320 construction matched pairs (#4)

* set up construction matched pairs tests

* Remove pair from names and add skeleton function

* WIP: Add simplest case test

* Add functionality for simplest test case

* Update construction match flag function and test following discussion about test cases

* Remove unused imports

---------

Co-authored-by: giaccg <[email protected]>

requirements.txt

@@ -2,7 +2,7 @@ coverage
 detect-secrets==1.0.3
 myst-parser
 pre-commit
-pytest
+pytest==7.0.1
 Sphinx
 toml
 black
@@ -11,3 +11,4 @@ nbstripout
 nbqa
 pre_commit_hooks
 flake8
+pandas==1.1.5

src/construction_matches.py

@@ -0,0 +1,27 @@
+import pandas as pd
+
+def flag_construction_matches(dataframe, target, period, auxiliary):
+    """
+    Add flag to indicate whether the record has non-null target, period and
+    auxiliary variables, and is therefore valid to use when calculating
+    construction links
+
+    Parameters
+    ----------
+    dataframe : pandas.DataFrame
+    target : string
+        name of column containing the target variable
+    period : string
+        name of column containing time period
+    auxiliary : string
+        name of column containing auxiliary information
+
+    Returns
+    -------
+    pandas.DataFrame
+        dataframe with additional flag_construction_matches column
+    """
+
+    dataframe["flag_construction_matches"] = pd.notna(dataframe[[target, period, auxiliary]]).all(axis="columns")
+
+    return dataframe

tests/test_construction_matches.py

@@ -0,0 +1,23 @@
+import pytest
+import pandas as pd
+import numpy as np
+
+from pandas.testing import assert_frame_equal
+
+from src.construction_matches import flag_construction_matches
+
+def test_construction_matches():
+    expected_output = pd.DataFrame(np.array([
+            [42,pd.to_datetime("202401", format="%Y%m"),10,True],
+            [pd.NA,pd.to_datetime("202401", format="%Y%m"),10,False],
+        ]),
+        columns=["target", "period", "auxiliary", "flag_construction_matches"],
+    )
+
+    # cast to python non-nullable bool type rather than pandas nullable boolean type
+    expected_output["flag_construction_matches"] = expected_output["flag_construction_matches"].astype(bool)
+
+    input_data = expected_output.drop(labels=["flag_construction_matches"], axis=1)
+    actual_output = flag_construction_matches(input_data, "target", "period", "auxiliary")
+
+    assert_frame_equal(actual_output, expected_output)