merge main

.github/workflows/ci-analytics.yml

@@ -37,7 +37,7 @@ jobs:
         run: make lint
 
       - name: Run tests
-        run: make test
+        run: make test-audit
 
       - name: Export GitHub data
         run: make gh-data-export

analytics/Makefile

@@ -8,6 +8,7 @@ ISSUE_FILE ?= data/issue-data.json
 SPRINT ?= @current
 UNIT ?= points
 ACTION ?= show-results
+MIN_TEST_COVERAGE ?= 80
 
 check-prereqs:
 	@echo "=> Checking for pre-requisites"
@@ -32,10 +33,20 @@ lint:
 	@echo "============================="
 	@echo "=> All checks succeeded"
 
-test:
-	@echo "=> Running tests"
+unit-test:
+	@echo "=> Running unit tests"
 	@echo "============================="
-	$(POETRY) run pytest
+	$(POETRY) run pytest --cov=src
+
+e2e-test:
+	@echo "=> Running end-to-end tests"
+	@echo "============================="
+	$(POETRY) run pytest tests/integrations --cov-append=src
+
+test-audit: unit-test
+	@echo "=> Running test coverage report"
+	@echo "============================="
+	$(POETRY) run coverage report --show-missing --fail-under=$(MIN_TEST_COVERAGE)
 
 sprint-data-export:
 	@echo "=> Exporting project data from the sprint board"
@@ -61,7 +72,7 @@ sprint-burndown:
 	poetry run analytics calculate sprint_burndown \
 	--sprint-file $(SPRINT_FILE) \
 	--issue-file $(ISSUE_FILE) \
-	--sprint  $(SPRINT) \
+	--sprint  "$(SPRINT)" \
 	--unit $(UNIT) \
 	--$(ACTION)
 

analytics/pyproject.toml

@@ -26,6 +26,7 @@ black = "^23.7.0"
 mypy = "^1.4.1"
 pylint = "^3.0.2"
 pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
 ruff = "^0.0.278"
 safety = "^2.3.5"
 
@@ -49,6 +50,7 @@ disable = [
   "W0511", # fix-me
   "R0913", # too-many-arguments
   "R0902", # too-many-instance-attributes
+  "R0903", # too-few-public-methods
 ]
 
 [tool.ruff]
@@ -67,3 +69,10 @@ ignore = [
 ]
 line-length = 100
 select = ["ALL"]
+
+[tool.pytest.ini_options]
+filterwarnings = [
+  # kaleido is throwing a Deprecation warning in one of its dependencies
+  # TODO(widal001): 2022-12-12 - Try removing after Kaleido issues a new release
+  'ignore:.*setDaemon\(\) is deprecated.*:DeprecationWarning',
+]

analytics/src/analytics/datasets/base.py

@@ -21,9 +21,14 @@ def from_dict(cls, data: list[dict]) -> Self:
         """Load the dataset from a list of python dictionaries representing records."""
         return cls(df=pd.DataFrame(data))
 
-    def to_csv(self, output_file: str) -> None:
+    def to_csv(
+        self,
+        output_file: str,
+        *,  # force include_index to be passed as keyword instead of positional arg
+        include_index: bool = False,
+    ) -> None:
         """Export the dataset to a csv."""
-        return self.df.to_csv(output_file)
+        return self.df.to_csv(output_file, index=include_index)
 
     def to_dict(self) -> list[dict]:
         """Export the dataset to a list of python dictionaries representing records."""

analytics/src/analytics/datasets/sprint_board.py

@@ -72,14 +72,14 @@ def sprints(self) -> pd.DataFrame:
     @property
     def current_sprint(self) -> str | None:
         """Return the name of the current sprint, if a sprint is currently active."""
-        return self.get_sprint_name_from_date(pd.Timestamp.today())
+        return self.get_sprint_name_from_date(pd.Timestamp.today().floor("d"))
 
     def get_sprint_name_from_date(self, date: pd.Timestamp) -> str | None:
         """Get the name of a sprint from a given date, if that date falls in a sprint."""
         # fmt: off
         date_filter = (
-            (self.sprints[self.sprint_start_col] <= date)  # after sprint start
-            & (self.sprints[self.sprint_end_col] > date)  # before sprint end
+            (self.sprints[self.sprint_start_col] < date)  # after sprint start
+            & (self.sprints[self.sprint_end_col] >= date)  # before sprint end
         )
         # fmt: on
         matching_sprints = self.sprints.loc[date_filter, self.sprint_col]

analytics/src/analytics/metrics/base.py

@@ -28,9 +28,9 @@ class Statistic:
 class BaseMetric:
     """Base class for all metrics."""
 
-    CHART_PNG = "data/chart-static.png"
-    CHART_HTML = "data/chart-interactive.html"
-    RESULTS_CSV = "data/results.csv"
+    CHART_PNG = "chart-static.png"
+    CHART_HTML = "chart-interactive.html"
+    RESULTS_CSV = "results.csv"
 
     def __init__(self) -> None:
         """Initialize and calculate the metric from the input dataset."""
@@ -64,29 +64,29 @@ def plot_results(self) -> Figure:
         """Create a plotly chart that visually represents the results."""
         raise NotImplementedError
 
-    def export_results(self) -> Path:
+    def export_results(self, output_dir: Path = Path("data")) -> Path:
         """Export the self.results dataframe to a csv file."""
         # make sure the parent directory exists
-        output_path = Path(self.RESULTS_CSV)
-        output_path.parent.mkdir(exist_ok=True, parents=True)
+        output_dir.mkdir(exist_ok=True, parents=True)
+        output_path = output_dir / self.RESULTS_CSV
         # export results dataframe to a csv
         self.results.to_csv(output_path)
         return output_path
 
-    def export_chart_to_html(self) -> Path:
+    def export_chart_to_html(self, output_dir: Path = Path("data")) -> Path:
         """Export the plotly chart in self.chart to a png file."""
         # make sure the parent directory exists
-        output_path = Path(self.CHART_HTML)
-        output_path.parent.mkdir(exist_ok=True, parents=True)
+        output_dir.mkdir(exist_ok=True, parents=True)
+        output_path = output_dir / self.CHART_HTML
         # export chart to a png
         self.chart.write_html(output_path)
         return output_path
 
-    def export_chart_to_png(self) -> Path:
+    def export_chart_to_png(self, output_dir: Path = Path("data")) -> Path:
         """Export the plotly chart in self.chart to a png file."""
         # make sure the parent directory exists
-        output_path = Path(self.CHART_PNG)
-        output_path.parent.mkdir(exist_ok=True, parents=True)
+        output_dir.mkdir(exist_ok=True, parents=True)
+        output_path = output_dir / self.CHART_PNG
         # export chart to a png
         self.chart.write_image(output_path, width=900)
         return output_path
@@ -103,11 +103,12 @@ def post_results_to_slack(
         self,
         slackbot: SlackBot,
         channel_id: str,
+        output_dir: Path = Path("data"),
     ) -> None:
-        """Upload copies of the results and chart to a slack channel.."""
-        results_csv = self.export_results()
-        chart_png = self.export_chart_to_png()
-        chart_html = self.export_chart_to_html()
+        """Upload copies of the results and chart to a slack channel."""
+        results_csv = self.export_results(output_dir)
+        chart_png = self.export_chart_to_png(output_dir)
+        chart_html = self.export_chart_to_html(output_dir)
         files = [
             FileMapping(path=str(results_csv), name=results_csv.name),
             FileMapping(path=str(chart_png), name=chart_png.name),

analytics/tests/conftest.py

@@ -8,6 +8,7 @@
 from pathlib import Path
 
 import pandas as pd
+import pytest
 
 # skips the integration tests in tests/integrations/
 # to run the integration tests, invoke them directly: pytest tests/integrations/
@@ -21,6 +22,28 @@
 DAY_5 = "2023-11-05"
 
 
+class MockSlackbot:
+    """Create a mock slackbot issue for unit tests."""
+
+    def upload_files_to_slack_channel(
+        self,
+        channel_id: str,
+        files: list,
+        message: str,
+    ) -> None:
+        """Stubs the corresponding method on the main SlackBot class."""
+        assert isinstance(channel_id, str)
+        print("Fake posting the following files to Slack with this message:")
+        print(message)
+        print(files)
+
+
+@pytest.fixture(name="mock_slackbot")
+def mock_slackbot_fixture():
+    """Create a mock slackbot instance to stub post_to_slack() method."""
+    return MockSlackbot()
+
+
 def write_test_data_to_file(data: dict, output_file: str):
     """Write test JSON data to a file for use in a test."""
     parent_dir = Path(output_file).parent

analytics/tests/datasets/test_base.py

@@ -0,0 +1,38 @@
+"""Test the BaseDataset class."""
+from pathlib import Path  # noqa: I001
+
+import pandas as pd
+
+from analytics.datasets.base import BaseDataset
+
+TEST_DATA = [
+    {"Col A": 1, "Col b": "One"},
+    {"Col A": 2, "Col b": "Two"},
+    {"Col A": 3, "Col b": "Three"},
+]
+
+
+def test_to_and_from_csv(tmp_path: Path):
+    """BaseDataset should write to csv with to_csv() and load from a csv with from_csv()."""
+    # setup - create sample dataframe and instantiate class
+    test_df = pd.DataFrame(TEST_DATA)
+    dataset_in = BaseDataset(test_df)
+    # setup - set output path and check that it doesn't exist
+    output_csv = tmp_path / "dataset.csv"
+    assert output_csv.exists() is False
+    # execution - write to csv and read from csv
+    dataset_in.to_csv(output_csv)
+    dataset_out = BaseDataset.from_csv(output_csv)
+    # validation - check that csv exists and that datasets match
+    assert output_csv.exists()
+    assert dataset_in.df.equals(dataset_out.df)
+
+
+def test_to_and_from_dict():
+    """BaseDataset should have same input and output with to_dict() and from_dict()."""
+    # execution
+    dict_in = TEST_DATA
+    dataset = BaseDataset.from_dict(TEST_DATA)
+    dict_out = dataset.to_dict()
+    # validation
+    assert dict_in == dict_out