Feature bio checks (#274)

* Added bio checks module

* Added bio checks and logic check

* Added kwargs to the add rule method

cuallee/__init__.py

@@ -12,7 +12,7 @@
 from toolz.curried import map as map_curried
 
 logger = logging.getLogger("cuallee")
-__version__ = "0.10.2"
+__version__ = "0.12.2"
 # Verify Libraries Available
 # ==========================
 try:
@@ -245,10 +245,12 @@ def __init__(
         self.table_name = table_name
         try:
             from .iso.checks import ISO
+            from .bio.checks import BioChecks
 
             self.iso = ISO(self)
-        except (ModuleNotFoundError, ImportError):
-            logger.error("ISO module requires requests")
+            self.bio = BioChecks(self)
+        except (ModuleNotFoundError, ImportError) as err:
+            logger.error(f"Dependency modules missing: {str(err)}")
         self.session = session
 
     def __repr__(self):
@@ -287,15 +289,15 @@ def _remove_rule_generic(self, key: str):
         if key in self._rule:
             self._rule.pop(key)
 
-    def add_rule(self, method: str, *arg):
+    def add_rule(self, method: str, *arg, **kwargs):
         """
         Add a new rule to the Check class.
 
         Args:
             method (str): Check name
             arg (list): Parameters of the check
         """
-        return operator.methodcaller(method, *arg)(self)
+        return operator.methodcaller(method, *arg, **kwargs)(self)
 
     def delete_rule_by_key(self, keys: Union[str, List[str]]):
         """

cuallee/bio/amino_acids.csv

@@ -0,0 +1,23 @@
+amino_acid,3_letter_code,1_letter_code
+alanine,ala,A
+arginine,arg,R
+asparagine,asn,N
+aspartic acid,asp,D
+asparagine or aspartic acid,asx,B
+cysteine,cys,C
+glutamic acid,glu,E
+glutamine,gln,Q
+glutamine or glutamic acid,glx,Z
+glycine,gly,G
+histidine,his,H
+isoleucine,ile,I
+leucine,leu,L
+lysine,lys,K
+methionine,met,M
+phenylalanine,phe,F
+proline,pro,P
+serine,ser,S
+threonine,thr,T
+tryptophan,trp,W
+tyrosine,tyr,Y
+valine,val,V

cuallee/bio/checks.py

@@ -0,0 +1,25 @@
+from .. import Check
+import pandas as pd
+from pathlib import Path
+
+
+class BioChecks:
+    def __init__(self, check: Check):
+        self._check = check
+        try:
+            parent_path = Path(__file__).parent
+            self._aminoacids = pd.read_csv(parent_path / "amino_acids.csv")
+        except Exception:
+            raise Exception("Unable to load aminoacid definitions")
+
+    def is_dna(self, column: str):
+        """Validates that a sequence contains only valid nucleotide bases of DNA strand"""
+        self._check.has_pattern(column, r"^[GTCA]*$")
+        return self._check
+
+    def is_protein(self, column: str):
+        """Verifies that country codes are valid against the ISO standard 3166"""
+        self._check.has_pattern(
+            column, rf"^[{''.join(self._aminoacids['1_letter_code'].tolist())}]*$"
+        )
+        return self._check

cuallee/logic/__init__.py

@@ -0,0 +1,9 @@
+from .. import Check
+from typing import Dict
+
+
+class LogicCheck:
+    """Performs logical inference on evaluated checks"""
+
+    def __init__(self, checks: Dict[str, Check] = {}):
+        pass

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cuallee"
-version = "0.12.1"
+version = "0.12.2"
 authors = [
   { name="Herminio Vazquez", email="[email protected]"},
   { name="Virginie Grosboillot", email="[email protected]" }
@@ -78,4 +78,5 @@ ignore = ["E731"]
 
 [project.urls]
 "Homepage" = "https://github.com/canimus/cuallee"
-"Bug Tracker" = "https://github.com/canimus/cuallee"
+"Bug Tracker" = "https://github.com/canimus/cuallee"
+

setup.cfg

@@ -1,5 +1,6 @@
 [metadata]
 name = cuallee
-version = 0.12.1
+version = 0.12.2
 [options]
-packages = find:
+packages = find:
+include_package_data = True

test/unit/dagster_checks/test_methods.py

@@ -3,6 +3,7 @@
 import pandas as pd
 from typing import Iterator
 
+
 def test_make_checks():
     df = pd.DataFrame({"id": [1, 2, 3, 4, 5]})
     check = Check(CheckLevel.WARNING, "Dagster")