feature (featurize): added encode and nt count functions

.gitignore

@@ -100,3 +100,72 @@ ENV/
 
 # mypy
 .mypy_cache/
+
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser

setup.py

@@ -11,7 +11,7 @@
 with open('HISTORY.rst') as history_file:
     history = history_file.read()
 
-requirements = [ ]
+requirements = ['pandas', ]
 
 setup_requirements = ['pytest-runner', ]
 

sgrna_modeler/sgrna_modeler.py

@@ -1,3 +1,16 @@
 # -*- coding: utf-8 -*-
-
+import numpy as np
 """Main module."""
+nt_codes = {'A':[1,0,0,0],
+            'C':[0,1,0,0],
+            'G':[0,0,1,0],
+            'T':[0,0,0,1]}
+def encode_seqs(seqs):
+    # 3d array with samples x position x nt
+    encoded_seqs = np.array([[nt_codes.get(x) for x in seq] for seq in seqs])
+    return encoded_seqs
+
+def get_nt_count(encoded_seqs, nt):
+    counts = np.sum(encoded_seqs[:,:,nt_codes.get(nt).index(1)], axis = 1)
+    return counts
+

tests/test_sgrna_modeler.py

@@ -5,19 +5,22 @@
 
 import pytest
 
-
-from sgrna_modeler import sgrna_modeler
-
-
-@pytest.fixture
-def response():
-    """Sample pytest fixture.
-
-    See more at: http://doc.pytest.org/en/latest/fixture.html
-    """
-    # import requests
-    # return requests.get('https://github.com/audreyr/cookiecutter-pypackage')
-
+import numpy as np
+from sgrna_modeler import sgrna_modeler as sm
+
+seqs = ['ACT','ACT','GCT','AAT','AAA']
+
+def test_encoding():
+    encoded = sm.encode_seqs(seqs)
+    np.testing.assert_array_equal(encoded[3,:,:],
+                                  np.array([[1,0,0,0],
+                                            [1,0,0,0],
+                                            [0,0,0,1]]))
+
+def test_nt_counts():
+    encoded = sm.encode_seqs(seqs)
+    A_content = sm.get_nt_count(encoded, 'A')
+    np.testing.assert_array_equal(A_content, np.array([1,1,0,2,3]))
 
 def test_content(response):
     """Sample pytest test function with the pytest fixture as an argument."""