Add new function to load fractures sample data (#1101)

Co-authored-by: Meghan Jones <[email protected]> Co-authored-by: Wei Ji <[email protected]> Co-authored-by: Dongdong Tian <[email protected]>
GenericMappingTools · Mar 24, 2021 · 9ecb7d8 · 9ecb7d8
1 parent 65f5aee
commit 9ecb7d8
Show file tree

Hide file tree

Showing 4 changed files with 38 additions and 0 deletions.
diff --git a/doc/api/index.rst b/doc/api/index.rst
@@ -142,6 +142,7 @@ and store them in the GMT cache folder.
     datasets.load_ocean_ridge_points
     datasets.load_sample_bathymetry
     datasets.load_usgs_quakes
+    datasets.load_fractures_compilation
 
 .. automodule:: pygmt.exceptions
 

diff --git a/pygmt/datasets/__init__.py b/pygmt/datasets/__init__.py
@@ -4,6 +4,7 @@
 
 from pygmt.datasets.earth_relief import load_earth_relief
 from pygmt.datasets.samples import (
+    load_fractures_compilation,
     load_japan_quakes,
     load_ocean_ridge_points,
     load_sample_bathymetry,

diff --git a/pygmt/datasets/samples.py b/pygmt/datasets/samples.py
@@ -101,3 +101,25 @@ def load_usgs_quakes():
     fname = which("@usgs_quakes_22.txt", download="c")
     data = pd.read_csv(fname)
     return data
+
+
+def load_fractures_compilation():
+    """
+    Load a table of fracture lengths and azimuths as hypothetically digitized
+    from geological maps as a pandas.DataFrame.
+
+    This is the ``@fractures_06.txt`` dataset used in the GMT tutorials.
+
+    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.
+
+    Returns
+    -------
+    data : pandas.DataFrame
+        The data table. Use ``print(data.describe())`` to see the available
+        columns.
+    """
+    fname = which("@fractures_06.txt", download="c")
+    data = pd.read_csv(fname, header=None, sep=r"\s+", names=["azimuth", "length"])
+    return data[["length", "azimuth"]]
diff --git a/pygmt/tests/test_datasets_samples.py b/pygmt/tests/test_datasets_samples.py
@@ -2,6 +2,7 @@
 Test basic functionality for loading sample datasets.
 """
 from pygmt.datasets import (
+    load_fractures_compilation,
     load_japan_quakes,
     load_ocean_ridge_points,
     load_sample_bathymetry,
@@ -58,3 +59,16 @@ def test_usgs_quakes():
     """
     data = load_usgs_quakes()
     assert data.shape == (1197, 22)
+
+
+def test_fractures_compilation():
+    """
+    Check that the @fractures_06.txt dataset loads without errors.
+    """
+    data = load_fractures_compilation()
+    assert data.shape == (361, 2)
+    summary = data.describe()
+    assert summary.loc["min", "length"] == 98.6561
+    assert summary.loc["max", "length"] == 984.652
+    assert summary.loc["min", "azimuth"] == 0.0
+    assert summary.loc["max", "azimuth"] == 360.0