From fc2497f32a37534ed1c95fe4a19481aab19d8973 Mon Sep 17 00:00:00 2001
From: Duroktar <duroktar@gmail.com>
Date: Mon, 10 Apr 2017 15:37:30 -0300
Subject: [PATCH] Update compress challenge with itertools.groupby() code

---
 .../compress/compress_solution.ipynb          | 79 +++++++++++++++----
 arrays_strings/compress/test_compress.py      |  4 +-
 2 files changed, 67 insertions(+), 16 deletions(-)

diff --git a/arrays_strings/compress/compress_solution.ipynb b/arrays_strings/compress/compress_solution.ipynb
index fbceb59..ad59c08 100644
--- a/arrays_strings/compress/compress_solution.ipynb
+++ b/arrays_strings/compress/compress_solution.ipynb
@@ -92,9 +92,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "class CompressString(object):\n",
@@ -119,6 +117,49 @@
     "        return prev_char + (str(count) if count > 1 else '')"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Algorithm 2\n",
+    "\n",
+    "Using itertools.groupby()\n",
+    "\n",
+    "- Get groups of letters and their counts.  ex: \"AAABCC\" -> ([\"A\", 3], [\"B\", 1], [\"C\", 2])\n",
+    "  - This works because itertools.groupby() returns an iterator of 2-tuples, the first item of the tuple is the current character and the second is an iterator over each occurence of said character. So we unpack each 2-tuple group using a comprehension and build it anew, this time replacing the second item of the tuple with the length of the list of occurences, giving us a result like that shown in the example above.\n",
+    "- Using string formatting inside a comprehension, we replace any count less than 2 with an empty string, effectively ignoring the 1's. The result is then string joined.\n",
+    "- Return our result if the length of the compressed string is less than the length of the original, otherwise return the original."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Code"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import itertools\n",
+    "\n",
+    "\n",
+    "class CompressString_2(object):\n",
+    "\n",
+    "    def compress_2(self, string):\n",
+    "        if string is None:\n",
+    "            return\n",
+    "\n",
+    "        groups = ([letter, len(list(group))] for letter, group in itertools.groupby(string))\n",
+    "        result = \"\".join(\"%s%s\" % (letter, count if count > 1 else '') for letter, count in groups)\n",
+    "        return result if len(result) < len(string) else string"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -128,10 +169,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 23,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -155,13 +194,15 @@
     "        assert_equal(func('AAABCCDDDDE'), 'A3BC2D4E')\n",
     "        assert_equal(func('BAAACCDDDD'), 'BA3C2D4')\n",
     "        assert_equal(func('AAABAACCDDDD'), 'A3BA2C2D4')\n",
-    "        print('Success: test_compress')\n",
+    "        print('Success: %s' % func.__name__)\n",
     "\n",
     "\n",
     "def main():\n",
     "    test = TestCompress()\n",
     "    compress_string = CompressString()\n",
+    "    compress_string_2 = CompressString_2()\n",
     "    test.test_compress(compress_string.compress)\n",
+    "    test.test_compress(compress_string_2.compress_2)\n",
     "\n",
     "\n",
     "if __name__ == '__main__':\n",
@@ -170,22 +211,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 24,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Success: test_compress\n"
+      "Success: compress\n",
+      "Success: compress_2\n"
      ]
     }
    ],
    "source": [
     "%run -i test_compress.py"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -204,9 +253,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.0"
+   "version": "3.6.1"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 1
 }
diff --git a/arrays_strings/compress/test_compress.py b/arrays_strings/compress/test_compress.py
index 6395f11..23beffa 100644
--- a/arrays_strings/compress/test_compress.py
+++ b/arrays_strings/compress/test_compress.py
@@ -10,13 +10,15 @@ class TestCompress(object):
         assert_equal(func('AAABCCDDDDE'), 'A3BC2D4E')
         assert_equal(func('BAAACCDDDD'), 'BA3C2D4')
         assert_equal(func('AAABAACCDDDD'), 'A3BA2C2D4')
-        print('Success: test_compress')
+        print('Success: %s' % func.__name__)
 
 
 def main():
     test = TestCompress()
     compress_string = CompressString()
+    compress_string_2 = CompressString_2()
     test.test_compress(compress_string.compress)
+    test.test_compress(compress_string_2.compress_2)
 
 
 if __name__ == '__main__':