beernlinux
diff --git a/‎python_patterns/patterns.ipynb
Lines changed: 57 additions & 1 deletion b/‎python_patterns/patterns.ipynb
Lines changed: 57 additions & 1 deletion
@@ -1,7 +1,7 @@
 {
  "metadata": {
   "name": "",
-  "signature": "sha256:0c9d8c8b65b0eec5bb7c2a2790f08a1e49daf27dac2c9dcfe8d85ce958046a2c"
+  "signature": "sha256:714a46a359c5b1c3e7e7bd4d19d73221f9def5bcb806840be82541070041d29e"
  },
  "nbformat": 3,
  "nbformat_minor": 0,
@@ -57,6 +57,7 @@
       "- [Differences between 2 files](#Differences-between-2-files)\n",
       "- [Differences between successive elements in a list](#Differences-between-successive-elements-in-a-list)\n",
       "- [Doctest example](#Doctest-example)\n",
+      "- [English language detection](#English-language-detection)\n",
       "- [File browsing basics](#File-browsing-basics)\n",
       "- [File reading basics](#File-reading-basics)\n",
       "- [Indices of min and max elements from a list](#Indices-of-min-and-max-elements-from-a-list)\n",
@@ -595,6 +596,61 @@
       "<br>"
      ]
     },
+    {
+     "cell_type": "heading",
+     "level": 2,
+     "metadata": {},
+     "source": [
+      "English language detection"
+     ]
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "[back to top](#Table-of-Contents)"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "import nltk\n",
+      "\n",
+      "def eng_ratio(text):\n",
+      "    ''' Returns the ratio of non-English to English words from a text '''\n",
+      "\n",
+      "    english_vocab = set(w.lower() for w in nltk.corpus.words.words()) \n",
+      "    text_vocab = set(w.lower() for w in text.split() if w.lower().isalpha()) \n",
+      "    unusual = text_vocab.difference(english_vocab)\n",
+      "    diff = len(unusual)/len(text_vocab)\n",
+      "    return diff\n",
+      "    \n",
+      "text = 'This is a test fahrrad'\n",
+      "\n",
+      "print(eng_ratio(text))"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "output_type": "stream",
+       "stream": "stdout",
+       "text": [
+        "0.2\n"
+       ]
+      }
+     ],
+     "prompt_number": 1
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "<br>\n",
+      "<br>"
+     ]
+    },
     {
      "cell_type": "heading",
      "level": 2,