pastastore 1.2.2__tar.gz → 1.4.0__tar.gz

{pastastore-1.2.2 → pastastore-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pastastore
-Version: 1.2.2
+Version: 1.4.0
 Summary: Tools for managing Pastas time series models.
 Author: D.A. Brakenhoff
 Maintainer-email: "D.A. Brakenhoff" <d.brakenhoff@artesia-water.nl>, "R. Calje" <r.calje@artesia-water.nl>, "M.A. Vonk" <m.vonk@artesia-water.nl>
@@ -49,15 +49,47 @@ Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Scientific/Engineering :: Hydrology
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pastas>=0.13
+Requires-Dist: tqdm>=4.36
+Requires-Dist: pyyaml
 Provides-Extra: full
+Requires-Dist: pastastore[arcticdb,optional]; extra == "full"
 Provides-Extra: lint
+Requires-Dist: black; extra == "lint"
+Requires-Dist: flake8; extra == "lint"
+Requires-Dist: isort; extra == "lint"
 Provides-Extra: optional
+Requires-Dist: contextily; extra == "optional"
+Requires-Dist: pyproj; extra == "optional"
+Requires-Dist: adjustText; extra == "optional"
 Provides-Extra: test
+Requires-Dist: pastastore[arcticdb,lint,optional]; extra == "test"
+Requires-Dist: hydropandas[full]; extra == "test"
+Requires-Dist: coverage; extra == "test"
+Requires-Dist: codecov; extra == "test"
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: pytest-cov; extra == "test"
+Requires-Dist: pytest-dependency; extra == "test"
+Requires-Dist: pytest-benchmark; extra == "test"
+Requires-Dist: codacy-coverage; extra == "test"
+Requires-Dist: lxml; extra == "test"
 Provides-Extra: pystore
+Requires-Dist: fsspec>=0.3.3; extra == "pystore"
+Requires-Dist: python-snappy; extra == "pystore"
+Requires-Dist: dask[dataframe]; extra == "pystore"
 Provides-Extra: arctic
+Requires-Dist: arctic; extra == "arctic"
 Provides-Extra: arcticdb
+Requires-Dist: arcticdb; extra == "arcticdb"
+Requires-Dist: protobuf~=4.0; extra == "arcticdb"
 Provides-Extra: docs
-License-File: LICENSE
+Requires-Dist: pastastore[optional]; extra == "docs"
+Requires-Dist: sphinx_rtd_theme; extra == "docs"
+Requires-Dist: Ipython; extra == "docs"
+Requires-Dist: ipykernel; extra == "docs"
+Requires-Dist: nbsphinx; extra == "docs"
+Requires-Dist: nbsphinx_link; extra == "docs"
 
 ![pastastore](https://github.com/pastas/pastastore/workflows/pastastore/badge.svg)
 [![Documentation Status](https://readthedocs.org/projects/pastastore/badge/?version=latest)](https://pastastore.readthedocs.io/en/latest/?badge=latest)

pastastore-1.4.0/pastastore/__init__.py

@@ -0,0 +1,11 @@
+# ruff: noqa: F401
+from pastastore import connectors, styling, util
+from pastastore.connectors import (
+    ArcticConnector,
+    ArcticDBConnector,
+    DictConnector,
+    PasConnector,
+    PystoreConnector,
+)
+from pastastore.store import PastaStore
+from pastastore.version import __version__

{pastastore-1.2.2 → pastastore-1.4.0}/pastastore/base.py

@@ -11,10 +11,10 @@ import pastas as ps
 from numpy import isin
 from packaging.version import parse as parse_version
 from pastas.io.pas import PastasEncoder
-from tqdm import tqdm
+from tqdm.auto import tqdm
 
-from .util import ItemInLibraryException, _custom_warning, validate_names
-from .version import PASTAS_LEQ_022
+from pastastore.util import ItemInLibraryException, _custom_warning, validate_names
+from pastastore.version import PASTAS_LEQ_022
 
 FrameorSeriesUnion = Union[pd.DataFrame, pd.Series]
 warnings.showwarning = _custom_warning
@@ -934,13 +934,24 @@ class BaseConnector(ABC):
             )
             if ui.lower() != "y":
                 return
-        names = self._parse_names(None, libname)
-        for name in (
-            tqdm(names, desc=f"Deleting items from {libname}") if progressbar else names
-        ):
-            self._del_item(libname, name)
-        self._clear_cache(libname)
-        print(f"Emptied library {libname} in {self.name}: " f"{self.__class__}")
+
+        if libname == "models":
+            # also delete linked modelnames linked to oseries
+            libs = ["models", "oseries_models"]
+        else:
+            libs = [libname]
+
+        # delete items and clear caches
+        for libname in libs:
+            names = self._parse_names(None, libname)
+            for name in (
+                tqdm(names, desc=f"Deleting items from {libname}")
+                if progressbar
+                else names
+            ):
+                self._del_item(libname, name)
+            self._clear_cache(libname)
+            print(f"Emptied library {libname} in {self.name}: " f"{self.__class__}")
 
     def _iter_series(self, libname: str, names: Optional[List[str]] = None):
         """Internal method iterate over time series in library.

{pastastore-1.2.2 → pastastore-1.4.0}/pastastore/connectors.py

@@ -8,8 +8,8 @@ from typing import Dict, Optional, Union
 import pandas as pd
 from pastas.io.pas import PastasEncoder, pastas_hook
 
-from .base import BaseConnector, ConnectorUtil, ModelAccessor
-from .util import _custom_warning
+from pastastore.base import BaseConnector, ConnectorUtil, ModelAccessor
+from pastastore.util import _custom_warning
 
 FrameorSeriesUnion = Union[pd.DataFrame, pd.Series]
 warnings.showwarning = _custom_warning

{pastastore-1.2.2 → pastastore-1.4.0}/pastastore/plotting.py

@@ -15,8 +15,6 @@ follows::
     pstore.maps.add_background_map(ax)  # for adding a background map
 """
 
-from collections.abc import Iterable
-
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
@@ -52,6 +50,9 @@ class Plots:
         split=False,
         figsize=(10, 5),
         progressbar=True,
+        show_legend=True,
+        labelfunc=None,
+        legend_kwargs=None,
         **kwargs,
     ):
         """Internal method to plot time series from pastastore.
@@ -74,6 +75,13 @@ class Plots:
         progressbar : bool, optional
             show progressbar when loading time series from store,
             by default True
+        show_legend : bool, optional
+            show legend, default is True.
+        labelfunc : callable, optional
+            function to create custom labels, function should take name of time series
+            as input
+        legend_kwargs : dict, optional
+            additional arguments to pass to legend
 
         Returns
         -------
@@ -96,15 +104,11 @@ class Plots:
 
         if ax is None:
             if split:
-                fig, axes = plt.subplots(len(names), 1, sharex=True, figsize=figsize)
+                _, axes = plt.subplots(len(names), 1, sharex=True, figsize=figsize)
             else:
-                fig, axes = plt.subplots(1, 1, figsize=figsize)
+                _, axes = plt.subplots(1, 1, figsize=figsize)
         else:
             axes = ax
-            if isinstance(axes, Iterable):
-                fig = axes[0].figure
-            else:
-                fig = axes.figure
 
         tsdict = self.pstore.conn._get_series(
             libname, names, progressbar=progressbar, squeeze=False
@@ -116,16 +120,33 @@ class Plots:
                 iax = axes
             else:
                 iax = ax
+            if labelfunc is not None:
+                n = labelfunc(n)
             iax.plot(ts.index, ts.squeeze(), label=n, **kwargs)
-            if split:
+
+            if split and show_legend:
                 iax.legend(loc="best", fontsize="x-small")
 
-        if not split:
-            axes.legend(loc=(0, 1), frameon=False, ncol=7, fontsize="x-small")
+        if not split and show_legend:
+            if legend_kwargs is None:
+                legend_kwargs = {}
+            ncol = legend_kwargs.pop("ncol", 7)
+            fontsize = legend_kwargs.pop("fontsize", "x-small")
+            axes.legend(loc=(0, 1), frameon=False, ncol=ncol, fontsize=fontsize)
 
         return axes
 
-    def oseries(self, names=None, ax=None, split=False, figsize=(10, 5), **kwargs):
+    def oseries(
+        self,
+        names=None,
+        ax=None,
+        split=False,
+        figsize=(10, 5),
+        show_legend=True,
+        labelfunc=None,
+        legend_kwargs=None,
+        **kwargs,
+    ):
         """Plot oseries.
 
         Parameters
@@ -141,6 +162,13 @@ class Plots:
             A maximum of 20 time series is supported when split=True.
         figsize : tuple, optional
             figure size, by default (10, 5)
+        show_legend : bool, optional
+            show legend, default is True.
+        labelfunc : callable, optional
+            function to create custom labels, function should take name of time series
+            as input
+        legend_kwargs : dict, optional
+            additional arguments to pass to legend
 
         Returns
         -------
@@ -153,6 +181,9 @@ class Plots:
             ax=ax,
             split=split,
             figsize=figsize,
+            show_legend=show_legend,
+            labelfunc=labelfunc,
+            legend_kwargs=legend_kwargs,
             **kwargs,
         )
 
@@ -163,6 +194,9 @@ class Plots:
         ax=None,
         split=False,
         figsize=(10, 5),
+        show_legend=True,
+        labelfunc=None,
+        legend_kwargs=None,
         **kwargs,
     ):
         """Plot stresses.
@@ -183,6 +217,13 @@ class Plots:
             A maximum of 20 time series is supported when split=True.
         figsize : tuple, optional
             figure size, by default (10, 5)
+        show_legend : bool, optional
+            show legend, default is True.
+        labelfunc : callable, optional
+            function to create custom labels, function should take name of time series
+            as input
+        legend_kwargs : dict, optional
+            additional arguments to pass to legend
 
         Returns
         -------
@@ -203,6 +244,9 @@ class Plots:
             ax=ax,
             split=split,
             figsize=figsize,
+            show_legend=show_legend,
+            labelfunc=labelfunc,
+            legend_kwargs=legend_kwargs,
             **kwargs,
         )
 
@@ -397,20 +441,31 @@ class Plots:
                     linewidth=0,
                     rasterized=True,
                 )
+
         # make a colorbar in an ax on the
         # right side, then set the current axes to ax again
         cb = fig.colorbar(pc, ax=ax, cax=cax, extend="both")
         cb.set_ticks(bounds)
         cb.ax.set_yticklabels(labels)
         cb.ax.minorticks_off()
+
         if set_yticks:
-            ax.set_yticks(np.arange(0.5, len(series) + 0.5))
+            ax.set_yticks(np.arange(0.5, len(series) + 0.5), minor=False)
+            ax.set_yticks(np.arange(0, len(series) + 1), minor=True)
             if names is None:
                 names = [s.name for s in series]
             ax.set_yticklabels(names)
+
+            for tick in ax.yaxis.get_major_ticks():  # don't show major ytick marker
+                tick.tick1line.set_visible(False)
+
+            ax.grid(True, which="minor", axis="y")
+            ax.grid(True, which="major", axis="x")
+
         else:
             ax.set_ylabel("Timeseries (-)")
-        ax.grid(True)
+            ax.grid(True, which="both")
+            ax.grid(True, which="both")
 
         return ax
 
@@ -507,6 +562,22 @@ class Plots:
 
         return ax
 
+    def compare_models(self, modelnames, ax=None, **kwargs):
+        models = self.pstore.get_models(modelnames)
+        names = []
+        onames = [iml.oseries.name for iml in models]
+        if len(np.unique(onames)) == 1:
+            for modelname in modelnames:
+                if onames[0] in modelname:
+                    names.append(modelname.replace(onames[0], ""))
+                else:
+                    names.append(modelname)
+        else:
+            names = modelnames
+        cm = ps.CompareModels(models, names=names)
+        cm.plot(**kwargs)
+        return cm
+
 
 class Maps:
     """Map Class for PastaStore.
@@ -535,10 +606,12 @@ class Maps:
         self,
         names=None,
         kind=None,
+        extent=None,
         labels=True,
         adjust=False,
         figsize=(10, 8),
         backgroundmap=False,
+        label_kwargs=None,
         **kwargs,
     ):
         """Plot stresses locations on map.
@@ -550,6 +623,8 @@ class Maps:
         kind: str, optional
             if passed, only plot stresses of a specific kind, default is None
             which plots all stresses.
+        extent : list of float, optional
+            plot only stresses within extent [xmin, xmax, ymin, ymax]
         labels: bool, optional
             label models, by default True
         adjust: bool, optional
@@ -561,6 +636,8 @@ class Maps:
         backgroundmap: bool, optional
             if True, add background map (default CRS is EPSG:28992) with default tiles
             by OpenStreetMap.Mapnik. Default option is False.
+        label_kwargs: dict, optional
+            dictionary with keyword arguments to pass to add_labels method
 
         Returns
         -------
@@ -571,10 +648,10 @@ class Maps:
         --------
         self.add_background_map
         """
-        if names is not None:
-            df = self.pstore.stresses.loc[names]
-        else:
-            df = self.pstore.stresses
+        names = self.pstore.conn._parse_names(names, "stresses")
+        if extent is not None:
+            names = self.pstore.within(extent, names=names, libname="stresses")
+        df = self.pstore.stresses.loc[names]
 
         if kind is not None:
             if isinstance(kind, str):
@@ -599,7 +676,9 @@ class Maps:
         else:
             ax = r
         if labels:
-            self.add_labels(stresses, ax, adjust=adjust)
+            if label_kwargs is None:
+                label_kwargs = {}
+            self.add_labels(stresses, ax, adjust=adjust, **label_kwargs)
 
         if backgroundmap:
             self.add_background_map(ax)
@@ -609,10 +688,12 @@ class Maps:
     def oseries(
         self,
         names=None,
+        extent=None,
         labels=True,
         adjust=False,
         figsize=(10, 8),
         backgroundmap=False,
+        label_kwargs=None,
         **kwargs,
     ):
         """Plot oseries locations on map.
@@ -621,8 +702,11 @@ class Maps:
         ----------
         names: list, optional
             oseries names, by default None which plots all oseries locations
-        labels: bool, optional
-            label models, by default True
+        extent : list of float, optional
+            plot only oseries within extent [xmin, xmax, ymin, ymax]
+        labels: bool or str, optional
+            label models, by default True, if passed as "grouped", only the first
+            label for each x,y-location is shown.
         adjust: bool, optional
             automated smart label placement using adjustText, by default False
         figsize: tuple, optional
@@ -630,6 +714,8 @@ class Maps:
         backgroundmap: bool, optional
             if True, add background map (default CRS is EPSG:28992) with default tiles
             by OpenStreetMap.Mapnik. Default option is False.
+        label_kwargs: dict, optional
+            dictionary with keyword arguments to pass to add_labels method
 
         Returns
         -------
@@ -642,6 +728,8 @@ class Maps:
         """
 
         names = self.pstore.conn._parse_names(names, "oseries")
+        if extent is not None:
+            names = self.pstore.within(extent, names=names)
         oseries = self.pstore.oseries.loc[names]
         mask0 = (oseries["x"] != 0.0) | (oseries["y"] != 0.0)
         r = self._plotmap_dataframe(oseries.loc[mask0], figsize=figsize, **kwargs)
@@ -650,7 +738,12 @@ class Maps:
         else:
             ax = r
         if labels:
-            self.add_labels(oseries, ax, adjust=adjust)
+            if label_kwargs is None:
+                label_kwargs = {}
+            if labels == "grouped":
+                gr = oseries.sort_index().reset_index().groupby(["x", "y"])
+                oseries = oseries.loc[gr["index"].first().tolist()]
+            self.add_labels(oseries, ax, adjust=adjust, **label_kwargs)
 
         if backgroundmap:
             self.add_background_map(ax)
@@ -712,6 +805,7 @@ class Maps:
     def modelstat(
         self,
         statistic,
+        modelnames=None,
         label=True,
         adjust=False,
         cmap="viridis",
@@ -728,6 +822,8 @@ class Maps:
         ----------
         statistic: str
             name of the statistic, e.g. "evp" or "aic"
+        modelnames : list of str, optional
+            list of modelnames to include
         label: bool, optional
             label points, by default True
         adjust: bool, optional
@@ -757,7 +853,9 @@ class Maps:
         --------
         self.add_background_map
         """
-        statsdf = self.pstore.get_statistics([statistic], progressbar=False).to_frame()
+        statsdf = self.pstore.get_statistics(
+            [statistic], modelnames=modelnames, progressbar=False
+        ).to_frame()
 
         statsdf["oseries"] = [
             self.pstore.get_models(m, return_dict=True)["oseries"]["name"]
@@ -1249,7 +1347,7 @@ class Maps:
         ctx.add_basemap(ax, source=providers[map_provider], crs=proj.srs, **kwargs)
 
     @staticmethod
-    def add_labels(df, ax, adjust=False, **kwargs):
+    def add_labels(df, ax, adjust=False, objects=None, **kwargs):
         """Add labels to points on plot.
 
         Uses dataframe index to label points.
@@ -1262,11 +1360,12 @@ class Maps:
             axes object to label points on
         adjust: bool
             automated smart label placement using adjustText
+        objects : list of matplotlib objects
+            use to avoid labels overlapping markers
         **kwargs:
-            keyword arguments to ax.annotate
+            keyword arguments to ax.annotate or adjusttext
         """
         stroke = [patheffects.withStroke(linewidth=3, foreground="w")]
-
         fontsize = kwargs.pop("fontsize", 10)
 
         if adjust:
@@ -1286,7 +1385,9 @@ class Maps:
 
             adjust_text(
                 texts,
-                force_text=0.05,
+                objects=objects,
+                force_text=(0.05, 0.10),
+                **kwargs,
                 **{
                     "arrowprops": {
                         "arrowstyle": "-",
@@ -1309,4 +1410,5 @@ class Maps:
                     textcoords=textcoords,
                     xytext=xytext,
                     **{"path_effects": stroke},
+                    **kwargs,
                 )

{pastastore-1.2.2 → pastastore-1.4.0}/pastastore/store.py

@@ -8,11 +8,13 @@ import pandas as pd
 import pastas as ps
 from packaging.version import parse as parse_version
 from pastas.io.pas import pastas_hook
-from tqdm import tqdm
+from tqdm.auto import tqdm
 
-from .plotting import Maps, Plots
-from .util import _custom_warning
-from .yaml_interface import PastastoreYAML
+from pastastore.base import BaseConnector
+from pastastore.connectors import DictConnector
+from pastastore.plotting import Maps, Plots
+from pastastore.util import _custom_warning
+from pastastore.yaml_interface import PastastoreYAML
 
 FrameorSeriesUnion = Union[pd.DataFrame, pd.Series]
 warnings.showwarning = _custom_warning
@@ -38,14 +40,19 @@ class PastaStore:
         name of the PastaStore, by default takes the name of the Connector object
     """
 
-    def __init__(self, connector, name: str = None):
+    def __init__(
+        self,
+        connector: Optional[BaseConnector] = None,
+        name: Optional[str] = None,
+    ):
         """Initialize PastaStore for managing pastas time series and models.
 
         Parameters
         ----------
-        connector : Connector object
-            object that provides the interface to the
-            database
+        connector : Connector object, optional
+            object that provides the connection to the database. Default is None, which
+            will create a DictConnector. This default Connector does not store data on
+            disk.
         name : str, optional
             name of the PastaStore, if not provided uses the Connector name
         """
@@ -53,6 +60,8 @@ class PastaStore:
             raise DeprecationWarning(
                 "PastaStore expects the connector as the first argument since v1.1!"
             )
+        if connector is None:
+            connector = DictConnector("pastas_db")
         self.conn = connector
         self.name = name if name is not None else self.conn.name
         self._register_connector_methods()
@@ -300,6 +309,81 @@ class PastaStore:
             data = pd.concat([data, series], axis=0)
         return data
 
+    def get_signatures(
+        self,
+        signatures=None,
+        names=None,
+        libname="oseries",
+        progressbar=False,
+        ignore_errors=False,
+    ):
+        """Get groundwater signatures. NaN-values are returned when the
+        signature could not be computed.
+
+        Parameters
+        ----------
+        signatures : list of str, optional
+            list of groundwater signatures to compute, if None all groundwater
+            signatures in ps.stats.signatures.__all__ are used, by default None
+        names : str, list of str, or None, optional
+            names of the time series, by default None which
+            uses all the time series in the library
+        libname : str
+            name of the library containing the time series
+            ('oseries' or 'stresses'), by default "oseries"
+        progressbar : bool, optional
+            show progressbar, by default False
+        ignore_errors : bool, optional
+            ignore errors when True, i.e. when non-existent timeseries is
+            encountered in names, by default False
+
+        Returns
+        -------
+        signatures_df : pandas.DataFrame
+            DataFrame containing the signatures (columns) per time series (rows)
+        """
+        names = self.conn._parse_names(names, libname=libname)
+
+        if signatures is None:
+            signatures = ps.stats.signatures.__all__.copy()
+
+        # create dataframe for results
+        signatures_df = pd.DataFrame(index=names, columns=signatures, data=np.nan)
+
+        # loop through oseries names
+        desc = "Get groundwater signatures"
+        for name in tqdm(names, desc=desc) if progressbar else names:
+            try:
+                if libname == "oseries":
+                    s = self.conn.get_oseries(name)
+                else:
+                    s = self.conn.get_stresses(name)
+            except Exception as e:
+                if ignore_errors:
+                    signatures_df.loc[name, :] = np.nan
+                    continue
+                else:
+                    raise e
+
+            try:
+                i_signatures = ps.stats.signatures.summary(s.squeeze(), signatures)
+            except Exception as e:
+                if ignore_errors:
+                    i_signatures = []
+                    for signature in signatures:
+                        try:
+                            sign_val = getattr(ps.stats.signatures, signature)(
+                                s.squeeze()
+                            )
+                        except Exception as _:
+                            sign_val = np.nan
+                        i_signatures.append(sign_val)
+                else:
+                    raise e
+            signatures_df.loc[name, signatures] = i_signatures.squeeze()
+
+        return signatures_df
+
     def get_tmin_tmax(self, libname, names=None, progressbar=False):
         """Get tmin and tmax for time series.
 
@@ -334,6 +418,23 @@ class PastaStore:
             tmintmax.loc[n, "tmax"] = s.last_valid_index()
         return tmintmax
 
+    def get_extent(self, libname, names=None, buffer=0.0):
+        names = self.conn._parse_names(names, libname=libname)
+        if libname in ["oseries", "stresses"]:
+            df = getattr(self, libname)
+        elif libname == "models":
+            df = self.oseries
+        else:
+            raise ValueError(f"Cannot get extent for library '{libname}'.")
+
+        extent = [
+            df.loc[names, "x"].min() - buffer,
+            df.loc[names, "x"].max() + buffer,
+            df.loc[names, "y"].min() - buffer,
+            df.loc[names, "y"].max() + buffer,
+        ]
+        return extent
+
     def get_parameters(
         self,
         parameters: Optional[List[str]] = None,
@@ -428,13 +529,13 @@ class PastaStore:
 
         modelnames = self.conn._parse_names(modelnames, libname="models")
 
-        # create dataframe for results
-        s = pd.DataFrame(index=modelnames, columns=statistics, data=np.nan)
-
         # if statistics is str
         if isinstance(statistics, str):
             statistics = [statistics]
 
+        # create dataframe for results
+        s = pd.DataFrame(index=modelnames, columns=statistics, data=np.nan)
+
         # loop through model names
         desc = "Get model statistics"
         for mlname in tqdm(modelnames, desc=desc) if progressbar else modelnames:
@@ -836,7 +937,7 @@ class PastaStore:
     def from_zip(
         cls,
         fname: str,
-        conn,
+        conn: Optional[BaseConnector] = None,
         storename: Optional[str] = None,
         progressbar: bool = True,
     ):
@@ -846,8 +947,9 @@ class PastaStore:
         ----------
         fname : str
             pathname of zipfile
-        conn : Connector object
-            connector for storing loaded data
+        conn : Connector object, optional
+            connector for storing loaded data, default is None which creates a
+            DictConnector. This Connector does not store data on disk.
         storename : str, optional
             name of the PastaStore, by default None, which
             defaults to the name of the Connector.
@@ -861,6 +963,9 @@ class PastaStore:
         """
         from zipfile import ZipFile
 
+        if conn is None:
+            conn = DictConnector("pastas_db")
+
         with ZipFile(fname, "r") as archive:
             namelist = [
                 fi for fi in archive.namelist() if not fi.endswith("_meta.json")
@@ -868,7 +973,7 @@ class PastaStore:
             for f in tqdm(namelist, desc="Reading zip") if progressbar else namelist:
                 libname, fjson = os.path.split(f)
                 if libname in ["stresses", "oseries"]:
-                    s = pd.read_json(archive.open(f), orient="columns")
+                    s = pd.read_json(archive.open(f), dtype=float, orient="columns")
                     if not isinstance(s.index, pd.DatetimeIndex):
                         s.index = pd.to_datetime(s.index, unit="ms")
                     s = s.sort_index()
@@ -886,8 +991,9 @@ class PastaStore:
         libname: str,
         s: Optional[Union[list, str]] = None,
         case_sensitive: bool = True,
+        sort=True,
     ):
-        """Search for names of time series or models starting with s.
+        """Search for names of time series or models starting with `s`.
 
         Parameters
         ----------
@@ -897,6 +1003,8 @@ class PastaStore:
             find names with part of this string or strings in list
         case_sensitive : bool, optional
             whether search should be case sensitive, by default True
+        sort : bool, optional
+            sort list of names
 
         Returns
         -------
@@ -926,7 +1034,8 @@ class PastaStore:
                 else:
                     m = np.append(m, [n for n in lib_names if sub.lower() in n.lower()])
             matches = list(np.unique(m))
-
+        if sort:
+            matches.sort()
         return matches
 
     def get_model_timeseries_names(
@@ -983,9 +1092,75 @@ class PastaStore:
                     structure.loc[mlnam, pnam] = 1
                     structure.loc[mlnam, enam] = 1
                 elif "stress" in sm:
-                    for s in sm["stress"]:
+                    smstress = sm["stress"]
+                    if isinstance(smstress, dict):
+                        smstress = [smstress]
+                    for s in smstress:
                         structure.loc[mlnam, s["name"]] = 1
         if dropna:
             return structure.dropna(how="all", axis=1)
         else:
             return structure
+
+    def apply(self, libname, func, names=None, progressbar=True):
+        """Apply function to items in library.
+
+        Supported libraries are oseries, stresses, and models.
+
+        Parameters
+        ----------
+        libname : str
+            library name, supports "oseries", "stresses" and "models"
+        func : callable
+            function that accepts items from one of the supported libraries as input
+        names : str, list of str, optional
+            apply function to these names, by default None which loops over all stored
+            items in library
+        progressbar : bool, optional
+            show progressbar, by default True
+
+        Returns
+        -------
+        dict
+            dict of results of func, with names as keys and results as values
+        """
+        names = self.conn._parse_names(names, libname)
+        result = {}
+        if libname not in ("oseries", "stresses", "models"):
+            raise ValueError(
+                "'libname' must be one of ['oseries', 'stresses', 'models']!"
+            )
+        getter = getattr(self.conn, f"get_{libname}")
+        for n in (
+            tqdm(names, desc=f"Applying {func.__name__}") if progressbar else names
+        ):
+            result[n] = func(getter(n))
+        return result
+
+    def within(self, extent, names=None, libname="oseries"):
+        xmin, xmax, ymin, ymax = extent
+        names = self.conn._parse_names(names, libname)
+        if libname == "oseries":
+            df = self.oseries.loc[names]
+        elif libname == "stresses":
+            df = self.stresses.loc[names]
+        elif libname == "models":
+            onames = np.unique(
+                [
+                    self.get_models(modelname, return_dict=True)["oseries"]["name"]
+                    for modelname in names
+                ]
+            )
+            df = self.oseries.loc[onames]
+        else:
+            raise ValueError(
+                "libname must be one of ['oseries', 'stresses', 'models']"
+                f", got '{libname}'"
+            )
+        mask = (
+            (df["x"] <= xmax)
+            & (df["x"] >= xmin)
+            & (df["y"] >= ymin)
+            & (df["y"] <= ymax)
+        )
+        return df.loc[mask].index.tolist()

pastastore-1.4.0/pastastore/styling.py

@@ -0,0 +1,66 @@
+import matplotlib as mpl
+import matplotlib.pyplot as plt
+import numpy as np
+
+
+def float_styler(val, norm, cmap=None):
+    """Style float values in DataFrame.
+
+    Parameters
+    ----------
+    val : float
+        value in cell
+    norm : matplotlib.colors.Normalize
+        normalizer to map values to range(0, 1)
+    cmap : colormap, optional
+        colormap to use, by default None, which uses RdYlBu
+
+    Returns
+    -------
+    str
+        css value pairs for styling dataframe
+
+    Usage
+    -----
+    Given some dataframe
+
+    >>> df.map(float_styler, subset=["some column"], norm=norm, cmap=cmap)
+
+    """
+    if cmap is None:
+        cmap = plt.get_cmap("RdYlBu")
+    bg = cmap(norm(val))
+    color = mpl.colors.rgb2hex(bg)
+    c = "White" if np.mean(bg[:3]) < 0.4 else "Black"
+    return f"background-color: {color}; color: {c}"
+
+
+def boolean_styler(b):
+    """Style boolean values in DataFrame.
+
+    Parameters
+    ----------
+    b : bool
+        value in cell
+
+    Returns
+    -------
+    str
+        css value pairs for styling dataframe
+
+    Usage
+    -----
+    Given some dataframe
+
+    >>> df.map(boolean_styler, subset=["some column"])
+    """
+    if b:
+        return (
+            f"background-color: {mpl.colors.rgb2hex((231/255, 255/255, 239/255))}; "
+            "color: darkgreen"
+        )
+    else:
+        return (
+            f"background-color: {mpl.colors.rgb2hex((255/255, 238/255, 238/255))}; "
+            "color: darkred"
+        )

{pastastore-1.2.2 → pastastore-1.4.0}/pastastore/util.py

@@ -6,9 +6,9 @@ import pandas as pd
 from numpy.lib._iotools import NameValidator
 from pandas.testing import assert_series_equal
 from pastas.stats.tests import runs_test, stoffer_toloi
-from tqdm import tqdm
+from tqdm.auto import tqdm
 
-from .version import PASTAS_LEQ_022
+from pastastore.version import PASTAS_LEQ_022
 
 
 def _custom_warning(message, category=UserWarning, filename="", lineno=-1, *args):
@@ -335,9 +335,11 @@ def compare_models(ml1, ml2, stats=None, detailed_comparison=False):
             try:
                 assert_series_equal(
                     oso,
-                    ml.oseries.series_original
-                    if PASTAS_LEQ_022
-                    else ml.oseries._series_original,
+                    (
+                        ml.oseries.series_original
+                        if PASTAS_LEQ_022
+                        else ml.oseries._series_original
+                    ),
                 )
                 compare_oso = True
             except (ValueError, AssertionError):
@@ -378,9 +380,9 @@ def compare_models(ml1, ml2, stats=None, detailed_comparison=False):
             for ts in stresses:
                 df.loc[f"- time series: '{ts.name}'"] = ts.name
                 for tsk in ts.settings.keys():
-                    df.loc[
-                        f"  - {ts.name} settings: {tsk}", f"model {i}"
-                    ] = ts.settings[tsk]
+                    df.loc[f"  - {ts.name} settings: {tsk}", f"model {i}"] = (
+                        ts.settings[tsk]
+                    )
 
                 if i == 0:
                     if PASTAS_LEQ_022:
@@ -403,9 +405,11 @@ def compare_models(ml1, ml2, stats=None, detailed_comparison=False):
                     try:
                         assert_series_equal(
                             so1[counter],
-                            ts.series_original
-                            if PASTAS_LEQ_022
-                            else ts._series_original,
+                            (
+                                ts.series_original
+                                if PASTAS_LEQ_022
+                                else ts._series_original
+                            ),
                         )
                         compare_so1 = True
                     except (ValueError, AssertionError):
@@ -703,7 +707,9 @@ def frontiers_checks(
                             check_tmem_passed,
                         )
                 else:
-                    tmem = ml.get_response_tmax(sm_name)
+                    tmem = ml.get_response_tmax(sm_name, cutoff=check3_cutoff)
+                    if tmem is None:  # no rfunc in stressmodel
+                        tmem = 0
                     check_tmem_passed = tmem < len_oseries_calib / 2
                     checks.loc[f"calib_period > 2*t_mem_95%: {sm_name}", :] = (
                         tmem,
@@ -736,23 +742,30 @@ def frontiers_checks(
                             "(unit head)/(unit well stress)",
                             check_gain_passed,
                         )
+                    continue
+                elif sm._name == "LinearTrend":
+                    gain = ml.parameters.loc[f"{sm_name}_a", "optimal"]
+                    gain_std = ml.parameters.loc[f"{sm_name}_a", "stderr"]
+                elif sm._name == "StepModel":
+                    gain = ml.parameters.loc[f"{sm_name}_d", "optimal"]
+                    gain_std = ml.parameters.loc[f"{sm_name}_d", "stderr"]
                 else:
                     gain = ml.parameters.loc[f"{sm_name}_A", "optimal"]
                     gain_std = ml.parameters.loc[f"{sm_name}_A", "stderr"]
-                    if gain_std is None:
-                        gain_std = np.nan
-                        check_gain_passed = pd.NA
-                    elif np.isnan(gain_std):
-                        check_gain_passed = pd.NA
-                    else:
-                        check_gain_passed = np.abs(gain) > 2 * gain_std
+
+                if gain_std is None:
+                    gain_std = np.nan
+                    check_gain_passed = pd.NA
+                elif np.isnan(gain_std):
+                    check_gain_passed = pd.NA
+                else:
                     check_gain_passed = np.abs(gain) > 2 * gain_std
-                    checks.loc[f"gain > 2*std: {sm_name}", :] = (
-                        gain,
-                        2 * gain_std,
-                        "(unit head)/(unit well stress)",
-                        check_gain_passed,
-                    )
+                checks.loc[f"gain > 2*std: {sm_name}", :] = (
+                    gain,
+                    2 * gain_std,
+                    "(unit head)/(unit well stress)",
+                    check_gain_passed,
+                )
 
         # Check 5 - Parameter Bounds
         if check5_parambounds:

{pastastore-1.2.2 → pastastore-1.4.0}/pastastore/version.py

@@ -4,4 +4,4 @@ from packaging.version import parse as parse_version
 PASTAS_VERSION = parse_version(ps.__version__)
 PASTAS_LEQ_022 = PASTAS_VERSION <= parse_version("0.22.0")
 
-__version__ = "1.2.2"
+__version__ = "1.4.0"

{pastastore-1.2.2 → pastastore-1.4.0}/pastastore/yaml_interface.py

@@ -2,14 +2,14 @@ import datetime
 import logging
 import os
 from copy import deepcopy
-from typing import Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
 import pandas as pd
 import pastas as ps
 import yaml
 
-from .version import PASTAS_LEQ_022
+from pastastore.version import PASTAS_LEQ_022
 
 ps.logger.setLevel("ERROR")
 
@@ -17,7 +17,7 @@ logging.basicConfig(level="INFO")
 logger = logging.getLogger(__name__)
 
 
-def _convert_dict_dtypes_for_yaml(d: Dict):
+def _convert_dict_dtypes_for_yaml(d: Dict[str, Any]):
     """Internal method to convert dictionary values for storing in YAML format.
 
     Parameters

{pastastore-1.2.2 → pastastore-1.4.0}/pastastore.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pastastore
-Version: 1.2.2
+Version: 1.4.0
 Summary: Tools for managing Pastas time series models.
 Author: D.A. Brakenhoff
 Maintainer-email: "D.A. Brakenhoff" <d.brakenhoff@artesia-water.nl>, "R. Calje" <r.calje@artesia-water.nl>, "M.A. Vonk" <m.vonk@artesia-water.nl>
@@ -49,15 +49,47 @@ Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Scientific/Engineering :: Hydrology
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pastas>=0.13
+Requires-Dist: tqdm>=4.36
+Requires-Dist: pyyaml
 Provides-Extra: full
+Requires-Dist: pastastore[arcticdb,optional]; extra == "full"
 Provides-Extra: lint
+Requires-Dist: black; extra == "lint"
+Requires-Dist: flake8; extra == "lint"
+Requires-Dist: isort; extra == "lint"
 Provides-Extra: optional
+Requires-Dist: contextily; extra == "optional"
+Requires-Dist: pyproj; extra == "optional"
+Requires-Dist: adjustText; extra == "optional"
 Provides-Extra: test
+Requires-Dist: pastastore[arcticdb,lint,optional]; extra == "test"
+Requires-Dist: hydropandas[full]; extra == "test"
+Requires-Dist: coverage; extra == "test"
+Requires-Dist: codecov; extra == "test"
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: pytest-cov; extra == "test"
+Requires-Dist: pytest-dependency; extra == "test"
+Requires-Dist: pytest-benchmark; extra == "test"
+Requires-Dist: codacy-coverage; extra == "test"
+Requires-Dist: lxml; extra == "test"
 Provides-Extra: pystore
+Requires-Dist: fsspec>=0.3.3; extra == "pystore"
+Requires-Dist: python-snappy; extra == "pystore"
+Requires-Dist: dask[dataframe]; extra == "pystore"
 Provides-Extra: arctic
+Requires-Dist: arctic; extra == "arctic"
 Provides-Extra: arcticdb
+Requires-Dist: arcticdb; extra == "arcticdb"
+Requires-Dist: protobuf~=4.0; extra == "arcticdb"
 Provides-Extra: docs
-License-File: LICENSE
+Requires-Dist: pastastore[optional]; extra == "docs"
+Requires-Dist: sphinx_rtd_theme; extra == "docs"
+Requires-Dist: Ipython; extra == "docs"
+Requires-Dist: ipykernel; extra == "docs"
+Requires-Dist: nbsphinx; extra == "docs"
+Requires-Dist: nbsphinx_link; extra == "docs"
 
 ![pastastore](https://github.com/pastas/pastastore/workflows/pastastore/badge.svg)
 [![Documentation Status](https://readthedocs.org/projects/pastastore/badge/?version=latest)](https://pastastore.readthedocs.io/en/latest/?badge=latest)

{pastastore-1.2.2 → pastastore-1.4.0}/pastastore.egg-info/SOURCES.txt

@@ -7,6 +7,7 @@ pastastore/connectors.py
 pastastore/datasets.py
 pastastore/plotting.py
 pastastore/store.py
+pastastore/styling.py
 pastastore/util.py
 pastastore/version.py
 pastastore/yaml_interface.py

{pastastore-1.2.2 → pastastore-1.4.0}/pastastore.egg-info/requires.txt

@@ -7,6 +7,7 @@ arctic
 
 [arcticdb]
 arcticdb
+protobuf~=4.0
 
 [docs]
 pastastore[optional]

{pastastore-1.2.2 → pastastore-1.4.0}/pyproject.toml

@@ -58,13 +58,16 @@ test = [
     "pytest-dependency",
     "pytest-benchmark",
     "codacy-coverage",
-    "lxml",  # temporary fix: for hydropandas 0.8.0
+    "lxml",                               # temporary fix: for hydropandas 0.8.0
 ]
 pystore = ["fsspec>=0.3.3", "python-snappy", "dask[dataframe]"]
 arctic = [
     "arctic", # will not work as releases not uploaded to PyPI
 ]
-arcticdb = ["arcticdb"]
+arcticdb = [
+    "arcticdb",
+    "protobuf~=4.0",
+] # TODO: temporarily set protobuf to version 4
 docs = [
     "pastastore[optional]",
     "sphinx_rtd_theme",

{pastastore-1.2.2 → pastastore-1.4.0}/tests/test_001_import.py

@@ -4,4 +4,4 @@ import warnings
 def test_import():
     with warnings.catch_warnings():
         warnings.simplefilter(action="ignore", category=FutureWarning)
-        import pastastore
+        import pastastore  # noqa: F401

{pastastore-1.2.2 → pastastore-1.4.0}/tests/test_002_connectors.py

@@ -14,7 +14,7 @@ ps.set_log_level("ERROR")
 
 
 def test_get_library(conn):
-    olib = conn._get_library("oseries")
+    _ = conn._get_library("oseries")
 
 
 def test_add_get_series(request, conn):
@@ -206,13 +206,13 @@ def test_add_stress(conn):
 @pytest.mark.dependency()
 def test_get_oseries(request, conn):
     depends(request, [f"test_add_oseries[{conn.type}]"])
-    o = conn.get_oseries("oseries1")
+    _ = conn.get_oseries("oseries1")
 
 
 @pytest.mark.dependency()
 def test_get_oseries_and_metadata(request, conn):
     depends(request, [f"test_add_oseries[{conn.type}]"])
-    o, m = conn.get_oseries("oseries1", return_metadata=True)
+    _ = conn.get_oseries("oseries1", return_metadata=True)
 
 
 @pytest.mark.dependency()
@@ -225,7 +225,7 @@ def test_get_stress(request, conn):
 @pytest.mark.dependency()
 def test_get_stress_and_metadata(request, conn):
     depends(request, [f"test_add_stress[{conn.type}]"])
-    s, m = conn.get_stresses("prec", return_metadata=True)
+    s, _ = conn.get_stresses("prec", return_metadata=True)
     s.name = "prec"
 
 

{pastastore-1.2.2 → pastastore-1.4.0}/tests/test_003_pastastore.py

@@ -1,5 +1,4 @@
 import os
-import warnings
 
 import numpy as np
 import pandas as pd
@@ -9,9 +8,7 @@ from numpy import allclose
 from packaging.version import parse
 from pytest_dependency import depends
 
-with warnings.catch_warnings():
-    warnings.simplefilter(action="ignore", category=FutureWarning)
-    import pastastore as pst
+import pastastore as pst
 
 
 @pytest.mark.dependency()
@@ -39,7 +36,7 @@ def test_search(pstore):
 
 @pytest.mark.dependency()
 def test_create_model(pstore):
-    ml = pstore.create_model("oseries1")
+    _ = pstore.create_model("oseries1")
 
 
 @pytest.mark.dependency()
@@ -139,7 +136,7 @@ def test_get_model(request, pstore):
             f"test_store_model_missing_series[{pstore.type}]",
         ],
     )
-    ml = pstore.conn.get_models("oseries1")
+    _ = pstore.conn.get_models("oseries1")
 
 
 @pytest.mark.dependency()
@@ -158,7 +155,7 @@ def test_del_model(request, pstore):
 
 @pytest.mark.dependency()
 def test_create_models(pstore):
-    mls = pstore.create_models_bulk(
+    _ = pstore.create_models_bulk(
         ["oseries1", "oseries2"], store=True, progressbar=False
     )
     _ = pstore.conn.models
@@ -172,6 +169,13 @@ def test_get_parameters(request, pstore):
     assert p.isna().sum().sum() == 0
 
 
+@pytest.mark.dependency()
+def test_get_signatures(request, pstore):
+    depends(request, [f"test_create_models[{pstore.type}]"])
+    s = pstore.get_signatures(progressbar=False)
+    assert s.shape[1] == len(ps.stats.signatures.__all__)
+
+
 @pytest.mark.dependency()
 def test_iter_models(request, pstore):
     depends(request, [f"test_create_models[{pstore.type}]"])
@@ -181,13 +185,24 @@ def test_iter_models(request, pstore):
 @pytest.mark.dependency()
 def test_solve_models_and_get_stats(request, pstore):
     depends(request, [f"test_create_models[{pstore.type}]"])
-    mls = pstore.solve_models(
+    _ = pstore.solve_models(
         ignore_solve_errors=False, progressbar=False, store_result=True
     )
     stats = pstore.get_statistics(["evp", "aic"], progressbar=False)
     assert stats.index.size == 2
 
 
+@pytest.mark.dependency()
+def test_apply(request, pstore):
+    depends(request, [f"test_solve_models_and_get_stats[{pstore.type}]"])
+
+    def func(ml):
+        return ml.parameters.loc["recharge_A", "optimal"]
+
+    result = pstore.apply("models", func)
+    assert len(result) == 2
+
+
 @pytest.mark.dependency()
 def test_save_and_load_model(request, pstore):
     ml = pstore.create_model("oseries2")

{pastastore-1.2.2 → pastastore-1.4.0}/tests/test_004_yaml.py

@@ -6,7 +6,6 @@ import pytest
 from pytest_dependency import depends
 
 import pastastore as pst
-from pastastore.version import PASTAS_LEQ_022
 
 
 @contextmanager

{pastastore-1.2.2 → pastastore-1.4.0}/tests/test_006_benchmark.py

@@ -9,7 +9,7 @@ import pastastore as pst
 
 # data
 data = np.random.random_sample(int(1e5))
-s = pd.Series(index=pd.date_range("1970", periods=1e5, freq="H"), data=data)
+s = pd.Series(index=pd.date_range("1970", periods=int(1e5), freq="h"), data=data)
 metadata = {"x": 100000.0, "y": 300000.0}
 
 

pastastore-1.2.2/pastastore/__init__.py

@@ -1,10 +0,0 @@
-from . import connectors, util
-from .connectors import (
-    ArcticConnector,
-    ArcticDBConnector,
-    DictConnector,
-    PasConnector,
-    PystoreConnector,
-)
-from .store import PastaStore
-from .version import __version__