def get_site_list(base_url, hts):
"""Creates a dataframe of sites from the WaterUse.hts file"""
all_sites = ws.site_list(base_url, hts)
################################
# Restrict to a subset of sites
sites = all_sites[3400:4000]
#sites = all_sites
#################################
return sites
def test_site_mtypes(hts):
sites = site_list(base_url, hts)
site1 = sites.iloc[2].SiteName
mtype_df1 = measurement_list(base_url, hts, site1).reset_index().iloc[0]
tsdata1 = get_data(base_url,
hts,
site1,
mtype_df1.Measurement,
from_date=str(mtype_df1.From),
to_date=str(mtype_df1.From))
assert len(tsdata1) == 1
def get_site():
"""This function prompts the user to enter the WAP that they wish to generate plots for"""
site = None
while site is None:
site_entry = input("Enter the WAP of interest: ")
site_list = ws.site_list('http://wateruse.ecan.govt.nz', 'WaterUse.hts')
if site_entry in site_list.values:
site = site_entry
else:
print("The WAP you have entered is not in the WaterUse.hts file. Please try again.")
return site
########################################### ### Parameters base_url = 'http://wateruse.ecan.govt.nz' hts = 'WQAll.hts' site = 'SQ31045' measurement = 'Total Phosphorus' from_date = '1983-11-22 10:50' to_date = '2018-04-13 14:05' dtl_method = 'trend' ########################################## ### Examples ## Get site list sites = site_list(base_url, hts) ## Get the measurement types for a specific site mtype_df1 = measurement_list(base_url, hts, site) ## Get the water quality parameter data (only applies to WQ data) mtype_df2 = wq_sample_parameter_list(base_url, hts, site) ## Get the time series data for a specific site and measurement type tsdata1 = get_data(base_url, hts, site, measurement, from_date=from_date, to_date=to_date) ## Get extra WQ time series data (only applies to WQ data) tsdata2, extra2 = get_data(base_url, hts, site, measurement, from_date=from_date, to_date=to_date, parameters=True) ## Get WQ sample data (only applies to WQ data) tsdata3 = get_data(base_url, hts, site, 'WQ Sample', from_date=from_date, to_date=to_date)
def test_site_list():
sites = site_list(base_url, hts, True)
assert len(sites) > 9000
sites = mssql.rd_sql(server, hydro_db, site_table, cols, where_in=where_in)
sites1 = sites[sites.ExtSiteID.str.contains('[A-Z]+\d\d/\d+')].copy()
return sites1
##############################################
### Query
sites1 = pd.read_csv(csv_path)
crc_dict = {'RecordNumber': sites1.RecordNumber.tolist()}
crc1 = rd_crc(crc_dict)
ht_sites = ws.site_list(ht_url, url_hts)
ht_sites['ExtSiteID'] = util.convert_site_names(ht_sites.SiteName)
ht_sites1 = ht_sites.dropna()
ht_crc_wap = pd.merge(crc1, ht_sites1,
on='ExtSiteID').drop_duplicates('SiteName')
ht_waps = ht_crc_wap[['SiteName']]
################################################
### Export meter name table
export_dir = r'C:\Users\hamishg\OneDrive - Environment Canterbury\Documents\_Projects\git\WaterUseQA\CreateTimeSeriesPlots'
meter_name_csv = 'list.csv'
@author: KurtV
"""
# import python modules
from hilltoppy import web_service as ws
import pandas as pd
# Set URL
base_url = 'http://wateruse.ecan.govt.nz'
# Set server hts file (Server hts name, not Hilltop01 hts name!)
# WQGroundwater.hts = \Hilltop01\Data\WQGroundwaterCombined.dsn
hts = 'WQAll.hts'
# Generate a dataframe of all sites in the server file with location data
hts_sites_df = ws.site_list(base_url, hts, location=True)
# Export hts sites table to csv file
hts_sites_df.to_csv('Sites in hts file.csv', index=False)
# Generate a list of all sites in the server file
hts_sites_list = sorted(hts_sites_df.SiteName.tolist(), key=str.lower)
# Generate a measurement summary and sample parameter summary for all sites
# Initialise empty lists
site_measurement_summary = []
site_sample_parameter_summary = []
# Loop through all sites in the hts file
for site in hts_sites_list:
# Call site-specific measurement list
measurement_summary = ws.measurement_list(base_url, hts, site)
up_takes2 = up_takes1[up_takes1.AllocatedRate > 0].copy()
up_takes2['AllocatedRateSum'] = up_takes2.groupby(
'Wap')['AllocatedRate'].transform('sum')
up_takes2['AllocatedRateRatio'] = up_takes2[
'AllocatedRate'] / up_takes2['AllocatedRateSum']
wap_ratios = up_takes2[up_takes2.HydroGroup ==
'Surface Water'].groupby(
'Wap')['AllocatedRateRatio'].sum()
wap_ratios.index.name = 'ExtSiteID'
####################################
### Pull out the Hilltop usage data
## Determine the sites available in Hilltop
ht_sites = ws.site_list(param['Input']['hilltop_base_url'],
param['Input']['hilltop_hts'])
ht_sites['Wap'] = convert_site_names(ht_sites.SiteName)
ht_sites1 = ht_sites[
ht_sites['Wap'].isin(wap_ratios.index)
& ~ht_sites['Wap'].isin(param['Input']['browns_rock_waps'])].copy(
)
ht_sites1.rename(columns={'SiteName': 'Site'}, inplace=True)
mtype_list = []
for site in ht_sites1.Site:
timer = 10
while timer > 0:
try:
m1 = ws.measurement_list(
param['Input']['hilltop_base_url'],
def test_site_list_with_collection(data):
sites = site_list(data['base_url'],
data['hts'],
collection=data['collection'])
assert len(sites) > 40
def test_site_list(data):
sites = site_list(data['base_url'], data['hts'], True)
assert len(sites) > 1000
min_n_days = 5 * 365
min_missing_days = 14
########################################
### Get data
## Nasa data
ds1 = xr.open_dataset(nc1)
da1 = ds1[nasa_mtype].resample(time='D', closed='right',
label='left').sum('time') * 3
del ds1
## Met stations
sites = ws.site_list(ecan_base_url, hts_name, True)
sites.rename(columns={'SiteName': 'Site'}, inplace=True)
mtypes = []
for s in sites['Site'].values:
mtypes.append(ws.measurement_list(ecan_base_url, hts_name, s, mtype))
mtypes_df = pd.concat(mtypes).reset_index().drop('DataType', axis=1)
mtypes_df['n_days'] = (mtypes_df['To'] - mtypes_df['From']).dt.days
mtypes_df1 = mtypes_df[mtypes_df['n_days'] >= min_n_days].copy()
sites1 = pd.merge(sites, mtypes_df1, on='Site')
ts_data = []
