work in progress

.pydevproject

@@ -1,17 +1,26 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
 <?eclipse-pydev version="1.0"?><pydev_project>
-
+
+
     <pydev_pathproperty name="org.python.pydev.PROJECT_SOURCE_PATH">
         <path>/${PROJECT_DIR_NAME}/src/kstream</path>
         <path>/${PROJECT_DIR_NAME}/src/krisp</path>
         <path>/${PROJECT_DIR_NAME}/src/diagvar</path>
+        <path>/${PROJECT_DIR_NAME}/src</path>
+        <path>/${PROJECT_DIR_NAME}</path>
     </pydev_pathproperty>
-
+
+
     <pydev_property name="org.python.pydev.PYTHON_PROJECT_VERSION">python interpreter</pydev_property>
-
+
+
     <pydev_property name="org.python.pydev.PYTHON_PROJECT_INTERPRETER">venv python 3</pydev_property>
+
 
     <pydev_pathproperty name="org.python.pydev.PROJECT_EXTERNAL_SOURCE_PATH">
+
         <path>/media/fosterz/external_ssd_2/files/projects/work/current/krisp/.venv/lib/python3.9/site-packages</path>
+
     </pydev_pathproperty>
+
 </pydev_project>

Makefile

@@ -3,9 +3,11 @@ install:
 	python3 -m pip install --upgrade setuptools	
 	python3 -m pip install --upgrade build
 	python3 -m pip install --upgrade colorama
-	python3 -m build --no-isolation .
-	python3 -m pip install dist/krisp-1.0.0-py3-none-any.whl --force-reinstall
+	python3 -m build .
+	python3 -m pip install --editable .
 
 uninstall:
 	python3 -m pip uninstall krisp
 
+test:
+	python3 -m unittest discover

misc_scripts/ex_data_for_mireia.py

@@ -0,0 +1,18 @@
+def my_new_function(my_arg1, my_arg2, my_opt = TRUE):
+    # All the code
+    return None
+
+
+
+ref =            ["A", "C", "GTC", "T",   "T", "G",  "G",         "C", "C"]
+seqs = {"seq 1": ["A", "G", "GTC", "T/G", "T", "GC", "G",         "A", "C"],
+        "seq 2": ["A", "G", "G",   "T",   "",  "G",  "<123G12?>", "A", "C"]}
+
+my_new_function(ref, seqs, mask_same = TRUE)
+
+# Should print:
+#
+# Reference : ACGTC T TG-    G    CC
+#     seq 1 : .G...T/GTGC    G    A.
+#     seq 2 : .G.-- T -G-<1234G2?>A. 
+

scratch/demo.py

@@ -0,0 +1,68 @@
+
+
+
+
+
+def _mask_same(seqs, reference):
+	"""
+	Parameters
+	----------
+	seqs : dict of list of str
+		sequecnes to align, named by group
+	reference : list of str
+		The refenrece used to call variants	
+	
+	Returns
+	-------
+	list str
+		Modified version of seqs
+	"""
+	for group in seqs.keys():
+		for index in range(len(seqs[group])):
+			if seqs[group][i] == reference[i]:
+				seqs[group][i] = "."
+	return(seqs)
+
+def _pad_columns(seqs, reference):
+	"""Adding space to account for formatting (non indels)."""
+	return seqs, reference
+
+def _pad_indel(seqs, reference):
+	"""Add dashes to pad indels."""
+	return seqs, reference
+
+def _print_alignment(seqs, reference, ref_name = "Reference"):
+	ref_name = ref_name.rjust(max_len, " ")
+	print(f'{ref_name} : ' + ''.join(reference))
+	for group_name, seq in seqs.items():
+		group_name = group_name.rjust(max_len, " ")
+		print(group_name + ' : ' + ''.join(seq))
+
+
+def render_variant(seqs, reference):
+	"""my short summary
+	
+	my llong summaryyyyyyyyyyyyyyyyyyyyyyyyyyyyy
+	yyyyyyyyyyyyyyyyyyyyyyyy
+	yyyyyyyyyyyy
+	
+	Parameters
+	----------
+	seqs : dict of list of str
+		sequecnes to align, named by group
+	reference : list of str
+		The refenrece used to call variants
+	"""
+
+	seqs = _mask_same(seqs, reference)
+	seqs, reference = _pad_columns(seqs, reference)
+	seqs = _pad_indel(seqs, reference)
+
+	_print_alignment(seqs, reference)
+
+
+
+
+if __name__ == "__main__":
+
+	render_variant()

src/diagvar/find_diag_region.py

@@ -13,6 +13,8 @@
 from contextlib import contextmanager
 from collections import Counter
 
+from .find_diag_var import find_diag_var
+
 # Constants
 SNP_DELIM = ('<', '>')
 PRIMER_DELIM =  ('(', ')')
@@ -86,8 +88,9 @@ def find_diag_region(
     variants : an iterable returning variants or str
         A series of consecutive variants in which to identifiy diagnostic 
         clusters of variants.
-    groups : list/dict/tuple of list/tuple of str
-        The sample IDs for each group to find diagnostic clusters for.
+    groups : dict of list/tuple of str
+        The sample IDs for each group to find diagnostic clusters for,
+        named by group.
     nontarget : list of str, optional
         The sample IDs that should be distict from those in `groups`, but
         are otherwise not of interest. `min_samples` does not apply to these.
@@ -140,17 +143,11 @@ def find_diag_region(
         subset of samples. TBD.
     """
     flank = 100
-    group_samples = "dict of samples in each group named by group" #TODO
-    windows = {g: var_sliding_window(subset, spacer_len=spacer_len, flank_len=flank) for g, subset in group_samples.items()}
+    windows = {g: var_sliding_window(subset, spacer_len=spacer_len, flank_len=flank) for g, subset in groups.items()}
     for variant in find_diag_var():
-        for group, subset in group_samples.items():
+        for group, subset in groups.items():
             windows[group].add_variant(variant)
             _check_variant_cluster(windows[group].spacer, subset)
 
-            # Check if spacer meets conditions
-            if sum([_is_diagostic(rec) for rec in windows[group].spacer]) > min_diag_var:
-                primer3_results = _primer3()
-                if "has primers":
-                    pass #yeild results