Adding functionality to read from local database, unit tests

.coveragerc

@@ -0,0 +1,3 @@
+[report]
+exclude_also =
+    # pragma: no cover

.github/workflows/testing-and-coverage.yml

@@ -27,8 +27,8 @@ jobs:
       run: |
         sudo apt-get update
         python -m pip install --upgrade pip
-        pip install .
-        pip install .[dev]
+        pip install -e .
+        pip install -e .[dev]
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
     - name: Run unit tests with pytest
       run: |

.gitignore

@@ -164,5 +164,3 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
 
-# ignore large db files
-*.db

src/adler/__init__.py

@@ -1,2 +1,3 @@
 from . import dataclasses
 from . import science
+from . import utilities

src/adler/dataclasses/AdlerPlanetoid.py

@@ -49,14 +49,56 @@ def __init__(
         self.AdlerData = adler_data
 
     @classmethod
-    def construct_from_SQL(cls):
-        # to-do
-        pass
+    def construct_from_SQL(
+        cls,
+        ssObjectId,
+        sql_filename,
+        filter_list=["u", "g", "r", "i", "z", "y"],
+        date_range=[60000.0, 67300.0],
+        schema=None,
+    ):
+        """Custom constructor which builds the AdlerPlanetoid object and the associated Observations, MPCORB and SSObject objects from
+        a local SQL database. Mostly used for testing.
+
+        Parameters
+        -----------
+        ssObjectId : str
+            ssObjectId of the object of interest.
+
+        sql_filename : str
+            Filepath to the local SQL database.
+
+        filter_list : list of str
+            A comma-separated list of the filters of interest.
+
+        date_range : list of int
+            The minimum and maximum dates of the desired observations.
+
+        schema : str or None
+            Schema/database from which to select the data tables. Can be None. Default is currently "dp03_catalogs_10yr" for testing using DP0.3.
+
+        """
+
+        if len(date_range) != 2:
+            raise Exception("date_range argument must be of length 2.")
+
+        observations_by_filter = cls.populate_observations(
+            cls, ssObjectId, filter_list, date_range, sql_filename=sql_filename, schema=schema
+        )
+
+        mpcorb = cls.populate_MPCORB(cls, ssObjectId, sql_filename=sql_filename, schema=schema)
+        ssobject = cls.populate_SSObject(
+            cls, ssObjectId, filter_list, sql_filename=sql_filename, schema=schema
+        )
+
+        adler_data = AdlerData(filter_list)
+
+        return cls(ssObjectId, filter_list, date_range, observations_by_filter, mpcorb, ssobject, adler_data)
 
     @classmethod
     def construct_from_RSP(
         cls, ssObjectId, filter_list=["u", "g", "r", "i", "z", "y"], date_range=[60000.0, 67300.0]
-    ):
+    ):  # pragma: no cover
         """Custom constructor which builds the AdlerPlanetoid object and the associated Observations, MPCORB and SSObject objects
         from the RSP.
 
@@ -87,7 +129,15 @@ def construct_from_RSP(
 
         return cls(ssObjectId, filter_list, date_range, observations_by_filter, mpcorb, ssobject, adler_data)
 
-    def populate_observations(self, ssObjectId, filter_list, date_range, service=None, sql_filename=None):
+    def populate_observations(
+        self,
+        ssObjectId,
+        filter_list,
+        date_range,
+        service=None,
+        sql_filename=None,
+        schema="dp03_catalogs_10yr",
+    ):
         """Populates the observations_by_filter class attribute. Can populate from either the RSP for a SQL database:
         this behaviour is controlled by the service and sql_filename parameters, one of which must be supplied.
 
@@ -102,27 +152,35 @@ def populate_observations(self, ssObjectId, filter_list, date_range, service=Non
         date_range : list of int
             The minimum and maximum dates of the desired observations.
 
-        service : pyvo.dal.tap.TAPService object
+        service : pyvo.dal.tap.TAPService object or None
             TAPService object linked to the RSP. Default=None.
 
-        sql_filename : str
+        sql_filename : str or None
             Filepath to a SQL database. Default=None.
 
+        schema : str or None
+            Schema/database from which to select the data tables. Can be None. Default is currently "dp03_catalogs_10yr" for testing using DP0.3.
+
         """
 
+        if schema:
+            schema = schema + "."
+        else:
+            schema = ""
+
         observations_by_filter = []
 
         for filter_name in filter_list:
             observations_sql_query = f"""
                 SELECT
-                    ssObject.ssObjectId, mag, magErr, band, midpointMjdTai, ra, dec, phaseAngle,
+                    ssObject.ssObjectId, mag, magErr, band, midPointMjdTai, ra, dec, phaseAngle,
                     topocentricDist, heliocentricDist
                 FROM
-                    dp03_catalogs_10yr.ssObject
-                    JOIN dp03_catalogs_10yr.diaSource ON dp03_catalogs_10yr.ssObject.ssObjectId   = dp03_catalogs_10yr.diaSource.ssObjectId
-                    JOIN dp03_catalogs_10yr.ssSource  ON dp03_catalogs_10yr.diaSource.diaSourceId = dp03_catalogs_10yr.ssSource.diaSourceId
+                    {schema}ssObject
+                    JOIN {schema}diaSource ON {schema}ssObject.ssObjectId   = {schema}diaSource.ssObjectId
+                    JOIN {schema}ssSource  ON {schema}diaSource.diaSourceId = {schema}ssSource.diaSourceId
                 WHERE
-                    ssObject.ssObjectId = {ssObjectId} AND band = '{filter_name}' AND midpointMjdTai BETWEEN {date_range[0]} AND {date_range[1]}
+                    ssObject.ssObjectId = {ssObjectId} AND band = '{filter_name}' AND midPointMjdTai BETWEEN {date_range[0]} AND {date_range[1]}
                 """
 
             data_table = get_data_table(observations_sql_query, service=service, sql_filename=sql_filename)
@@ -133,7 +191,7 @@ def populate_observations(self, ssObjectId, filter_list, date_range, service=Non
 
         return observations_by_filter
 
-    def populate_MPCORB(self, ssObjectId, service=None, sql_filename=None):
+    def populate_MPCORB(self, ssObjectId, service=None, sql_filename=None, schema="dp03_catalogs_10yr"):
         """Populates the MPCORB object class attribute. Can populate from either the RSP for a SQL database:
         this behaviour is controlled by the service and sql_filename parameters, one of which must be supplied.
 
@@ -142,19 +200,28 @@ def populate_MPCORB(self, ssObjectId, service=None, sql_filename=None):
         ssObjectId : str
             ssObjectId of the object of interest.
 
-        service : pyvo.dal.tap.TAPService object
+        service : pyvo.dal.tap.TAPService object or None
             TAPService object linked to the RSP. Default=None.
 
-        sql_filename : str
+        sql_filename : str or None
             Filepath to a SQL database. Default=None.
 
+        schema : str or None
+            Schema/database from which to select the data tables. Can be None. Default is currently "dp03_catalogs_10yr" for testing using DP0.3.
+
         """
+
+        if schema:
+            schema = schema + "."
+        else:
+            schema = ""
+
         MPCORB_sql_query = f"""
             SELECT
                 ssObjectId, mpcDesignation, mpcNumber, mpcH, mpcG, epoch, peri, node, incl, e, n, q, 
                 uncertaintyParameter, flags
             FROM
-                dp03_catalogs_10yr.MPCORB
+                {schema}MPCORB
             WHERE
                 ssObjectId = {ssObjectId}
         """
@@ -163,7 +230,9 @@ def populate_MPCORB(self, ssObjectId, service=None, sql_filename=None):
 
         return MPCORB.construct_from_data_table(ssObjectId, data_table)
 
-    def populate_SSObject(self, ssObjectId, filter_list, service=None, sql_filename=None):
+    def populate_SSObject(
+        self, ssObjectId, filter_list, service=None, sql_filename=None, schema="dp03_catalogs_10yr"
+    ):
         """Populates the SSObject class attribute. Can populate from either the RSP for a SQL database:
         this behaviour is controlled by the service and sql_filename parameters, one of which must be supplied.
 
@@ -175,18 +244,26 @@ def populate_SSObject(self, ssObjectId, filter_list, service=None, sql_filename=
         filter_list : list of str
             A comma-separated list of the filters of interest.
 
-        service : pyvo.dal.tap.TAPService object
+        service : pyvo.dal.tap.TAPService object or None
             TAPService object linked to the RSP. Default=None.
 
-        sql_filename : str
+        sql_filename : str or None
             Filepath to a SQL database. Default=None.
 
+        schema : str or None
+            Schema/database from which to select the data tables. Can be None. Default is currently "dp03_catalogs_10yr" for testing using DP0.3.
+
         """
 
+        if schema:
+            schema = schema + "."
+        else:
+            schema = ""
+
         filter_dependent_columns = ""
 
         for filter_name in filter_list:
-            filter_string = "{}_H, {}_G12, {}_Herr, {}_G12err, {}_nData, ".format(
+            filter_string = "{}_H, {}_G12, {}_HErr, {}_G12Err, {}_Ndata, ".format(
                 filter_name, filter_name, filter_name, filter_name, filter_name
             )
 
@@ -198,7 +275,7 @@ def populate_SSObject(self, ssObjectId, filter_list, service=None, sql_filename=
                 {filter_dependent_columns}
                 maxExtendedness, minExtendedness, medianExtendedness
             FROM
-                dp03_catalogs_10yr.SSObject
+                {schema}SSObject
             WHERE
                 ssObjectId = {ssObjectId}
         """

src/adler/dataclasses/Observations.py

@@ -52,15 +52,15 @@ class Observations:
 
     ssObjectId: str = ""
     filter_name: str = ""
-    mag: np.ndarray = field(default_factory=np.zeros(0))
-    magErr: np.ndarray = field(default_factory=np.zeros(0))
-    midpointMjdTai: np.ndarray = field(default_factory=np.zeros(0))
-    ra: np.ndarray = field(default_factory=np.zeros(0))
-    dec: np.ndarray = field(default_factory=np.zeros(0))
-    phaseAngle: np.ndarray = field(default_factory=np.zeros(0))
-    topocentricDist: np.ndarray = field(default_factory=np.zeros(0))
-    heliocentricDist: np.ndarray = field(default_factory=np.zeros(0))
-    reduced_mag: np.ndarray = field(default_factory=np.zeros(0))
+    mag: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    magErr: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    midpointMjdTai: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    ra: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    dec: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    phaseAngle: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    topocentricDist: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    heliocentricDist: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    reduced_mag: np.ndarray = field(default_factory=lambda: np.zeros(0))
     num_obs: int = 0
 
     @classmethod
@@ -85,21 +85,28 @@ def construct_from_data_table(cls, ssObjectId, filter_name, data_table):
 
         """
 
-        reduced_mag = cls.calculate_reduced_mag(
-            cls, data_table["mag"], data_table["topocentricDist"], data_table["heliocentricDist"]
-        )
+        mag = get_from_table(data_table, "mag", "array")
+        magErr = get_from_table(data_table, "magErr", "array")
+        midpointMjdTai = get_from_table(data_table, "midPointMjdTai", "array")
+        ra = get_from_table(data_table, "ra", "array")
+        dec = get_from_table(data_table, "dec", "array")
+        phaseAngle = get_from_table(data_table, "phaseAngle", "array")
+        topocentricDist = get_from_table(data_table, "topocentricDist", "array")
+        heliocentricDist = get_from_table(data_table, "heliocentricDist", "array")
+
+        reduced_mag = cls.calculate_reduced_mag(cls, mag, topocentricDist, heliocentricDist)
 
         return cls(
             ssObjectId,
             filter_name,
-            data_table["mag"],
-            data_table["magErr"],
-            data_table["midpointMjdTai"],
-            data_table["ra"],
-            data_table["dec"],
-            data_table["phaseAngle"],
-            data_table["topocentricDist"],
-            data_table["heliocentricDist"],
+            mag,
+            magErr,
+            midpointMjdTai,
+            ra,
+            dec,
+            phaseAngle,
+            topocentricDist,
+            heliocentricDist,
             reduced_mag,
             len(data_table),
         )

src/adler/dataclasses/SSObject.py

@@ -61,11 +61,11 @@ class SSObject:
     firstObservationDate: float = 0.0
     arc: float = 0.0
     numObs: int = 0
-    H: np.ndarray = field(default_factory=np.zeros(0))
-    G12: np.ndarray = field(default_factory=np.zeros(0))
-    Herr: np.ndarray = field(default_factory=np.zeros(0))
-    G12err: np.ndarray = field(default_factory=np.zeros(0))
-    nData: np.ndarray = field(default_factory=np.zeros(0))
+    H: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    G12: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    Herr: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    G12err: np.ndarray = field(default_factory=lambda: np.zeros(0))
+    nData: np.ndarray = field(default_factory=lambda: np.zeros(0))
     maxExtendedness: float = 0.0
     minExtendedness: float = 0.0
     medianExtendedness: float = 0.0
@@ -86,9 +86,9 @@ def construct_from_data_table(cls, ssObjectId, filter_list, data_table):
         for i, filter in enumerate(filter_list):
             H[i] = get_from_table(data_table, filter + "_H", "float")
             G12[i] = get_from_table(data_table, filter + "_G12", "float")
-            Herr[i] = get_from_table(data_table, filter + "_Herr", "float")
-            G12err[i] = get_from_table(data_table, filter + "_G12err", "float")
-            nData[i] = get_from_table(data_table, filter + "_nData", "int")
+            Herr[i] = get_from_table(data_table, filter + "_HErr", "float")
+            G12err[i] = get_from_table(data_table, filter + "_G12Err", "float")
+            nData[i] = get_from_table(data_table, filter + "_Ndata", "int")
 
         maxExtendedness = get_from_table(data_table, "maxExtendedness", "float")
         minExtendedness = get_from_table(data_table, "minExtendedness", "float")
@@ -110,19 +110,3 @@ def construct_from_data_table(cls, ssObjectId, filter_list, data_table):
             minExtendedness,
             medianExtendedness,
         )
-
-    def populate_from_table(self, data_table):
-        """Populates the SSObject object from the data_table class variable created on initialisation."""
-
-        self.discoverySubmissionDate = self.get_from_table(data_table, "discoverySubmissionDate", "float")
-        self.firstObservationDate = self.get_from_table(data_table, "firstObservationDate", "float")
-        self.arc = self.get_from_table(data_table, "arc", "float")
-        self.numObs = self.get_from_table(data_table, "numObs", "int")
-        self.r_H = self.get_from_table(data_table, "r_H", "float")
-        self.r_G12 = self.get_from_table(data_table, "r_G12", "float")
-        self.r_Herr = self.get_from_table(data_table, "r_Herr", "float")
-        self.r_G12Err = self.get_from_table(data_table, "r_G12err", "float")
-        self.r_nData = self.get_from_table(data_table, "r_nData", "int")
-        self.maxExtendedness = self.get_from_table(data_table, "maxExtendedness", "float")
-        self.minExtendedness = self.get_from_table(data_table, "minExtendedness", "float")
-        self.medianExtendedness = self.get_from_table(data_table, "medianExtendedness", "float")

src/adler/dataclasses/__init__.py

@@ -0,0 +1,6 @@
+from . import AdlerData
+from . import Observations
+from . import dataclass_utilities
+from . import MPCORB
+from . import AdlerPlanetoid
+from . import SSObject