def as_data_frame(self, copy=True):
"""
Convert a GriddedData object to a Pandas DataFrame.
:param copy: Create a copy of the data for the new DataFrame? Default is True.
:return: A Pandas DataFrame representing the data and coordinates. Note that this won't include any metadata.
"""
from iris.pandas import as_data_frame
return as_data_frame(self, copy=copy)
def as_data_frame(self, copy=True):
"""
Convert a GriddedData object to a Pandas DataFrame.
:param copy: Create a copy of the data for the new DataFrame? Default is True.
:return: A Pandas DataFrame representing the data and coordinates. Note that this won't include any metadata.
"""
from iris.pandas import as_data_frame
return as_data_frame(self, copy=copy)
def cube_to_df(cube_max):
df = as_data_frame(cube_max, copy=True)
df = df.reset_index()
df['month'] = pd.DatetimeIndex(df['index']).month
df['year'] = pd.DatetimeIndex(df['index']).year
df.drop('index', axis=1, inplace=True)
df = df.rename(columns={0: "Temperature"})
df = df.query("year >= 1992 and year <=2015")
return df
def nc2df(fname):
cube = iris.load_cube(fname)
for coord in cube.coords(dimensions=[0]):
name = coord.name()
if name != 'time':
cube.remove_coord(name)
for coord in cube.coords(dimensions=[1]):
name = coord.name()
if name != 'station name':
cube.remove_coord(name)
df = as_data_frame(cube)
if cube.ndim == 1: # Horrible work around iris.
station = cube.coord('station name').points[0]
df.columns = [station]
return df
def nc2df(fname):
cube = iris.load_cube(fname)
for coord in cube.coords(dimensions=[0]):
name = coord.name()
if name != 'time':
cube.remove_coord(name)
for coord in cube.coords(dimensions=[1]):
name = coord.name()
if name != 'station name':
cube.remove_coord(name)
df = as_data_frame(cube)
if cube.ndim == 1: # Horrible work around iris.
station = cube.coord('station name').points[0]
df.columns = [station]
return df
def nc2df(fname, columns_name='station_code'):
"""
Load a netCDF timeSeries file as a dataframe.
"""
cube = iris.load_cube(fname)
for coord in cube.coords(dimensions=[0]):
name = coord.name()
if name != 'time':
cube.remove_coord(name)
for coord in cube.coords(dimensions=[1]):
name = coord.name()
if name != columns_name:
cube.remove_coord(name)
df = as_data_frame(cube)
if cube.ndim == 1: # Horrible work around iris.
station = cube.coord(columns_name).points[0]
df.columns = [station]
return df
def nc2df(fname, columns_name='station_code'):
"""
Load a netCDF timeSeries file as a dataframe.
"""
cube = iris.load_cube(fname)
for coord in cube.coords(dimensions=[0]):
name = coord.name()
if name != 'time':
cube.remove_coord(name)
for coord in cube.coords(dimensions=[1]):
name = coord.name()
if name != columns_name:
cube.remove_coord(name)
df = as_data_frame(cube)
if cube.ndim == 1: # Horrible work around iris.
station = cube.coord(columns_name).points[0]
df.columns = [station]
return df
def save_results(regridded_profiles, tracer_columns, params):
"""
Save (merged) results.
"""
# SET OUTPUT FILE NAMES
out_profiles_basename = string.replace(
params['out_profiles_basename'], "*", params['station_name']
)
out_columns_basename = string.replace(
params['out_columns_basename'], "*", params['station_name'])
if params['out_dir'] is None:
params['out_dir'] = os.path.abspath(os.getcwd())
out_profiles_basepath = os.path.join(params['out_dir'],
out_profiles_basename)
out_columns_basepath = os.path.join(params['out_dir'],
out_columns_basename)
out_profiles_cubes_fn = out_profiles_basepath + '.nc'
out_columns_cubes_fn = out_columns_basepath + '.nc'
out_profiles_tables_fn = '.'.join([out_profiles_basepath,
params['out_format']])
out_columns_tables_fn = '.'.join([out_columns_basepath,
params['out_format']])
# SAVE IN NETCDF FILES (CUBES)
# make altitude as dimension coord
for profile_cube in regridded_profiles:
if isinstance(profile_cube.coord('altitude'), iris.coords.AuxCoord):
iris_tools.permute_dim_aux_coords(profile_cube,
'model_level_number',
'altitude')
for cube in regridded_profiles:
iris_tools.fix_cube_attributes_vals(cube)
for cube in tracer_columns:
iris_tools.fix_cube_attributes_vals(cube)
iris.save(regridded_profiles, out_profiles_cubes_fn)
iris.save(tracer_columns, out_columns_cubes_fn)
# SAVE AS DATA TABLES (EXCEL, CSV...)
dataframe_profiles = {}
for profile in regridded_profiles:
profile_cube = profile.copy()
# there must be only one defined dimension coordinate for each
# cube dimension (no auxilliary coordinate (convert iris to pandas)
z_dim = profile_cube.coord_dims(profile_cube.coord(name='altitude'))
iris_tools.remove_dim_aux_coords(profile_cube, z_dim)
dataframe_units = str(profile_cube.units).replace('/', '_')
if dataframe_units == 'unknown':
dataframe_units = profile_cube.attributes['no_udunits2']
dataframe_name = "{tracer}_{units}".format(
tracer=profile_cube.attributes['name'],
units=dataframe_units
)
# scalar time coordinate
if profile_cube.ndim == 1:
series = ipandas.as_series(profile)
time_coord = profile_cube.coord('time')
date = time_coord.units.num2date(time_coord.points[0])
dataframe_profiles[dataframe_name] = pd.DataFrame({date : series}).transpose()
# dimensional time coordinate
else:
dataframe_profiles[dataframe_name] = ipandas.as_data_frame(profile_cube)
panel_profiles = pd.Panel(dataframe_profiles).astype(np.float64)
series_columns = {}
for column in tracer_columns:
series_name = "{tracer}_{units}".format(
tracer=column.attributes['name'],
units='molec_cm-2'
)
series_columns[series_name] = ipandas.as_series(column)
time_coord = column.coord('time')
date = time_coord.units.num2date(time_coord.points)
series_columns[series_name].index = date
dataframe_columns = pd.DataFrame(series_columns).astype(np.float64)
if params['out_format'] in ('hdf', 'hdf5'):
panel_profiles.to_hdf(out_profiles_tables_fn, 'profiles')
dataframe_columns.to_hdf(out_columns_tables_fn, 'columns')
elif params['out_format'] in ('xls', 'xlsx'):
panel_profiles.to_excel(out_profiles_tables_fn, 'profiles')
dataframe_columns.to_excel(out_columns_tables_fn, 'columns')
elif params['out_format'] == 'csv':
for pr in panel_profiles:
panel_profiles[pr].to_csv('{0}_{1}.csv'
.format(out_profiles_basepath, pr))
dataframe_columns.to_csv(out_columns_tables_fn)
return ([panel_profiles, dataframe_columns],
[out_profiles_cubes_fn, out_columns_cubes_fn,
out_profiles_tables_fn, out_columns_tables_fn])