def plot_wateruse(wel_files, perioddata, add_data=None,
wel_flux_col='q',
model_volume_units='$m^3$', model_time_units='day',
plot_volume_units='mgal', plot_time_units='day',
outfile=None):
"""
Parameters
----------
wel_files :
A head line with column names is assumed. For example:
#k,i,j,q,boundname
perioddata :
add_data :
model_volume_units :
model_time_units :
plot_volume_units :
plot_time_units :
Returns
-------
"""
# read the stress period information
if not isinstance(perioddata, pd.DataFrame):
perioddata = pd.read_csv(perioddata)
else:
perioddata = perioddata.copy()
perioddata.index = perioddata['per']
dfs = []
for i, f in wel_files.items():
df = pd.read_csv(f, delim_whitespace=True)
df.columns = [c.strip('#') for c in df.columns]
df['per'] = i
df['start_datetime'] = perioddata.loc[i, 'start_datetime']
df['end_datetime'] = perioddata.loc[i, 'end_datetime']
dfs.append(df)
df = pd.concat(dfs)
# sum the model pumping by stress period
period_sums = df.groupby('per').first()
period_sums[wel_flux_col] = df.groupby('per')[wel_flux_col].sum()
# fill nan values (from any periods without wel files) with 0s
period_sums = period_sums.reindex(range(period_sums.index.max()))
period_sums['start_datetime'] = perioddata['start_datetime']
period_sums['end_datetime'] = perioddata['end_datetime']
period_sums[wel_flux_col].fillna(0, inplace=True)
period_sums.index = pd.to_datetime(period_sums['start_datetime'])
period_sums['WEL package input'] = period_sums['q']
period_sums = period_sums[['WEL package input', 'start_datetime', 'end_datetime']]
# convert units
model_vol_conv = convert_volume_units(model_volume_units, plot_volume_units)
model_time_conv = convert_time_units(model_time_units, plot_time_units)
model_conv = model_vol_conv * model_time_conv
# plot any additional comparison data
if add_data is not None:
for label, items in add_data.items():
# read the stress period information
if not isinstance(items['data'], pd.DataFrame):
items['data'] = pd.read_csv(items['data'])
req_cols = {'q', 'start_datetime'}
assert not req_cols.difference(items['data'].columns), \
f"add_data: {label} data must have columns: {req_cols}"
items['data']['start_datetime'] = pd.to_datetime(items['data']['start_datetime'])
aux_period_sums = items['data'].groupby('start_datetime').first()
aux_period_sums[label] = items['data'].groupby('start_datetime')['q'].sum()
# fill nan values (from any periods without wel files) with 0s
#aux_period_sums[label].fillna(0, inplace=True)
aux_period_sums['start_datetime'] = aux_period_sums.index
period_sums = period_sums.join(aux_period_sums[[label]], how='outer')
j=2
# forward fill nan WEL values values
# (where other times may have been inserted)
period_sums['WEL package input'] = period_sums['WEL package input'].ffill()
#period_sums = period_sums.resample('M').mean() #.ffill()
# make a plot
fig, ax = plt.subplots(figsize=(11, 8.5))
ax = period_sums.plot(ax=ax)
units_text = f'{model_volume_units}/{model_time_units}'
ax.set_ylabel(f'Pumpage, in {units_text}')
ax.set_xlabel('')
# second axis with another volume unit
def second_axis_conversion(x):
return x * model_conv
def second_axis_conversion_r(x):
return x * 1 / model_conv
ax2 = ax.secondary_yaxis('right', functions=(second_axis_conversion,
second_axis_conversion_r))
ax2.set_ylabel(f'Pumpage, in {plot_volume_units}/{plot_time_units}')
#format_xtick_labels(period_sums, ax, maxlabels=30, date_format='%Y-%m-%d')
h, l = ax.get_legend_handles_labels()
means = (period_sums.mean(axis=0) * model_conv).to_dict()
plot_units_text = f'{plot_volume_units}/{plot_time_units}'
labels_with_means = []
for label in l:
new_label = label
if label in means:
new_label += f' (mean: {means[label]:g} {plot_units_text})'
labels_with_means.append(new_label)
ax.legend(h, labels_with_means)
if outfile is not None:
Path(outfile).parent.mkdir(parents=True, exist_ok=True)
plt.savefig(outfile)
plt.close()
print(f'wrote {outfile}')
else:
return ax
def preprocess_flows(
data,
metadata=None,
flow_data_columns=['flow'],
start_date=None,
active_area=None,
active_area_id_column=None,
active_area_feature_id=None,
source_crs=4269,
dest_crs=5070,
datetime_col='datetime',
site_no_col='site_no',
line_id_col='line_id',
x_coord_col='x',
y_coord_col='y',
name_col='name',
flow_qualifier_column=None,
default_qualifier='measured',
include_sites=None,
include_line_ids=None,
source_volume_units='ft3',
source_time_units='s',
dest_volume_units='m3',
dest_time_units='d',
geographic_groups=None,
geographic_groups_col=None,
max_obsname_len=None,
add_leading_zeros_to_sw_site_nos=False,
column_renames=None,
outfile=None,
):
"""Preprocess stream flow observation data, for example, from NWIS or another data source that
outputs time series in CSV format with site locations and identifiers.
* Data are reprojected from a `source_crs` (Coordinate reference system; assumed to be in geographic coordinates)
to the CRS of the model (`dest_crs`)
* Data are culled to a `start_date` and optionally, a polygon or set of polygons defining the model area
* length and time units are converted to those of the groundwater model.
* Prefixes for observation names (with an optional length limit) that identify the location are generated
* Preliminary observation groups can also be assigned, based on geographic areas defined by polygons
(`geographic_groups` parameter)
Parameters
----------
data : csv file or DataFrame
Time series of stream flow observations.
Columns:
===================== ======================================
site_no site identifier
datetime measurement dates/times
x x-coordinate of site
y y-coordinate of site
flow_data_columns Columns of observed streamflow values
flow_qualifier_column Optional column with qualifiers for flow values
===================== ======================================
Notes:
* x and y columns can alternatively be in the metadata table
* flow_data_columns are denoted in `flow_data_columns`; multiple
columns can be included to process base flow and total flow, or
other statistics in tandem
* For example, `flow_qualifier_column` may have "estimated" or "measured"
flags denoting whether streamflows were derived from measured values
or statistical estimates.
metadata : csv file or DataFrame
Stream flow observation site information.
May include columns:
================= ================================================================================
site_no site identifier
x x-coordinate of site
y y-coordinate of site
name name of site
line_id_col Identifier for a line in a hydrography dataset that the site is associated with.
================= ================================================================================
Notes:
* other columns in metadata will be passed through to the metadata output
flow_data_columns : list of strings
Columns in data with flow values or their statistics.
By default, ['q_cfs']
start_date : str (YYYY-mm-dd)
Simulation start date (cull observations before this date)
active_area : str
Shapefile with polygon to cull observations to. Automatically reprojected
to dest_crs if the shapefile includes a .prj file.
by default, None.
active_area_id_column : str, optional
Column in active_area with feature ids.
By default, None, in which case all features are used.
active_area_feature_id : str, optional
ID of feature to use for active area
By default, None, in which case all features are used.
source_crs : obj
Coordinate reference system of the head observation locations.
A Python int, dict, str, or :class:`pyproj.crs.CRS` instance
passed to :meth:`pyproj.crs.CRS.from_user_input`
Can be any of:
- PROJ string
- Dictionary of PROJ parameters
- PROJ keyword arguments for parameters
- JSON string with PROJ parameters
- CRS WKT string
- An authority string [i.e. 'epsg:4326']
- An EPSG integer code [i.e. 4326]
- A tuple of ("auth_name": "auth_code") [i.e ('epsg', '4326')]
- An object with a `to_wkt` method.
- A :class:`pyproj.crs.CRS` class
By default, epsg:4269
dest_crs : obj
Coordinate reference system of the model. Same input types
as ``source_crs``.
By default, epsg:5070
datetime_col : str, optional
Column name in data with observation date/times,
by default 'datetime'
site_no_col : str, optional
Column name in data and metadata with site identifiers,
by default 'site_no'
line_id_col : str, optional
Column name in data or metadata with identifiers for
hydrography lines associated with observation sites.
by default 'line_id'
x_coord_col : str, optional
Column name in data or metadata with x-coordinates,
by default 'x'
y_coord_col : str, optional
Column name in data or metadata with y-coordinates,
by default 'y'
name_col : str, optional
Column name in data or metadata with observation site names,
by default 'name'
flow_qualifier_column : str, optional
Column name in data with flow observation qualifiers, such
as "measured" or "estimated"
by default 'category'
default_qualifier : str, optional
Default qualifier to populate flow_qualifier_column if it
is None. By default, "measured"
include_sites : list-like, optional
Exclude output to these sites.
by default, None (include all sites)
include_line_ids : list-like, optional
Exclude output to these sites, represented by line identifiers.
by default, None (include all sites)
source_volume_units : str, 'm3', 'cubic meters', 'ft3', etc.
Volume units of the source data. By default, 'ft3'
source_time_units : str, 's', 'seconds', 'days', etc.
Time units of the source data. By default, 's'
dest_volume_units : str, 'm3', 'cubic meters', 'ft3', etc.
Volume units of the output (model). By default, 'm3'
dest_time_units : str, 's', 'seconds', 'days', etc.
Time units of the output (model). By default, 'd'
geographic_groups : file, dict or list-like
Option to group observations by area(s) of interest. Can
be a shapefile, list of shapefiles, or dictionary of shapely polygons.
A 'group' column will be created in the metadata, and observation
sites within each polygon will be assigned the group name
associated with that polygon.
For example::
geographic_groups='../source_data/extents/CompositeHydrographArea.shp'
geographic_groups=['../source_data/extents/CompositeHydrographArea.shp']
geographic_groups={'cha': <shapely Polygon>}
Where 'cha' is an observation group name for observations located within the
the area defined by CompositeHydrographArea.shp. For shapefiles,
group names are provided in a `geographic_groups_col`.
geographic_groups_col : str
Field name in the `geographic_groups` shapefile(s) containing the
observation group names associated with each polygon.
max_obsname_len : int or None
Maximum length for observation name prefix. Default of 13
allows for a PEST obsnme of 20 characters or less with
<prefix>_yyyydd or <prefix>_<per>d<per>
(e.g. <prefix>_2d1 for a difference between stress periods 2 and 1)
If None, observation names will not be truncated. PEST++ does not have
a limit on observation name length.
add_leading_zeros_to_sw_site_nos : bool
Whether or not to pad site numbers using the
:func:~`mapgwm.swflows.format_usgs_sw_site_id` function.
By default, False.
column_renames : dict, optional
Option to rename columns in the data or metadata that are different than those listed above.
For example, if the data file has a 'SITE_NO' column instead of 'SITE_BADGE'::
column_renames={'SITE_NO': 'site_no'}
by default None, in which case the renames listed above will be used.
Note that the renames must be the same as those listed above for
:func:`mapgwm.swflows.preprocess_flows` to work.
outfile : str
Where output file will be written. Metadata are written to a file
with the same name, with an additional "_info" suffix prior to
the file extension.
Returns
-------
data : DataFrame
Preprocessed time series
metadata : DataFrame
Preprocessed metadata
References
----------
`The PEST++ Manual <https://github.com/usgs/pestpp/tree/master/documentation>`
Notes
-----
"""
# outputs
if outfile is not None:
outpath, filename = os.path.split(outfile)
makedirs(outpath)
outname, ext = os.path.splitext(outfile)
out_info_csvfile = outname + '_info.csv'
out_data_csvfile = outfile
out_shapefile = outname + '_info.shp'
# read the source data
if not isinstance(data, pd.DataFrame):
df = pd.read_csv(data, dtype={site_no_col: object})
else:
df = data.copy()
# check the columns
for col in [datetime_col] + flow_data_columns:
assert col in df.columns, "Column {} not found in {}".format(col, data)
assert any({site_no_col, line_id_col}.intersection(df.columns)), \
"Neither {} or {} found in {}. Need to specify a site_no_col or line_id_col".format(site_no_col,
line_id_col, data)
# rename input columns to these names,
# for consistent output
dest_columns = {
datetime_col: 'datetime',
site_no_col: 'site_no',
line_id_col: 'line_id',
x_coord_col: 'x',
y_coord_col: 'y',
name_col: 'name',
flow_qualifier_column: 'category'
}
# update the default column renames
# with any supplied via column_renames parameter
if isinstance(column_renames, collections.Mapping):
dest_columns.update(column_renames)
df.rename(columns=dest_columns, inplace=True)
flow_data_columns = [
c if c not in dest_columns else dest_columns[c]
for c in flow_data_columns
]
# convert site numbers to strings;
# add leading 0s to any USGS sites that should have them
if 'site_no' in df.columns:
df['site_no'] = format_site_ids(df['site_no'],
add_leading_zeros_to_sw_site_nos)
else:
df['site_no'] = df[line_id_col]
# read the source data
if metadata is not None:
if not isinstance(metadata, pd.DataFrame):
md = pd.read_csv(metadata, dtype={site_no_col: object})
else:
md = metadata.copy()
if site_no_col not in md.columns or 'site_no' not in df.columns:
raise IndexError(
'If metadata are supplied, both data and metadata must '
'have a site_no column.')
md.rename(columns=dest_columns, inplace=True)
md['site_no'] = format_site_ids(md['site_no'],
add_leading_zeros_to_sw_site_nos)
md.index = md['site_no']
by_site = df.groupby('site_no')
md['start_dt'] = pd.DataFrame(by_site['datetime'].first())
else:
by_site = df.groupby('site_no')
md = pd.DataFrame(by_site['datetime'].first())
md.columns = ['start_dt']
md['site_no'] = md.index
md['end_dt'] = pd.DataFrame(by_site['datetime'].last())
md['n'] = pd.DataFrame(by_site['datetime'].count())
md.reset_index(inplace=True, drop=True)
# assign metadata if supplied
for col in 'x', 'y', 'line_id', 'name':
if col in df.columns and col not in md.columns:
by_site_no = dict(zip(df['site_no'], df[col]))
md[col] = [by_site_no[sn] for sn in md['site_no']]
if col != 'line_id':
df.drop(col, axis=1, inplace=True)
# index the dataframe to times;
# truncate data before start date
df.index = pd.to_datetime(df['datetime'])
df.index.name = 'datetime'
df = df.loc[start_date:].copy()
# project x, y to model crs
x_pr, y_pr = project((md.x.values, md.y.values), source_crs, dest_crs)
md['x'], md['y'] = x_pr, y_pr
md['geometry'] = [Point(x, y) for x, y in zip(x_pr, y_pr)]
# cull data to that within the model area
if active_area is not None:
df, md = cull_data_to_active_area(df,
active_area,
active_area_id_column,
active_area_feature_id,
data_crs=dest_crs,
metadata=md)
# get the hydrography IDs corresponding to each site
# using the included lookup table
#if 'line_id' not in df.columns:
# assert line_id_lookup is not None, \
# "need to include line_ids in a column, or line_id_lookup dictionary mapping line_ids to site numbers"
# df = df.loc[df['site_no'].isin(line_id_lookup)].copy()
# df['line_id'] = [line_id_lookup[sn] for sn in df['site_no']]
if include_sites is not None:
md = md.loc[md.site_no.isin(include_sites)]
df = df.loc[df.site_no.isin(include_sites)]
if include_line_ids is not None:
md = md.loc[md.line_id.isin(include_line_ids)]
df = df.loc[df.line_id.isin(include_line_ids)]
# convert units
# ensure that flow values are numeric (may be objects if taken directly from NWIS)
unit_conversion = (
convert_volume_units(source_volume_units, dest_volume_units) /
convert_time_units(source_time_units, dest_time_units))
for flow_col in flow_data_columns:
df[flow_col] = pd.to_numeric(df[flow_col],
errors='coerce') * unit_conversion
df.dropna(subset=flow_data_columns, axis=0, inplace=True)
# reformat qualifiers for consistent output
# (lump to dest category columns of either estimated or measured)
# with measured including values derived from baseflow separation or actual measurements)
# output column name for flow qualifier column:
dest_flow_qualifier_column = 'category'
if flow_qualifier_column is not None:
flow_qualifiers = {
'calculated': 'measured', # 'measured',
'base flow separated from measured values':
'measured', # 'measured',
'measured total flow': 'measured',
'estimated gaged': 'estimated',
'estimated ungaged': 'estimated'
}
df[dest_flow_qualifier_column] = df[flow_qualifier_column].replace(
flow_qualifiers)
else:
df['category'] = default_qualifier
# make unique n-character prefixes (site identifiers) for each observation location
# 13 character length allows for prefix_yyyymmm in 20 character observation names
# (BeoPEST limit)
unique_obsnames = set()
obsnames = []
for sn in md['site_no'].tolist():
if max_obsname_len is not None:
name = make_obsname(sn,
unique_names=unique_obsnames,
maxlen=max_obsname_len)
assert name not in unique_obsnames
else:
name = sn
unique_obsnames.add(name)
obsnames.append(name)
md['obsprefix'] = obsnames
# add area of interest information
md['group'] = 'fluxes'
md = assign_geographic_obsgroups(md,
geographic_groups,
geographic_groups_col,
metadata_crs=dest_crs)
# data columns
data_cols = ['site_no', 'line_id', 'datetime'
] + flow_data_columns + ['category']
#if 'line_id' in md.columns and 'line_id' not in df.columns:
# # only map line_ids to data if there are more site numbers
# # implying that no site number maps to more than one line_id
# if len(set(df.site_no)) >= len(set(df.line_id)):
# ids = dict(zip(md['site_no'], md['line_id']))
# df['line_id'] = [ids[sn] for sn in df['site_no']]
data_cols = [c for c in data_cols if c in df.columns]
df = df[data_cols]
md.index = md['site_no']
# save out the results
if outfile is not None:
df2shp(md.drop(['x', 'y'], axis=1), out_shapefile, crs=dest_crs)
print('writing {}'.format(out_info_csvfile))
md.drop('geometry', axis=1).to_csv(out_info_csvfile,
index=False,
float_format='%g')
print('writing {}'.format(out_data_csvfile))
df.to_csv(out_data_csvfile, index=False, float_format='%g')
return df, md
def assign_monthly_production(self, outfile='processed_swuds.csv'):
""" Assign production wells for water use, skipping IR (irrigation) and
TE (thermal electric) to production zones. If production zones are not
assigned or if the well bottom doesn't fall into a production zone, then
the screen_top and screen_bot are assigned using well_depth and the
default screen length.
Production is given in cubic m per day.
todo: add unit conversion parameter so other units can be used?
Parameters
----------
outfile: str
path to final processed monthly water-use file with production zone
information
"""
# fill in missing monthly values with annual value
for c in self.monthly_cols:
idx = self.df.loc[self.df[c].isnull()].index.values
self.df.loc[idx, c] = self.df.loc[idx, 'ANNUAL_VAL']
# pull out groundwater sites that are not IR, AQ or TE
self.df = self.df.loc[(self.df['WATER_CD'] == 'GW')
& ~(self.df['FROM_NAT_WATER_USE_CD'] == 'IR')
& ~(self.df['FROM_NAT_WATER_USE_CD'] == 'AQ')
& ~(self.df['FROM_NAT_WATER_USE_CD'] == 'TE')]
# reshape dataframe to have monthly values in same column
stacked = pd.DataFrame(self.df[self.monthly_cols].stack())
stacked.reset_index(inplace=True)
stacked.rename(columns={
'level_1': 'month',
0: 'q_monthly'
},
inplace=True)
stacked.q_monthly = stacked.q_monthly
stacked.index = stacked.level_0
stacked = stacked.join(self.df)
keep_cols = [c for c in stacked.columns if c not in self.monthly_cols]
stacked = stacked[keep_cols]
month = {name: i + 1 for i, name in enumerate(self.monthly_cols)}
dates = [
'{}-{:02d}'.format(year, month[month_column_name])
for year, month_column_name in zip(stacked.YEAR, stacked.month)
]
stacked['datetime'] = pd.to_datetime(dates)
stacked.sort_values(by=['SITE_NO', 'datetime'], inplace=True)
# set start and end dates if not already set
if self.start_date is None:
self.start_date = stacked.datetime.min()
if self.end_date is None:
self.end_date = stacked.datetime.max()
groups = stacked.groupby('SITE_NO')
all_groups = []
for site_no, group in groups:
group = group.copy()
group.index = pd.to_datetime(group['datetime'])
start_date = pd.Timestamp(self.start_date)
end_date = pd.Timestamp(self.end_date)
monthly_values_2010 = group.loc[group.datetime.dt.year == 2010]
monthly_values_2010 = dict(
zip(monthly_values_2010.datetime.dt.month,
monthly_values_2010.q_monthly))
avg_monthly_values = group.groupby(
group.index.month).mean().q_monthly.to_dict()
q_mean = group.q_monthly.mean()
# reindex the site data to include all months for simulation period
all_dates = pd.date_range(start_date, end_date, freq='MS')
group = group.reindex(all_dates)
# fill empty dates
q = []
for month, q_monthly in zip(group.index.month, group.q_monthly):
# try to use 2010 values if they exist
if np.isnan(q_monthly):
q_monthly = monthly_values_2010.get(month, np.nan)
# otherwise take the average value for each month
if np.isnan(q_monthly):
q_monthly = avg_monthly_values[month]
# fill missing months with the mean value for the site
if np.isnan(q_monthly):
q_monthly = q_mean
q.append(q_monthly)
# assume most values represent abstraction
# if sum is positive, invert so that output values are negative
if np.sum(q) > 0:
q = -np.array(q)
group['q'] = q
#group['q'] = group['q'] * 3785.4 # convert from mgd to cubic m per d
group['q'] = group['q'] * convert_volume_units(
self.data_volume_units, self.model_length_units)
group['site_no'] = f'swuds_{site_no}'
group['well_elev'] = self.well_elevations[site_no]
group['depth'] = self.depths[site_no]
well_botm_depth = self.well_elevations[site_no] - self.depths[
site_no]
group['x'] = np.nanmin(group['x'])
group['y'] = np.nanmin(group['y'])
# assign a production zone from default dict. If the bottom of the
# well does not fall in a zone, or if the dictionary is empty; then
# the production zone is assigned 'unnamed'
production_zone = 'unnamed'
for prod_name in self.prod_zone_top.keys():
prod_zone_top = self.prod_zone_top[prod_name][site_no]
prod_zone_bot = self.prod_zone_bot[prod_name][site_no]
if np.isnan(prod_zone_top) or np.isnan(
prod_zone_bot): # missing zone
group['screen_bot'] = self.well_elevations[
site_no] - self.depths[site_no]
group['screen_top'] = self.well_elevations[
site_no] - self.depths[
site_no] + self.default_screen_len
group['open_int_method'] = 'well depth'
else:
if well_botm_depth < prod_zone_top and well_botm_depth > prod_zone_bot:
production_zone = prod_name
group['screen_bot'] = prod_zone_bot
group['screen_top'] = prod_zone_top
group['open_int_method'] = 'production zone'
else:
group['screen_bot'] = self.well_elevations[
site_no] - self.depths[site_no]
group['screen_top'] = self.well_elevations[
site_no] - self.depths[
site_no] + self.default_screen_len
group['open_int_method'] = 'well depth'
group['production_zone'] = production_zone
# add aquifer name
group['aquifer_name'] = self.aquifer_names.get(
group["FROM_AQFR_CD"].values[0], 'unnamed')
cols = [
'site_no', 'q', 'q_monthly', 'month', 'well_elev', 'depth',
'screen_bot', 'screen_top', 'x', 'y'
]
all_groups.append(group[cols])
self.df = pd.concat(all_groups)
self.df[
'start_datetime'] = self.df.index # start date of each pumping period
if outfile is not None:
outfile = Path(outfile)
self.df.to_csv(outfile, index=False)
print(
'processed SWUDS data written to {0} and in dataframe attribute'
.format(outfile))
self.df['geometry'] = [
Point(x, y) for x, y in zip(self.df.x, self.df.y)
]
# write only unique pumping values to shapefile
to_shapefile = self.df.groupby(['site_no',
'q']).first().reset_index()
shapefile = outfile.with_suffix('.shp')
df2shp(to_shapefile, shapefile, crs=self.dest_crs)
def test_convert_volume_units():
assert np.allclose(convert_volume_units('cubic meters', 'mgal'),
264.172 / 1e6)
assert np.allclose(convert_volume_units('$m^3$', '$ft^3$'), 35.3147)
assert np.allclose(convert_volume_units('cubic meters', 'cubic feet'),
35.3147)
assert np.allclose(convert_volume_units('cubic feet', 'cubic meters'),
0.0283168)
assert np.allclose(convert_volume_units('meters', 'feet'), 35.3147)
assert np.allclose(convert_volume_units('feet', 'meters'), 0.0283168)
assert np.allclose(convert_volume_units('feet3', 'm3'), 0.0283168)
assert np.allclose(convert_volume_units('feet3', 'meters3'), 0.0283168)
assert np.allclose(convert_volume_units('gallons', 'ft3'), 1 / 7.48052)
assert np.allclose(convert_volume_units('gallons', 'm3'),
(.3048**3) / 7.48052)
assert np.allclose(convert_volume_units('gallons', 'acre foot'),
1 / 7.48052 / 43560)
assert np.allclose(convert_volume_units('gallons', 'af'),
1 / 7.48052 / 43560)
assert np.allclose(convert_volume_units('gallons', 'acre-ft'),
1 / 7.48052 / 43560)
assert np.allclose(convert_volume_units('mgal', 'acre-ft'),
1e6 / 7.48052 / 43560)
assert np.allclose(convert_volume_units('liters', 'gallon'), 1 / 3.78541)
assert np.allclose(convert_volume_units(None, 'cubic feet'), 1.)
assert np.allclose(convert_volume_units('cubic feet', None), 1.)
assert np.allclose(convert_volume_units('junk', 'junk'), 1.)
def resample_pumping_rates(wu_file, wu_points, model,
active_area=None,
minimum_layer_thickness=2,
drop_ids=None,
exclude_steady_state=True,
dropna=False, na_fill_value=0.,
verbose=False):
"""Read water use data from a master file generated from
WDNR_wu_data.ipynb. Cull data to area of model. Convert
from monthly gallons to daily averages in m3/d
for model stress periods.
Parameters
----------
wu_file : csv file
Water use data ouput from the WDNR_wu_data.ipynb.
wu_points : point shapefile
Water use locations, generated in the WDNR_wu_data.ipynb
Must be in same CRS as sr.
model : flopy.modflow.Modflow instance
Must have a valid attached .sr attribute defining the model grid.
Only wells within the bounds of the sr will be retained.
Sr is also used for row/column lookup.
Must be in same CRS as wu_points.
active_area : str (shapefile path) or shapely.geometry.Polygon
Polygon denoting active area of the model. If specified,
wells are culled to this area instead of the model bounding box.
(default None)
exclude_steady_state : bool
Exclude steady-state stress periods from resampled output.
(default True)
minimum_layer_thickness : scalar
Minimum layer thickness to have pumping.
dropna : bool
Flag to drop times (stress periods) where there is no data for a well
na_fill_value : float
If dropna == False, fill missing times (stress periods) with this value.
Returns
-------
wu_data : DataFrame
"""
assert not np.isnan(na_fill_value), "na_fill_value must be a number!"
well_info, monthly_data = read_wdnr_monthly_water_use(wu_file,
wu_points,
model,
drop_ids=drop_ids,
active_area=active_area,
minimum_layer_thickness=minimum_layer_thickness)
print('\nResampling pumping rates in {} to model stress periods...'.format(wu_file))
if dropna:
print(' wells with no data for a stress period will be dropped from that stress period.')
else:
print(' wells with no data for a stress period will be assigned {} pumping rates.'.format(na_fill_value))
if exclude_steady_state:
perioddata = model.perioddata.loc[~model.perioddata.steady].copy()
else:
perioddata = model.perioddata.copy()
t0 = time.time()
# reindex the record at each site to the model stress periods
dfs = []
for site, sitedata in monthly_data.groupby('site_no'):
if site not in well_info.index:
continue
sitedata.index = sitedata.datetime
assert not sitedata.index.duplicated().any()
if dropna:
site_period_data = sitedata.reindex(perioddata.start_datetime).dropna(axis=1)
else:
site_period_data = sitedata.reindex(perioddata.start_datetime, fill_value=na_fill_value)
isna = site_period_data['site_no'] == 0.
if np.any(isna):
if verbose:
years = set(site_period_data.loc[isna, 'year'])
years = ', '.join(list(years))
print('Site {} has {} times with nans (in years {})- filling with {}s'.format(site,
np.sum(isna),
years,
na_fill_value))
site_period_data['site_no'] = site
site_period_data['year'] = site_period_data.index.year
site_period_data['month'] = site_period_data.index.month
site_period_data['datetime'] = site_period_data.index
assert not site_period_data.isna().any().any()
site_period_data.index = perioddata.index
# copy stress periods and lengths from master stress period table
for col in ['perlen', 'per']:
site_period_data[col] = perioddata[col]
# convert units from monthly gallon totals to daily model length units
site_period_data['gal_d'] = site_period_data['gallons'] / site_period_data['perlen']
gal_to_model_units = convert_volume_units('gal', get_model_length_units(model))#model.dis.lenuni]
site_period_data['q'] = site_period_data.gal_d * gal_to_model_units
for col in ['i', 'j', 'k']:
site_period_data[col] = well_info.loc[site, col]
site_period_data.index = [site] * len(site_period_data)
dfs.append(site_period_data[['k', 'i', 'j', 'q', 'per']])
wel_data = pd.concat(dfs)
# water use fluxes should be negative
if not wel_data.q.max() <= 0:
wel_data.loc[wel_data.q.abs() != 0., 'q'] *= -1
wel_data['boundname'] = ['site{:d}'.format(s) for s in wel_data.index]
assert not np.any(wel_data.isna()), "Nans in Well Data"
print("took {:.2f}s\n".format(time.time() - t0))
return wel_data
def get_mean_pumping_rates(wu_file, wu_points, model,
start_date='2012-01-01', end_date='2018-12-31',
period_stats={0: 'mean'},
active_area=None,
drop_ids=None,
minimum_layer_thickness=2):
"""Read water use data from a master file generated from
WDNR_wu_data.ipynb. Cull data to area of model. Convert
from monthly gallons to daily averages in m3/d
for model stress periods.
Parameters
----------
wu_file : csv file
Water use data ouput from the WDNR_wu_data.ipynb.
wu_points : point shapefile
Water use locations, generated in the WDNR_wu_data.ipynb
Must be in same CRS as sr.
model : flopy.modflow.Modflow instance
Must have a valid attached .sr attribute defining the model grid.
Only wells within the bounds of the sr will be retained.
Sr is also used for row/column lookup.
Must be in same CRS as wu_points.
start_date : str (YYYY-MM-dd)
Start date of time period to average.
end_date : str (YYYY-MM-dd)
End date of time period to average.
period_stats : dict
Dictionary of stats keyed by stress period. Stats include zero values, unless noted.
keys : 0, 1, 2 ...
values: str; indicate statistic to apply for each stress period
'mean': mean pumping for period defined by start_date and end_date
'<month>': average for a month of the year (e.g. 'august'),
for the for period defined by start_date and end_date
minimum_layer_thickness : scalar
Minimum layer thickness to have pumping.
Returns
-------
wu_data : DataFrame
"""
start_date, end_date = pd.Timestamp(start_date), pd.Timestamp(end_date)
well_info, monthly_data = read_wdnr_monthly_water_use(wu_file, wu_points, model,
active_area=active_area,
drop_ids=drop_ids,
minimum_layer_thickness=minimum_layer_thickness)
if well_info is None:
return
# determine period for computing average pumping
# make a dataframe for each stress period listed
wel_data = []
for per, stat in period_stats.items():
if isinstance(stat, str):
stat = stat.lower()
elif isinstance(stat, list):
stat, start_date, end_date = stat
start_date, end_date = pd.Timestamp(start_date), pd.Timestamp(end_date)
stat = stat.lower()
# slice the monthly values to the period of start_date, end_date
# aggregate to mean values in m3/d
# (this section will need some work for generalized transient run setup)
is_inperiod = (monthly_data.datetime > start_date) & (monthly_data.datetime < end_date)
inperiod = monthly_data.loc[is_inperiod].copy()
# compute average daily flux using the sum and number of days for each site
# (otherwise each month is weighted equally)
# convert units from monthly gallons to daily gallons
inperiod['days'] = inperiod.datetime.dt.daysinmonth
if stat == 'mean':
period_data = inperiod.copy()
# mean for given month (e.g. august mean)
elif stat in months.keys() or stat in months.values():
period_data = inperiod.loc[inperiod.month == months.get(stat, stat)].copy()
else:
raise ValueError('Unrecognized input for stat: {}'.format(stat))
site_means = period_data.groupby('site_no').mean()
site_sums = period_data.groupby('site_no').sum()
site_means['gal_d'] = site_sums['gallons'] / site_sums['days']
# conversion to model units is based on lenuni variable in DIS package
gal_to_model_units = convert_volume_units('gal', get_model_length_units(model))
site_means['q'] = site_means.gal_d * gal_to_model_units
site_means['per'] = per
wel_data.append(well_info[['k', 'i', 'j']].join(site_means[['q', 'per']], how='inner'))
wel_data = pd.concat(wel_data, axis=0)
# water use fluxes should be negative
if not wel_data.q.max() <= 0:
wel_data.loc[wel_data.q.abs() != 0., 'q'] *= -1
wel_data['boundname'] = ['site{:d}'.format(s) for s in wel_data.index]
assert not np.any(wel_data.isna()), "Nans in Well Data"
return wel_data
def preprocess_iwum_pumping(ncfile,
start_date=None,
end_date=None,
active_area=None,
active_area_id_column=None,
active_area_feature_id=None,
estimated_production_zone_top=None,
estimated_production_zone_botm=None,
flux_variable='value',
nc_crs=5070,
dest_crs=5070,
nc_length_units='meters',
estimated_production_surface_units='meters',
model_length_units='meters',
outfile=None):
"""Get pumping from the Irrigation Water Use Model (IWUM; Wilson, 2020) output and
assign open interval information, using raster surfaces of the
top and bottom of an estimated production zone.
Parameters
----------
ncfile : file path
NetCDF output from Irrigation Water Use Model
start_date : str
Cull data before this date.
end_date : str
Cull data after this date.
active_area : str
Shapefile with polygon to cull observations to. Automatically reprojected
to dest_crs if the shapefile includes a .prj file.
by default, None.
active_area_id_column : str, optional
Column in active_area with feature ids.
By default, None, in which case all features are used.
active_area_feature_id : str, optional
ID of feature to use for active area
By default, None, in which case all features are used.
estimated_production_zone_top : file path
Raster surface for assigning screen tops
estimated_production_zone_botm : file path
Raster surface for assigning screen bottoms
flux_variable : str
Varible in ncfile for pumping fluxes. Fluxes are assumed to
represent total volumes for each time period.
nc_crs : obj
Coordinate Reference System (CRS) of ncfile.
A Python int, dict, str, or pyproj.crs.CRS instance
passed to the pyproj.crs.from_user_input
See http://pyproj4.github.io/pyproj/stable/api/crs/crs.html#pyproj.crs.CRS.from_user_input.
Can be any of:
- PROJ string
- Dictionary of PROJ parameters
- PROJ keyword arguments for parameters
- JSON string with PROJ parameters
- CRS WKT string
- An authority string [i.e. 'epsg:4326']
- An EPSG integer code [i.e. 4326]
- A tuple of ("auth_name": "auth_code") [i.e ('epsg', '4326')]
- An object with a `to_wkt` method.
- A :class:`pyproj.crs.CRS` class
nc_length_units : str, {'meters', 'ft', etc.}
Length units of pumped volumes in ncfile
estimated_production_surface_units : str, {'meters', 'ft', etc.}
Length units of elevations in estimated production surface rasters.
model_length_units : str, {'meters', 'ft', etc.}
Length units of model.
outfile : csv file for output table
Returns
-------
df : DataFrame
Table of pumping rates in m3/day, location
and open interval information.
Columns:
============== ================================================
site_no index position of pumping rate in ncfile grid
x x-coordinate in `dest_crs`
y y-coordinate in `dest_crs`
start_datetime start date of pumping period
end_datetime end date of pumping period
screen_top screen top elevation, in `model_length_units`
screen_botm screen bottom elevation, in `model_length_units`
q pumping rate, in model units
geometry shapely Point object representing location
============== ================================================
Notes
-----
* Time units are assumed to be days.
* Fluxes are assumed to represent total volumes for each time period
indicated by the differences between successive values along the time axis of ncfile.
"""
ds = xr.open_dataset(ncfile)
time_variable = [k for k in ds.coords.keys() if k.lower() not in {'x', 'y'}][0]
ds_x, ds_y = np.meshgrid(ds['x'], ds['y'])
# original values are in m3, in each 1 mi2 cell
# can leave in m3 if reassigning to 1km grid as point values
length_conversion = convert_volume_units(nc_length_units,
model_length_units) ** 3
unit_suffix = vol_suffix[model_length_units] + 'd'
flux_col = 'q' # 'flux_{}'.format(unit_suffix) # output field name for fluxes
# get top/botm elevations
est_screen_top = None
est_screen_botm = None
if estimated_production_zone_top is not None and \
estimated_production_zone_botm is not None:
surf_unit_conversion = convert_length_units(estimated_production_surface_units,
model_length_units)
est_screen_top = get_values_at_points(estimated_production_zone_top, ds_x, ds_y,
points_crs=nc_crs)
est_screen_top *= surf_unit_conversion
est_screen_botm = get_values_at_points(estimated_production_zone_botm, ds_x, ds_y,
points_crs=nc_crs)
est_screen_botm *= surf_unit_conversion
# in any places where screen top is less than the screen botm,
# set both at the mean
loc = est_screen_top < est_screen_botm
means = np.mean([est_screen_top, est_screen_botm], axis=0)
est_screen_top[loc] = means[loc]
est_screen_botm[loc] = means[loc]
print(f'Reset screen top and bottom to mean elevation at {loc.ravel().sum()} '
f'locations where screen top was < screen bottom')
dfs = []
times = pd.DatetimeIndex(ds[time_variable].loc[start_date:end_date].values)
for n, period_start_date in enumerate(times):
# for each time entry, get the data
kwargs = {time_variable: period_start_date}
arr = ds[flux_variable].sel(**kwargs).values
# make sure pumping sign is negative
# based on assumption that values are mostly abstraction
if arr.sum() > 0:
arr *= -1
# set up a dataframe
data = {'site_no': np.arange(ds_x.size),
'x': ds_x.ravel(),
'y': ds_y.ravel(),
}
if est_screen_top is not None and est_screen_botm is not None:
data.update({'screen_top': est_screen_top.ravel(),
'screen_botm': est_screen_botm.ravel()
}
)
df = pd.DataFrame(data)
df['start_datetime'] = period_start_date
# get the end_date, handling last entry
if n + 1 < len(times):
period_end_date = times[n + 1]
else:
# set end date for last period on previous period length
last_start = dfs[-1]['start_datetime'].values[0]
ndays = (pd.Timestamp(period_start_date) -
pd.Timestamp(last_start)).days
period_end_date = period_start_date + pd.Timedelta(ndays, unit='d')
# convert the time units
ndays = (pd.Timestamp(period_end_date) -
pd.Timestamp(period_start_date)).days
assert ndays > 0, "period_end_date {} is before period_start_date {}"\
.format(period_end_date, period_start_date)
time_conversion = 1 / ndays # original quantities are volumes for the time period
# time indexing in pandas is through last value
period_end_date = pd.Timestamp(period_end_date) - pd.Timedelta(1, unit='d')
df['end_datetime'] = period_end_date
df[flux_col] = arr.ravel() * length_conversion * time_conversion
# only includes fluxes > 0
df = df.loc[df[flux_col] < 0]
dfs.append(df)
df = pd.concat(dfs)
# site number column (that would be unique from other integers from other data sources)
df['site_no'] = [f'iwum_{node}' for node in df.site_no]
# project the data to a destination crs, if provided
# make a separate metadata dataframe with 1 row per location
# to avoid redundant operations
metadata = df.groupby('site_no').first().reset_index()[['site_no', 'x', 'y']]
metadata.index = metadata['site_no']
x_pr, y_pr = project((metadata.x.values, metadata.y.values), nc_crs, dest_crs)
metadata['x'], metadata['y'] = x_pr, y_pr
metadata['geometry'] = [Point(x, y) for x, y in zip(x_pr, y_pr)]
# cull the data to the model area, if provided
if active_area is not None:
df, metadata = cull_data_to_active_area(df, active_area,
active_area_id_column,
active_area_feature_id,
data_crs=dest_crs, metadata=metadata)
# update data with x,y values projected in metadata
x = dict(zip(metadata.site_no, metadata.x))
y = dict(zip(metadata.site_no, metadata.y))
df['x'] = [x[sn] for sn in df.site_no]
df['y'] = [y[sn] for sn in df.site_no]
if outfile is not None:
outfile = Path(outfile)
df.to_csv(outfile, index=False, float_format='%g')
print('wrote {}'.format(outfile))
# Make a plot of iwum output in mgal/day
out_pdf_path = outfile.parent / 'plots'
out_pdf_path.mkdir(exist_ok=True)
plot_iwum_output(ncfile, flux_variable=flux_variable, outpath=out_pdf_path)
return df
def plot_iwum_output(ncfile, flux_variable='value', outpath='.'):
"""Make a plot of iwum output in mgal/day
for comparison with subsequent datasets.
"""
ds = xr.open_dataset(ncfile)
time_variable = [k for k in ds.coords.keys() if k.lower() not in {'x', 'y'}][0]
xydims = tuple([i for i, len in enumerate(ds[flux_variable].shape)
if len != ds[time_variable].shape[0]])
ts = ds[flux_variable][:, :, :].sum(axis=xydims).to_pandas()
if ts.index.dtype == np.object:
ts.index = pd.to_datetime(ts.index)
ndays = pd.to_timedelta(np.diff(ts.index)).days.tolist()
ndays.append(ndays[-1]) # pad the last time period
df = pd.DataFrame(ts, columns=['m3'])
df['m3d'] = df['m3'] / ndays # convert volumes to daily rate
fig, ax = plt.subplots(figsize=(11, 8.5))
ax = df['m3d'].plot.bar(ax=ax)
ax.set_ylabel('Cubic meters per day')
ymin, ymax = ax.get_ylim()
ax2 = ax.twinx()
to_mg = convert_volume_units('m3', 'mgal')
ax2.set_ylim(ymin * to_mg, ymax * to_mg)
ax2.set_ylabel('Million gallons per day')
# can't use .mean(),
# because periods with 0 pumping may not be included
mean_mgd = df['m3'].sum() * to_mg / np.sum(ndays)
ax2.axhline(mean_mgd, c='r')
ax2.text(0.75, 0.9, 'Mean: {:,.0f} mgal/day'.format(mean_mgd),
transform=ax.transAxes)
# format the tick labels
format_xtick_labels(df, ax, maxlabels=30, date_format='%Y-%m-%d')
#maxlabels = 30
#xticklabels = df.index.strftime('%Y-%m-%d').tolist()
#stride = max(int(np.floor(len(xticklabels) / maxlabels)), 1)
#formatted_labels = []
#for label in xticklabels[::stride]:
# formatted_labels += [label] + [''] * (stride - 1)
#formatted_labels = formatted_labels[:len(xticklabels)]
#junk = ax.set_xticklabels(formatted_labels)
# record the file name and last modified date
ftime = pd.Timestamp(os.path.getmtime(ncfile), unit='s')
ax2.text(0.02, 0.98, '{}\n{}'.format(ncfile,
ftime.strftime('%Y-%m-%d')),
va='top', fontsize=8,
transform=ax.transAxes)
# annotate the bars with the values
for i, p in enumerate(ax.patches):
value = '{:,.0f}'.format(to_mg * p.get_height())
ax.annotate(value, (p.get_x() * 1.01, p.get_height() * 1.01),
ha='center', fontsize=8)
ncfile = Path(ncfile)
ftime = pd.Timestamp(ncfile.stat().st_mtime, unit='s')
outfile = Path(outpath, f'{ncfile.name}_{ftime:%Y-%m-%d}.pdf')
plt.savefig(outfile)
print('wrote {}'.format(outfile))
plt.close()
def preprocess_te_wateruse(data,
start_date=None,
end_date=None,
active_area=None,
active_area_id_column=None,
active_area_feature_id=None,
estimated_production_zone_top=None,
estimated_production_zone_botm=None,
estimated_production_surface_units='feet',
source_crs=4269,
dest_crs=5070,
interp_method='linear',
data_volume_units='mgal',
model_length_units='meters',
outfile=None):
"""Preprocess water use data from thermoelectric power plants:
* reproject data to a destination CRS `dest_crs`)
* cull data to an area of interest (`active_area`)
* if input data do not have information on the well screen intervals;
sample screen tops and bottoms from raster surfaces bounding
an estimated production zone (e.g. `estimated_production_zone_top`)
* reindex the data to continous monthly values extending from `start_date`
to `end_date`. Typically, these would bracket the time period for which
the pumping should be simulated in a model. For example, the earliest data
may be from 2010, but if the model starts in 2008, it may be appropriate to
begin using the 2010 rates then (``start_date='2008'``). If no start or end
date are given, the first and last years of pumping in `data` are used.
* fill empty months by interpolation via a specified `interp_method`
* backfill any remaining empty months going back to the `start_date`
* write processed data to a CSV file and shapefile of the same name
Parameters
----------
data : DataFrame
Thermoelectric water use data in the following format
(similar to that output by :func:`mapgwm.te_wateruse.read_te_water_use_spreadsheet`):
=============== =======================================================
site_no power plant identifier (plant code)
start_datetime pandas datetime representative of flux (e.g. '2010')
x x-coordinate of withdrawl, in `source_crs`
y y-coordinate of withdrawl, in `source_crs`
q withdrawl flux, in `data_volume_units` per days
=============== =======================================================
start_date : str
Start date for pumping rates. If earlier than the dates in `data`,
pumping rates will be backfilled to this date.
end_date : str
End date for pumping rates. If later than the dates in `data`,
pumping rates will be forward filled to this date.
active_area : str
Shapefile with polygon to cull observations to. Automatically reprojected
to dest_crs if the shapefile includes a .prj file.
by default, None.
active_area_id_column : str, optional
Column in active_area with feature ids.
By default, None, in which case all features are used.
active_area_feature_id : str, optional
ID of feature to use for active area
By default, None, in which case all features are used.
estimated_production_zone_top : file path
Raster surface for assigning screen tops
estimated_production_zone_botm : file path
Raster surface for assigning screen bottoms
estimated_production_surface_units : str, {'meters', 'ft', etc.}
Length units of elevations in estimated production surface rasters.
source_crs : obj
Coordinate reference system of the head observation locations.
A Python int, dict, str, or :class:`pyproj.crs.CRS` instance
passed to :meth:`pyproj.crs.CRS.from_user_input`
Can be any of:
- PROJ string
- Dictionary of PROJ parameters
- PROJ keyword arguments for parameters
- JSON string with PROJ parameters
- CRS WKT string
- An authority string [i.e. 'epsg:4326']
- An EPSG integer code [i.e. 4326]
- A tuple of ("auth_name": "auth_code") [i.e ('epsg', '4326')]
- An object with a `to_wkt` method.
- A :class:`pyproj.crs.CRS` class
By default, epsg:4269
dest_crs : obj
Coordinate reference system of the model. Same input types
as ``source_crs``.
By default, epsg:5070
interp_method : str
Interpolation method to use for filling pumping rates to monthly values.
By default, 'linear'
data_volume_units : str; e.g. 'mgal', 'm3', 'cubic feet', etc.
Volume units of pumping data. All time units are assumed to be in days.
model_length_units : str; e.g. 'feet', 'm', 'meters', etc.
Length units of model.
outfile : str
Path for output file. A shapefile of the same name is also written.
If None, no output file is written. By default, None
Returns
-------
df_monthly : DataFrame
Notes
-----
* time units for TE data and model are assumed to be days
"""
df = data.copy()
# reproject to dest_crs
x, y = project(zip(df['x'], df['y']), source_crs, dest_crs)
df['x'], df['y'] = x, y
df['geometry'] = [Point(x, y) for x, y in zip(x, y)]
# drop wells with no location information (for now)
df.dropna(subset=['x', 'y'], axis=0, inplace=True)
# cull sites to those within the Delta footprint
# cull data to that within the model area
if active_area is not None:
df = cull_data_to_active_area(df,
active_area,
active_area_id_column,
active_area_feature_id,
data_crs=dest_crs)
# get top and bottom of estimated production interval at each well
if estimated_production_zone_top is not None and \
estimated_production_zone_botm is not None:
surf_unit_conversion = convert_length_units(
estimated_production_surface_units, model_length_units)
x, y = df.x.values, df.y.values
est_screen_top = get_values_at_points(estimated_production_zone_top,
x,
y,
points_crs=dest_crs)
est_screen_top *= surf_unit_conversion
est_screen_botm = get_values_at_points(estimated_production_zone_botm,
x,
y,
points_crs=dest_crs)
est_screen_botm *= surf_unit_conversion
df['screen_top'] = est_screen_top
df['screen_botm'] = est_screen_botm
# distribute fluxes to monthly values
# set start and end dates if not already set
if start_date is None:
start_date = df.start_datetime.min()
if end_date is None:
end_date = df.start_datetime.mmax()
groups = df.groupby('site_no')
all_groups = []
for site_no, group in groups:
dfg = group.copy()
# create a continuous monthly time index
# labeled at the month start
all_dates = pd.date_range(start_date, end_date, freq='MS')
dfg.index = dfg['start_datetime']
dfg = dfg.reindex(all_dates)
# interpolate the discharge values;
# back filling to the start date
dfg['q'] = dfg.q.interpolate(method=interp_method).bfill()
dfg['q'] *= convert_volume_units(data_volume_units, model_length_units)
# fill remaining columns
dfg['start_datetime'] = dfg.index
fill_columns = set(dfg.columns).difference({'q', 'start_datetime'})
fill_values = group.iloc[0].to_dict()
for c in fill_columns:
dfg[c] = fill_values[c]
# add 'te' prefix to site number
dfg['site_no'] = f'te_{site_no}'
all_groups.append(dfg)
df_monthly = pd.concat(all_groups)
# assume most values represent abstraction
# if sum is positive, invert so that output values are negative
if df_monthly['q'].sum() > 0:
df_monthly['q'] *= -1
# clean up the columns
cols = [
'site_no', 'start_datetime', 'x', 'y', 'screen_top', 'screen_botm',
'q', 'geometry'
]
cols += list(set(df_monthly.columns).difference(cols))
df_monthly = df_monthly[cols]
# write the output
if outfile is not None:
outfile = Path(outfile)
df_monthly.drop('geometry', axis=1).to_csv(outfile,
index=False,
float_format='%g')
print('wrote {}'.format(outfile))
# write only unique pumping values to shapefile
to_shapefile = df_monthly.groupby(['site_no',
'q']).first().reset_index()
shapefile = outfile.with_suffix('.shp')
df2shp(to_shapefile, shapefile, crs=dest_crs)
return df_monthly
