dict[str, Any]:
'''
TODO: include this attribute in base data again
'''
counted_trees: Dict[str, int] = {}
for tree in tree_data:
district_name = clean_key(tree["geo_info"]["district"])
if counted_trees.get(district_name) is None:
counted_trees[district_name]: Dict[str, Any] = {
"min": None,
"max": None,
"mean": None,
"median": None,
"tmp_list": []
}
num_neighbours = tree["num_neighbours_radius_50"] # not included in base data right now
if num_neighbours is None:
continue
counted_trees[district_name]["tmp_list"].append(num_neighbours)
for district, vals in counted_trees.items():
counted_trees[district]["min"] = min(vals["tmp_list"])
counted_trees[district]["max"] = max(vals["tmp_list"])
counted_trees[district]["mean"] = round(mean(vals["tmp_list"]))
counted_trees[district]["median"] = median(vals["tmp_list"])
del counted_trees[district]["tmp_list"]
return counted_trees
def _count_trees(tree_data: List[Dict[str, Any]],
use_prediction: bool) -> Dict[str, Any]:
counted_trees: Dict[str, int] = {}
for tree in tree_data:
genus_name = tree["tree_taxonomy"]["genus"]
if genus_name is None:
if use_prediction is True:
try:
if tree["predictions"]["by_radius_prediction"]["genus"][
"probability"] >= MIN_PROBABILITY:
genus_name = tree["predictions"][
"by_radius_prediction"]["genus"]["prediction"]
except:
pass
genus_name = clean_key(genus_name)
if counted_trees.get(genus_name) is None:
counted_trees[genus_name]: Dict[str, Any] = {
"absolute": 0,
"percentage": 0
}
counted_trees[genus_name]["absolute"] += 1
for genus, vals in counted_trees.items():
counted_trees[genus]["percentage"] = round(
vals["absolute"] / len(tree_data), 2)
return counted_trees
def _genus_species_name_german_tree(
tree_data: List[Dict[str, Any]]) -> Dict[str, Any]:
names_tree: Dict[str, int] = {}
for tree in tree_data:
genus_name = tree["tree_taxonomy"]["genus"]
if genus_name is None:
continue
if names_tree.get(genus_name) is None:
names_tree[genus_name]: Dict[str, List[str]] = {}
species_name = clean_key(tree["tree_taxonomy"]["species"])
if names_tree[genus_name].get(species_name) is None:
names_tree[genus_name][species_name] = []
name_german_list = tree["tree_taxonomy"]["name_german"]
if name_german_list is None:
continue
for name_german in name_german_list:
if name_german not in names_tree[genus_name][species_name]:
names_tree[genus_name][species_name].append(name_german)
# ***
# default for empty values: null
for genus_key, genus_vals in names_tree.items():
for species_key, species_vals in genus_vals.items():
if len(species_vals) == 0:
names_tree[genus_key][species_key] = None
return names_tree
def _suburb_data_completeness(
tree_data: List[Dict[str, Any]]) -> Dict[str, Any]:
completeness_in_suburb: Dict[str, List[str]] = {}
for tree in tree_data:
suburb_name = clean_key(tree["geo_info"]["suburb"])
# if suburb_name is None:
# continue
if completeness_in_suburb.get(suburb_name) is None:
completeness_in_suburb[suburb_name]: Dict[str, Any] = {
"mean": None,
"median": None,
"min": None,
"max": None,
"tmp_list": []
}
dataset_completeness = tree["dataset_completeness"]
completeness_in_suburb[suburb_name]["tmp_list"].append(
dataset_completeness)
for suburb, vals in completeness_in_suburb.items():
completeness_in_suburb[suburb]["min"] = min(vals["tmp_list"])
completeness_in_suburb[suburb]["max"] = max(vals["tmp_list"])
completeness_in_suburb[suburb]["mean"] = round(mean(vals["tmp_list"]),
2)
completeness_in_suburb[suburb]["median"] = median(vals["tmp_list"])
del completeness_in_suburb[suburb]["tmp_list"]
return completeness_in_suburb
def _count_age_group_by_genus(tree_data: List[Dict[str, Any]],
use_prediction: bool) -> Dict[str, Any]:
counted_trees: Dict[str, int] = {}
for tree in tree_data:
age_group = tree["tree_age"]["age_group_2020"]
if age_group is None:
if use_prediction is True:
try:
if tree["predictions"]["by_radius_prediction"][
"age_group"]["probability"] >= MIN_PROBABILITY:
age_group = tree["predictions"][
"by_radius_prediction"]["age_group"]["prediction"]
except:
pass
age_group = clean_key(age_group)
if counted_trees.get(age_group) is None:
counted_trees[age_group]: Dict[str, Any] = {}
genus_name = tree["tree_taxonomy"]["genus"]
if genus_name is None:
if use_prediction is True:
try:
genus_name = tree["predictions"]["by_radius_prediction"][
"genus"]
except:
pass
genus_name = clean_key(genus_name)
if counted_trees[age_group].get(genus_name) is None:
counted_trees[age_group][genus_name]: Dict[str, Any] = {
"absolute": 0,
"percentage": 0
}
counted_trees[age_group][genus_name]["absolute"] += 1
for agegroup, agegroup_vals in counted_trees.items():
all_agegroup_trees = sum(
[x["absolute"] for x in agegroup_vals.values()])
for genus, vals in agegroup_vals.items():
counted_trees[agegroup][genus]["percentage"] = round(
vals["absolute"] / all_agegroup_trees, 2)
return counted_trees
def _count_district_by_object_type(tree_data: List[Dict[str, Any]]) -> Dict[str, Any]:
counted_trees: Dict[str, int] = {}
for tree in tree_data:
district_name = clean_key(tree["geo_info"]["district"])
if counted_trees.get(district_name) is None:
counted_trees[district_name]: Dict[str, Any] = {}
object_type = tree["base_info"]["object_type"]
object_type = clean_key(object_type)
if counted_trees[district_name].get(object_type) is None:
counted_trees[district_name][object_type]: Dict[str, Any] = {
"absolute": 0,
"percentage": 0
}
counted_trees[district_name][object_type]["absolute"] += 1
for district, district_vals in counted_trees.items():
all_district_trees = sum([x["absolute"] for x in district_vals.values()])
for object_type, vals in district_vals.items():
counted_trees[district][object_type]["percentage"] = round(vals["absolute"]/all_district_trees, 2)
return counted_trees
def _count_trees(tree_data: List[Dict[str, Any]]) -> Dict[str, Any]:
counted_trees: Dict[str, int] = {}
for tree in tree_data:
district_name = clean_key(tree["geo_info"]["district"])
if counted_trees.get(district_name) is None:
counted_trees[district_name]: Dict[str, Any] = {
"absolute": 0,
"percentage": 0
}
counted_trees[district_name]["absolute"] += 1
for district, vals in counted_trees.items():
counted_trees[district]["percentage"] = round(vals["absolute"]/len(tree_data), 2)
return counted_trees
def _count_trees(tree_data: List[Dict[str, Any]]) -> Dict[str, Any]:
counted_trees: Dict[str, int] = {}
for tree in tree_data:
object_type = tree["base_info"]["object_type"]
object_type = clean_key(object_type)
if counted_trees.get(object_type) is None:
counted_trees[object_type]: Dict[str, Any] = {
"absolute": 0,
"percentage": 0
}
counted_trees[object_type]["absolute"] += 1
for object_type, vals in counted_trees.items():
counted_trees[object_type]["percentage"] = round(
vals["absolute"] / len(tree_data), 2)
return counted_trees
def _osm_keys(tree_data: List[Dict[str, Any]]) -> Dict[str, Any]:
osm_keys_count: Dict[str, int] = {}
for tree in tree_data:
location_types = tree["tree_location_type"]
if location_types is None:
location_type = clean_key(location_types)
if osm_keys_count.get(location_type) is None:
osm_keys_count[location_type] = 0
osm_keys_count[location_type] += 1
continue
is_highway = False
if len(location_types) == 1 and "highway" in location_types:
is_highway = True
use_green_spaces_agriculture = True
if len(
location_types
) > 1 and "green_spaces_leisure" in location_types and "green_spaces_agriculture" in location_types:
use_green_spaces_agriculture = False
for location_type, osm_node in location_types.items():
if location_type == "highway" and is_highway is False:
continue
if location_type == "green_spaces_agriculture" and use_green_spaces_agriculture is False:
continue
if is_highway is True:
if osm_keys_count.get(location_type) is None:
osm_keys_count[location_type] = 0
osm_keys_count[location_type] += 1
else:
osm_key = osm_node["type"]
if osm_keys_count.get(osm_key) is None:
osm_keys_count[osm_key] = 0
osm_keys_count[osm_key] += 1
return osm_keys_count