├── proxysiphon ├── tests │ ├── __init__.py │ ├── test_records.py │ └── test_proxychimp.py ├── lmr_hdf5 │ ├── foram_seasons.nc │ └── __init__.py ├── __init__.py ├── records.py ├── agemodel.py ├── proxychimp.py └── lgm.py ├── README.md ├── ci └── requirements-py37.yml ├── .gitignore ├── setup.py ├── .travis.yml ├── NEWS.md └── LICENSE /proxysiphon/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /proxysiphon/lmr_hdf5/foram_seasons.nc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/brews/proxysiphon/master/proxysiphon/lmr_hdf5/foram_seasons.nc -------------------------------------------------------------------------------- /proxysiphon/__init__.py: -------------------------------------------------------------------------------- 1 | from proxysiphon.records import read_ncdc, read_lgm, read_petm 2 | from proxysiphon.agemodel import get_deltar_online, fit_agedepthmodel, date_proxy 3 | from proxysiphon.lmr_hdf5 import nc2lmrh5, nc2lmrdf 4 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # proxysiphon 2 | 3 | [![Build Status](https://travis-ci.org/brews/proxysiphon.svg?branch=master)](https://travis-ci.org/brews/proxysiphon) 4 | 5 | Internal lab tool to parse and clean marine sediment proxy data. 6 | 7 | This project is under heavy development. 8 | 9 | Requires Python >= 3.7. 10 | -------------------------------------------------------------------------------- /ci/requirements-py37.yml: -------------------------------------------------------------------------------- 1 | name: test_env 2 | channels: 3 | - conda-forge 4 | - sbmalev 5 | - defaults 6 | dependencies: 7 | - attrs 8 | - cartopy 9 | - coverage 10 | - docutils 11 | - matplotlib>=2.0 12 | - numpy 13 | - pandas 14 | - chardet 15 | - carbonferret 16 | - erebusfall 17 | - netCDF4 18 | - pytest 19 | - python=3.7 20 | - scipy>=1.0 21 | - unidecode 22 | - xarray 23 | - pytables 24 | - shapely 25 | -------------------------------------------------------------------------------- /proxysiphon/tests/test_records.py: -------------------------------------------------------------------------------- 1 | from proxysiphon import records 2 | 3 | 4 | def test_publication_to_citationstr(): 5 | pub = records.Publication(authors='White, Tom; New, White', 6 | published_date_or_year=1986, 7 | published_title='Article title', 8 | journal_name='Cool Journal', 9 | volume=12, issue=3, pages=173, 10 | doi='sfdjla/vcxl.3') 11 | goal = "White, Tom; New, White (1986): Article title. Cool Journal, 12, 3, 173, doi:sfdjla/vcxl.3" 12 | assert pub.to_citationstr() == goal -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | 3 | # Byte-compiled / optimized / DLL files 4 | __pycache__/ 5 | *.py[cod] 6 | 7 | # C extensions 8 | *.so 9 | 10 | # Distribution / packaging 11 | .Python 12 | env/ 13 | bin/ 14 | build/ 15 | develop-eggs/ 16 | dist/ 17 | eggs/ 18 | lib/ 19 | lib64/ 20 | parts/ 21 | sdist/ 22 | var/ 23 | *.egg-info/ 24 | .installed.cfg 25 | *.egg 26 | 27 | # Installer logs 28 | pip-log.txt 29 | pip-delete-this-directory.txt 30 | 31 | # Unit test / coverage reports 32 | htmlcov/ 33 | .tox/ 34 | .coverage 35 | .cache 36 | nosetests.xml 37 | coverage.xml 38 | 39 | # Translations 40 | *.mo 41 | 42 | # Mr Developer 43 | .mr.developer.cfg 44 | .project 45 | .pydevproject 46 | 47 | # Rope 48 | .ropeproject 49 | 50 | # Django stuff: 51 | *.log 52 | *.pot 53 | 54 | # Sphinx documentation 55 | docs/_build/ 56 | 57 | #Ignore figures 58 | *.jpg 59 | *.pdf 60 | *.png 61 | 62 | #Data Files 63 | *.npy 64 | *.h5 65 | 66 | #Ipython stuff 67 | *.ipynb 68 | matplotlibrc 69 | 70 | #pyCharm stuff 71 | .idea/* 72 | 73 | #scratch files 74 | scratch/* 75 | tests/data/* 76 | 77 | #Video Files 78 | *.gif 79 | *.avi 80 | *.mp4 81 | Figs/* 82 | Archive/* 83 | *.nc 84 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup, find_packages 2 | 3 | 4 | setup( 5 | name='proxysiphon', 6 | version='0.0.1b1', 7 | description='Internal lab tool to parse and clean marine sediment proxy data.', 8 | license='GPLv3', 9 | 10 | author='S. Brewster Malevich', 11 | author_email='malevich@email.arizona.edu', 12 | url='https://github.com/brews/proxysiphon', 13 | classifiers=[ 14 | 'Development Status :: 4 - Beta', 15 | 16 | 'Intended Audience :: Developers', 17 | 'Intended Audience :: Science/Research', 18 | 'Topic :: Scientific/Engineering', 19 | 20 | 'License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)', 21 | 22 | 'Programming Language :: Python :: 3', 23 | ], 24 | keywords='marine paleoclimate', 25 | 26 | packages=find_packages(exclude=['docs']), 27 | 28 | install_requires=['numpy', 'scipy', 'pandas', 'chardet', 'carbonferret', 29 | 'erebusfall', 'netCDF4', 'unidecode', 'xarray', 'tables', 30 | 'shapely'], 31 | extras_require={ 32 | 'plots': ['matplotlib>=3.0.0', 'cartopy'], 33 | 'agemodel': ['snakebacon'] 34 | }, 35 | tests_require=['pytest'], 36 | package_data={'proxysiphon': ['tests/*.txt', 'lmr_hdf5/*.nc']}, 37 | ) 38 | -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- 1 | language: python 2 | dist: bionic 3 | notifications: 4 | email: false 5 | matrix: 6 | fast_finish: true 7 | include: 8 | - python: 3.7 9 | env: 10 | - CONDA_ENV=py37 11 | - JOB_OS=Linux 12 | - os: osx 13 | language: generic 14 | env: 15 | - CONDA_ENV=py37 16 | - JOB_OS=MacOSX 17 | before_install: 18 | - if [[ "$TRAVIS_PYTHON_VERSION" == "2.7" ]]; then wget https://repo.continuum.io/miniconda/Miniconda2-latest-$JOB_OS-x86_64.sh 19 | -O miniconda.sh; else wget https://repo.continuum.io/miniconda/Miniconda3-latest-$JOB_OS-x86_64.sh 20 | -O miniconda.sh; fi 21 | - bash miniconda.sh -b -p $HOME/miniconda 22 | - export PATH="$HOME/miniconda/bin:$PATH" 23 | - hash -r 24 | - conda config --set always_yes yes --set changeps1 no 25 | - conda update -q conda 26 | - conda info -a 27 | install: 28 | - conda env create -q -f ci/requirements-$CONDA_ENV.yml 29 | - source activate test_env 30 | - pip install . 31 | script: 32 | - pytest --pyargs proxysiphon 33 | deploy: 34 | provider: pypi 35 | distributions: sdist bdist_wheel 36 | on: 37 | tags: true 38 | user: __token__ 39 | password: 40 | secure: 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 41 | skip_existing: true 42 | -------------------------------------------------------------------------------- /NEWS.md: -------------------------------------------------------------------------------- 1 | # proxysiphon v0.0.1b1 2 | 3 | * Fix bad C14 dates and errors in chronology section of output proxy netCDF files (Issue #12). 4 | 5 | 6 | # proxysiphon v0.0.1a5 7 | 8 | * `nc2lmrh5()` and `nc2lmrdf()` should now trim based on depth cutoffs of `LgmRecord` objects. These are optional floats at `self.chronology_information.cut_shallow` and `self.chronology_information.cut_deep`. 9 | 10 | 11 | # proxysiphon v0.0.1a4 12 | 13 | * Add `LgmRecord.chronology_depth_range()` to get the depth range of chronology determinants (Issue #11). 14 | * `LgmRecord.slice_datadepths()` now slices `data.age_ensemble` and `data.age_median` in addition to the general dataframe. 15 | * `LgmRecord.to_netcdf()` will now add attributes to the chronology section of the output netCDF file if the LgmRecord object `chronology_information` has `cut_shallow` or `cut_deep` attributes. 16 | * `LgmRecord.plot_agedepth()` now automatically plots `self.chronology_information.cut_shallow` and `self.chronology_information.cut_deep` attributes as vertical lines, if the cutoff attributes are available. 17 | 18 | 19 | # proxysiphon v0.0.1a3 20 | 21 | * Add method `RedateMixin.swapin_custom_deltar()` to handle swapping-in new carbon reservoir values into proxy record chronology information. 22 | * `QcPlotMixin.plot_agedepth()` now returns near empty axis if the proxy record has no data to plot. 23 | * Add 'plot_agedepth_kws' arguement to `to_qcpdf()`. 24 | * `plot_agedepth` now accepts passing an optional iterable of depths to 'depthlines'. It then plots vertical lines at those depths. This is used to indicate cut-off points for a proxy record. 25 | 26 | 27 | # proxysiphon v0.0.1a2 28 | 29 | * `cartopy`, and `snakebacon` have been made recommended dependencies. 30 | * New method `records.Publication.to_citationstr()` to get quick and dirty bibliography strings. 31 | * Add `PetmRecord` and `LgmRecord`, specialized subclasses of `NcdcRecord`. These are created with `read_lgm()` and `read_petm()`. 32 | * `LgmRecord` instances now have several methods for age modeling with 14C. 33 | * `LgmRecord` and `PetmRecord` records now have a `.to_netcdf()` method. 34 | * `proxysiphon.qcreport` submodule has be refactored into `LgmRecord` and `PetmRecord` methods. This should make it easier to do quick plots (e.g. with `.plot_agedepth()`) and output more comprehensive PDF quality-control reports with `.to_qcpdf()`. 35 | * Add `nc2lmrh5`, a function to read output proxy NetCDF files and convert them to LMR-style HDF5 proxy files. 36 | 37 | 38 | # proxysiphon v0.0.1a1 39 | 40 | * Refactoring to use Python 3.7 `dataclasses` to simplify code. 41 | * New `Guts.yank_variables()` and `NcdcRecord.Variables` classes for the "Variables" file section. 42 | * `NcdcRecord.original_source_url` is now an optional string with a default value of None. 43 | * `DataCollection` `first_year` & `last_year` are now floats and not int. 44 | * More flexible record creation with keywords. 45 | * `NcdcRecord` `description` and `original_source_url` attributes refactored to simple string. 46 | * Removed `contribution_date` attribute from `NcdcRecord`. This was unused in our analysis. 47 | * `proxysiphon.agemodel.fit_agedepthmodel` now also returns snakebacon agemodel kwargs. 48 | * Grab new field from proxy text files ("Description" and "Original_Source_URL"). 49 | * Now pull more fields from "Publication" section, including support for multiple publicatioins. 50 | * `Guts.pull_section()` now returns list of lists to deal with sections that appear multiple times (i.e. "Publication"). 51 | * Fix missing dependency in setup.py. 52 | 53 | 54 | # proxysiphon v0.0.1a0 55 | 56 | * Initial release. -------------------------------------------------------------------------------- /proxysiphon/records.py: -------------------------------------------------------------------------------- 1 | from dataclasses import dataclass, field 2 | from chardet import detect as chdetect 3 | from pandas import DataFrame 4 | from proxysiphon.proxychimp import Guts 5 | import proxysiphon.lgm as lgm 6 | 7 | 8 | def read_ncdc(filepath_or_buffer, encoding=None): 9 | """Read NOAA NCDC txt file 10 | 11 | Parameters 12 | ---------- 13 | filepath_or_buffer 14 | encoding : str or None, optional 15 | File encoding. Default is None which attempts to guess the encoding with 16 | `chardet.detect`. 17 | 18 | Returns 19 | ------- 20 | out : NcdcRecord 21 | """ 22 | with open(filepath_or_buffer, 'rb') as fl: 23 | flbytes = fl.read() 24 | if encoding is None: 25 | encoding = chdetect(flbytes)['encoding'] 26 | g = Guts(flbytes.decode(encoding)) 27 | return g.to_ncdcrecord() 28 | 29 | 30 | def read_lgm(filepath_or_buffer, encoding=None): 31 | """Read NOAA NCDC txt file for LGM proxies 32 | 33 | Parameters 34 | ---------- 35 | filepath_or_buffer 36 | encoding : str or None, optional 37 | File encoding. Default is None which attempts to guess the encoding with 38 | `chardet.detect`. 39 | 40 | Returns 41 | ------- 42 | out : NcdcRecord 43 | """ 44 | out = read_ncdc(filepath_or_buffer, encoding=encoding) 45 | return LgmRecord(**out.__dict__) 46 | 47 | 48 | def read_petm(filepath_or_buffer, encoding=None): 49 | """Read NOAA NCDC txt file for PETM proxies 50 | 51 | Parameters 52 | ---------- 53 | filepath_or_buffer 54 | encoding : str or None, optional 55 | File encoding. Default is None which attempts to guess the encoding with 56 | `chardet.detect`. 57 | 58 | Returns 59 | ------- 60 | out : NcdcRecord 61 | """ 62 | out = read_ncdc(filepath_or_buffer, encoding=encoding) 63 | return PetmRecord(**out.__dict__) 64 | 65 | 66 | @dataclass 67 | class SiteInformation: 68 | """Proxy site information""" 69 | site_name: str = None 70 | location: str = None 71 | country: str = None 72 | northernmost_latitude: float = None 73 | southernmost_latitude: float = None 74 | easternmost_longitude: float = None 75 | westernmost_longitude: float = None 76 | elevation: float = None 77 | 78 | 79 | @dataclass 80 | class DataCollection: 81 | """Proxy site data collection information""" 82 | collection_name: str = None 83 | first_year: float = None 84 | last_year: float = None 85 | time_unit: str = None 86 | core_length: str = None 87 | notes: str = None 88 | collection_year: int = None 89 | 90 | 91 | @dataclass 92 | class VariableInfo: 93 | """Proxy site Data Variable information""" 94 | what: str 95 | material: str 96 | error: str 97 | units: str 98 | seasonality: str 99 | archive: str 100 | detail: str 101 | method: str 102 | datatype: str 103 | 104 | 105 | @dataclass 106 | class ChronologyInformation: 107 | """Proxy site chronology information""" 108 | df: DataFrame = field(default_factory=DataFrame) 109 | 110 | 111 | @dataclass 112 | class Data: 113 | """Proxy site data variables""" 114 | df: DataFrame = field(default_factory=DataFrame) 115 | 116 | 117 | @dataclass 118 | class Publication: 119 | """Proxy site publication""" 120 | authors: str = None 121 | published_date_or_year: int = None 122 | published_title: str = None 123 | journal_name: str = None 124 | volume: str = None 125 | edition: str = None 126 | issue: str = None 127 | pages: str = None 128 | report_number: str = None 129 | doi: str = None 130 | online_resource: str = None 131 | full_citation: str = None 132 | abstract: str = None 133 | 134 | def to_citationstr(self): 135 | """Citation str of publication""" 136 | if self.full_citation is not None: 137 | return str(self.full_citation) 138 | 139 | out = '{authors} ({year}): {title}.'.format(authors=self.authors, 140 | year=self.published_date_or_year, 141 | title=self.published_title) 142 | # This is a bit lazy... 143 | if self.journal_name is not None: 144 | out += ' {},'.format(self.journal_name) 145 | if self.edition is not None: 146 | out += ' {},'.format(self.edition) 147 | if self.volume is not None: 148 | out += ' {},'.format(self.volume) 149 | if self.issue is not None: 150 | out += ' {},'.format(self.issue) 151 | if self.pages is not None: 152 | out += ' {},'.format(self.pages) 153 | if self.report_number is not None: 154 | out += ' {},'.format(self.report_number) 155 | if self.doi is not None: 156 | out += ' doi:{}'.format(self.doi) 157 | if self.online_resource is not None: 158 | out += ' {}'.format(self.online_resource) 159 | 160 | return out 161 | 162 | 163 | @dataclass 164 | class NcdcRecord: 165 | """Proxy site NCDC record""" 166 | chronology_information: ChronologyInformation = None 167 | data: Data = None 168 | data_collection: DataCollection = None 169 | description: str = None 170 | original_source_url: str = None 171 | publication: list = field(default_factory=list) 172 | site_information: SiteInformation = None 173 | variables: dict = field(default_factory=dict) 174 | 175 | 176 | class LgmRecord(lgm.QcPlotMixin, lgm.RedateMixin, lgm.NetcdfMixin, NcdcRecord): 177 | """Proxy site LGM NCDC record""" 178 | pass 179 | 180 | 181 | class PetmRecord(LgmRecord): 182 | """PETM proxy site NCDC record""" 183 | pass 184 | -------------------------------------------------------------------------------- /proxysiphon/agemodel.py: -------------------------------------------------------------------------------- 1 | import logging 2 | 3 | import numpy as np 4 | import pandas as pd 5 | import scipy.stats as stats 6 | import carbonferret as cf 7 | 8 | 9 | log = logging.getLogger(__name__) 10 | 11 | 12 | def remove_outliers(df, col_name, iqr_min=10): 13 | """Remove outliers from dataframe copy based on col_name""" 14 | out = df.copy() 15 | iqr = stats.iqr(df.loc[:, col_name]) 16 | if iqr < iqr_min: 17 | return out 18 | upper = np.percentile(df.loc[:, col_name], 75) 19 | lower = np.percentile(df.loc[:, col_name], 25) 20 | out = out[out.loc[:, col_name] < (upper + 1.5 * iqr)] 21 | out = out[out.loc[:, col_name] > (lower - 1.5 * iqr)] 22 | return out 23 | 24 | 25 | def get_deltar_online(latlon, max_distance=3000): 26 | """Use carbonferret to grab an estimate ΔR from internet""" 27 | max_distance = int(max_distance) 28 | nearby = cf.find_near(lat=latlon[0], lon=latlon[1], n=10) 29 | 30 | nearby = nearby[nearby['distance (km)'] <= max_distance] 31 | # nearby = remove_outliers(nearby, 'DeltaR') 32 | # nearby = remove_outliers(nearby, 'DeltaRErr') 33 | log.debug('ΔR and ΔRσ from {} samples'.format(len(nearby))) 34 | 35 | w = 1/len(nearby) 36 | deltar_mean = nearby['DeltaR'].mean() 37 | # Use pooled or combined variance of carbonferret deltaR distributions. 38 | var = (w * ((nearby['DeltaR'] - deltar_mean)**2 + nearby['DeltaRErr']**2)).sum() 39 | sigma = np.sqrt(var) 40 | return tuple([deltar_mean, sigma]) 41 | 42 | 43 | def fit_agedepthmodel(chron, pdata, deltar=None, deltar_error=None, minyr=None, mcmc_kws=None): 44 | log.debug('Fitting new age model.') 45 | 46 | try: 47 | import snakebacon as sb 48 | except ModuleNotFoundError: 49 | raise ModuleNotFoundError('snakebacon needs to be installed for age models') 50 | 51 | if minyr is None: 52 | minyr = -1000 53 | 54 | chron = pd.DataFrame(chron).copy() 55 | pdata = pd.DataFrame(pdata).copy() 56 | 57 | chron['depth'] = chron.loc[:, ('depth_top', 'depth_bottom')].mean(axis=1) 58 | chron['labid'] = chron.Labcode 59 | chron['age'] = chron.loc[:, '14C_date'] 60 | chron['error'] = chron.loc[:, '14C_1s_err'] 61 | 62 | chron['cc'] = 2 # This is marine calibration curve, use for all depths. 63 | 64 | chron.sort_values('depth', inplace=True) 65 | 66 | # Cleanup dataframe so works with snakebacon. 67 | if deltar is not None: 68 | chron['delta_R'] = deltar 69 | if deltar_error is not None: 70 | chron['delta_R_1s_err'] = deltar_error 71 | 72 | if chron.other_date.notnull().any(): 73 | # Check that can't have 14C_date and other_date at same depth. Same for 1s_error. 74 | assert ~chron.loc[:, ['14C_date', 'other_date']].notnull().all(axis=1).any() 75 | assert ~chron.loc[:, ['14C_1s_err', 'other_1s_err']].notnull().all(axis=1).any() 76 | other_msk = ~chron['14C_date'].notnull() 77 | # `other_dates` should not have delta_R values 78 | chron.loc[other_msk, 'delta_R'] = 0 79 | chron.loc[other_msk, 'delta_R_1s_err'] = 0 80 | # Move `other_dates` and `errors` to chron.age and chron.error. 81 | chron.loc[other_msk, 'age'] = chron.loc[other_msk, 'other_date'] 82 | chron.loc[other_msk, 'error'] = chron.loc[other_msk, 'other_1s_err'] 83 | chron.loc[other_msk, 'cc'] = 0 # Using constant calibration curve for non-14C dates 84 | # Drop rows with `other_date` but no `other_1s_error`. 85 | chron.drop(chron[other_msk & chron['other_date'].notnull() & ~chron['other_1s_err'].notnull()].index, 86 | inplace=True) 87 | 88 | # Have any NaNs in age, depth or error? 89 | assert chron.loc[:, ['age', 'depth', 'error']].notnull().all().all() 90 | 91 | coredates = sb.ChronRecord(chron) 92 | 93 | d_min = np.min([x.min() for x in [chron.depth, pdata.depth]]) 94 | d_max = np.max([x.max() for x in [chron.depth, pdata.depth]]) 95 | sug_acc_mean = sb.suggest_accumulation_rate(coredates) 96 | # n_segs = np.ceil((d_max - d_min) / 5) # Num segments in mcmc, ~ 5cm, rounded up. 97 | 98 | # TODO(brews): Check whether need sqrt error here. 99 | guesses = np.random.randn(2) * coredates.error[:2] + coredates.age[:2] 100 | guesses[guesses < minyr] = minyr # Line #70 of Bacon.R warns that otherwise twalk MCMC will not run. 101 | 102 | # if n_segs > 200 or n_segs < 5: 103 | # n_segs = np.ceil((d_max - d_min) / 10) 104 | # assert (n_segs < 500) and (n_segs > 5) # Sanity check for extremely long or short MCMC runs. 105 | 106 | mcmc_params = dict(depth_min=d_min, depth_max=d_max, 107 | cc=chron.cc.values, 108 | d_r=chron.delta_R.values, 109 | d_std=chron.delta_R_1s_err.values, 110 | t_a=[3], t_b=[4], k=50, # n_segs, 111 | minyr=minyr, maxyr=50000, 112 | th01=guesses[0], th02=guesses[1], 113 | acc_mean=sug_acc_mean, acc_shape=1.5, 114 | mem_strength=4, mem_mean=0.7) 115 | 116 | if mcmc_kws is not None: 117 | mcmc_params.update(mcmc_kws) 118 | 119 | log.debug('MCMC parameters: {}'.format(mcmc_params)) 120 | 121 | agemodel = sb.AgeDepthModel(coredates, mcmc_kws=mcmc_params) 122 | log.debug('Age model fit done') 123 | return agemodel, coredates, mcmc_params 124 | 125 | 126 | def date_proxy(admodel, pdata, nsims): 127 | try: 128 | import snakebacon as sb 129 | except ModuleNotFoundError: 130 | raise ModuleNotFoundError('snakebacon needs to be installed for age models') 131 | 132 | pdata = pd.DataFrame(pdata).copy() 133 | if 'age' in pdata.columns: 134 | # Rename to avoid error with sb.ProxyRecord 135 | log.debug('Renaming age column in proxy data') 136 | cols = list(pdata.columns.values) 137 | cols[cols.index('age')] = 'original_age' 138 | pdata.columns = cols 139 | 140 | orig_pdata = sb.ProxyRecord(pdata) 141 | pdata_median = admodel.date(orig_pdata, 'median').to_pandas() 142 | pdata_ensemble = admodel.date(orig_pdata, 'ensemble', nsims).to_pandas() 143 | pdata_median['age'] = pdata_median['age'].round() 144 | pdata_ensemble['age'] = pdata_ensemble['age'].round() 145 | return pdata_median, pdata_ensemble 146 | -------------------------------------------------------------------------------- /proxysiphon/tests/test_proxychimp.py: -------------------------------------------------------------------------------- 1 | from tempfile import NamedTemporaryFile 2 | import pytest 3 | import pandas as pd 4 | 5 | from proxysiphon import proxychimp 6 | 7 | 8 | datapayload = ['#------------------------', 9 | '# Contribution_Date', 10 | '#', 11 | '#------------------------', 12 | '# Title', 13 | '#', 14 | '#------------------------', 15 | '# Chronology_Information', 16 | '#', 17 | '# Labcode\tdepth_top\tdepth_bottom\tmat_dated\t14C_date\t14C_1s_err\tdelta_R\tdelta_R_1s_err\tother_date\tother_1s_err\tother_type\t', 18 | '# 152757 5 6 G. ruber or mixed planktonic 475 30 188 73 -999 -999 -999 ', 19 | '#', 20 | '#------------------------', 21 | '# Data', 22 | '# Data lines follow (have no #)', 23 | '# Missing Value: -999', 24 | 'depth\tage\tbacon', 25 | '1\t2\t3', 26 | '4\t5\t6'] 27 | 28 | 29 | @pytest.fixture(scope='module') 30 | def chron_nodeltaR_nodata_guts(): 31 | payload = ['#------------------------', 32 | '# Contribution_Date', 33 | '#', 34 | '#------------------------', 35 | '# Title', 36 | '#', 37 | '#------------------------', 38 | '# Chronology_Information', 39 | '#', 40 | '# Labcode\tdepth_top\tdepth_bottom\tmat_dated\t14C_date\t14C_1s_err\tdelta_R\tdelta_R_1s_err\tother_date\tother_1s_err\tother_type\t', 41 | '# 152757 5 6 G. ruber or mixed planktonic -999 -999 -999 -999 -999 -999 -999 ', 42 | '#', 43 | '#------------------------', 44 | '# Data', 45 | '# Data lines follow (have no #)', 46 | '# Missing Value: -999', 47 | 'depth\tage\tbacon'] 48 | with NamedTemporaryFile('wb') as tf: 49 | tf.write('\n'.join(payload).encode('utf-8')) 50 | tf.flush() 51 | g = proxychimp.Guts(tf.name) 52 | return g 53 | 54 | 55 | @pytest.fixture(scope='module') 56 | def chron_guts(): 57 | payload = datapayload 58 | with NamedTemporaryFile('wb') as tf: 59 | tf.write('\n'.join(payload).encode('utf-8')) 60 | tf.flush() 61 | g = proxychimp.Guts(tf.name) 62 | return g 63 | 64 | 65 | @pytest.fixture(scope='module') 66 | def dumb_guts(): 67 | payload = ['#------------------------', 68 | '# NOTE: Please cite original publication, online resource and date accessed when using this data.', 69 | '# If there is no publication information, please cite Investigator,', '#', 70 | '# Description/Documentation lines begin with #', '# Data lines have no #', '#', 71 | '# Online_Resource: http://www.ncdc.noaa.gov/paleo/study/', 72 | '# Online_Resource: http://www1.ncdc.noaa.gov/pub/data/paleo/', '#', 73 | '# Original_Source_URL: https://www.ncdc.noaa.gov/paleo-search/study/2622', 74 | '#------------------------', 75 | '# Contribution_Date', 76 | '#', 77 | '#------------------------', 78 | '# Title', 79 | '#', 80 | '#------------------------', 81 | '# Data_Collection', '# Collection_Name: P178-15P', 82 | '# First_Year: 39485', '# Last_Year: -18', 83 | '# Time_Unit: cal yr BP', '# Core_Length: ', 84 | '# Notes: mg_red', '# Collection_Year: 1923', 85 | '#------------------------', 86 | '# Site Information', '# Site_Name: P178-15P', 87 | '# Location: Arabian Sea', '# Country: ', 88 | '# Northernmost_Latitude: 11.955', '# Southernmost_Latitude: 11.955', 89 | '# Easternmost_Longitude: 44.3', '# Westernmost_Longitude: 44.3', 90 | '# Elevation: -869', 91 | '#------------------------', 92 | '# Description and Notes', 93 | '# Description: d18O sacc from 2003 paper, mg/ca sacc from 2002 paper, alkeno', 94 | '#------------------------', 95 | '# Publication', 96 | '# Authors: Tierney, Jessica E.; Pausata, Francesco S. R.; deMenocal, Peter B.', 97 | '# Published_Date_or_Year: 2016', 98 | '# Published_Title: Deglacial Indian monsoon failure and North Atlantic stadials linked by Indian Ocean surface cooling', 99 | '# Journal_Name: Nature Geoscience', '# Volume: 9', 100 | '# Edition: ', '# Issue: ', '# Pages: 46-50', 101 | '# Report Number: ', '# DOI: 10.1038/ngeo2603', 102 | '# Online_Resource: ', '# Full_Citation: ', '# Abstract:', 103 | '#------------------------', 104 | '# Chronology_Information', 105 | '#', 106 | '# Labcode\tdepth_top\tdepth_bottom\tmat_dated\t14C_date\t14C_1s_err\tdelta_R\tdelta_R_1s_err\tother_date\tother_1s_err\tother_type\t', 107 | '#', 108 | '#---------------------------------------', 109 | '# Variables', 110 | '# Data variables follow that are preceded by "##" in columns one and two.', 111 | '# Variables list, one per line, shortname-tab-longname components (9 components: what, material, error, units, seasonality, archive, detail, method, C or N for Character or Numeric data)', 112 | '## depth ,,,cm,,,,,', 113 | '## age ,,,cal yr BP,,,,,', 114 | '## bacon ,,,index,,,,,', 115 | '#------------------------', 116 | '# Data', 117 | '# Data lines follow (have no #)', 118 | '# Missing Value: -999', 119 | 'depth\tage\tbacon', 120 | '1\t2\t3', 121 | '4\t5\t6'] 122 | with NamedTemporaryFile('wb') as tf: 123 | tf.write('\n'.join(payload).encode('utf-8')) 124 | tf.flush() 125 | g = proxychimp.Guts(tf.name) 126 | return g 127 | 128 | 129 | def test_find_values(): 130 | lines = ['apple: 1\n', 'bee: 1:2\n', 'charlie: 1.5\n', 'dingo-2\t\n', 'echo: '] 131 | assert proxychimp.find_values(lines, 'NotAKey') is None 132 | assert proxychimp.find_values(lines, 'apple') == '1' 133 | assert proxychimp.find_values(lines, 'bee') == '1:2' 134 | assert proxychimp.find_values(lines, 'charlie', fun=float) == 1.5 135 | assert proxychimp.find_values(lines, 'bee', sep='-', fun=int) is None 136 | assert proxychimp.find_values(lines, 'dingo', sep='-', fun=int) == 2 137 | assert proxychimp.find_values(lines, 'echo') is None 138 | 139 | 140 | def test_str_guts__init_(): 141 | filestr = '\n'.join(datapayload) 142 | g = proxychimp.Guts(filestr) 143 | goal_dict = {'Labcode': [152757], 'depth_top': [5], 'depth_bottom': [6], 144 | 'mat_dated': ['G. ruber or mixed planktonic'], 145 | '14C_date': [475],'14C_1s_err': [30], 146 | 'delta_R': [188], 'delta_R_1s_err': [73], 147 | 'other_date': [pd.np.nan], 'other_1s_err': [pd.np.nan], 148 | 'other_type': [pd.np.nan]} 149 | goal = pd.DataFrame(goal_dict) 150 | df = g.yank_chron_df() 151 | for k in goal_dict.keys(): 152 | pd.testing.assert_series_equal(goal[k], df[k]) 153 | 154 | 155 | def test__divide_portions(dumb_guts): 156 | goal_data = ['depth\tage\tbacon', '1\t2\t3', '4\t5\t6'] 157 | goal_description_ends = ('#------------------------', '# Missing Value: -999') 158 | goal_beginline = 70 159 | assert goal_data == dumb_guts.data 160 | assert goal_description_ends[0] == dumb_guts.description[0] 161 | assert goal_description_ends[-1] == dumb_guts.description[-1] 162 | assert goal_beginline == dumb_guts.data_beginline 163 | 164 | 165 | def test__write_sectionindex(dumb_guts): 166 | goal_index = {'Chronology_Information': [(55, 59)], 167 | 'Contribution_Date': [(12, 14)], 168 | 'Data': [(67, 70)], 169 | 'Title': [(15, 17)]} 170 | assert 10 == len(dumb_guts.sectionindex.keys()) 171 | for k, goal in goal_index.items(): 172 | assert goal == dumb_guts.sectionindex[k] 173 | 174 | 175 | def test_pull_section(dumb_guts): 176 | goal = ['# Data', '# Data lines follow (have no #)', 177 | '# Missing Value: -999'] 178 | assert dumb_guts.pull_section('Data')[0] == goal 179 | 180 | 181 | def test_pull_section_badname(dumb_guts): 182 | with pytest.raises(KeyError): 183 | dumb_guts.pull_section('data') 184 | 185 | def test_available_sections(dumb_guts): 186 | goal = ['Contribution_Date', 'Title', 'Data_Collection', 187 | 'Site Information', 'Description and Notes', 'Publication', 188 | 'Chronology_Information', 'Variables', 'Data'] 189 | # Skip first section as it is very long: 190 | assert goal == dumb_guts.available_sections()[1:] 191 | 192 | 193 | def test_guess_missingvalues(dumb_guts): 194 | goal = '-999' 195 | assert goal == dumb_guts.guess_missingvalues() 196 | 197 | 198 | def test_yank_data_df(dumb_guts): 199 | goal_dict = {'depth': [1, 4], 'age': [2, 5], 'bacon': [3, 6]} 200 | goal = pd.DataFrame(goal_dict) 201 | df = dumb_guts.yank_data_df() 202 | for k in goal_dict.keys(): 203 | pd.testing.assert_series_equal(goal[k], df[k]) 204 | 205 | 206 | def test_yank_chron_df(chron_guts): 207 | goal_dict = {'Labcode': [152757], 'depth_top': [5], 'depth_bottom': [6], 208 | 'mat_dated': ['G. ruber or mixed planktonic'], 209 | '14C_date': [475],'14C_1s_err': [30], 210 | 'delta_R': [188], 'delta_R_1s_err': [73], 211 | 'other_date': [pd.np.nan], 'other_1s_err': [pd.np.nan], 212 | 'other_type': [pd.np.nan]} 213 | goal = pd.DataFrame(goal_dict) 214 | df = chron_guts.yank_chron_df() 215 | for k in goal_dict.keys(): 216 | pd.testing.assert_series_equal(goal[k], df[k]) 217 | 218 | 219 | def test_yank_publication(dumb_guts): 220 | v1 = dumb_guts.yank_publication()[0] 221 | assert 'Tierney, Jessica E.; Pausata, Francesco S. R.; deMenocal, Peter B.' == v1['authors'] 222 | assert '10.1038/ngeo2603' == v1['doi'] 223 | 224 | 225 | def test_yank_site_infromation(dumb_guts): 226 | v = dumb_guts.yank_site_information() 227 | assert 'P178-15P' == v['site_name'] 228 | assert 'Arabian Sea' == v['location'] 229 | assert v['country'] is None 230 | assert 11.955 == v['northernmost_latitude'] 231 | assert 11.955 == v['southernmost_latitude'] 232 | assert 44.3 == v['easternmost_longitude'] 233 | assert 44.3 == v['westernmost_longitude'] 234 | assert -869 == v['elevation'] 235 | 236 | 237 | def test_yank_data_collection(dumb_guts): 238 | v = dumb_guts.yank_data_collection() 239 | assert 'P178-15P' == v['collection_name'] 240 | assert 39485 == v['first_year'] 241 | assert -18 == v['last_year'] 242 | assert 'cal yr BP' == v['time_unit'] 243 | assert v['core_length'] is None 244 | assert 'mg_red' == v['notes'] 245 | assert 1923 == v['collection_year'] 246 | 247 | 248 | def test_pull_variables(dumb_guts): 249 | v = dumb_guts.yank_variables() 250 | assert 'cm' == v['depth'][3] 251 | 252 | 253 | def test_yank_description_and_notes(dumb_guts): 254 | v = dumb_guts.yank_description_and_notes() 255 | assert 'd18O sacc from 2003 paper, mg/ca sacc from 2002 paper, alkeno' == v 256 | 257 | 258 | def test_yank_original_source_url(dumb_guts): 259 | v = dumb_guts.yank_original_source_url() 260 | assert 'https://www.ncdc.noaa.gov/paleo-search/study/2622' == v 261 | 262 | 263 | def test_has_chron(dumb_guts, chron_guts): 264 | assert dumb_guts.has_chron() is False 265 | assert chron_guts.has_chron() is True 266 | 267 | 268 | def test_has_deltar(dumb_guts, chron_guts, chron_nodeltaR_nodata_guts): 269 | assert chron_nodeltaR_nodata_guts.has_deltar() is False 270 | assert dumb_guts.has_deltar() is False 271 | assert chron_guts.has_deltar() is True 272 | 273 | 274 | def test_has_datacolumn(dumb_guts, chron_nodeltaR_nodata_guts): 275 | assert chron_nodeltaR_nodata_guts.has_datacolumn('boogers') is False 276 | assert dumb_guts.has_datacolumn('depth') is True 277 | -------------------------------------------------------------------------------- /proxysiphon/proxychimp.py: -------------------------------------------------------------------------------- 1 | import logging 2 | import collections 3 | import datetime 4 | from io import BytesIO 5 | 6 | import pandas as pd 7 | from chardet import detect as chdetect 8 | import proxysiphon.records as records 9 | 10 | 11 | DIVIDER = '#------------------------' 12 | DATALINE_TRIGGER = '# Data lines follow (have no #)' 13 | HEADINGS = ['Contribution_Date', 'Title', 'Investigators', 14 | 'NOTE: Please cite original publication, online resource and date accessed when using this data.', 15 | 'Description and Notes', 'Publication', 'Funding_Agency', 16 | 'Site Information', 'Data_Collection', 'Species', 17 | 'Chronology_Information', 'Variables', 'Data'] 18 | CHRON_HEADER = '# Labcode\tdepth_top\tdepth_bottom\tmat_dated\t14C_date\t14C_1s_err\tdelta_R\tdelta_R_1s_err\tother_date\tother_1s_err\tother_type\t' 19 | MISSINGVALUE_LABEL = '# Missing Value: ' 20 | 21 | 22 | log = logging.getLogger(__name__) 23 | 24 | 25 | def grab_latlon(g): 26 | """Grab latitude from proxychimp.Guts""" 27 | victim = g.pull_section('Site Information')[0] 28 | fields = dict(Northernmost_Latitude=None, 29 | Southernmost_Latitude=None, 30 | Easternmost_Longitude=None, 31 | Westernmost_Longitude=None) 32 | for ln in victim: 33 | if any([x in ln for x in fields.keys()]): 34 | ln_split = ln.split(':') 35 | v = float(ln_split[-1]) 36 | k = ln_split[0][1:].lstrip().rstrip() 37 | assert k in fields.keys() 38 | fields[k] = v 39 | return fields['Northernmost_Latitude'], fields['Westernmost_Longitude'] 40 | 41 | 42 | def grab_elevation(g): 43 | """Grab site elevation from proxychimp.Guts""" 44 | victim = g.pull_section('Site Information')[0] 45 | elevation = None 46 | for ln in victim: 47 | if 'Elevation:' in ln: 48 | ln_split = ln.split(':') 49 | elevation = float(ln_split[-1]) 50 | return elevation 51 | 52 | 53 | def grab_collection_year(g): 54 | """Get collection year from Data_Collection section of proxychimp.Guts""" 55 | victim = g.pull_section('Data_Collection')[0] 56 | yr = None 57 | for ln in victim: 58 | if 'Collection_Year' in ln: 59 | ln_split = ln.split(':') 60 | yr = int(ln_split[-1]) 61 | return yr 62 | 63 | 64 | def grab_publication_year(g): 65 | """Get publication year from proxychimp.Guts""" 66 | victim = g.pull_section('Publication') 67 | yr = [] 68 | for p in victim: 69 | for ln in p: 70 | if 'Published_Date_or_Year' in ln: 71 | ln_split = ln.split(':') 72 | yr.append(int(ln_split[-1])) 73 | return yr 74 | 75 | 76 | def grab_contribution_date(g): 77 | """Get contribution date from proxychimp.Guts""" 78 | victim = g.pull_section('Contribution_Date')[0] 79 | d = None 80 | for ln in victim: 81 | if 'Date' in ln: 82 | ln_split = ln.split(':') 83 | d_str = ln_split[-1].split('-') 84 | assert len(d_str) == 3 85 | d = datetime.date(int(d_str[0]), int(d_str[1]), int(d_str[2])) 86 | return d 87 | 88 | 89 | def find_values(x, k, sep=':', fun=None): 90 | """Find values in a list of strings containing [k][sep][values] 91 | 92 | Parameters 93 | ---------- 94 | x : iterable 95 | Iterable of strings representing lines in a file. 96 | k : str 97 | A key or pattern that to search x for. 98 | sep : str 99 | A separator that divides the `k` pattern from the target value. 100 | fun : function-like, optional 101 | Function used to format target value before returning. 102 | 103 | Returns 104 | ------- 105 | The target value is returned after removing excess whitespace from left 106 | and right of the value. If the key or target pattern is not found, 107 | then None is returned. If an empty string, or whitespace is the found 108 | value, then None is returned. 109 | """ 110 | out = None 111 | for l in x: 112 | if k in l and sep in l: 113 | val = l.split(sep, maxsplit=1)[1:][0].lstrip().rstrip() 114 | if val != '': 115 | out = val 116 | if fun is not None and out is not None: 117 | out = fun(out) 118 | return out 119 | 120 | 121 | class Guts: 122 | """Ghetto and error-tolerant way to parse sections of NCDC proxy text files 123 | """ 124 | 125 | def __init__(self, str_or_path): 126 | self._section_headings = ['# ' + s for s in HEADINGS] 127 | 128 | self.path = None 129 | self.encodingguess = None 130 | self.filestr = None 131 | try: 132 | with open(str_or_path, 'rb') as fl: 133 | flbytes = fl.read() 134 | self.path = str(str_or_path) 135 | self.encodingguess = chdetect(flbytes) 136 | # TODO(brews): Not sure we need ~both~ filestr, and lines + self.data + self.description. 137 | self.filestr = flbytes.decode(self.encodingguess['encoding']) 138 | except (FileNotFoundError, OSError): 139 | self.filestr = str(str_or_path) 140 | lines = self.filestr.splitlines() 141 | 142 | self.data = [] 143 | self.description = [] 144 | self.data_beginline = None 145 | self._divide_portions(lines) 146 | 147 | self.sectionindex = None 148 | self._write_sectionindex() 149 | 150 | def _divide_portions(self, lines): 151 | """Divide guts into 'description' and 'data' sections 152 | """ 153 | prev_description = True 154 | dataline_flag = False 155 | for n, ln in enumerate(lines): 156 | if ln[0] == '#' or dataline_flag is False: 157 | self.description.append(ln) 158 | if DATALINE_TRIGGER in ln: 159 | dataline_flag = True 160 | log.debug('Found dataline flag on line {0}'.format(n)) 161 | elif dataline_flag: 162 | self.data.append(ln) 163 | if prev_description is True: 164 | self.data_beginline = n 165 | log.debug('Data portion begins on line {0}'.format(n)) 166 | prev_description = False 167 | 168 | def _write_sectionindex(self): 169 | """Populate the section index""" 170 | all_keys = [] 171 | all_start = [] 172 | all_stop = [] 173 | prev_divider = False 174 | 175 | for idx, ln in enumerate(self.description): # Lines after 6-line title. 176 | if prev_divider is True and any([h == ln.rstrip() for h in self._section_headings]): 177 | key = ln[1:].rstrip().lstrip() 178 | 179 | # If already have start idx for other section, append end idx 180 | # for that section 181 | if len(all_start) > 0: 182 | all_stop.append(idx - 1) 183 | 184 | all_keys.append(key) 185 | all_start.append(idx) 186 | prev_divider = False 187 | if DIVIDER in ln: 188 | prev_divider = True 189 | all_stop.append(self.data_beginline) 190 | 191 | section_map = collections.defaultdict(list) 192 | for (k, start, stop) in zip(all_keys, all_start, all_stop): 193 | section_map[k].append((start, stop)) 194 | section_map.default_factory = None 195 | self.sectionindex = section_map 196 | 197 | def pull_section(self, section): 198 | """Grab a list of list of line strings from the file description for each 'section'""" 199 | try: 200 | out = [self.description[slice(*idx)] for idx in self.sectionindex[section]] 201 | except KeyError: 202 | raise KeyError('section key "{}" not found'.format(section)) 203 | return out 204 | 205 | def available_sections(self): 206 | """Get a list of available sections in the file""" 207 | return list(self.sectionindex.keys()) 208 | 209 | def yank_data_df(self): 210 | """Get 'data' information as dataframe""" 211 | lines = [x.rstrip() for x in self.data] 212 | data_bytes = '\n'.join(lines).encode('utf-8') 213 | missingvalues = self.guess_missingvalues() 214 | df = pd.read_csv(BytesIO(data_bytes), sep='\t', na_values=missingvalues) 215 | return df 216 | 217 | def yank_chron_df(self, section_name='Chronology_Information', missingvalues=None): 218 | """Get chronology information as pandas.DataFrame""" 219 | if missingvalues is None: 220 | missingvalues = [-999, 'NaN'] 221 | section = self.pull_section(section_name)[0] 222 | start_idx = section.index(CHRON_HEADER) 223 | g_chrond = section[start_idx:] 224 | g_chrond_cleaned = [x[2:].rstrip() for x in g_chrond] # Removes the '# ' and ending white space. 225 | data_bytes = '\n'.join(g_chrond_cleaned).encode('utf-8') 226 | df = pd.read_csv(BytesIO(data_bytes), sep='\t', na_values=missingvalues) 227 | return df 228 | 229 | def guess_missingvalues(self): 230 | """Guess data section missing values""" 231 | section = self.pull_section('Data')[0] 232 | out = None 233 | for ln in section: 234 | if MISSINGVALUE_LABEL in ln: 235 | out = ln.split(MISSINGVALUE_LABEL)[1] 236 | log.debug('Guessed missing value(s): {}'.format(out)) 237 | return out 238 | 239 | def has_data(self): 240 | """Check if has populated data information""" 241 | try: 242 | d = self.yank_data_df() 243 | except KeyError: 244 | return False 245 | if len(d) > 0: 246 | result = True 247 | else: 248 | result = False 249 | return result 250 | 251 | def has_chron(self): 252 | """Check if has populated chronology information""" 253 | try: 254 | chron = self.yank_chron_df() 255 | except KeyError: 256 | return False 257 | if len(chron) > 0: 258 | result = True 259 | else: 260 | result = False 261 | return result 262 | 263 | def has_deltar(self): 264 | """Check if has populated delta R chronology information""" 265 | try: 266 | chron = self.yank_chron_df() 267 | except KeyError: 268 | return False 269 | if any(chron.delta_R.notnull()): 270 | result = True 271 | else: 272 | result = False 273 | return result 274 | 275 | def has_deltar_error(self): 276 | """Check if has populated delta R error chronology information""" 277 | try: 278 | chron = self.yank_chron_df() 279 | except KeyError: 280 | return False 281 | if any(chron.delta_R_1s_err.notnull()): 282 | result = True 283 | else: 284 | result = False 285 | return result 286 | 287 | def has_datacolumn(self, name): 288 | """Check if name is in data section columns""" 289 | try: 290 | data = self.yank_data_df() 291 | except KeyError: 292 | return False 293 | if name in data.columns: 294 | result = True 295 | else: 296 | result = False 297 | return result 298 | 299 | def yank_original_source_url(self): 300 | """Get string of original source URL 301 | 302 | Returns 303 | ------- 304 | out : str or None 305 | 306 | Raises 307 | ------ 308 | AssertionError 309 | If more than one section is found in the file data. 310 | """ 311 | target_section = 'NOTE: Please cite original publication, online ' \ 312 | 'resource and date accessed when using this data.' 313 | target_key = 'Original_Source_URL:' 314 | 315 | sections = self.pull_section(target_section) 316 | assert len(sections) < 2, 'More than one section found' 317 | section = sections[0] 318 | 319 | try: 320 | out = find_values(section, target_key, fun=str) 321 | except AttributeError: 322 | # target key not found in string 323 | out = None 324 | 325 | return out 326 | 327 | def yank_data_collection(self): 328 | """Get data collection information 329 | 330 | Returns 331 | ------- 332 | out : dict or None 333 | 334 | Raises 335 | ------ 336 | AssertionError 337 | If more than one section is found in the file data. 338 | """ 339 | target_section = 'Data_Collection' 340 | # List of tuples, tuples give (dict_key, source_key, type_fun) 341 | target_keys = [('collection_name', 'Collection_Name:', str), 342 | ('first_year', 'First_Year:', float), 343 | ('last_year', 'Last_Year:', float), 344 | ('time_unit', 'Time_Unit:', str), 345 | ('core_length', 'Core_Length:', str), 346 | ('notes', 'Notes:', str), 347 | ('collection_year', 'Collection_Year:', int)] 348 | out = {k[0]: None for k in target_keys} 349 | 350 | sections = self.pull_section(target_section) 351 | assert len(sections) < 2, 'More than one section found' 352 | section = sections[0] 353 | 354 | for dict_key, source_key, type_fun in target_keys: 355 | out[dict_key] = find_values(section, source_key, fun=type_fun) 356 | 357 | return out 358 | 359 | def yank_description_and_notes(self): 360 | """Get string of description and notes 361 | 362 | Returns 363 | ------- 364 | out : str or None 365 | 366 | Raises 367 | ------ 368 | AssertionError 369 | If more than one section is found in the file data. 370 | """ 371 | target_section = 'Description and Notes' 372 | target_key = 'Description:' 373 | 374 | sections = self.pull_section(target_section) 375 | assert len(sections) < 2, 'More than one section found' 376 | section = sections[0] 377 | 378 | try: 379 | out = find_values(section, target_key, fun=str) 380 | except AttributeError: 381 | # target key not found in string 382 | out = None 383 | 384 | return out 385 | 386 | def yank_publication(self): 387 | """Get list of publication information 388 | 389 | Returns 390 | ------- 391 | out : list[dict] 392 | """ 393 | target_section = 'Publication' 394 | # List of tuples, tuples give (dict_key, source_key, type_fun) 395 | target_keys = [('authors', '# Authors:', str), 396 | ('published_date_or_year', '# Published_Date_or_Year:', int), 397 | ('published_title', '# Published_Title:', str), 398 | ('journal_name', '# Journal_Name:', str), 399 | ('volume', '# Volume:', str), 400 | ('edition', '# Edition:', str), 401 | ('issue', '# Issue:', str), 402 | ('pages', '# Pages:', str), 403 | ('report_number', '# Report Number:', str), 404 | ('doi', '# DOI:', str), 405 | ('online_resource', '# Online_Resource:', str), 406 | ('full_citation', '# Full_Citation:', str), 407 | ('abstract', '# Abstract:', str)] 408 | dict_template = {k[0]: None for k in target_keys} 409 | 410 | out = [] 411 | sections = self.pull_section(target_section) 412 | 413 | for section in sections: 414 | 415 | this_pub = dict_template.copy() 416 | for dict_key, source_key, type_fun in target_keys: 417 | this_pub[dict_key] = find_values(section, source_key, fun=type_fun) 418 | out.append(this_pub) 419 | 420 | return out 421 | 422 | def yank_variables(self): 423 | """Get variable section information 424 | 425 | Returns 426 | ------- 427 | out : dict 428 | 429 | Raises 430 | ------ 431 | AssertionError 432 | If more than one section is found in the file data. 433 | """ 434 | target_section = 'Variables' 435 | sections = self.pull_section(target_section) 436 | assert len(sections) < 2, 'More than one section found' 437 | section = sections[0] 438 | 439 | out = {} 440 | for ln in section: 441 | 442 | # Skip line if not data variables line. 443 | if ln[:3] != '## ': 444 | continue 445 | 446 | var_name, components_group = ln[3:].split('\t') 447 | out[var_name] = tuple(components_group.split(',')) 448 | 449 | return out 450 | 451 | def yank_site_information(self): 452 | """Get site information 453 | 454 | Returns 455 | ------- 456 | out : dict 457 | 458 | Raises 459 | ------ 460 | AssertionError 461 | If more than one section is found in the file data. 462 | """ 463 | target_section = 'Site Information' 464 | # List of tuples, tuples give (dict_key, source_key, type_fun) 465 | target_keys = [('site_name', '# Site_Name:', str), 466 | ('location', '# Location:', str), 467 | ('country', '# Country:', str), 468 | ('northernmost_latitude', '# Northernmost_Latitude:', float), 469 | ('southernmost_latitude', '# Southernmost_Latitude:', float), 470 | ('easternmost_longitude', '# Easternmost_Longitude:', float), 471 | ('westernmost_longitude', '# Westernmost_Longitude:', float), 472 | ('elevation', '# Elevation:', float)] 473 | out = {k[0]: None for k in target_keys} 474 | 475 | sections = self.pull_section(target_section) 476 | assert len(sections) < 2, 'More than one section found' 477 | section = sections[0] 478 | 479 | for dict_key, source_key, type_fun in target_keys: 480 | out[dict_key] = find_values(section, source_key, fun=type_fun) 481 | 482 | return out 483 | 484 | def to_ncdcrecord(self): 485 | """to NcdcRecord instance""" 486 | chron = records.ChronologyInformation(df=self.yank_chron_df()) 487 | d = records.Data(df=self.yank_data_df()) 488 | d_collection = records.DataCollection(**self.yank_data_collection()) 489 | description = self.yank_description_and_notes() 490 | orig_url = self.yank_original_source_url() 491 | pubs = [records.Publication(**p) for p in self.yank_publication()] 492 | site_info = records.SiteInformation(**self.yank_site_information()) 493 | 494 | varis = {} 495 | file_vars = self.yank_variables() 496 | for k, v in file_vars.items(): 497 | varis[k] = records.VariableInfo(*v) 498 | 499 | out = records.NcdcRecord(chronology_information=chron, 500 | data=d, 501 | data_collection=d_collection, 502 | description=description, 503 | original_source_url=orig_url, 504 | publication=pubs, 505 | site_information=site_info, 506 | variables=varis) 507 | return out 508 | -------------------------------------------------------------------------------- /proxysiphon/lmr_hdf5/__init__.py: -------------------------------------------------------------------------------- 1 | """Read proxies netCDF5 file and write proxies HDF5 file for LMR Data Assimilation workflow 2 | """ 3 | 4 | 5 | __all__ = ['nc2lmrh5', 'nc2lmrdf'] 6 | 7 | 8 | import os 9 | import logging 10 | import numpy as np 11 | import pandas as pd 12 | import xarray as xr 13 | import netCDF4 14 | import shapely.affinity 15 | import shapely.geometry 16 | 17 | import erebusfall as ef 18 | 19 | 20 | log = logging.getLogger(__name__) 21 | 22 | 23 | class DistanceThresholdError(Exception): 24 | """Raised when the distance between two points is further than a threshold 25 | 26 | Parameters 27 | ---------- 28 | target_distance : int or float 29 | The distance between two target points (km). 30 | distance_threshold : int or float 31 | The distance threshold. 32 | 33 | """ 34 | 35 | def __init__(self, target_distance, distance_threshold): 36 | self.target_distance = target_distance 37 | self.distance_threshold = distance_threshold 38 | 39 | 40 | def chord_distance(latlon1, latlon2): 41 | """Chordal distance between two sequences of (lat, lon) points 42 | 43 | Parameters 44 | ---------- 45 | latlon1 : sequence of tuples 46 | (latitude, longitude) for one set of points. 47 | latlon2 : sequence of tuples 48 | A sequence of (latitude, longitude) for another set of points. 49 | 50 | Returns 51 | ------- 52 | dists : 2d array 53 | An mxn array of Earth chordal distances [1]_ (km) between points in 54 | latlon1 and latlon2. 55 | 56 | References 57 | ---------- 58 | .. [1] https://en.wikipedia.org/wiki/Chord_(geometry) 59 | 60 | """ 61 | earth_radius = 6378.137 # in km 62 | 63 | latlon1 = np.atleast_2d(latlon1) 64 | latlon2 = np.atleast_2d(latlon2) 65 | 66 | n = latlon1.shape[0] 67 | m = latlon2.shape[0] 68 | 69 | paired = np.hstack((np.kron(latlon1, np.ones((m, 1))), 70 | np.kron(np.ones((n, 1)), latlon2))) 71 | 72 | latdif = np.deg2rad(paired[:, 0] - paired[:, 2]) 73 | londif = np.deg2rad(paired[:, 1] - paired[:, 3]) 74 | 75 | a = np.sin(latdif / 2) ** 2 76 | b = np.cos(np.deg2rad(paired[:, 0])) 77 | c = np.cos(np.deg2rad(paired[:, 2])) 78 | d = np.sin(np.abs(londif) / 2) ** 2 79 | 80 | half_angles = np.arcsin(np.sqrt(a + b * c * d)) 81 | 82 | dists = 2 * earth_radius * np.sin(half_angles) 83 | 84 | return dists.reshape(m, n) 85 | 86 | 87 | def get_nearest(latlon, dain, depth=None, lat_coord='Latitude', lon_coord='Longitude', 88 | depth_coord='depth', distance_threshold=1500): 89 | """Get nearest non-NaN to latlon from xarray.DataArray obj 90 | 91 | Finds the nearest not NaN to latlon, and optionally depth. It searches for a 92 | nearest depth first, if given, and then searches for nearest latlon. Note 93 | that this does not work with irregular grids, such as rotated polar, etc. 94 | 95 | Parameters 96 | ---------- 97 | latlon : tuple 98 | Target latitude and longitude. Must be within -90 to 90 and -180 to 180. 99 | dain : xarray.DataArray 100 | Field with regular latlon coordinates. 101 | depth : float or int, optional 102 | Target depth to get nearest. 103 | lat_coord : str, optional 104 | Name of the latitude coordinate in ``da``. 105 | lon_coord : str, optional 106 | Name of the longitude coordinate in ``da``. 107 | depth_coord : str, optional 108 | Name of the depth coordinate in ``da``. 109 | distance_threshold : float or int, optional 110 | If the nearest distance is larger than this, raise 111 | 112 | Returns 113 | ------- 114 | nearest : xarray.DataArray 115 | Nearest points. 116 | nearest_distance : float 117 | Chordal distance (km) from target to matched gridpoint. 118 | 119 | Raises 120 | ------ 121 | DistanceThresholdError 122 | """ 123 | da = dain.copy() 124 | 125 | assert latlon[0] <= 90 and latlon[0] >= -90 126 | assert latlon[1] <= 180 and latlon[1] >= -180 127 | 128 | assert lat_coord in da.coords 129 | assert lon_coord in da.coords 130 | 131 | assert (da[lat_coord].ndim == 1) and (da[lon_coord].ndim == 1) 132 | 133 | # First, find the nearest depth index, if given. 134 | if depth is not None: 135 | assert depth_coord in da.coords 136 | 137 | # Note use 'pad' because want next upper water column level value. 138 | da = da.sortby('depth') 139 | da = da.sel(**{depth_coord: depth}, method='nearest') 140 | 141 | # Now search for nearest latlon point. 142 | da_stack = da.stack(yx=[lat_coord, lon_coord]).dropna('yx') 143 | da_latlon_stack = np.vstack((da_stack[lat_coord], da_stack[lon_coord])).T 144 | 145 | # Any values above 180 become negative -- needed for 0-360 longitudes. 146 | highlon_msk = da_latlon_stack > 180 147 | da_latlon_stack[highlon_msk] = da_latlon_stack[highlon_msk] - 360 148 | 149 | distance = chord_distance(np.array([latlon]), da_latlon_stack) 150 | nearest = da_stack.isel(yx=np.argmin(distance)) 151 | nearest_distance = np.min(distance) 152 | 153 | if nearest_distance > distance_threshold: 154 | raise DistanceThresholdError(nearest_distance, distance_threshold) 155 | 156 | return nearest, nearest_distance 157 | 158 | 159 | def get_netcdf_resource(fl, **kwargs): 160 | """Read NetCDF files as package resource, output for xarray.Dataset 161 | 162 | Parameters 163 | ---------- 164 | fl : str 165 | NetCDF resource name. 166 | **kwargs : 167 | Passed to ``xarray.open_dataset``. 168 | 169 | Returns 170 | ------- 171 | data : xarray.Dataset 172 | """ 173 | here = os.path.abspath(os.path.dirname(__file__)) 174 | flpath = os.path.join(here, fl) 175 | data = xr.open_dataset(flpath, **kwargs) 176 | return data 177 | 178 | 179 | def poly_dateline_wrap(p): 180 | """Split dateline crossing polygon into multipoly so wraps. 181 | 182 | Parameters 183 | ---------- 184 | p : shapely.geometry.Polygon 185 | 186 | Returns 187 | ------- 188 | out : shapely.geometry.Polygon or shapely.geometry.MultiPolygon 189 | """ 190 | dateline = shapely.geometry.LineString([(180, 90), (180, -90)]) 191 | 192 | if not dateline.crosses(p): 193 | return p 194 | 195 | right_ls = shapely.geometry.LineString([(360, 90), (360, -90)]) 196 | left_ls = shapely.geometry.LineString([(-180, 90), (-180, -90)]) 197 | left_clip = shapely.geometry.MultiLineString([left_ls, dateline]).convex_hull 198 | right_clip = shapely.geometry.MultiLineString([dateline, right_ls]).convex_hull 199 | 200 | northpacific_left = p.intersection(left_clip) 201 | dl_right_off = p.intersection(right_clip) 202 | 203 | # Shift right of dateline back so lon (x) is within [-180, 180] 204 | northpacific_lr = shapely.affinity.translate(shapely.geometry.LinearRing(dl_right_off.exterior.coords), 205 | xoff=-360) 206 | northpacific_right = shapely.geometry.Polygon(northpacific_lr) 207 | out = shapely.geometry.MultiPolygon([northpacific_left, northpacific_right]) 208 | return out 209 | 210 | 211 | def find_seasonality(sitegrp, proxy_grp): 212 | """Return string list of ints giving site variable seasonality. 213 | 214 | Parameters 215 | ---------- 216 | sitegrp : netCDF4.Group 217 | Proxy site netcdf group. 218 | proxy_grp: netCDF4.Group 219 | Proxy variable netcdf group 220 | 221 | Returns 222 | ------- 223 | out : str 224 | """ 225 | out = list(range(1, 13)) 226 | 227 | proxy_type = str(proxy_grp.long_name) 228 | if proxy_type == "UK'37": 229 | log.debug('finding seasonality for UK37 proxy') 230 | # Jess Tierney polygons from BAYSPLINE 231 | mediterranean = shapely.geometry.Polygon([(-5.5, 36.25), 232 | (3, 47.5), 233 | (45, 47.5), 234 | (45, 30), 235 | (-5.5, 30)]) 236 | northatlantic = shapely.geometry.Polygon([(-55, 48), 237 | (-50, 70), 238 | (20, 70), 239 | (10, 62.5), 240 | (-4.5, 58.2), 241 | (-4.5, 48)]) 242 | northpacific_raw = shapely.geometry.Polygon([(135, 45), 243 | (135, 70), 244 | (250, 70), 245 | (232, 52.5), 246 | (180, 45)]) 247 | northpacific = poly_dateline_wrap(northpacific_raw) 248 | 249 | latlon = (float(sitegrp.latitude), float(sitegrp.longitude)) 250 | assert -90 < latlon[0] < 90, 'site latitude must be -90 < lat < 90' 251 | assert -180 < latlon[1] < 180, 'site longitude must be -180 < lon < 180' 252 | 253 | site_location = shapely.geometry.Point(latlon[::-1]) 254 | if mediterranean.contains(site_location): 255 | out = [1, 2, 3, 4, 5, 11, 12] 256 | if northatlantic.contains(site_location): 257 | out = [8, 9, 10] 258 | if northpacific.contains(site_location): 259 | out = [6, 7, 8] 260 | 261 | elif proxy_type == 'd18O': 262 | foram_type = str(proxy_grp.foraminifera_type) 263 | latlon = (float(sitegrp.latitude), float(sitegrp.longitude)) 264 | log.debug('finding seasonality for d18O proxy ({}) @ {}'.format(foram_type, latlon)) 265 | foram_seas = get_netcdf_resource('foram_seasons.nc', group='d18oc') 266 | foram_seas = foram_seas.where(foram_seas != '') # Replace '' with nan. 267 | # Need to normalize full species/subspecies names to the variable names used 268 | # in the FORAM_SEASONS_NETCDF group. 269 | foraminifera_map = {'Globigerina bulloides': 'G. bulloides', 270 | 'Neogloboquadrina pachyderma sinistral': 'N. pachyderma', 271 | 'Neogloboquadrina incompta': 'N. incompta', 272 | 'Globigerinoides ruber white': 'G. ruber', 273 | 'Globigerinoides ruber pink': 'G. ruber', 274 | 'Trilobatus sacculifer': 'T. sacculifer', 275 | } 276 | foram_spp_str = foraminifera_map.get(foram_type) 277 | if foram_spp_str is not None: 278 | nearest_seas, _ = get_nearest(latlon, foram_seas[foram_spp_str], 279 | lat_coord='lat', lon_coord='lon') 280 | out = nearest_seas.item() 281 | 282 | else: 283 | pass # foram type not in our species mapping so use annual. 284 | 285 | elif proxy_type == 'Mg/Ca': 286 | foram_type = str(proxy_grp.foraminifera_type) 287 | latlon = (float(sitegrp.latitude), float(sitegrp.longitude)) 288 | log.debug('finding seasonality for Mg/Ca proxy ({}) @ {}'.format(foram_type, latlon)) 289 | foram_seas = get_netcdf_resource('foram_seasons.nc', group='mgca') 290 | foram_seas = foram_seas.where(foram_seas != '') # Replace '' with nan. 291 | # Need to normalize full species/subspecies names to the variable names used 292 | # in the FORAM_SEASONS_NETCDF group. 293 | foraminifera_map = {'Globigerina bulloides': 'G. bulloides', 294 | 'Neogloboquadrina pachyderma sinistral': 'N. pachyderma sinistral', 295 | 'Neogloboquadrina incompta': 'N. pachyderma dextral', 296 | 'Globigerinoides ruber white': 'G. ruber white', 297 | 'Globigerinoides ruber pink': 'G. ruber pink', 298 | 'Trilobatus sacculifer': 'G. sacculifer', 299 | } 300 | foram_spp_str = foraminifera_map.get(foram_type) 301 | if foram_spp_str is not None: 302 | nearest_seas, _ = get_nearest(latlon, foram_seas[foram_spp_str], 303 | lat_coord='lat', lon_coord='lon') 304 | out = nearest_seas.item() 305 | else: 306 | pass # foram type not in our species mapping so use annual. 307 | log.debug('season months are: {}'.format(out)) 308 | return str(out) 309 | 310 | 311 | def icevol_correction(proxies, metadata): 312 | """Apply ice-volume correction to d18O proxies in LMR proxy dataframes. 313 | 314 | Returns modified copies of the original data. 315 | """ 316 | p = proxies.copy() 317 | m = metadata.copy() 318 | 319 | matches = ['d18o' in c.lower() for c in p.columns] 320 | 321 | if not any(matches): 322 | return p, m 323 | 324 | m.set_index('Proxy ID', inplace=True) 325 | 326 | matches_idx = np.where(matches) 327 | matched_columns = p.columns[matches_idx] 328 | 329 | for c in matched_columns: 330 | proxy_raw = proxies[c].values 331 | age_raw = proxies[c].index.values 332 | age_yr = 1950 - age_raw # CE/BC to Yr BP 333 | proxy_adjusted = ef.icevol_correction(age_yr, proxy_raw, proxytype='d18o', 334 | timeunit='ya') 335 | p.loc[:, c] = proxy_adjusted 336 | 337 | m.loc[c, 'Oldest (C.E.)'] = p[c].dropna().index.min() 338 | m.loc[c, 'Youngest (C.E.)'] = p[c].dropna().index.max() 339 | 340 | m.reset_index(inplace=True) 341 | return p, m 342 | 343 | 344 | def lmr_da_dfs(sitegrp=None, agemodel_iter=None, find_modern_seasonality=True): 345 | """Return proxy data and metadata pandas df needed for LMR DA proxy input 346 | 347 | If no args are passed, return empty proxy and metadata (template) pandas 348 | dataframes. 349 | 350 | Parameters 351 | ---------- 352 | sitegrp : netCDF4.Group or None, optional 353 | Proxy site netcdf group. 354 | agemodel_iter : int or None, optional 355 | Age-depth model iteration to use, if available. This is the index of the 356 | 'agemodel_ensemble' column to use for the output data. If ``None`` (default), 357 | uses median age. 358 | find_modern_seasonality : bool 359 | Do you want to estimate sample seasonality using the modern record? 360 | Sets annual seasonality if False. Default is True. 361 | 362 | Returns 363 | ------- 364 | data : pandas.DataFrame 365 | meta : pandas.DataFrame 366 | """ 367 | data_template = pd.DataFrame() 368 | meta_template = pd.DataFrame({'Proxy ID': [], 'Site': [], 'Lat (N)': [], 'Lon (E)': [], 369 | 'Archive type': [], 'Proxy measurement': [], 370 | 'Resolution (yr)': [], 'Reference': [], 'Databases': [], 371 | 'Seasonality': [], 'Elev': [], 372 | 'Oldest (C.E.)': [], 'Youngest (C.E.)': []}) 373 | meta_template = meta_template.astype(dtype={'Proxy ID': 'object', 'Site': 'object', 374 | 'Lat (N)': 'float64', 'Lon (E)': 'float64', 375 | 'Archive type': 'object', 376 | 'Proxy measurement': 'object', 377 | 'Resolution (yr)': 'float64', 378 | 'Reference': 'object', 'Databases': 'object', 379 | 'Seasonality': 'object', 'Elev': 'float64', 380 | 'Oldest (C.E.)': 'float64', 381 | 'Youngest (C.E.)': 'float64'}) 382 | 383 | if sitegrp is None: 384 | return data_template.copy(), meta_template.copy() 385 | 386 | log.info('extracting LMR data from {}'.format(str(sitegrp.site_name))) 387 | 388 | variables_to_skip = ['depth', 'age_original', 'age_median', 'age_ensemble'] 389 | proxy_variables = [(k, v) for k, v in sitegrp['data'].variables.items() if k not in variables_to_skip] 390 | 391 | latitude = float(sitegrp.latitude) 392 | longitude = float(sitegrp.longitude) 393 | elevation = float(sitegrp.elevation) 394 | data_df = data_template.copy() 395 | meta_df = meta_template.copy() 396 | 397 | for k, v in proxy_variables: 398 | log.debug('processing variable {}'.format(str(k))) 399 | 400 | # Convert years BP to CE/BP and find min max. 401 | if agemodel_iter is None: 402 | try: 403 | age_yrs_ce = 1950 - sitegrp['data'].variables['age_median'][:] 404 | except KeyError: 405 | age_yrs_ce = 1950 - sitegrp['data'].variables['age_original'][:] 406 | else: 407 | idx = int(agemodel_iter) 408 | age_yrs_ce = 1950 - sitegrp['data'].variables['age_ensemble'][:, idx] 409 | 410 | # Make depth cutoff mask from depth cutoffs, if available. 411 | cut_deep = np.inf 412 | if hasattr(sitegrp['chronology'], 'cut_deep'): 413 | cut_deep = float(sitegrp['chronology'].cut_deep) 414 | cut_shallow = -np.inf 415 | if hasattr(sitegrp['chronology'], 'cut_shallow'): 416 | cut_shallow = float(sitegrp['chronology'].cut_shallow) 417 | depth = sitegrp['data'].variables['depth'][:] 418 | cutoff_msk = (depth >= cut_shallow) & (depth <= cut_deep) 419 | 420 | notnan_and_notcut = ~np.isnan(v[:].filled(np.nan)) & cutoff_msk 421 | youngest_ce = np.max(age_yrs_ce[notnan_and_notcut]) 422 | oldest_ce = np.min(age_yrs_ce[notnan_and_notcut]) 423 | 424 | # Put together proxy ID and proxy measurement strings. 425 | siteid = str(sitegrp.site_name).strip().lower() 426 | pmeasurement = str(k).strip().lower() 427 | # Append cleaning protocol info if available for Mg/Ca 428 | try: 429 | if v.long_name == 'Mg/Ca': 430 | log.debug('Mg/Ca variable, attempting to find cleaning protocol') 431 | # Should throw error if have Mg/Ca record w/o cleaning protocol info. 432 | cleaning_protocol = str(v.mgca_cleaning_protocol) 433 | cleaning_str = None 434 | if 'reductive' in cleaning_protocol.lower(): 435 | cleaning_str = ':reductive' 436 | elif 'barker' in cleaning_protocol.lower(): 437 | cleaning_str = ':barker' 438 | pmeasurement += cleaning_str 439 | except AttributeError: # caught if v doesn't have long_name attrib... 440 | pass 441 | proxyid = siteid + ':' + pmeasurement 442 | 443 | this_meta = meta_template.copy() 444 | this_meta['Proxy ID'] = [proxyid] 445 | this_meta['Site'] = [siteid] 446 | this_meta['Lat (N)'] = latitude 447 | this_meta['Lon (E)'] = longitude 448 | this_meta['Archive type'] = ['Marine sediments'] 449 | this_meta['Proxy measurement'] = [pmeasurement] 450 | this_meta['Resolution (yr)'] = [(youngest_ce - oldest_ce) / len(age_yrs_ce[notnan_and_notcut])] 451 | this_meta['Reference'] = [str(None)] 452 | this_meta['Databases'] = ['[DTDA]'] 453 | if find_modern_seasonality: 454 | this_meta['Seasonality'] = find_seasonality(sitegrp, v) 455 | else: 456 | this_meta['Seasonality'] = str(list(range(1, 13))) 457 | this_meta['Elev'] = elevation 458 | this_meta['Oldest (C.E.)'] = oldest_ce 459 | this_meta['Youngest (C.E.)'] = youngest_ce 460 | meta_df = meta_df.append(this_meta, ignore_index=True) 461 | 462 | d = (pd.DataFrame({'Year C.E.': age_yrs_ce[cutoff_msk], 463 | proxyid: v[:].filled(np.nan)[cutoff_msk]}) 464 | .set_index('Year C.E.') 465 | .dropna(how='any')) 466 | data_df = data_df.join(d, how='outer') 467 | 468 | data_df = data_df.sort_index(ascending=False) 469 | 470 | return data_df, meta_df 471 | 472 | 473 | def _lmr_df_from_nc_sites(fl, agemodel_iter=None, find_modern_seasonality=True): 474 | """Create LMR data and metadata dataframes from opened netCDF file group""" 475 | all_data_df, all_meta_df = lmr_da_dfs() 476 | 477 | for site_grp in fl.groups.values(): 478 | try: 479 | site_data_df, site_meta_df = lmr_da_dfs(site_grp, 480 | agemodel_iter=agemodel_iter, 481 | find_modern_seasonality=find_modern_seasonality) 482 | except TypeError as e: 483 | errormsg = '{} raised - skipping file - {} - Mg/Ca variable likely missing cleaning protocol info' 484 | log.error(errormsg.format(e, site_grp.site_name)) 485 | continue 486 | 487 | all_meta_df = all_meta_df.append(site_meta_df, ignore_index=True) 488 | all_data_df = all_data_df.join(site_data_df, how='outer') 489 | 490 | return all_meta_df, all_data_df 491 | 492 | 493 | def nc2lmrdf(path_or_buffer, agemodel_iter=None, 494 | icevol_cor=True, find_modern_seasonality=True): 495 | """Read proxy netCDF and output to LMR DA-format dataframes. 496 | 497 | Parameters 498 | ---------- 499 | path_or_buffer : str or netCDF4.Dataset 500 | Input proxy netCDF file path or opened buffer. 501 | agemodel_iter : int or None, optional 502 | Optional index of age-model iteration to use in output -- if multiple 503 | age-model iterations are available. 504 | icevol_cor : bool, optional 505 | Do you want to apply ice-volume correction to the d18O foraminiferal 506 | records? This is done with the `erebusfalls` package. `True` by default. 507 | find_modern_seasonality : bool, optional 508 | Do you want to estimate sample seasonality using the modern record? 509 | Sets annual seasonality if False. Default is True. 510 | 511 | Returns 512 | ------- 513 | all_data_df : pd.Dataframe 514 | LMR proxy data. 515 | all_meta_df : pd.Dataframe 516 | LMR proxy metadata. 517 | 518 | Also see 519 | -------- 520 | `proxysiphon.nc2lmrh5` 521 | 522 | """ 523 | # Open proxy site netCDF file and collect needed data or read directly from 524 | # obj if it's already open. 525 | if isinstance(path_or_buffer, str): 526 | with netCDF4.Dataset(filename=path_or_buffer, mode='r') as fl: 527 | all_meta_df, all_data_df = _lmr_df_from_nc_sites(fl, 528 | agemodel_iter=agemodel_iter, 529 | find_modern_seasonality=find_modern_seasonality) 530 | else: 531 | all_meta_df, all_data_df = _lmr_df_from_nc_sites(path_or_buffer, 532 | agemodel_iter=agemodel_iter, 533 | find_modern_seasonality=find_modern_seasonality) 534 | 535 | all_data_df = all_data_df.sort_index(ascending=False) 536 | 537 | if icevol_cor: 538 | # Ice-volume correction to d18O foram proxies: 539 | all_data_df, all_meta_df = icevol_correction(all_data_df, all_meta_df) 540 | 541 | return all_data_df, all_meta_df 542 | 543 | 544 | def nc2lmrh5(path_or_buffer, h5file, agemodel_iter=None, icevol_cor=True, 545 | find_modern_seasonality=True): 546 | """Read proxy netCDF and output to LMR DA-format HDF5 file. 547 | 548 | Parameters 549 | ---------- 550 | path_or_buffer : str or netCDF4.Dataset 551 | Input proxy netCDF file path or opened buffer. 552 | h5file : str 553 | Path to output HDF5 file. Not written if None. 554 | agemodel_iter : int or None, optional 555 | Optional index of age-model iteration to use in output -- if multiple 556 | age-model iterations are available. 557 | icevol_cor : bool, optional 558 | Do you want to apply ice-volume correction to the d18O foraminiferal 559 | records? This is done with the `erebusfalls` package. `True` by default. 560 | find_modern_seasonality : bool, optional 561 | Do you want to estimate sample seasonality using the modern record? 562 | Sets annual seasonality if False. Default is True. 563 | 564 | Returns 565 | ------- 566 | Nothing is returned, output is written to `h5file`. 567 | 568 | Also see 569 | -------- 570 | `proxysiphon.nc2lmrdf` 571 | """ 572 | all_data_df, all_meta_df = nc2lmrdf(path_or_buffer, agemodel_iter=agemodel_iter, 573 | icevol_cor=icevol_cor, 574 | find_modern_seasonality=find_modern_seasonality) 575 | 576 | # Write to H5 file. 577 | log.debug('writing to HDF5 file: {}'.format(h5file)) 578 | all_meta_df.to_hdf(h5file, key='meta', mode='w', format='table', 579 | complevel=9, complib='blosc') 580 | all_data_df.to_hdf(h5file, key='proxy', mode='r+', format='table', 581 | complevel=9, complib='blosc') 582 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /proxysiphon/lgm.py: -------------------------------------------------------------------------------- 1 | import datetime 2 | import logging 3 | from copy import deepcopy 4 | 5 | import netCDF4 6 | import numpy as np 7 | import unidecode 8 | 9 | from proxysiphon.agemodel import get_deltar_online, fit_agedepthmodel, date_proxy 10 | 11 | log = logging.getLogger(__name__) 12 | 13 | 14 | def _normalize_to_ascii_array(a, dtype='S50'): 15 | """Normalize sequence of UTF-8 string to np.Array of ASCII""" 16 | normed = np.array([unidecode.unidecode(str(x)) for x in a], dtype=dtype) 17 | return normed 18 | 19 | 20 | class RedateMixin: 21 | """Mixins to redate LGM proxy records""" 22 | 23 | def swapin_custom_deltar(self, d_r=None, d_std=None): 24 | """Swap-in custom proxy ΔR mean and standard-deviation values. 25 | 26 | ``d_r`` is put into self.chronology_information.df column "delta_R" and 27 | ``d_std`` is put into column "delta_R_1s_err". Any existing values in 28 | these columns are first moved to a new column "*_original", but only if 29 | the "*_original" columns don't already exist. If "*_original" columns 30 | already exist, then current values in "delta_R" or "delta_R_1s_err" are 31 | discarded in the returned proxy record. 32 | 33 | Parameters 34 | ---------- 35 | d_r : ndarray, scalar or None 36 | Carbon reservoir (ΔR) mean value to swap-in. Ignored if None. 37 | d_std : ndarray, scalar or None 38 | ΔR standard-deviation value to swap-in. Ignored 39 | if None. 40 | 41 | Returns 42 | ------- 43 | out : Modified copy of proxy record. 44 | """ 45 | out = self.copy() 46 | 47 | if d_r is None and d_std is None: 48 | return out 49 | 50 | # If we're plugging in a new value, we preserve the original but moving it to a new *_original 51 | # columns. 52 | if d_r is not None: 53 | if 'delta_R_original' not in out.chronology_information.df.columns: 54 | out.chronology_information.df['delta_R_original'] = out.chronology_information.df['delta_R'] 55 | out.chronology_information.df['delta_R'] = d_r 56 | out.chronology_information.df['delta_R'].replace(to_replace='None', value=np.nan, inplace=True) 57 | 58 | if d_std is not None: 59 | if 'delta_R_1s_err_original' not in out.chronology_information.df.columns: 60 | out.chronology_information.df['delta_R_1s_err_original'] = out.chronology_information.df[ 61 | 'delta_R_1s_err'] 62 | out.chronology_information.df['delta_R_1s_err'] = d_std 63 | out.chronology_information.df['delta_R_1s_err'].replace(to_replace='None', value=np.nan, inplace=True) 64 | 65 | return out 66 | 67 | def copy(self): 68 | """Return deep copy of self""" 69 | return deepcopy(self) 70 | 71 | def redate(self, **kwargs): 72 | """Redate proxy data with (snake)bacon 73 | 74 | Parameters 75 | ---------- 76 | nsims : int 77 | Number of age-model simulations to retain. 78 | kwargs : 79 | Passed on to ``self._fit_agemodel``. 80 | 81 | Returns 82 | ------- 83 | Updated copy of self. The ``snakebacon.AgeDepthModel`` used to redate 84 | the record is monkeypatched into 85 | ``self.chronology_information.bacon_agemodel`` in this returned copy. 86 | """ 87 | rec = self.copy() 88 | 89 | agemodel, mcmc_kwargs = rec._fit_agemodel(**kwargs) 90 | a_median, a_ensemble = rec._date_sampledepths(agemodel, kwargs.pop('nsims', None)) 91 | rec.chronology_information.bacon_agemodel = agemodel 92 | rec.data.age_median = a_median 93 | rec.data.age_ensemble = a_ensemble 94 | return rec 95 | 96 | def _fit_agemodel(self, **kwargs): 97 | """Fit snakebacon model to NcdcRecord 98 | """ 99 | chron_df = self.chronology_information.df.copy() 100 | data_df = self.data.df.copy() 101 | myr = 1950 - self.recent_date() 102 | deltar = self.chronology_information.df['delta_R'].values 103 | deltar_error = self.chronology_information.df['delta_R_1s_err'].values 104 | 105 | agemodel, _, mcmc_kwargs = fit_agedepthmodel(chron_df, data_df, deltar, deltar_error, 106 | minyr=myr, mcmc_kws=kwargs) 107 | return agemodel, mcmc_kwargs 108 | 109 | def _date_sampledepths(self, agemodel, nsims=1000): 110 | """Date self proxy sample depths given a snakebacon.AgeModel 111 | 112 | Parameters 113 | ---------- 114 | agemodel : snakebacon.AgeModel 115 | Age model to date from. 116 | nsims : scalar or None, optional 117 | Number of draws to include in returned ensemble. ``None`` returns 118 | 1000 draws. 119 | 120 | Returns 121 | ------- 122 | p_median : pandas.DataFrame 123 | Median age per depth. 124 | p_ensemble : 125 | Ensemble of ages per depth. 126 | """ 127 | if nsims is None: 128 | nsims = 1000 129 | 130 | data_df = self.data.df.copy() 131 | p_median, p_ensemble = date_proxy(agemodel, data_df, nsims) 132 | 133 | p_median = (p_median[['depth', 'age']].rename(columns={'age': 'age_median'}) 134 | .set_index('depth')) 135 | p_ensemble = (p_ensemble[['depth', 'age', 'mciter']].rename(columns={'mciter': 'draw'}) 136 | .pivot(index='depth', columns='draw', values='age')) 137 | return p_median, p_ensemble 138 | 139 | def recent_date(self): 140 | """Get the most recent date from self metadata. 141 | 142 | First try "Collection_Year" in "Data_Collection" section. If can't 143 | find, then earliest year in publications list. 144 | """ 145 | out = None 146 | col_year = self.data_collection.collection_year 147 | if col_year is not None: 148 | out = col_year 149 | else: 150 | # Return earliest year in publications. 151 | out = min([int(p.published_date_or_year) for p in self.publication if p.published_date_or_year is not None]) 152 | return out 153 | 154 | def update_deltar(self): 155 | """Set self.ChronologyInformation.df delta_R and delta_r_1s_error, returning an updated copy 156 | 157 | If these variables are changed/updated, the originals are moved to column names *_original. 158 | """ 159 | x = self.copy() 160 | latlon = (float(x.site_information.northernmost_latitude), 161 | float(x.site_information.easternmost_longitude)) 162 | 163 | chron_df = x.chronology_information.df.copy() 164 | 165 | delta_r_used = None 166 | delta_r_1s_err_used = None 167 | 168 | n_unique_deltarerror = len(chron_df['delta_R'].dropna().unique()) 169 | n_unique_deltar = len(chron_df['delta_R_1s_err'].dropna().unique()) 170 | 171 | if (n_unique_deltarerror > 1) and (n_unique_deltar > 1): 172 | log.info('Found multi-depth deltar and deltar_error. Using NcdcRecords original values') 173 | elif n_unique_deltar > 1: 174 | log.info('Found multi-depth deltar, without deltar_error. Using carbonferret "delta_R_1s_err".') 175 | delta_r_1s_err_used = get_deltar_online(latlon)[1] 176 | else: 177 | delta_r_used, delta_r_1s_err_used = get_deltar_online(latlon) 178 | log.debug('deltar(deltar_error): {}({})'.format(delta_r_used, delta_r_1s_err_used)) 179 | 180 | if delta_r_used is not None: 181 | chron_df['delta_R_original'] = chron_df['delta_R'].copy() 182 | chron_df['delta_R'] = delta_r_used 183 | 184 | if delta_r_1s_err_used is not None: 185 | chron_df['delta_R_1s_err_original'] = chron_df['delta_R_1s_err'].copy() 186 | chron_df['delta_R_1s_err'] = delta_r_1s_err_used 187 | 188 | x.chronology_information.df = chron_df.copy() 189 | return x 190 | 191 | def average_duplicate_datadepths(self): 192 | """Average obs at the same depth in self.data.df, return copy of self 193 | """ 194 | if not self.data.df['depth'].duplicated().any(): 195 | log.debug('Found no duplicate depths in Data') 196 | # Return if no duplicates 197 | return self 198 | 199 | x = self.copy() 200 | log.debug('Found duplicate depths in Data') 201 | x.data.df = x.data.df.groupby('depth', as_index=False).mean() 202 | return x 203 | 204 | def has_chron(self): 205 | """True if self has populated chronology information""" 206 | result = False 207 | try: 208 | chron = self.chronology_information.df 209 | except KeyError: 210 | return result 211 | if len(chron) > 1: # Needs to have more than one date. 212 | result = True 213 | return result 214 | 215 | def has_data(self): 216 | """True if self has populated data information""" 217 | result = False 218 | try: 219 | d = self.data.df 220 | except KeyError: 221 | return result 222 | if len(d) > 0: 223 | result = True 224 | return result 225 | 226 | def chronology_depth_range(self, chronology='original'): 227 | """Get (min, max) range of chronology determinant depths 228 | 229 | Parameters 230 | ---------- 231 | chronology : str, optional 232 | Which chronology information do we get depth ranges from. Can be 233 | 'original' or 'redate'. 'original' uses the depths in chronology information from 234 | self.chronology_information.df. 'redate' looks to 235 | self.chronology_information.bacon_agemodel.mcmcsetup.coredates.depth, 236 | assuming that the record has been redated with self.readate(). 237 | 238 | Returns 239 | ------- 240 | out : tuple 241 | Depths range (min, max). 242 | 243 | See Also 244 | -------- 245 | LgmRecord.slice_datadepths : Cut self.data.df to given depths 246 | """ 247 | assert chronology in ['original', 'redate'] 248 | if chronology == 'redate': 249 | depths = np.array(self.chronology_information.bacon_agemodel.mcmcsetup.coredates.depth) 250 | elif chronology == 'original': 251 | depths = np.concatenate([self.chronology_information.df['depth_top'], 252 | self.chronology_information.df['depth_bottom']]) 253 | out = (np.nanmin(depths), np.nanmax(depths)) 254 | return out 255 | 256 | def slice_datadepths(self, shallow=None, deep=None): 257 | """Cut self.data to given depths, return updated copy of self 258 | 259 | The cut is inclusive for `shallow` and `deep` limits. Both `shallow` and 260 | `deep` must be positive. If no values are given for `shallow` and `deep`, 261 | the cuts are at the deepest and shallowest samples in 262 | `self.chronology_information`. 263 | 264 | Note also that it cuts self.data.df, in addition to self.data.age_median 265 | and self.data.age_ensemble, if available. 266 | 267 | See Also 268 | -------- 269 | LgmRecord.chronology_depth_range : Get range of chronology determinant depths 270 | """ 271 | if len(self.data.df) < 1 or 'depth' not in self.data.df.columns: 272 | return self 273 | 274 | out = self.copy() 275 | 276 | if shallow is None: 277 | shallow = out.data.df['depth'].min() 278 | if deep is None: 279 | deep = out.data.df['depth'].max() 280 | 281 | assert shallow >= 0 and deep >= 0, 'cut depths must be positive' 282 | 283 | out.data.df = out.data.df[(out.data.df['depth'] >= shallow) & (out.data.df['depth'] <= deep)] 284 | 285 | if hasattr(out.data, 'age_ensemble'): 286 | out.data.age_ensemble = out.data.age_ensemble[ 287 | (out.data.age_ensemble.index >= shallow) & (out.data.age_ensemble.index <= deep)] 288 | if hasattr(out.data, 'age_median'): 289 | out.data.age_median = out.data.age_median[ 290 | (out.data.age_median.index >= shallow) & (out.data.age_median.index <= deep)] 291 | 292 | return out 293 | 294 | 295 | class NetcdfMixin: 296 | """Mixins to export LGM proxy records to a NetCDF file""" 297 | 298 | @staticmethod 299 | def _variable_attributes(varname): 300 | """Get dict of netCDF4 variable attributes for a given NcdcRecord Data column name""" 301 | proxy_map = {'d13c': ('d13C', 'per mil'), 302 | 'd18o': ('d18O', 'per mil'), 303 | 'mgca': ('Mg/Ca', 'per mil'), 304 | 'percent': ('Percent foraminifera', '%'), 305 | 'tex86': ('TEX86', 'index'), 306 | 'uk37': ("UK'37", 'index')} 307 | # Second part of the column name... 308 | foraminifera_map = {'bulloides': 'Globigerina bulloides', 309 | 'crassaformis': 'Globorotalia crassaformis', 310 | 'dutertrei': 'Neogloboquadrina dutertrei', 311 | 'inflata': 'Globoconella inflata', 312 | 'mabahethi': 'Cibicides mabahethi', 313 | 'marginata': 'Bulimina marginata', 314 | 'menardii': 'Globorotalia menardii', 315 | 'obliquiloculata': 'Pulleniatina obliquiloculata', 316 | 'pachyderma': 'Neogloboquadrina pachyderma sinistral', 317 | 'pachysin': 'Neogloboquadrina pachyderma sinistral', 318 | 'pachyderma_d': 'Neogloboquadrina incompta', 319 | 'peregrina': 'Uvigerina peregrina', 320 | 'quinqueloba': 'Turborotalita quinqueloba', 321 | 'ruber': 'Globigerinoides ruber white', 322 | 'ruber_lato': 'Globigerinoides ruber white', 323 | 'ruber_pink': 'Globigerinoides ruber pink', 324 | 'ruber_stricto': 'Globigerinoides ruber white', 325 | 'sacculifer': 'Trilobatus sacculifer', 326 | 'truncatulinoides': 'Globorotalia pachytheca', 327 | 'tumida': 'Globorotalia tumida', 328 | 'acicula': 'Creseis acicula', 329 | } 330 | varname = varname.lower() 331 | try: 332 | if '_' not in varname: 333 | out = {'long_name': proxy_map[varname][0], 'units': proxy_map[varname][1]} 334 | else: 335 | proxy, foram = varname.split('_', 1) 336 | out = {'long_name': proxy_map[proxy][0], 'units': proxy_map[proxy][1], 337 | 'foraminifera_type': foraminifera_map[foram]} 338 | except KeyError: # Variable name not found. 339 | out = {} 340 | return out 341 | 342 | def _attach_site_ncgroup(self, parent): 343 | """Create the NetCDF4 site group and populate it 344 | 345 | This is run whenever self.to_netcdf() is called. 346 | 347 | Parameters 348 | ---------- 349 | parent : netcdf4.Group or netcdf4.Dataset 350 | Object the created site group will use as a parent. 351 | 352 | Returns 353 | ------- 354 | this_site : netcdf4.Group 355 | Reference to the created chronology group. 356 | """ 357 | site_name = self.site_information.site_name.strip() 358 | # Normalize site group name to ASCII and replace whitespace characters. 359 | grp_name = unidecode.unidecode(site_name.lower()).replace(' ', '_') 360 | 361 | # Create and populate site group 362 | this_site = parent.createGroup(grp_name) 363 | this_site.site_name = str(site_name) 364 | this_site.comment = str(self.description) 365 | this_site.latitude = float(self.site_information.northernmost_latitude) 366 | this_site.longitude = float(self.site_information.easternmost_longitude) 367 | this_site.elevation = int(self.site_information.elevation) 368 | try: 369 | this_site.collection_year = int(self.data_collection.collection_year) 370 | except TypeError: # If collection year doesn't exist 371 | pass 372 | publication_str = '\n\n'.join([x.to_citationstr() for x in self.publication]) 373 | this_site.references = publication_str 374 | return this_site 375 | 376 | def _attach_chronology_ncgroup(self, parent): 377 | chron = parent.createGroup('chronology') 378 | chron.createDimension('depth_top', None) 379 | chron.createDimension('str_dim', 50) 380 | 381 | labcode = chron.createVariable('labcode', 'S1', ('depth_top', 'str_dim')) 382 | labcode.long_name = 'Lab sample code' 383 | labcode.missing_value = 'NA' 384 | labcode._Encoding = 'ascii' 385 | labcode[:] = _normalize_to_ascii_array(self.chronology_information.df['Labcode'].fillna('NA')) 386 | 387 | depth_top = chron.createVariable('depth_top', 'f4', ('depth_top',)) 388 | depth_top.long_name = 'Sample top depth' 389 | depth_top.axis = 'Z' 390 | depth_top.positive = 'down' 391 | depth_top.units = 'cm' 392 | depth_top.missing_value = np.nan 393 | depth_top[:] = self.chronology_information.df['depth_top'].values 394 | 395 | depth_bottom = chron.createVariable('depth_bottom', 'f4', ('depth_top',)) 396 | depth_bottom.long_name = 'Sample bottom depth' 397 | depth_bottom.units = 'cm' 398 | depth_bottom.positive = 'down' 399 | depth_bottom.missing_value = np.nan 400 | depth_bottom[:] = self.chronology_information.df['depth_bottom'].values 401 | 402 | mat_dated = chron.createVariable('mat_dated', 'S1', ('depth_top', 'str_dim')) 403 | mat_dated.long_name = 'Material dated' 404 | mat_dated.missing_value = 'NA' 405 | mat_dated._Encoding = 'ascii' 406 | mat_dated[:] = _normalize_to_ascii_array(self.chronology_information.df['mat_dated'].fillna('NA')) 407 | 408 | c14_date = chron.createVariable('c14_date', 'f4', ('depth_top',)) 409 | c14_date.long_name = '14C date' 410 | c14_date.units = 'RC yr BP' 411 | c14_date.missing_value = np.nan 412 | c14_date[:] = self.chronology_information.df['14C_date'].values 413 | 414 | c14_1s_err = chron.createVariable('c14_1s_err', 'f4', ('depth_top',)) 415 | c14_1s_err.long_name = '14C 1-sigma error' 416 | c14_1s_err.units = 'RC yr BP' 417 | c14_1s_err.missing_value = np.nan 418 | c14_1s_err[:] = self.chronology_information.df['14C_1s_err'].values 419 | 420 | delta_r = chron.createVariable('delta_r', 'f4', ('depth_top',)) 421 | delta_r.long_name = 'delta R' 422 | delta_r.missing_value = np.nan 423 | delta_r[:] = self.chronology_information.df['delta_R'].values 424 | 425 | if 'delta_R_original' in self.chronology_information.df.columns: 426 | delta_r_orig = chron.createVariable('delta_r_original', 'f4', ('depth_top',)) 427 | delta_r_orig.long_name = 'Original delta R' 428 | delta_r_orig.description = 'Carbon reservoir correction (delta R) value(s) given in the orignal proxy site data set.' 429 | delta_r_orig.missing_value = np.nan 430 | delta_r_orig[:] = self.chronology_information.df['delta_R_original'].values 431 | 432 | delta_r_1s_error = chron.createVariable('delta_r_1s_error', 'f4', ('depth_top',)) 433 | delta_r_1s_error.missing_value = np.nan 434 | delta_r_1s_error.long_name = 'delta R 1-sigma error' 435 | delta_r_1s_error[:] = self.chronology_information.df['delta_R_1s_err'].values 436 | 437 | if 'delta_R_1s_err_original' in self.chronology_information.df.columns: 438 | delta_r_1s_error_orig = chron.createVariable('delta_r_1s_error_original', 'f4', ('depth_top',)) 439 | delta_r_1s_error_orig.long_name = 'Original delta R 1-sigma error' 440 | delta_r_1s_error_orig.description = 'Carbon reservoir correction 1-sigma error value(s) given in the orignal proxy site data set.' 441 | delta_r_1s_error_orig.missing_value = np.nan 442 | delta_r_1s_error_orig[:] = self.chronology_information.df['delta_R_1s_err_original'].values 443 | 444 | other_date = chron.createVariable('other_date', 'f4', ('depth_top',)) 445 | other_date.missing_value = np.nan 446 | other_date.long_name = 'Other date' 447 | other_date[:] = self.chronology_information.df['other_date'].values 448 | 449 | other_1s_err = chron.createVariable('other_1s_err', 'f4', ('depth_top',)) 450 | other_1s_err.long_name = 'Other date 1-sigma error' 451 | other_1s_err.missing_value = np.nan 452 | other_1s_err[:] = self.chronology_information.df['other_1s_err'].values 453 | 454 | other_type = chron.createVariable('other_type', 'S1', ('depth_top', 'str_dim')) 455 | other_type.long_name = 'Other date type' 456 | other_type.missing_value = 'NA' 457 | other_type._Encoding = 'ascii' 458 | other_type[:] = _normalize_to_ascii_array(self.chronology_information.df['other_type'].fillna('NA')) 459 | 460 | # Add depth cutoff value attributes to chronology group if 461 | # self.chronology_information has `cut_shallow` and `cut_deep` attributes. 462 | if hasattr(self.chronology_information, 'cut_shallow'): 463 | chron.cut_shallow = self.chronology_information.cut_shallow 464 | if hasattr(self.chronology_information, 'cut_deep'): 465 | chron.cut_deep = self.chronology_information.cut_deep 466 | 467 | return chron 468 | 469 | def _attach_data_ncgroup(self, parent): 470 | """Create and populate data group""" 471 | data = parent.createGroup('data') 472 | data.createDimension('depth', None) 473 | depth = data.createVariable('depth', 'f4', ('depth',), zlib=True) 474 | depth.long_name = 'Sample depth' 475 | depth.positive = 'down' 476 | depth.axis = 'Z' 477 | depth[:] = self.data.df['depth'].values 478 | 479 | file_depth_unit = str(self.variables['depth'].units) 480 | if file_depth_unit == '' or file_depth_unit is None: 481 | depth.units = 'cm' 482 | else: 483 | depth.units = file_depth_unit 484 | 485 | 486 | age_original = data.createVariable('age_original', 'f4', ('depth',), 487 | zlib=True) 488 | age_original.missing_value = np.nan 489 | age_original.long_name = 'Original age' 490 | age_original[:] = self.data.df['age'].values 491 | 492 | file_age_unit = str(self.variables['age'].units) 493 | if file_age_unit == '' or file_age_unit is None: 494 | age_original.units = 'cal years BP' 495 | else: 496 | age_original.units = file_age_unit 497 | 498 | if hasattr(self.data, 'age_ensemble') and hasattr(self.data, 'age_median'): 499 | data.createDimension('draw', self.data.age_ensemble.shape[1]) 500 | 501 | age_median = data.createVariable('age_median', 'f4', ('depth',), 502 | zlib=True) 503 | age_median.units = 'cal years BP' 504 | age_median.long_name = 'Median age' 505 | age_median.missing_value = np.nan 506 | age_median[:] = self.data.age_median['age_median'].values 507 | 508 | agedraw = data.createVariable('age_ensemble', 'f4', ('depth', 'draw'), 509 | zlib=True) 510 | agedraw.units = 'cal years BP' 511 | agedraw.long_name = 'Age ensemble' 512 | agedraw.missing_value = np.nan 513 | agedraw[:] = self.data.age_ensemble.values 514 | 515 | for col in list(self.data.df.columns): 516 | col_name = col.lower() 517 | 518 | if col_name in ['depth', 'age']: 519 | continue 520 | 521 | var = data.createVariable(col_name, 'f4', ('depth',), zlib=True) 522 | var.missing_value = np.nan 523 | 524 | # Add more attributes to variable. 525 | attrib_dict = self._variable_attributes(col_name) 526 | for k, v in attrib_dict.items(): 527 | setattr(var, k, v) 528 | 529 | # Overwrite units attributes with whatever units are given in the NcdcRecord. 530 | var.units = str(self.variables[col].units) 531 | var.comments = str(self.variables[col].detail) 532 | 533 | # Grab Mg/Ca cleaning information from "Data Collection Information - Notes" 534 | if 'mgca' in col_name: 535 | cleaning_note = str(self.data_collection.notes) 536 | if 'mg_bcp' in cleaning_note: 537 | var.mgca_cleaning_protocol = 'Barker cleaning with hydrogen peroxide' 538 | elif 'mg_red' in cleaning_note: 539 | var.mgca_cleaning_protocol = 'Fully reductive cleaning' 540 | else: 541 | var.mgca_cleaning_protocol = 'NA' 542 | var[:] = self.data.df[col].values 543 | return data 544 | 545 | def _attach_ncgroups(self, fl): 546 | """Dump contents into netCDF4.Dataset 547 | 548 | This is run whenever self.to_netcdf() is called. 549 | 550 | This runs all of the self._attach_*ncgroup() methods and attaches them 551 | to a netcdf4.Dataset object. 552 | """ 553 | site_group = self._attach_site_ncgroup(fl) 554 | # Create and populate chronology group, if chronology_information exists 555 | if not self.chronology_information.df.empty: 556 | self._attach_chronology_ncgroup(site_group) 557 | self._attach_data_ncgroup(site_group) 558 | 559 | def to_netcdf(self, path_or_buffer): 560 | """Write NcdcRecord contents to a netCDF file 561 | """ 562 | if isinstance(path_or_buffer, str): 563 | # Append to file, if it exists, if doesn't exist, create file. 564 | try: 565 | with netCDF4.Dataset(filename=path_or_buffer, mode='a', format='NETCDF4') as fl: 566 | self._attach_ncgroups(fl) 567 | except FileNotFoundError: 568 | with netCDF4.Dataset(filename=path_or_buffer, mode='w', format='NETCDF4') as fl: 569 | self._attach_ncgroups(fl) 570 | 571 | else: 572 | self._attach_ncgroups(path_or_buffer) 573 | 574 | 575 | class QcPlotMixin: 576 | """Mixins to add QC plot methods LGM proxy records""" 577 | 578 | @staticmethod 579 | def _ax_setup(*args, **kwargs): 580 | try: 581 | import matplotlib.pylab as plt 582 | except ModuleNotFoundError: 583 | raise ModuleNotFoundError('matplotlib needs to be installed for plots') 584 | 585 | return plt.gca(*args, **kwargs) 586 | 587 | def plot_datavariable(self, variable, ax=None): 588 | """ 589 | Plot a variable in the record data as timeseries. 590 | 591 | The plot also compares the variables from a redated age model with 592 | the original age model, if the record has been redated. 593 | 594 | Parameters 595 | ---------- 596 | variable : str 597 | Name of variable to plot. Must be in ``self.data``. 598 | ax : :class:`mpl.axes.Axes` or None, optional 599 | Existing axes to plot onto. 600 | 601 | Returns 602 | ------- 603 | ax : :class:`mpl.axes.Axes` 604 | 605 | """ 606 | if ax is None: 607 | ax = self._ax_setup() 608 | 609 | if variable not in self.data.df.columns: 610 | raise KeyError('{} not found'.format(variable)) 611 | 612 | if hasattr(self.data, 'age_median'): 613 | proxy_df = (self.data.df.set_index('depth') 614 | .join(self.data.age_median, lsuffix='__', sort=True)) 615 | 616 | new_age = proxy_df.loc[:, ('age_median', variable)].dropna() 617 | ax.plot(new_age.loc[:, 'age_median'], new_age.loc[:, variable], '.', 618 | color='C3', label='MCMC median age') 619 | ax.plot(new_age.loc[:, 'age_median'], new_age.loc[:, variable], 620 | color='C3', linewidth=0.5, label='_nolegend_') 621 | log.debug('Found new agemodel proxy timeseries') 622 | else: 623 | proxy_df = self.data.df.set_index('depth') 624 | log.debug('Assuming no new agemodel proxy timeseries') 625 | 626 | old_age = proxy_df.loc[:, ('age', variable)].dropna() 627 | ax.plot(old_age.loc[:, 'age'], old_age.loc[:, variable], 'x', 628 | color='C0', label='File age') 629 | ax.plot(old_age.loc[:, 'age'], old_age.loc[:, variable], 630 | color='C0', linewidth=0.5, label='_nolegend_') 631 | 632 | if 'd18o' in variable.lower(): 633 | ax.invert_yaxis() 634 | ax.set_ylabel(variable) 635 | ax.grid() 636 | 637 | return ax 638 | 639 | def plot_sitemap(self, ax=None): 640 | """ 641 | Plot sample site map using cartopy. 642 | 643 | Requires ``cartopy`` to be installed. Uses the site's northmost latitude 644 | and easternmost longitude to plot. So, we assume 645 | ``self.site_information.northernmost_latitude`` and 646 | ``self.site_information.easternmost_longitude`` are populated. 647 | 648 | Parameters 649 | ---------- 650 | ax : :class:`mpl.axes.Axes` or None, optional 651 | Existing axes to plot onto. 652 | 653 | Returns 654 | ------- 655 | ax : :class:`mpl.axes.Axes` 656 | 657 | """ 658 | try: 659 | import cartopy.crs as ccrs 660 | import cartopy.feature as cfeature 661 | except ModuleNotFoundError: 662 | raise ModuleNotFoundError('cartopy needs to be installed for mapping') 663 | 664 | latlon = (self.site_information.northernmost_latitude, 665 | self.site_information.easternmost_longitude) 666 | 667 | if ax is None: 668 | ax = self._ax_setup(projection=ccrs.Robinson(central_longitude=latlon[1])) 669 | 670 | ax.set_global() 671 | ax.add_feature(cfeature.LAND, facecolor='#B0B0B0') 672 | ax.outline_patch.set_linewidth(0.5) 673 | ax.plot(latlon[1], latlon[0], 'o', color='C0', transform=ccrs.Geodetic()) 674 | 675 | return ax 676 | 677 | def plot_sedrate(self, ax=None): 678 | """ 679 | Plot prior and posterior sediment rates for record agemodel. 680 | 681 | Requires ``self.chronology_information.bacon_agemodel` to be populated 682 | with a ``snakebacon.AgeDepthModel``-like instance. You can do this with 683 | :method:`self.redateredated()`, for example. 684 | 685 | Parameters 686 | ---------- 687 | ax : :class:`mpl.axes.Axes` or None, optional 688 | Existing axes to plot onto. 689 | 690 | Returns 691 | ------- 692 | ax : :class:`mpl.axes.Axes` 693 | 694 | """ 695 | if ax is None: 696 | ax = self._ax_setup() 697 | 698 | ax = self.chronology_information.bacon_agemodel.plot_sediment_rate(ax) 699 | ax.lines[-1].set_color('C3') 700 | 701 | return ax 702 | 703 | def plot_sedmemory(self, ax=None): 704 | """ 705 | Plot prior and posterior sediment memory for record agemodel. 706 | 707 | Requires ``self.chronology_information.bacon_agemodel` to be populated 708 | with a ``snakebacon.AgeDepthModel``-like instance. You can do this with 709 | :method:`self.redateredated()`, for example. 710 | 711 | Parameters 712 | ---------- 713 | ax : :class:`mpl.axes.Axes` or None, optional 714 | Existing axes to plot onto. 715 | 716 | Returns 717 | ------- 718 | ax : :class:`mpl.axes.Axes` 719 | 720 | """ 721 | if ax is None: 722 | ax = self._ax_setup() 723 | 724 | ax = self.chronology_information.bacon_agemodel.plot_sediment_memory(ax) 725 | ax.lines[-1].set_color('C3') 726 | 727 | return ax 728 | 729 | def plot_agedepth(self, maxage=None, prior_dwidth=30, ax=None): 730 | """ 731 | Plot age models in relation to core depth. 732 | 733 | Parameters 734 | ---------- 735 | maxage : float, int, or None, optional 736 | Cutoff age for the plot age model. 737 | prior_dwidth : int, optional 738 | Passed to :method:`snakebacon.AgeDepthModel.plot_prior_dates`. 739 | ax : :class:`mpl.axes.Axes` or None, optional 740 | Existing axes to plot onto. 741 | 742 | Returns 743 | ------- 744 | ax : :class:`mpl.axes.Axes` 745 | 746 | """ 747 | if ax is None: 748 | ax = self._ax_setup() 749 | 750 | agemodel = self.chronology_information.bacon_agemodel 751 | data_df = self.data.df 752 | # Hack to copy and crop the age model to a certain age. 753 | if maxage is not None: 754 | agemodel = deepcopy(agemodel) 755 | too_old = ~(agemodel.age_median() > maxage) 756 | agemodel._depth = agemodel.depth[too_old] 757 | agemodel._age_ensemble = agemodel.age_ensemble[too_old] 758 | 759 | # data_df = self.data.df.copy() 760 | # data_df = data_df.loc[data_df['age'] <= maxage, ('depth', 'age')] 761 | 762 | if len(agemodel._depth) > 0: 763 | # Skip age model plotting if maxage cut-out all samples. 764 | ax = agemodel.plot(ax=ax) 765 | ax.collections[-1].set_cmap('Greys') 766 | 767 | for l in ax.lines: 768 | l.set_color('C3') 769 | 770 | ax.plot(data_df.loc[:, 'depth'], data_df.loc[:, 'age'], 'C0', 771 | label='File age model') 772 | ax = agemodel.plot_prior_dates(dwidth=prior_dwidth, ax=ax) 773 | ax.collections[-1].set_color('k') 774 | ax.collections[-1].set_zorder(10) 775 | 776 | ax.autoscale_view() 777 | else: 778 | log.warning('No data age-depth data to plot') 779 | 780 | # Cut cut-off information, if available. 781 | if hasattr(self.chronology_information, 'cut_shallow'): 782 | ax.axvline(x=float(self.chronology_information.cut_shallow), color='C4', 783 | linestyle='-.', zorder=1.5) 784 | if hasattr(self.chronology_information, 'cut_deep'): 785 | ax.axvline(x=float(self.chronology_information.cut_deep), color='C4', 786 | linestyle='-.', zorder=1.5) 787 | 788 | ax.set_title('Age model') 789 | 790 | return ax 791 | 792 | def plot_deltar(self, ax=None): 793 | """ 794 | Plot a description of the site carbon reservoir information. 795 | 796 | Parameters 797 | ---------- 798 | ax : :class:`mpl.axes.Axes` or None, optional 799 | Existing axes to plot onto. 800 | 801 | Returns 802 | ------- 803 | ax : :class:`mpl.axes.Axes` 804 | 805 | """ 806 | if ax is None: 807 | ax = self._ax_setup() 808 | 809 | latlon = (self.site_information.northernmost_latitude, 810 | self.site_information.easternmost_longitude) 811 | 812 | elevation = self.site_information.elevation 813 | 814 | # These checks are not well written. 815 | try: 816 | deltar_original = np.int(np.round(self.chronology_information.df['delta_R_original'].values[0])) 817 | if np.isnan(deltar_original): 818 | deltar_original = None 819 | except (KeyError, ValueError, IndexError) as e: 820 | deltar_original = None 821 | 822 | try: 823 | deltar_std_original = np.int(np.round(self.chronology_information.df['delta_R_1s_err_original'].values[0])) 824 | if np.isnan(deltar_std_original): 825 | deltar_std_original = None 826 | except (KeyError, ValueError, IndexError) as e: 827 | deltar_std_original = None 828 | 829 | try: 830 | deltar_used = np.int(np.round(self.chronology_information.df['delta_R'].values[0])) 831 | except (KeyError, TypeError): 832 | deltar_used = None 833 | 834 | try: 835 | deltar_error_used = np.int(np.round(self.chronology_information.df['delta_R_1s_err'].values[0])) 836 | except (KeyError, TypeError): 837 | deltar_error_used = None 838 | 839 | text_template = 'Latitude: {}°\nLongitude: {}°\nElevation: {} m ' \ 840 | '\n\nΔR: {}\nΔRσ: {}\nFile ΔR: {}\nFile ΔRσ: {}' 841 | text_str = text_template.format(latlon[0], latlon[1], elevation, 842 | deltar_used, deltar_error_used, 843 | deltar_original, deltar_std_original) 844 | 845 | ax.text(0.05, 0.9, text_str, verticalalignment='top', 846 | horizontalalignment='left', transform=ax.transAxes) 847 | ax.set_title('{}\n{}'.format(self.site_information.site_name, datetime.date.today().isoformat())) 848 | ax.axis('off') 849 | 850 | return ax 851 | 852 | def to_qcpdf(self, pdfpath, proxy_vars=None, plot_agedepth_kws=None): 853 | """ 854 | Write quality-control report PDF. 855 | 856 | Requires :module:`matplotlib` and :module:`cartopy` to be installed. 857 | 858 | Parameters 859 | ---------- 860 | pdfpath : str 861 | Path to write PDF to. 862 | proxy_vars : iterable or None, optional 863 | Name of series to include in time series plot. Attempts to use all 864 | available proxies if ``None``. 865 | plot_agedepth_kws : dict or None, optional 866 | Key-word arguments to pass to both call to ``self.plot_agedepth`` 867 | when plotting. 868 | """ 869 | log.debug('Writing QC report plots') 870 | 871 | try: 872 | from matplotlib.backends.backend_pdf import PdfPages 873 | import matplotlib.pylab as plt 874 | except ModuleNotFoundError: 875 | raise ModuleNotFoundError('matplotlib needs to be installed for plots') 876 | 877 | try: 878 | import cartopy.crs as ccrs 879 | except ModuleNotFoundError: 880 | raise ModuleNotFoundError('cartopy needs to be installed for mapping') 881 | 882 | if plot_agedepth_kws is None: 883 | plot_agedepth_kws = {} 884 | 885 | # Find "non-dimension" data variables to plot, if none were passed. 886 | not_proxy = ['age', 'age_median', 'depth', 'age_ensemble'] 887 | if proxy_vars is None: 888 | # TODO(brews): This logic might be good candidate for a more general method. 889 | proxy_vars = [str(x) for x in self.data.df.columns if str(x).lower() not in not_proxy] 890 | 891 | latlon = (self.site_information.northernmost_latitude, 892 | self.site_information.easternmost_longitude) 893 | 894 | n_vars = len(proxy_vars) 895 | n_cols = n_vars + 1 896 | 897 | has_baconagemodel = hasattr(self.chronology_information, 'bacon_agemodel') 898 | 899 | with PdfPages(pdfpath) as pdf: 900 | fig = plt.figure(figsize=(6.5, 9)) 901 | 902 | ax2 = plt.subplot2grid((n_cols, 2), (0, 1), 903 | projection=ccrs.Robinson(central_longitude=latlon[1])) 904 | ax3 = plt.subplot2grid((n_cols, 2), (0, 0)) 905 | 906 | self.plot_sitemap(ax=ax2) 907 | 908 | self.plot_deltar(ax=ax3) 909 | 910 | for i, varstr in enumerate(proxy_vars): 911 | this_ax = plt.subplot2grid((n_cols, 1), (1 + i, 0), colspan=2) 912 | this_ax = self.plot_datavariable(varstr, ax=this_ax) 913 | this_ax.xaxis.label.set_visible(False) 914 | this_ax.title.set_visible(False) 915 | if i == 0: 916 | this_ax.title.set_visible(True) 917 | this_ax.set_title('Proxy variables') 918 | 919 | this_ax.xaxis.label.set_visible(True) 920 | this_ax.set_xlabel('Age (cal yr BP)') 921 | fig.tight_layout() 922 | pdf.savefig(bbox_inches='tight') 923 | plt.close() 924 | 925 | fig = plt.figure(figsize=(6.5, 9)) 926 | ax1 = plt.subplot2grid((3, 2), (0, 0)) 927 | ax2 = plt.subplot2grid((3, 2), (0, 1)) 928 | ax4 = plt.subplot2grid((3, 2), (1, 0), rowspan=2, colspan=2) 929 | 930 | if has_baconagemodel: 931 | self.plot_sedrate(ax=ax1) 932 | self.plot_sedmemory(ax=ax2) 933 | self.plot_agedepth(maxage=50000, ax=ax4, **plot_agedepth_kws) 934 | 935 | fig.tight_layout() 936 | pdf.savefig(bbox_inches='tight') 937 | plt.close() 938 | 939 | fig = plt.figure(figsize=(6.5, 9)) 940 | ax1 = plt.subplot(1, 1, 1) 941 | if has_baconagemodel: 942 | self.plot_agedepth(maxage=25000, ax=ax1, **plot_agedepth_kws) 943 | fig.tight_layout() 944 | pdf.savefig(bbox_inches='tight') 945 | plt.close() 946 | 947 | log.debug('QC report plot saved to {}'.format(pdfpath)) 948 | --------------------------------------------------------------------------------