Updates to Chapter 5 notebooks

Author: ScottMcCormack

chapter_5/0501_Dependency_Parsing.ipynb

@@ -4,12 +4,12 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {
-    "collapsed": true
+    "tags": []
    },
    "outputs": [],
    "source": [
-    "from spacy.en import English\n",
-    "parser = English()"
+    "import spacy\n",
+    "parser = spacy.load(\"en_core_web_sm\")"
    ]
   },
   {
@@ -20,7 +20,8 @@
     {
      "data": {
       "text/plain": [
-       "['__bytes__',\n",
+       "['_',\n",
+       " '__bytes__',\n",
        " '__class__',\n",
        " '__delattr__',\n",
        " '__dir__',\n",
@@ -32,6 +33,7 @@
        " '__gt__',\n",
        " '__hash__',\n",
        " '__init__',\n",
+       " '__init_subclass__',\n",
        " '__le__',\n",
        " '__len__',\n",
        " '__lt__',\n",
@@ -58,40 +60,52 @@
        " 'ent_id_',\n",
        " 'ent_iob',\n",
        " 'ent_iob_',\n",
+       " 'ent_kb_id',\n",
+       " 'ent_kb_id_',\n",
        " 'ent_type',\n",
        " 'ent_type_',\n",
-       " 'has_repvec',\n",
+       " 'get_extension',\n",
+       " 'has_dep',\n",
+       " 'has_extension',\n",
+       " 'has_head',\n",
+       " 'has_morph',\n",
        " 'has_vector',\n",
        " 'head',\n",
        " 'i',\n",
        " 'idx',\n",
+       " 'iob_strings',\n",
        " 'is_alpha',\n",
        " 'is_ancestor',\n",
-       " 'is_ancestor_of',\n",
        " 'is_ascii',\n",
        " 'is_bracket',\n",
+       " 'is_currency',\n",
        " 'is_digit',\n",
        " 'is_left_punct',\n",
        " 'is_lower',\n",
        " 'is_oov',\n",
        " 'is_punct',\n",
        " 'is_quote',\n",
        " 'is_right_punct',\n",
+       " 'is_sent_end',\n",
+       " 'is_sent_start',\n",
        " 'is_space',\n",
        " 'is_stop',\n",
        " 'is_title',\n",
+       " 'is_upper',\n",
        " 'lang',\n",
        " 'lang_',\n",
        " 'left_edge',\n",
        " 'lefts',\n",
        " 'lemma',\n",
        " 'lemma_',\n",
+       " 'lex',\n",
        " 'lex_id',\n",
        " 'like_email',\n",
        " 'like_num',\n",
        " 'like_url',\n",
        " 'lower',\n",
        " 'lower_',\n",
+       " 'morph',\n",
        " 'n_lefts',\n",
        " 'n_rights',\n",
        " 'nbor',\n",
@@ -105,19 +119,23 @@
        " 'prefix_',\n",
        " 'prob',\n",
        " 'rank',\n",
-       " 'repvec',\n",
+       " 'remove_extension',\n",
        " 'right_edge',\n",
        " 'rights',\n",
+       " 'sent',\n",
+       " 'sent_start',\n",
        " 'sentiment',\n",
+       " 'set_extension',\n",
+       " 'set_morph',\n",
        " 'shape',\n",
        " 'shape_',\n",
        " 'similarity',\n",
-       " 'string',\n",
        " 'subtree',\n",
        " 'suffix',\n",
        " 'suffix_',\n",
        " 'tag',\n",
        " 'tag_',\n",
+       " 'tensor',\n",
        " 'text',\n",
        " 'text_with_ws',\n",
        " 'vector',\n",
@@ -132,7 +150,7 @@
     }
    ],
    "source": [
-    "# Recell that spaCy gives us a lot of information about each token when it parses\n",
+    "# Recall that spaCy gives us a lot of information about each token when it parses\n",
     "tokens = parser('She ran')\n",
     "dir(tokens[0])"
    ]
@@ -141,7 +159,7 @@
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {
-    "collapsed": true
+    "tags": []
    },
    "outputs": [],
    "source": [
@@ -177,7 +195,7 @@
    "cell_type": "code",
    "execution_count": 5,
    "metadata": {
-    "collapsed": true
+    "tags": []
    },
    "outputs": [],
    "source": [
@@ -207,20 +225,11 @@
    "source": [
     "show_dep(\"She hit the wall.\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -234,9 +243,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.8.10"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

chapter_5/0502_Head_of_a_Sentence.ipynb

@@ -4,13 +4,13 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {
-    "collapsed": true
+    "tags": []
    },
    "outputs": [],
    "source": [
     "# Recall that we can show the part of speech, the dependency, and the head of each token\n",
-    "from spacy.en import English\n",
-    "parser = English()\n",
+    "import spacy\n",
+    "parser = spacy.load(\"en_core_web_sm\")\n",
     "def show_dep(text):\n",
     "    tokens = parser(text)\n",
     "    for token in tokens:\n",
@@ -45,14 +45,14 @@
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {
-    "collapsed": true
+    "tags": []
    },
    "outputs": [],
    "source": [
     "def get_head_of_sentence(text):\n",
     "    tokens = parser(text)\n",
     "    for token in tokens:\n",
-    "        if token.head is token:\n",
+    "        if token.head == token:\n",
     "            return token\n",
     "    return None"
    ]
@@ -76,20 +76,11 @@
    "source": [
     "get_head_of_sentence(\"She hit the wall.\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -103,9 +94,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.8.10"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

chapter_5/0503_Entity_Recognition.ipynb

@@ -3,21 +3,17 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "from spacy.en import English\n",
-    "parser = English()"
+    "import spacy\n",
+    "parser = spacy.load(\"en_core_web_sm\")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def show_ents(text):\n",
@@ -82,7 +78,7 @@
       "$ \n",
       "50 MONEY\n",
       "and \n",
-      "50 CARDINAL\n",
+      "50 \n",
       "dollars \n",
       "on \n",
       "March DATE\n",
@@ -92,13 +88,12 @@
       "\n",
       "Just showing the entities ....\n",
       "MONEY 50\n",
-      "CARDINAL 50\n",
       "DATE March 12 , 2016\n"
      ]
     }
    ],
    "source": [
-    "# Another example\n",
+    "# Another example (Note: \"50\" doesn't show as a CARDINAL entity in this version of spacy)\n",
     "show_ents(\"I paid $50 and 50 dollars on March 12, 2016\")"
    ]
   },
@@ -134,9 +129,7 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# I O B format\n",
@@ -170,20 +163,11 @@
    "source": [
     "show_ent_IOB(\"I went to New Orleans to speak French.\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -197,9 +181,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.8.10"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }