Clean up chapters

DOsinga · Jan 16, 2018 · 6dd4900 · 6dd4900
1 parent baf1af3
commit 6dd4900
Show file tree

Hide file tree

Showing 13 changed files with 2,484 additions and 1,667 deletions.
diff --git a/03.1 Using pre build word embeddings.ipynb b/03.1 Using pre build word embeddings.ipynb
diff --git a/...king using word2vec cosine distance.ipynb → ...king using word2vec cosine distance.ipynb b/...king using word2vec cosine distance.ipynb → ...king using word2vec cosine distance.ipynb
diff --git a/...1 Collect movie data from Wikipedia.ipynb → 04.1 Collect movie data from Wikipedia.ipynb b/...1 Collect movie data from Wikipedia.ipynb → 04.1 Collect movie data from Wikipedia.ipynb
@@ -39,33 +39,44 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 2,
+   "metadata": {},
    "outputs": [],
    "source": [
     "index = requests.get('https://dumps.wikimedia.org/enwiki/').text"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 3,
+   "metadata": {},
    "outputs": [],
    "source": [
     "soup_index = BeautifulSoup(index, 'html.parser')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['20171001/',\n",
+       " '20171020/',\n",
+       " '20171103/',\n",
+       " '20171120/',\n",
+       " '20171201/',\n",
+       " '20171220/',\n",
+       " '20180101/']"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "dumps = [a['href'] for a in soup_index.find_all('a') \n",
     "             if a.has_attr('href') and a.text[:-1].isdigit()]\n",
@@ -81,14 +92,14 @@
    "outputs": [],
    "source": [
     "for dump_url in sorted(dumps, reverse=True):\n",
-    "  print(dump_url)\n",
-    "  dump_html = index = requests.get('https://dumps.wikimedia.org/enwiki/' + dump_url).text\n",
-    "  soup_dump = BeautifulSoup(dump_html, 'html.parser')\n",
-    "  pages_xml = [a['href'] for a in soup_dump.find_all('a') \n",
-    "             if a.has_attr('href') and a['href'].endswith('-pages-articles.xml.bz2')]\n",
-    "  if pages_xml:\n",
-    "    break\n",
-    "  time.sleep(0.8)"
+    "    print(dump_url)\n",
+    "    dump_html = index = requests.get('https://dumps.wikimedia.org/enwiki/' + dump_url).text\n",
+    "    soup_dump = BeautifulSoup(dump_html, 'html.parser')\n",
+    "    pages_xml = [a['href'] for a in soup_dump.find_all('a') \n",
+    "                 if a.has_attr('href') and a['href'].endswith('-pages-articles.xml.bz2')]\n",
+    "    if pages_xml:\n",
+    "        break\n",
+    "    time.sleep(0.8)"
    ]
   },
   {

diff --git a/...m based on outgoing Wikipedia links.ipynb → ...m based on outgoing Wikipedia links.ipynb b/...m based on outgoing Wikipedia links.ipynb → ...m based on outgoing Wikipedia links.ipynb
@@ -40,7 +40,9 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "with open('data/wp_movies_10k.ndjson') as fin:\n",
@@ -109,7 +111,9 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "def movie_embedding_model(embedding_size=30):\n",
@@ -386,7 +390,9 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "rotten_y = np.asarray([float(movie[-2][:-1]) / 100 for movie in movies if movie[-2]])\n",
@@ -515,7 +521,9 @@
   {
    "cell_type": "code",
    "execution_count": 43,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "gross_y = np.asarray([gr for gr in movie_gross if gr])\n",

diff --git a/1.1 Using pre build word embeddings.ipynb b/1.1 Using pre build word embeddings.ipynb