Add a sample dataset MaunaLoa_CO2 (#1961)

Co-authored-by: Wei Ji <[email protected]>

Author: willschlitzer

pygmt/datasets/samples.py

@@ -31,6 +31,7 @@ def list_sample_data():
         "japan_quakes": "Table of earthquakes around Japan from NOAA NGDC database",
         "mars_shape": "Table of topographic signature of the hemispheric dichotomy of "
         " Mars from Smith and Zuber (1996)",
+        "maunaloa_co2": "Table of CO2 readings from Mauna Loa",
         "ocean_ridge_points": "Table of ocean ridge points for the entire world",
         "notre_dame_topography": "Table 5.11 in Davis: Statistics and Data Analysis in Geology",
         "usgs_quakes": "Table of global earthquakes from the USGS",
@@ -80,6 +81,7 @@ def load_sample_data(name):
     # Dictionary of private load functions
     load_func = {
         "earth_relief_holes": _load_earth_relief_holes,
+        "maunaloa_co2": _load_maunaloa_co2,
         "notre_dame_topography": _load_notre_dame_topography,
     }
 
@@ -371,6 +373,21 @@ def _load_notre_dame_topography():
     return pd.read_csv(fname, sep=r"\s+", header=None, names=["x", "y", "z"])
 
 
+def _load_maunaloa_co2():
+    """
+    Load a table of CO2 values from Mauna Loa.
+
+    Returns
+    -------
+    data : pandas.DataFrame
+        The data table with columns "date" and "co2_ppm".
+    """
+    fname = which("@MaunaLoa_CO2.txt", download="c")
+    return pd.read_csv(
+        fname, header=None, skiprows=1, sep=r"\s+", names=["date", "co2_ppm"]
+    )
+
+
 def _load_earth_relief_holes():
     """
     Loads the remote file @earth_relief_20m_holes.grd.

pygmt/tests/test_datasets_samples.py

@@ -173,3 +173,16 @@ def test_earth_relief_holes():
     npt.assert_allclose(grid.min(), -4929.5)
     # Test for the NaN values in the remote file
     assert grid[2, 21].isnull()
+
+
+def test_maunaloa_co2():
+    """
+    Check that the @MaunaLoa_CO2.txt dataset loads without errors.
+    """
+    data = load_sample_data(name="maunaloa_co2")
+    assert data.shape == (730, 2)
+    summary = data.describe()
+    assert summary.loc["min", "date"] == 1958.2027
+    assert summary.loc["max", "date"] == 2019.3699
+    assert summary.loc["min", "co2_ppm"] == 313.2
+    assert summary.loc["max", "co2_ppm"] == 414.83