-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
99e7a05
commit e6261c8
Showing
1 changed file
with
100 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,100 @@ | ||
from time import sleep | ||
|
||
from django.conf import settings | ||
|
||
import pandas as pd | ||
from tqdm import tqdm | ||
|
||
from hub.models import Area, AreaData, DataSet, DataType | ||
|
||
from .base_importers import BaseLatLongImportCommand | ||
|
||
|
||
class Command(BaseLatLongImportCommand): | ||
help = "Import number of RSPB reserves by constituency" | ||
|
||
data_file = settings.BASE_DIR / "data" / "rspb_reserves_centroids.csv" | ||
message = "Importing RSPB reserves data" | ||
uses_gss = False | ||
|
||
defaults = {} | ||
|
||
data_sets = { | ||
"": { | ||
"defaults": defaults, | ||
}, | ||
} | ||
|
||
def add_data_sets(self): | ||
data_set, created = DataSet.objects.update_or_create( | ||
name="rspb_nature_reserves", | ||
defaults={ | ||
"label": "RSPB Reserves", | ||
"data_type": "integer", | ||
"category": "place", | ||
"label": "RSPB Reserves", | ||
"description": "Number of RSPB reserves by constituency.", | ||
"source_label": "Data from the RSPB.", | ||
"release_date": "September 2023", | ||
"source": "https://www.rspb.org.uk", | ||
"source_type": "csv", | ||
"table": "areadata", | ||
"default_value": {}, | ||
"data_url": "", | ||
"is_filterable": False, | ||
"comparators": DataSet.comparators_default, | ||
}, | ||
) | ||
|
||
data_type, created = DataType.objects.update_or_create( | ||
data_set=data_set, | ||
name="rspb_nature_reserves", | ||
defaults={ | ||
"data_type": "integer", | ||
"label": "RSPB Reserves", | ||
"description": "Number of RSPB reserves by constituency.", | ||
}, | ||
) | ||
|
||
self.data_type = data_type | ||
self.data_types[data_type.name] = data_type | ||
|
||
def get_dataframe(self): | ||
df = pd.read_csv( | ||
self.data_file, | ||
usecols=["xcoord", "ycoord"], | ||
) | ||
df.columns = ["Longitude", "Latitude"] | ||
return df | ||
|
||
def process_data(self, df): | ||
df = self.get_dataframe() | ||
|
||
if not self._quiet: | ||
self.stdout.write("Importing RSPB reserve count data") | ||
|
||
for index, row in tqdm(df.iterrows(), disable=self._quiet): | ||
lat = row["Latitude"] | ||
lon = row["Longitude"] | ||
|
||
self.process_lat_long(lat=lat, lon=lon, row_name=index) | ||
|
||
if index > 0 and index % 50 == 0: | ||
sleep(10) | ||
|
||
def add_arguments(self, parser): | ||
parser.add_argument( | ||
"-q", "--quiet", action="store_true", help="Silence progress bars." | ||
) | ||
|
||
def handle(self, quiet=False, *args, **options): | ||
self._quiet = quiet | ||
self.add_data_sets() | ||
self.delete_data() | ||
df = self.get_dataframe() | ||
self.process_data(df) | ||
self.update_averages() | ||
self.update_max_min() | ||
|
||
def delete_data(self): | ||
AreaData.objects.filter(data_type__in=self.data_types.values()).delete() |