From 18fd3fc4a7142281cf87d2b15ee86f19d9a9e3eb Mon Sep 17 00:00:00 2001
From: Piotr Tynecki <contact@pypassion.com>
Date: Fri, 23 Oct 2020 07:18:40 +0200
Subject: [PATCH] Extended KMersTransformer to support editable sliding window

---
 CHANGELOG.md                              |  5 +++++
 docs/conf.py                              |  2 +-
 phages2050/features/transformers/kmers.py | 16 +++++++++-------
 setup.py                                  |  2 +-
 4 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index ca65929..0e6a459 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,6 +2,11 @@
 All notable changes to this project will be documented in this file.
 
 
+## [0.0.9] - 23.10.2020
+### Changed
+* Extended `KMersTransformer` to support editable sliding window;
+
+
 ## [0.0.8] - 11.10.2020
 ### Added
 * Initial online documentation;
diff --git a/docs/conf.py b/docs/conf.py
index 82bd87d..b8ce597 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -22,7 +22,7 @@
 author = 'Piotr Tynecki, Iwona Świętochowska, Yana Minina, Przemysław Mitura, Wojciech Łaguna'
 
 # The full version, including alpha/beta/rc tags
-release = version = '0.0.8'
+release = version = '0.0.9'
 
 
 # -- General configuration ---------------------------------------------------
diff --git a/phages2050/features/transformers/kmers.py b/phages2050/features/transformers/kmers.py
index 1106a58..995dc84 100644
--- a/phages2050/features/transformers/kmers.py
+++ b/phages2050/features/transformers/kmers.py
@@ -20,12 +20,13 @@
 
 class KMersTransformer(BaseEstimator, TransformerMixin):
     """
-    K-mer transformer is responsible to extract set of
-    words which are subsequences of length (6 by default)
-    contained within a biological sequence
+    K-mer transformer is responsible to extract set of words -
+    using configurable sliding window - which are subsequences
+    of length (6 by default) contained within a biological sequence
 
-    Each of the word is called k-mer and are composed of
-    nucleotides (i.e. A, T, G, and C)
+    Each of the word is called k-mer and are composed of nucleotides
+    (i.e. A, T, G, and C). Each word which includes other characters
+    is removed from the output
 
     Example:
         fname = 'NC_001604.fasta'
@@ -37,9 +38,10 @@ class KMersTransformer(BaseEstimator, TransformerMixin):
         kmt.transform(sample)
     """
 
-    def __init__(self, size: int = 6):
+    def __init__(self, size: int = 6, sliding_window: int = 1):
         self.accepted_chars: Set[str] = {"A", "C", "T", "G"}
         self.size: int = size
+        self.sliding_window: int = sliding_window
 
     def _extract_kmers_from_sequence(self, sequence: str) -> str:
         """
@@ -57,7 +59,7 @@ def _extract_kmers_from_sequence(self, sequence: str) -> str:
         return " ".join(
             [
                 sequence[x : x + self.size]
-                for x in range(len(sequence) - self.size + 1)
+                for x in range(0, len(sequence) - self.size + 1, self.sliding_window)
                 if not set(sequence[x : x + self.size]) - self.accepted_chars
             ]
         )
diff --git a/setup.py b/setup.py
index d81983f..88964e7 100644
--- a/setup.py
+++ b/setup.py
@@ -17,7 +17,7 @@
 dependencies = list(map(str.strip, filter(None, dependencies.split("\n"))))
 
 
-version = "0.0.8"
+version = "0.0.9"
 
 setup(
     name="phages2050",