def test_rank_stations_is_cz2010(lat_long_fresno, snapshot):
lat, lng = lat_long_fresno
df = rank_stations(lat, lng, is_cz2010=True)
snapshot.assert_match(df.shape, "is_cz2010=True")
df = rank_stations(lat, lng, is_cz2010=False)
snapshot.assert_match(df.shape, "is_cz2010=False")
def lat_lng_to_station_using_eeweather(lat, lng, is_cz2010=False):
ranked_stations = eeweather.rank_stations(lat,
lng,
match_iecc_climate_zone=True,
match_iecc_moisture_regime=True,
match_ba_climate_zone=True,
match_ca_climate_zone=True,
minimum_quality='high',
is_tmy3=True,
is_cz2010=is_cz2010)
naive_ranked_stations = eeweather.rank_stations(
lat,
lng,
minimum_quality='high',
is_tmy3=True,
is_cz2010=is_cz2010,
)
ranked_stations = eeweather.combine_ranked_stations(
[ranked_stations, naive_ranked_stations])
curr = datetime.now()
curr = datetime(curr.year, curr.month, curr.day, tzinfo=pytz.utc)
start = curr - timedelta(days=(365 * 5))
primary_match_station, warning_descs = eeweather.select_station(
ranked_stations,
coverage_range=(start, curr),
min_fraction_coverage=0.9,
rank=1,
)
return primary_match_station.usaf_id if primary_match_station else None
def test_rank_stations_max_difference_elevation_meters(lat_long_fresno,
snapshot):
lat, lng = lat_long_fresno
# no site_elevation
df = rank_stations(lat, lng, max_difference_elevation_meters=200)
snapshot.assert_match(df.shape, 'max_difference_elevation_meters=200')
df = rank_stations(lat,
lng,
site_elevation=0,
max_difference_elevation_meters=200)
snapshot.assert_match(
df.shape, 'site_elevation=0, max_difference_elevation_meters=200')
df = rank_stations(lat,
lng,
site_elevation=0,
max_difference_elevation_meters=50)
snapshot.assert_match(
df.shape, 'site_elevation=0, max_difference_elevation_meters=50')
df = rank_stations(lat,
lng,
site_elevation=1000,
max_difference_elevation_meters=50)
snapshot.assert_match(
df.shape, 'site_elevation=1000, max_difference_elevation_meters=50')
def test_rank_stations_is_tmy3(lat_long_fresno, snapshot):
lat, lng = lat_long_fresno
df = rank_stations(lat, lng, is_tmy3=True)
snapshot.assert_match(df.shape, 'is_tmy3=True')
df = rank_stations(lat, lng, is_tmy3=False)
snapshot.assert_match(df.shape, 'is_tmy3=False')
def test_rank_stations_max_distance_meters(lat_long_fresno, snapshot):
lat, lng = lat_long_fresno
df = rank_stations(lat, lng, max_distance_meters=200000)
snapshot.assert_match(df.shape, 'max_distance_meters=200000')
df = rank_stations(lat, lng, max_distance_meters=50000)
snapshot.assert_match(df.shape, 'max_distance_meters=50000')
def test_rank_stations_minimum_quality(lat_long_fresno, snapshot):
lat, lng = lat_long_fresno
df = rank_stations(lat, lng, minimum_quality="low")
snapshot.assert_match(df.shape, "minimum_quality=low")
df = rank_stations(lat, lng, minimum_quality="medium")
snapshot.assert_match(df.shape, "minimum_quality=medium")
df = rank_stations(lat, lng, minimum_quality="high")
snapshot.assert_match(df.shape, "minimum_quality=high")
def test_rank_stations_minimum_quality(lat_long_fresno, snapshot):
lat, lng = lat_long_fresno
df = rank_stations(lat, lng, minimum_quality='low')
snapshot.assert_match(df.shape, 'minimum_quality=low')
df = rank_stations(lat, lng, minimum_quality='medium')
snapshot.assert_match(df.shape, 'minimum_quality=medium')
df = rank_stations(lat, lng, minimum_quality='high')
snapshot.assert_match(df.shape, 'minimum_quality=high')
def test_rank_stations_match_state(lat_long_fresno, snapshot):
lat, lng = lat_long_fresno
df = rank_stations(lat, lng, site_state='CA')
snapshot.assert_match(df.shape, 'site_state=CA, match_state=False')
df = rank_stations(lat, lng, site_state='CA', match_state=True)
snapshot.assert_match(df.shape, 'site_state=CA, match_state=True')
df = rank_stations(lat, lng, site_state=None, match_state=True)
snapshot.assert_match(df.shape, 'site_state=None, match_state=True')
def test_rank_stations_minimum_tmy3_class(lat_long_fresno, snapshot):
lat, lng = lat_long_fresno
df = rank_stations(lat, lng, minimum_tmy3_class='III')
snapshot.assert_match(df.shape, 'minimum_tmy3_class=III')
df = rank_stations(lat, lng, minimum_tmy3_class='II')
snapshot.assert_match(df.shape, 'minimum_tmy3_class=II')
df = rank_stations(lat, lng, minimum_tmy3_class='I')
snapshot.assert_match(df.shape, 'minimum_tmy3_class=I')
def test_rank_stations_match_climate_zones_null(lat_long_africa, snapshot):
lat, lng = lat_long_africa
df = rank_stations(lat, lng, match_iecc_climate_zone=True)
snapshot.assert_match(df.shape, 'match_iecc_climate_zone')
df = rank_stations(lat, lng, match_iecc_moisture_regime=True)
snapshot.assert_match(df.shape, 'match_iecc_moisture_regime')
df = rank_stations(lat, lng, match_ba_climate_zone=True)
snapshot.assert_match(df.shape, 'match_ba_climate_zone')
df = rank_stations(lat, lng, match_ca_climate_zone=True)
snapshot.assert_match(df.shape, 'match_ca_climate_zone')
def test_rank_stations_match_climate_zones_not_null(lat_long_fresno, snapshot):
lat, lng = lat_long_fresno
df = rank_stations(lat, lng, match_iecc_climate_zone=True)
snapshot.assert_match(df.shape, "match_iecc_climate_zone")
df = rank_stations(lat, lng, match_iecc_moisture_regime=True)
snapshot.assert_match(df.shape, "match_iecc_moisture_regime")
df = rank_stations(lat, lng, match_ba_climate_zone=True)
snapshot.assert_match(df.shape, "match_ba_climate_zone")
df = rank_stations(lat, lng, match_ca_climate_zone=True)
snapshot.assert_match(df.shape, "match_ca_climate_zone")
def naive_candidates(lat_long_fresno):
lat, lng = lat_long_fresno
return rank_stations(lat,
lng,
minimum_quality="high",
is_tmy3=True,
is_cz2010=True).head()
def test_select_station_distance_warnings_check(lat_long_africa):
lat, lng = lat_long_africa
df = rank_stations(lat, lng)
station, warnings = select_station(df)
assert len(warnings) == 2
assert warnings[0].qualified_name == 'eeweather.exceeds_maximum_distance'
assert warnings[1].qualified_name == 'eeweather.exceeds_maximum_distance'
assert warnings[0].data['max_distance_meters'] == 50000
assert warnings[1].data['max_distance_meters'] == 200000
def cz_candidates(lat_long_fresno):
lat, lng = lat_long_fresno
return rank_stations(
lat,
lng,
match_iecc_climate_zone=True,
match_iecc_moisture_regime=True,
match_ba_climate_zone=True,
match_ca_climate_zone=True,
minimum_quality='high',
is_tmy3=True,
is_cz2010=True,
)
def _get_closest_station_by_zcta_ranked(zcta):
"""Selects the nth ranked station from a list of ranked stations
Parameters
----------
zcta : string
ZIP Code Tabulation Area (ZCTA)
Returns
-------
station : string
Station that was found
lat : float
latitude for the search
lon : float
longitude for the search
"""
zcta = zcta.zfill(
5
) # Ensure that we have 5 characters, and if not left-pad it with zeroes.
try:
lat, lon = zcta_to_lat_long(zcta)
except UnrecognizedZCTAError:
warnings.warn(
"%s is not recognized as a ZCTA. Treating as a ZIP Code instead." % zcta
)
lat, lon = _zip_to_lat_long(zcta)
station = None
for min_quality, max_distance_meters in METHOD:
station_ranking = rank_stations(
lat,
lon,
minimum_quality=min_quality,
max_distance_meters=max_distance_meters,
)
# Remove airport stations like A00008
if len(station_ranking) > 0:
station_ranking = station_ranking[
station_ranking.index.str.contains("^[0-9]")
]
station, _ = select_station(station_ranking)
if station:
break
return station, lat, lon
def _rank_stations_by_distance_and_quality(lat, lon):
""" Ranks the stations by distance and quality based on latitude / longitude
Parameters
----------
lat : float
latitude for the search
lon : float
longitude for the search
Returns
-------
station_ranking : Pandas.DataFrame
"""
station_ranking = rank_stations(lat, lon)
station_ranking['enumerated_quality'] = station_ranking['rough_quality'].map(QUALITY_SORT)
station_ranking = station_ranking.sort_values(by=['distance_meters', 'enumerated_quality'])
return station_ranking
def convert_coor_to_stations(sample, n_stations):
"""
Converts coordinates to nearest, high quality weather stations, removing duplicates
:param array sample: sample of coordinates to be converted to nearest station
:param integer n_stations: number of stations to grab per sample point
:return: array of coordinates for n_stations nearest weather stations
:rtype: array
"""
station_lat = []
station_lon = []
for i in sample:
x = eeweather.rank_stations(i[0], i[1])
for n in range(n_stations):
station_lat.append(x[x['rough_quality'] == 'high']['latitude'][n])
station_lon.append(x[x['rough_quality'] == 'high']['longitude'][n])
station_coor = np.column_stack((station_lat, station_lon))
station_coor = np.unique(station_coor, axis=0)
return station_coor
def test_rank_stations_no_filter(lat_long_fresno, snapshot):
lat, lng = lat_long_fresno
df = rank_stations(lat, lng)
snapshot.assert_match(df.shape, 'df.shape')
assert list(df.columns) == [
'rank',
'distance_meters',
'latitude',
'longitude',
'iecc_climate_zone',
'iecc_moisture_regime',
'ba_climate_zone',
'ca_climate_zone',
'rough_quality',
'elevation',
'state',
'tmy3_class',
'is_tmy3',
'is_cz2010',
'difference_elevation_meters',
]
assert round(df.distance_meters.iloc[0]) == 3008.0
assert round(df.distance_meters.iloc[-10]) == 9614514.0
assert pd.isnull(df.distance_meters.iloc[-1]) is True
def test_rank_stations_no_filter(lat_long_fresno, snapshot):
lat, lng = lat_long_fresno
df = rank_stations(lat, lng)
snapshot.assert_match(df.shape, "df.shape")
assert list(df.columns) == [
"rank",
"distance_meters",
"latitude",
"longitude",
"iecc_climate_zone",
"iecc_moisture_regime",
"ba_climate_zone",
"ca_climate_zone",
"rough_quality",
"elevation",
"state",
"tmy3_class",
"is_tmy3",
"is_cz2010",
"difference_elevation_meters",
]
assert round(df.distance_meters.iloc[0]) == 3008.0
assert round(df.distance_meters.iloc[-10]) == 9614514.0
assert pd.isnull(df.distance_meters.iloc[-1]) is True
import eeweather
import datetime
import pytz
latitude = 33.8688
longitude = 151.2093
# for documentation read https://eeweather.readthedocs.io/en/latest/api.html#summaries
ranked_stations = eeweather.rank_stations(latitude, longitude, is_tmy3=True)
station, warnings = eeweather.select_station(ranked_stations)
print(ranked_stations.loc[station.usaf_id])
start_date = datetime.datetime(2016, 6, 1, tzinfo=pytz.UTC)
end_date = datetime.datetime(2016, 6, 15, tzinfo=pytz.UTC)
tempC = station.load_isd_hourly_temp_data(
start_date, end_date) #Integrated Surface Database (ISD)
tempC = station.load_isd_hourly_pcp24_data(
start_date, end_date) #Integrated Surface Database (ISD)
# tempC = station.load_gsod_daily_temp_data(start_date, end_date) #GSOD : Global Surface Summary Of Day
# eeweather.plot_station_mapping(latitude, longitude, station, distance_meters=ranked_stations.loc[station.usaf_id][1])#, target='91104')
