Add slides

ewinge · Sep 22, 2015 · b6c6ecd · b6c6ecd
commit b6c6ecd
Show file tree

Hide file tree

Showing 7 changed files with 182 additions and 0 deletions.
diff --git a/03_python_summary-beamer-handouts2x3.pdf b/03_python_summary-beamer-handouts2x3.pdf
diff --git a/03_python_summary-beamer.pdf b/03_python_summary-beamer.pdf
diff --git a/06_encoding-beamer-handouts2x3.pdf b/06_encoding-beamer-handouts2x3.pdf
diff --git a/06_encoding-beamer.pdf b/06_encoding-beamer.pdf
diff --git a/06_peer_review-beamer-handouts2x3.pdf b/06_peer_review-beamer-handouts2x3.pdf
diff --git a/06_peer_review-beamer.pdf b/06_peer_review-beamer.pdf
diff --git a/Unicode in Python.ipynb b/Unicode in Python.ipynb
@@ -0,0 +1,182 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Lets read in a UTF-8 file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Bokm\\xc3\\xa5l'"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# -*- coding: utf-8 -*-                                                                                                                                                                                              \n",
+    "                                                                                                                                                                                                                     \n",
+    "# wget http://fil.nrk.no/yr/viktigestader/noreg.txt                                                                                                                                                                  \n",
+    "                                                                                                                                                                                                                     \n",
+    "f = open(\"noreg.txt\", \"r\")                                                                                                                                                                                           \n",
+    "                                                                                                                                                                                                                     \n",
+    "s_utf8 = f.readline().split(\"\\t\")[12]     \n",
+    "s_utf8"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "7\n"
+     ]
+    }
+   ],
+   "source": [
+    "print len(s_utf8)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<type 'unicode'>\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "u'Bokm\\xe5l'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "s_unicode = s_utf8.decode(\"utf-8\")\n",
+    "print type(s_unicode)\n",
+    "s_unicode"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "6\n"
+     ]
+    }
+   ],
+   "source": [
+    "print len(s_unicode)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<type 'str'>\n",
+      "<type 'unicode'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "print type(\"Bokmål\")                                                                                                                                                                                                 \n",
+    "print type(u\"Bokmål\")                                                                                                                                                                                                "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "True\n",
+      "False\n",
+      "True\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/usr/local/lib/python2.7/dist-packages/IPython/kernel/__main__.py:2: UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal\n",
+      "  from IPython.kernel.zmq import kernelapp as app\n"
+     ]
+    }
+   ],
+   "source": [
+    "print s_unicode == u\"Bokmål\"                                                                                                                                                                                         \n",
+    "print s_unicode == \"Bokmål\"                                                                                                                                                                                          \n",
+    "print s_unicode.encode(\"utf-8\") == \"Bokmål\" "
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 2",
+   "language": "python",
+   "name": "python2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}