Added sample data functions and updated testing workflow

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.12-slim
+
+WORKDIR /project
+
+COPY . .
+
+RUN pip install --upgrade pip
+RUN pip install pytest sphinx sphinx-autobuild
+
+RUN pip install -e .
+
+
+CMD ["pytest", "-v", "hdp/tests/"]

hdp/__init__.py

@@ -1,6 +0,0 @@
-from hdp import hdp
-from hdp import measure
-from hdp import threshold
-from hdp import metric
-from hdp import utils
-from hdp import definitions

hdp/graphics/figure.py

@@ -135,11 +135,13 @@ def get_unique_metric_names(hw_ds):
     return unique_metrics
 
 
-def plot_map(metric_da, axis, cmap="hot"):
+def plot_map(metric_da, ax, cmap="hot"):
     cmap_obj = plt.get_cmap(cmap)
+    metric_da = metric_da.transpose(..., "lon")
+
     cyclic_values, cyclic_lons = add_cyclic_point(metric_da.values, metric_da.lon.values, axis=-1)
-    ax_contour = axis.contourf(cyclic_lons, metric_da.lat.values, cyclic_values, transform=ccrs.PlateCarree(), cmap=cmap_obj)
-    axis.coastlines()
+    ax_contour = ax.contourf(cyclic_lons, metric_da.lat.values, cyclic_values, transform=ccrs.PlateCarree(), cmap=cmap_obj)
+    ax.coastlines()
     return ax_contour
 
 

hdp/graphics/notebook.py

@@ -3,6 +3,9 @@
 import nbformat
 from io import BytesIO
 from datetime import datetime
+from hdp.utils import get_func_description
+from hdp.graphics.figure import *
+from tqdm.auto import tqdm
 
 
 class HDPNotebook():
@@ -92,4 +95,50 @@ def save_notebook(self, path, title=None):
                     notebook_node.cells.append(cell)
 
         with open(path, 'w') as nb_file:
-            nbformat.write(notebook_node, nb_file)
+            nbformat.write(notebook_node, nb_file)
+
+
+def create_notebook(hw_ds):
+    assert "hdp_type" in hw_ds.attrs, "Missing 'hdp_type' attribute."
+
+    notebook = HDPNotebook()
+
+    if hw_ds.attrs["hdp_type"] == "measure":
+        pass
+    elif hw_ds.attrs["hdp_type"] == "threshold":
+        pass
+    elif hw_ds.attrs["hdp_type"] == "metric":
+        index = 1
+
+        section_name = f"Figures {index}"
+        notebook.create_section(section_name)
+        desc = get_func_description(plot_multi_measure_metric_comparisons)
+        notebook.add_markdown_cell(f"### Figure {index}.2 \n{desc}", section_name)
+        notebook.add_figure_cell(plot_multi_measure_metric_comparisons(hw_ds), section_name, alt_text=f"{section_name}")
+
+        index += 1
+        for metric in tqdm(list(hw_ds.data_vars), desc="Generating figures:"):
+            section_name = f"Figures {index}-{metric}"
+
+            notebook.create_section(section_name)
+            notebook.add_markdown_cell("Description of these figures.", section_name)
+
+            desc = get_func_description(plot_metric_parameter_comparison)
+            notebook.add_markdown_cell(f"### Figure {index}.1 \n{desc}", section_name)
+            notebook.add_figure_cell(plot_metric_parameter_comparison(hw_ds[metric]), section_name, alt_text=f"{section_name}")
+
+            desc = get_func_description(plot_metric_timeseries)
+            notebook.add_markdown_cell(f"### Figure {index}.2 \n{desc}", section_name)
+            notebook.add_figure_cell(plot_metric_timeseries(hw_ds[metric]), section_name, alt_text=f"{section_name}")
+
+            iindex = 3
+            for fig in plot_metric_decadal_maps(hw_ds[metric]):
+                desc = get_func_description(plot_metric_decadal_maps)
+                notebook.add_markdown_cell(f"### Figure {index}.{iindex} \n{desc}", section_name)
+                notebook.add_figure_cell(fig, section_name, alt_text=f"{section_name}")
+                iindex += 1
+            index += 1
+    else:
+        raise ValueError(f"Unexpected value for 'hdp_type' attribute, '{hw_ds.attrs["hdp_type"]}' is not 'measure', 'threshold', or 'metric'.")
+
+    return notebook

hdp/metric.py

@@ -462,7 +462,7 @@ def compute_individual_metrics(measure: xarray.DataArray, threshold: xarray.Data
 
     start_ts = cftime.datetime(ds.year[0], 1, 1, calendar=measure.time.values[0].calendar)
     end_ts = cftime.datetime(ds.year[-1], 1, 1, calendar=measure.time.values[0].calendar)
-    ds = ds.rename(dict(year="time")).assign_coords(dict(time=xarray.cftime_range(start_ts, end_ts, periods=ds.year.size)))
+    ds = ds.rename(dict(year="time")).assign_coords(dict(time=xarray.date_range(start_ts, end_ts, periods=ds.year.size, use_cftime=True)))
 
     ds.attrs |= {
         "description": f"Heatwave metric dataset generated by Heatwave Diagnostics Package (HDP v{get_version()})",

hdp/sample.py

@@ -0,0 +1,63 @@
+#!/usr/bin/env python
+"""
+hdp.py
+
+Heatwave Diagnostics Package (HDP)
+
+Entry point for package.
+
+Developer: Cameron Cummins
+Contact: cameron.cummins@utexas.edu
+"""
+from hdp.graphics.notebook import create_notebook
+from os.path import isdir
+import hdp.measure
+import hdp.threshold
+import hdp.metric
+import numpy as np
+import sys
+
+
+def generate_sample_data(output_dir):
+    if not isdir(output_dir):
+        raise RuntimeError(f"Output directory '{output_dir}' does not exist!")
+
+    sample_control_temp = hdp.utils.generate_test_control_dataarray()
+    sample_warming_temp = hdp.utils.generate_test_warming_dataarray()
+
+    baseline_measures = hdp.measure.format_standard_measures(
+        temp_datasets=[sample_control_temp]
+    )
+    test_measures = hdp.measure.format_standard_measures(
+        temp_datasets=[sample_warming_temp]
+    )
+
+    percentiles = np.arange(0.9, 1.0, 0.01)
+
+    thresholds_dataset = hdp.threshold.compute_thresholds(
+        baseline_measures,
+        percentiles
+    )
+
+    definitions = [[3,0,0], [3,1,1], [4,0,0], [4,1,1], [5,0,0], [5,1,1]]
+
+    metrics_dataset = hdp.metric.compute_group_metrics(test_measures, thresholds_dataset, definitions, include_threshold=True)
+    metrics_dataset.to_netcdf(f"{output_dir}/sample_hw_metrics.nc", mode='w')
+
+    figure_notebook = create_notebook(metrics_dataset)
+    figure_notebook.save_notebook(f"{output_dir}/sample_hw_summary_figures.ipynb")
+
+    sample_control_temp = sample_control_temp.to_dataset()
+    sample_control_temp.attrs["description"] = "Mock control temperature dataset generated by HDP for unit testing."
+    sample_control_temp.to_netcdf(f"{output_dir}/sample_control_temp.nc", mode='w')
+
+    sample_warming_temp = sample_warming_temp.to_dataset()
+    sample_warming_temp.attrs["description"] = "Mock temperature dataset with warming trend generated by HDP for unit testing."
+    sample_warming_temp.to_netcdf(f"{output_dir}/sample_warming_temp.nc", mode='w')
+
+if __name__ == "__main__":
+    print("Generating testing data and simulating a full data-to-figure workflow: ")
+    if len(sys.argv) != 2:
+        assert Exception("Please specifiy the path to output sample data and results to.")
+    generate_sample_data(sys.argv[1])
+    print("Done!")

hdp/tests/test_utils.py

@@ -1,46 +1,57 @@
-import hdp.utils
-import xarray
+from hdp.utils import *
 import numpy as np
-
+from math import isclose
+from xarray import DataArray
 
 def test_get_time_stamp():
-    assert type(hdp.utils.get_time_stamp()) is str
+    assert type(get_time_stamp()) is str
 
 
 def test_get_version():
-    assert type(hdp.utils.get_version()) is str
-
-
-def test_synthetic_data_functions():
-    var = "test"
-    center_val = 10
-    amplitude_val = 1
-    units = "test_units"
-
-    ds = hdp.utils.generate_synthetic_dataset(name=var, units=units, center=center_val, amplitude=amplitude_val)
-    assert type(ds) is xarray.Dataset
-    assert len(ds.data_vars) == 1
-    assert var in ds
-
-    assert "units" in ds[var].attrs
-    assert ds[var].attrs["units"] == units
-    assert ds[var].dims == ("lat", "lon", "time")
-    assert ds[var].dtype == float
-    assert ds[var].time.values[0].calendar == "noleap"
-    assert ds[var].lat.size > 1
-    assert ds[var].lon.size > 1
-    assert ds[var].time.size >= 2*365
-
-    data = ds[var].compute()
-
-    assert np.isclose(data.mean(), center_val)
-    assert np.isclose(data.max(), center_val + amplitude_val)
-    assert np.isclose(data.values, data.values[0]).all()
-
-    exceed_data = hdp.utils.generate_exceedance_dataarray(ds[var], exceedance_pattern=[1, 0, 1, 0]).compute()
-
-    assert np.isclose(exceed_data.mean(), center_val + 0.5)
-    assert exceed_data.attrs == ds[var].attrs
-    assert exceed_data.dims == ds[var].dims
-    assert exceed_data.shape == ds[var].shape
-    assert exceed_data.dtype == ds[var].dtype
+    assert type(get_version()) is str
+
+
+def test_control_dataarray():
+    control_da = generate_test_control_dataarray(grid_shape=(1,1), start_date="2000", end_date="2100")
+    assert type(control_da) is DataArray
+    var = control_da.name
+    assert control_da.attrs["units"] == "degC"
+    assert control_da.dims == ("lon", "lat", "time")
+    assert control_da.dtype == float
+    assert control_da.time.values[0].calendar == "noleap"
+    assert control_da.time.values.size >= 365
+    assert np.sum(np.isnan(control_da)) == 0
+
+    control_slope = np.polyfit(np.arange(control_da["time"].size), control_da.mean(dim=["lat", "lon"]).values, 1)[0]
+    assert np.abs(control_slope) < 0.01
+
+
+def test_warming_dataarray():
+    warming_da = generate_test_warming_dataarray(grid_shape=(1,1), start_date="2000", end_date="2100")
+    avg_da = warming_da.mean(dim=["lat", "lon"]).values
+    warm_slope = np.polyfit(np.arange(avg_da.size), avg_da, 1)[0]
+
+    assert warm_slope > 0
+    assert not isclose(warm_slope, 0)
+
+
+def test_rh_dataarray():
+    rh_da = generate_test_rh_dataarray()
+
+    assert rh_da.max() <= 1
+    assert rh_da.min() >= 0
+
+
+def test_defaults_compatibility():
+    control_da = generate_test_control_dataarray()
+    warming_da = generate_test_warming_dataarray()
+    rh_da = generate_test_rh_dataarray()
+
+    assert control_da.shape == warming_da.shape
+    assert warming_da.shape == rh_da.shape
+
+    assert control_da.dims == warming_da.dims
+    assert warming_da.dims == rh_da.dims
+
+    assert control_da.name == warming_da.name
+    assert control_da.units == warming_da.units