Use a single function for loading any sample dataset

doc/api/index.rst

@@ -210,8 +210,10 @@ and store them in the GMT cache folder.
 .. autosummary::
     :toctree: generated
 
+    datasets.list_sample_data
     datasets.load_earth_age
     datasets.load_earth_relief
+    datasets.load_sample_data
     datasets.load_fractures_compilation
     datasets.load_hotspots
     datasets.load_japan_quakes

pygmt/datasets/__init__.py

@@ -5,11 +5,13 @@
 from pygmt.datasets.earth_age import load_earth_age
 from pygmt.datasets.earth_relief import load_earth_relief
 from pygmt.datasets.samples import (
+    list_sample_data,
     load_fractures_compilation,
     load_hotspots,
     load_japan_quakes,
     load_mars_shape,
     load_ocean_ridge_points,
     load_sample_bathymetry,
+    load_sample_data,
     load_usgs_quakes,
 )

pygmt/datasets/samples.py

@@ -1,13 +1,91 @@
 """
 Functions to load sample data.
 """
+import warnings
+
 import pandas as pd
+from pygmt.exceptions import GMTInvalidInput
 from pygmt.src import which
 
 
-def load_japan_quakes():
+def list_sample_data():
+    """
+    Report datasets available for tests and documentation examples.
+
+    Returns
+    -------
+    dict
+        Names and short descriptions of available sample datasets.
+
+    See Also
+    --------
+    load_sample_data : Load an example dataset from the GMT server.
     """
-    Load a table of earthquakes around Japan as a pandas.DataFrame.
+    names = {
+        "japan_quakes": "Table of earthquakes around Japan from NOAA NGDC database",
+        "ocean_ridge_points": "Table of ocean ridge points for the entire world",
+        "bathymetry": "Table of ship bathymetric observations off Baja California",
+        "usgs_quakes": "Table of global earthquakes from the USGS",
+        "fractures": "Table of hypothetical fracture lengths and azimuths",
+        "hotspots": "Table of locations, names, and symbol sizes of hotpots from "
+        " Mueller et al., 1993",
+        "mars_shape": "Table of topographic signature of the hemispheric dichotomy of "
+        " Mars from Smith and Zuber (1996)",
+    }
+    return names
+
+
+def load_sample_data(name):
+    """
+    Load an example dataset from the GMT server.
+
+    The data are downloaded to a cache directory (usually ``~/.gmt/cache``) the
+    first time you invoke this function. Afterwards, it will load the data from
+    the cache. So you'll need an internet connection the first time around.
+
+    Parameters
+    ----------
+    name : str
+        Name of the dataset to load.
+
+    Returns
+    -------
+    :class:`pandas.DataFrame` or :class:`xarray.DataArray`
+        Sample dataset loaded as a pandas.DataFrame for tabular data or
+        xarray.DataArray for raster data
+
+    See Also
+    --------
+    list_sample_data : Report datasets available for tests and documentation
+        examples.
+    """
+    names = list_sample_data()
+    if name not in names:
+        raise GMTInvalidInput(f"Invalid dataset name '{name}'.")
+
+    load_func = {
+        "japan_quakes": load_japan_quakes,
+        "ocean_ridge_points": load_ocean_ridge_points,
+        "bathymetry": load_sample_bathymetry,
+        "usgs_quakes": load_usgs_quakes,
+        "fractures": load_fractures_compilation,
+        "hotspots": load_hotspots,
+        "mars_shape": load_mars_shape,
+    }
+
+    data = load_func[name](suppress_warning=True)
+
+    return data
+
+
+def load_japan_quakes(**kwargs):
+    """
+    (Deprecated) Load a table of earthquakes around Japan as a
+    pandas.DataFrame.
+
+    .. warning:: Deprecated since v0.6.0. This function has been replaced with
+       ``load_sample_data(name="japan_quakes")`` and will be removed in
+       v0.9.0.
 
     Data is from the NOAA NGDC database. This is the ``@tut_quakes.ngdc``
     dataset used in the GMT tutorials.
@@ -22,6 +100,16 @@ def load_japan_quakes():
         The data table. Columns are year, month, day, latitude, longitude,
         depth (in km), and magnitude of the earthquakes.
     """
+
+    if "suppress_warning" not in kwargs:
+        warnings.warn(
+            "This function has been deprecated since v0.6.0 and will be "
+            "removed in v0.9.0. Please use "
+            "load_sample_data(name='japan_quakes') instead.",
+            category=FutureWarning,
+            stacklevel=2,
+        )
+
     fname = which("@tut_quakes.ngdc", download="c")
     data = pd.read_csv(fname, header=1, sep=r"\s+")
     data.columns = [
@@ -33,14 +121,19 @@ def load_japan_quakes():
         "depth_km",
         "magnitude",
     ]
+
     return data
 
 
-def load_ocean_ridge_points():
+def load_ocean_ridge_points(**kwargs):
     """
-    Load a table of ocean ridge points for the entire world as a
+    (Deprecated) Load a table of ocean ridge points for the entire world as a
     pandas.DataFrame.
 
+    .. warning:: Deprecated since v0.6.0. This function has been replaced with
+       ``load_sample_data(name="ocean_ridge_points")`` and will be removed in
+       v0.9.0.
+
     This is the ``@ridge.txt`` dataset used in the GMT tutorials.
 
     The data are downloaded to a cache directory (usually ``~/.gmt/cache``) the
@@ -52,17 +145,31 @@ def load_ocean_ridge_points():
     data : pandas.DataFrame
         The data table. Columns are longitude and latitude.
     """
+
+    if "suppress_warning" not in kwargs:
+        warnings.warn(
+            "This function has been deprecated since v0.6.0 and will be removed "
+            "in v0.9.0. Please use load_sample_data(name='ocean_ridge_points') "
+            "instead.",
+            category=FutureWarning,
+            stacklevel=2,
+        )
+
     fname = which("@ridge.txt", download="c")
     data = pd.read_csv(
         fname, sep=r"\s+", names=["longitude", "latitude"], skiprows=1, comment=">"
     )
     return data
 
 
-def load_sample_bathymetry():
+def load_sample_bathymetry(**kwargs):
     """
-    Load a table of ship observations of bathymetry off Baja California as a
-    pandas.DataFrame.
+    (Deprecated) Load a table of ship observations of bathymetry off Baja
+    California as a pandas.DataFrame.
+
+    .. warning:: Deprecated since v0.6.0. This function has been replaced with
+       ``load_sample_data(name="bathymetry")`` and will be removed in
+       v0.9.0.
 
     This is the ``@tut_ship.xyz`` dataset used in the GMT tutorials.
 
@@ -75,16 +182,30 @@ def load_sample_bathymetry():
     data : pandas.DataFrame
         The data table. Columns are longitude, latitude, and bathymetry.
     """
+
+    if "suppress_warning" not in kwargs:
+        warnings.warn(
+            "This function has been deprecated since v0.6.0 and will be "
+            "removed in v0.9.0. Please use "
+            "load_sample_data(name='bathymetry') instead.",
+            category=FutureWarning,
+            stacklevel=2,
+        )
     fname = which("@tut_ship.xyz", download="c")
     data = pd.read_csv(
         fname, sep="\t", header=None, names=["longitude", "latitude", "bathymetry"]
     )
     return data
 
 
-def load_usgs_quakes():
+def load_usgs_quakes(**kwargs):
     """
-    Load a table of global earthquakes form the USGS as a pandas.DataFrame.
+    (Deprecated) Load a table of global earthquakes from the USGS as a
+    pandas.DataFrame.
+
+    .. warning:: Deprecated since v0.6.0. This function has been replaced with
+       ``load_sample_data(name="usgs_quakes")`` and will be removed in
+       v0.9.0.
 
     This is the ``@usgs_quakes_22.txt`` dataset used in the GMT tutorials.
 
@@ -98,15 +219,28 @@ def load_usgs_quakes():
         The data table. Use ``print(data.describe())`` to see the available
         columns.
     """
+
+    if "suppress_warning" not in kwargs:
+        warnings.warn(
+            "This function has been deprecated since v0.6.0 and will be "
+            "removed in v0.9.0. Please use "
+            "load_sample_data(name='usgs_quakes') instead.",
+            category=FutureWarning,
+            stacklevel=2,
+        )
     fname = which("@usgs_quakes_22.txt", download="c")
     data = pd.read_csv(fname)
     return data
 
 
-def load_fractures_compilation():
+def load_fractures_compilation(**kwargs):
     """
-    Load a table of fracture lengths and azimuths as hypothetically digitized
-    from geological maps as a pandas.DataFrame.
+    (Deprecated) Load a table of fracture lengths and azimuths as
+    hypothetically digitized from geological maps as a pandas.DataFrame.
+
+    .. warning:: Deprecated since v0.6.0. This function has been replaced with
+       ``load_sample_data(name="fractures")`` and will be removed in
+       v0.9.0.
 
     This is the ``@fractures_06.txt`` dataset used in the GMT tutorials.
 
@@ -120,15 +254,28 @@ def load_fractures_compilation():
         The data table. Use ``print(data.describe())`` to see the available
         columns.
     """
+
+    if "suppress_warning" not in kwargs:
+        warnings.warn(
+            "This function has been deprecated since v0.6.0 and will be "
+            "removed in v0.9.0. Please use "
+            "load_sample_data(name='fractures') instead.",
+            category=FutureWarning,
+            stacklevel=2,
+        )
     fname = which("@fractures_06.txt", download="c")
     data = pd.read_csv(fname, header=None, sep=r"\s+", names=["azimuth", "length"])
     return data[["length", "azimuth"]]
 
 
-def load_hotspots():
+def load_hotspots(**kwargs):
     """
-    Load a table with the locations, names, and suggested symbol sizes of
-    hotspots.
+    (Deprecated) Load a table with the locations, names, and suggested symbol
+    sizes of hotspots.
+
+    .. warning:: Deprecated since v0.6.0. This function has been replaced with
+       ``load_sample_data(name="hotspots")`` and will be removed in
+       v0.9.0.
 
     This is the ``@hotspots.txt`` dataset used in the GMT tutorials, with data
     from Mueller, Royer, and Lawver, 1993, Geology, vol. 21, pp. 275-278. The
@@ -145,15 +292,28 @@ def load_hotspots():
         The data table with columns "longitude", "latitude", "symbol_size", and
         "placename".
     """
+
+    if "suppress_warning" not in kwargs:
+        warnings.warn(
+            "This function has been deprecated since v0.6.0 and will be "
+            "removed in v0.9.0. Please use "
+            "load_sample_data(name='hotspots') instead.",
+            category=FutureWarning,
+            stacklevel=2,
+        )
     fname = which("@hotspots.txt", download="c")
     columns = ["longitude", "latitude", "symbol_size", "place_name"]
     data = pd.read_table(filepath_or_buffer=fname, sep="\t", skiprows=3, names=columns)
     return data
 
 
-def load_mars_shape():
+def load_mars_shape(**kwargs):
     """
-    Load a table of data for the shape of Mars.
+    (Deprecated) Load a table of data for the shape of Mars.
+
+    .. warning:: Deprecated since v0.6.0. This function has been replaced with
+       ``load_sample_data(name="mars_shape")`` and will be removed in
+       v0.9.0.
 
     This is the ``@mars370d.txt`` dataset used in GMT examples, with data and
     information from Smith, D. E., and M. T. Zuber (1996), The shape of Mars
@@ -169,6 +329,15 @@ def load_mars_shape():
     data : pandas.DataFrame
         The data table with columns "longitude", "latitude", and "radius(m)".
     """
+
+    if "suppress_warning" not in kwargs:
+        warnings.warn(
+            "This function has been deprecated since v0.6.0 and will be "
+            "removed in v0.9.0. Please use "
+            "load_sample_data(name='mars_shape') instead.",
+            category=FutureWarning,
+            stacklevel=2,
+        )
     fname = which("@mars370d.txt", download="c")
     data = pd.read_csv(
         fname, sep="\t", header=None, names=["longitude", "latitude", "radius(m)"]