def _import_data(self, server, database, max_facilities_to_import=DEFAULT_FACILITIES_TO_IMPORT,
max_mdg_to_import=DEFAULT_MDG_TO_IMPORT):
from mangrove.datastore.database import DatabaseManager
from mangrove.datastore.entity import Entity, get_entities_by_value
from mangrove.datastore.datadict import DataDictType, get_datadict_type, create_datadict_type
from mangrove.utils import GoogleSpreadsheetsClient
from mangrove.utils.google_spreadsheets import get_string, get_number, get_boolean, get_list
from mangrove.utils.spreadsheets import CsvReader
from mangrove.utils.helpers import slugify
from mangrove.georegistry.api import get_feature_by_id
import os
import datetime
import json
from pytz import UTC
print "Loading 'NIMS Data'..."
print "\tServer: %s" % server
print "\tDatabase: %s" % database
dbm = DatabaseManager(server=server, database=database)
user_spreadsheets = GoogleSpreadsheetsClient(settings.GMAIL_USERNAME, settings.GMAIL_PASSWORD)
nims_data = user_spreadsheets['NIMS Data Deux']
load_population = True
load_other = True
load_mdg = True
load_health = True
load_water = True
load_education = True
countries = {}
states = {}
locations = {}
num_cgs = 0
datadict_types = {}
geo_id_dict = {}
cgs_type = create_datadict_type(
dbm,
slug='cgs',
name='CGS',
primitive_type='boolean'
)
datadict_types['cgs'] = cgs_type.id
geo_id_type = create_datadict_type(
dbm,
slug='geo_id',
name='Geographic ID',
primitive_type='string'
)
datadict_types['geo_id'] = geo_id_type.id
name_type = create_datadict_type(
dbm,
slug='name',
name='Name',
primitive_type='string'
)
datadict_types['name'] = name_type.id
mdg_type = create_datadict_type(
dbm,
slug='mdg',
name='MDG',
primitive_type='string'
)
datadict_types['mdg'] = mdg_type.id
country_geo_id = {}
for row in nims_data['Nigeria Country ALL']:
country_geo_id[row['name']] = row['grid']
state_geo_ids = {}
for row in nims_data['Nigeria States ALL']:
state_geo_ids[row['name']] = row['grid']
num_rows = 0
print "Importing location entities from 'Nigeria LGAs ALL' worksheet"
for row in nims_data['Nigeria LGAs ALL']:
country = get_string('country', row)
state = get_string('state', row)
lga = get_string('lga', row)
cgs = get_boolean('cgs', row)
geo_id = get_string('geoid', row)
lga_gr_id = get_string('grid', row)
location = (country, state, lga)
if country not in countries:
gr_id = country_geo_id[country]
feature = get_feature_by_id(gr_id)
# geometry = feature['geometry']
centroid = json.loads(feature['properties']['geometry_centroid'])
e = Entity(dbm,
entity_type=["Location", "Country"],
location=[country],
centroid=centroid,
gr_id=gr_id)
locations[(country,)] = e.save()
countries[country] = e.id
data = [(name_type.slug, country, name_type)]
e.add_data(data, event_time=datetime.datetime(2011, 03, 01, tzinfo=UTC))
num_rows += 1
print "[%s]...(%s) -- %s" % (num_rows, country, e.id)
def _import_data(self,
server,
database,
max_facilities_to_import=DEFAULT_FACILITIES_TO_IMPORT,
max_mdg_to_import=DEFAULT_MDG_TO_IMPORT):
from mangrove.datastore.database import DatabaseManager
from mangrove.datastore.entity import Entity, get_entities_by_value
from mangrove.datastore.datadict import DataDictType, get_datadict_type, create_datadict_type
from mangrove.utils import GoogleSpreadsheetsClient
from mangrove.utils.google_spreadsheets import get_string, get_number, get_boolean, get_list
from mangrove.utils.spreadsheets import CsvReader
from mangrove.utils.helpers import slugify
from mangrove.georegistry.api import get_feature_by_id
import os
import datetime
import json
from pytz import UTC
print "Loading 'NIMS Data'..."
print "\tServer: %s" % server
print "\tDatabase: %s" % database
dbm = DatabaseManager(server=server, database=database)
user_spreadsheets = GoogleSpreadsheetsClient(settings.GMAIL_USERNAME,
settings.GMAIL_PASSWORD)
nims_data = user_spreadsheets['NIMS Data Deux']
load_population = True
load_other = True
load_mdg = True
load_health = True
load_water = True
load_education = True
countries = {}
states = {}
locations = {}
num_cgs = 0
datadict_types = {}
geo_id_dict = {}
cgs_type = create_datadict_type(dbm,
slug='cgs',
name='CGS',
primitive_type='boolean')
datadict_types['cgs'] = cgs_type.id
geo_id_type = create_datadict_type(dbm,
slug='geo_id',
name='Geographic ID',
primitive_type='string')
datadict_types['geo_id'] = geo_id_type.id
name_type = create_datadict_type(dbm,
slug='name',
name='Name',
primitive_type='string')
datadict_types['name'] = name_type.id
mdg_type = create_datadict_type(dbm,
slug='mdg',
name='MDG',
primitive_type='string')
datadict_types['mdg'] = mdg_type.id
country_geo_id = {}
for row in nims_data['Nigeria Country ALL']:
country_geo_id[row['name']] = row['grid']
state_geo_ids = {}
for row in nims_data['Nigeria States ALL']:
state_geo_ids[row['name']] = row['grid']
num_rows = 0
print "Importing location entities from 'Nigeria LGAs ALL' worksheet"
for row in nims_data['Nigeria LGAs ALL']:
country = get_string('country', row)
state = get_string('state', row)
lga = get_string('lga', row)
cgs = get_boolean('cgs', row)
geo_id = get_string('geoid', row)
lga_gr_id = get_string('grid', row)
location = (country, state, lga)
if country not in countries:
gr_id = country_geo_id[country]
feature = get_feature_by_id(gr_id)
# geometry = feature['geometry']
centroid = json.loads(
feature['properties']['geometry_centroid'])
e = Entity(dbm,
entity_type=["Location", "Country"],
location=[country],
centroid=centroid,
gr_id=gr_id)
locations[(country, )] = e.save()
countries[country] = e.id
data = [(name_type.slug, country, name_type)]
e.add_data(data,
event_time=datetime.datetime(2011,
03,
01,
tzinfo=UTC))
num_rows += 1
print "[%s]...(%s) -- %s" % (num_rows, country, e.id)
if cgs:
num_cgs += 1
e.add_data(data=[(cgs_type.slug, cgs, cgs_type)])
print "Countries (%d)" % len(countries)
print "States (%d)" % len(states)
print "LGAs (%d) (%d as CGS)" % ((len(locations) - len(countries) - len(states)), num_cgs)
print "Total locations (%d)" % len(locations)
lga_loaded = []
lga_failed = []
if load_population:
print "Adding data from 'Population Data' worksheet"
for row in nims_data['Population Variables']:
slug = get_string('slug', row)
name = get_string('name', row)
primitive_type = get_string('primitivetype', row)
tags = get_list('tags', row)
if not slug in datadict_types:
dd_type = create_datadict_type(
dbm,
slug=slug,
name=name,
primitive_type=primitive_type,
tags=tags
)
datadict_types[slug] = dd_type.id
for row in nims_data['Population Data']:
state = get_string('state', row)
num_cgs += 1
e.add_data(data=[(cgs_type.slug, cgs, cgs_type)])
print "Countries (%d)" % len(countries)
print "States (%d)" % len(states)
print "LGAs (%d) (%d as CGS)" % (
(len(locations) - len(countries) - len(states)), num_cgs)
print "Total locations (%d)" % len(locations)
lga_loaded = []
lga_failed = []
if load_population:
print "Adding data from 'Population Data' worksheet"
for row in nims_data['Population Variables']:
slug = get_string('slug', row)
name = get_string('name', row)
primitive_type = get_string('primitivetype', row)
tags = get_list('tags', row)
if not slug in datadict_types:
dd_type = create_datadict_type(
dbm,
slug=slug,
name=name,
primitive_type=primitive_type,
tags=tags)
datadict_types[slug] = dd_type.id
for row in nims_data['Population Data']:
state = get_string('state', row)
lga = get_string('lga', row)