nlp-lab/Jonas_Solutions/Exercise01.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# NLP-LAB Exercise 01 by jonas weinz\n",
    "----"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib ipympl\n",
    "import nltk\n",
    "import pprint\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.feature_extraction import DictVectorizer\n",
    "from sklearn.pipeline import Pipeline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## implementing own classifiers"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* writing an own feature funtion"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def features(sentence, index):\n",
    "    word = sentence[index]\n",
    "    is_punctuation_mark = word == \"!\" or word == \".\" or word == \",\" or word == \"?\"\n",
    "    sentence_length = len(sentence)\n",
    "    relative_third = (index * 3) // sentence_length \n",
    "    vowels = word.count('a') + word.count('e') + word.count('i') + word.count('o') + word.count('u')\n",
    "    return {\n",
    "        'word': word,\n",
    "        'is_capitalized': sentence[index][0].upper() == sentence[index][0],\n",
    "        'prefix-1': sentence[index][0],\n",
    "        'suffix-1': sentence[index][-1],\n",
    "        'prefix-2': sentence[index][1] if len(word) > 1 else '',\n",
    "        'suffix-2': sentence[index][-2] if len(word) > 1 else '',\n",
    "        'prev_word': '' if index == 0 else sentence[index - 1],\n",
    "        'next_word': '' if index == len(sentence) - 1 else sentence[index + 1],\n",
    "        'length': len(word),\n",
    "        'index' : index,\n",
    "        'rev_index': len(sentence) - index,\n",
    "        'sentence_length_': len(sentence),\n",
    "        'relative_third': relative_third,\n",
    "        'numerical': word.isnumeric(),\n",
    "        'is_punctuation_mark': is_punctuation_mark,\n",
    "        ',': word == \",\",\n",
    "        '.': word == \".\",\n",
    "        '!': word == \"!\",\n",
    "        '?': word == \"?\",\n",
    "        'vowels' : vowels\n",
    "    }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "#test_sentence = ['The','cake','is','a','lie','!']\n",
    "#for i in range(len(test_sentence)):\n",
    "#    pprint.pprint(features(test_sentence, i))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* function for creating training sets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def untag(tagged_sentence):\n",
    "    return [w for w,t in tagged_sentence]\n",
    "\n",
    "def transform_to_dataset(tagged_sentences):\n",
    "    X,y = [], []\n",
    "    \n",
    "    for s in tagged_sentences:\n",
    "        for i in range(len(s)):\n",
    "            X.append(features(untag(s),i))\n",
    "            y.append(s[i][1])\n",
    "    return X,y\n",
    "\n",
    "def create_training_and_test_set(annotated_sentences, relative_cutoff):\n",
    "    cutoff = int(relative_cutoff * len(annotated_sentences))\n",
    "    training_sentences = annotated_sentences[:cutoff]\n",
    "    test_sentences = annotated_sentences[cutoff:]\n",
    "    \n",
    "    X,y = transform_to_dataset(training_sentences)\n",
    "    tX, ty = transform_to_dataset(test_sentences)\n",
    "    \n",
    "    return X,y,tX,ty"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Decision Tree classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def train_classifier(X,y,classifier,max_size=10000):\n",
    "    clf = Pipeline([\n",
    "        ('vectorizer', DictVectorizer(sparse=False)),\n",
    "        ('classifier', classifier)\n",
    "    ])\n",
    "    \n",
    "    print(\"start training…\")\n",
    "    \n",
    "    clf.fit(\n",
    "        X if len(X) < max_size else X[:max_size],\n",
    "        y if len(y) < max_size else y[:max_size]\n",
    "    )\n",
    "    \n",
    "    print(\"training done\")\n",
    "    \n",
    "    return clf"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* classifier evaluater"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def test_classifier(clf, tX, ty):\n",
    "    accuracy = clf.score(tX, ty)\n",
    "    print(\"Accuracy: \", accuracy)\n",
    "    # TODO: more analytics\n",
    "    return accuracy"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Task 01:"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Performance 1\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Model 01\n",
    "* train and testing english custom POS tagger model:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def model_01(X,y,tX,ty, max_size=1000):\n",
    "    #classifier = DecisionTreeClassifier(criterion='entropy')\n",
    "    from sklearn.neural_network import MLPClassifier\n",
    "    model01_clf = train_classifier(X,y,MLPClassifier(),max_size=max_size)\n",
    "    return test_classifier(clf=model01_clf, tX=tX, ty=ty)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Model 02"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "def model_02(tX,ty):\n",
    "    m2_y = nltk.pos_tag([w['word'] for w in tX])\n",
    "    # compare results\n",
    "    n_correct = sum((1 if m2_y[i][1] == ty[i] else 0) for i in range(len(ty)))\n",
    "    return n_correct / len(ty)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Model 03"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def model_03(corpus_tagged, corpus_sents, cut=0.8):\n",
    "    \n",
    "    patterns = [(r'.*ing$', 'VBG'), (r'.*ed$', 'VBD'), (r'.*es$', 'VBZ'), (r'.*ould$', 'MD'), (r'.*\\'s$', 'NN$'),               \n",
    "             (r'.*s$', 'NNS'), (r'^-?[0-9]+(.[0-9]+)?$', 'CD'), (r'.*', 'NN')]\n",
    "    \n",
    "    s = int(len(corpus_tagged) * cut)\n",
    "    train_sents = corpus_tagged[:s]\n",
    "    test_sents = corpus_tagged[s:]\n",
    "    \n",
    "    models = {\n",
    "        'def_model': nltk.DefaultTagger('NN'),\n",
    "        'regexp_model': nltk.RegexpTagger(patterns),\n",
    "        'uni_model': nltk.UnigramTagger(train_sents),\n",
    "        'bi_model': nltk.BigramTagger(train_sents),\n",
    "        'tri_model': nltk.TrigramTagger(train_sents)\n",
    "    }\n",
    "    \n",
    "    performance = {}\n",
    "    for name,model in models.items():\n",
    "        performance[name] = model.evaluate(test_sents)\n",
    "    \n",
    "    return performance\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Applying models on Datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Pierre', 'NNP'),\n",
       " ('Vinken', 'NNP'),\n",
       " (',', ','),\n",
       " ('61', 'CD'),\n",
       " ('years', 'NNS'),\n",
       " ('old', 'JJ'),\n",
       " (',', ','),\n",
       " ('will', 'MD'),\n",
       " ('join', 'VB'),\n",
       " ('the', 'DT'),\n",
       " ('board', 'NN'),\n",
       " ('as', 'IN'),\n",
       " ('a', 'DT'),\n",
       " ('nonexecutive', 'JJ'),\n",
       " ('director', 'NN'),\n",
       " ('Nov.', 'NNP'),\n",
       " ('29', 'CD'),\n",
       " ('.', '.')]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "P1.1\n",
      "start training…\n",
      "training done\n",
      "Accuracy:  0.7755377014821099\n",
      "P1.2\n",
      "P1.3\n",
      "P1.4\n",
      "start training…\n",
      "training done\n",
      "Accuracy:  0.63253390325317\n",
      "P1.5\n",
      "P1.6\n",
      "{'P1.1': 0.7755377014821099,\n",
      " 'P1.2': 0.8936074654423873,\n",
      " 'P1.3 -- bi_model': 0.1132791057437996,\n",
      " 'P1.3 -- def_model': 0.1447677029791906,\n",
      " 'P1.3 -- regexp_model': 0.24232746145017217,\n",
      " 'P1.3 -- tri_model': 0.06736863116922003,\n",
      " 'P1.3 -- uni_model': 0.8608213982733669,\n",
      " 'P1.4': 0.63253390325317,\n",
      " 'P1.5': 0.6044583741861567,\n",
      " 'P1.6 -- bi_model': 0.1132791057437996,\n",
      " 'P1.6 -- def_model': 0.1447677029791906,\n",
      " 'P1.6 -- regexp_model': 0.24232746145017217,\n",
      " 'P1.6 -- tri_model': 0.06736863116922003,\n",
      " 'P1.6 -- uni_model': 0.8608213982733669}\n"
     ]
    }
   ],
   "source": [
    "performances = {}\n",
    "\n",
    "treebank_tagged = nltk.corpus.treebank.tagged_sents()\n",
    "treebank_sents = nltk.corpus.treebank.sents()\n",
    "\n",
    "brown_tagged = nltk.corpus.brown.tagged_sents()#(categories='news')\n",
    "brown_sents = nltk.corpus.brown.sents()#(categories='news')\n",
    "\n",
    "display(treebank_tagged[0])\n",
    "\n",
    "X1,y1,tX1,ty1 = create_training_and_test_set(annotated_sentences=treebank_tagged, \n",
    "                                         relative_cutoff=0.8)\n",
    "\n",
    "X2,y2,tX2,ty2 = create_training_and_test_set(annotated_sentences=brown_tagged, \n",
    "                                         relative_cutoff=0.8)\n",
    "\n",
    "\n",
    "print(\"P1.1\")\n",
    "performances['P1.1'] = model_01(X1,y1,tX1,ty1)\n",
    "\n",
    "print(\"P1.2\")\n",
    "performances['P1.2'] = model_02(tX1,ty1)\n",
    "\n",
    "print(\"P1.3\")\n",
    "p3 = model_03(treebank_tagged, treebank_sents)\n",
    "for k,v in p3.items():\n",
    "    performances[\"P1.3 -- \" + k] = v\n",
    "\n",
    "print(\"P1.4\")\n",
    "performances['P1.4'] = model_01(X2,y2,tX2,ty2)\n",
    "\n",
    "print(\"P1.5\")\n",
    "performances['P1.5'] = model_02(tX2,ty2)\n",
    "\n",
    "print(\"P1.6\")\n",
    "p6 = model_03(brown_tagged, brown_sents)\n",
    "for k,v in p3.items():\n",
    "    performances[\"P1.6 -- \" + k] = v\n",
    "\n",
    "pprint.pprint(performances)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c6d8e1186c1f44dcb77b146346b1dedb",
       "version_major": 2,
       "version_minor": 0
      },
      "text/html": [
       "<p>Failed to display Jupyter Widget of type <code>FigureCanvasNbAgg</code>.</p>\n",
       "<p>\n",
       "  If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
       "  that the widgets JavaScript is still loading. If this message persists, it\n",
       "  likely means that the widgets JavaScript library is either not installed or\n",
       "  not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
       "  Widgets Documentation</a> for setup instructions.\n",
       "</p>\n",
       "<p>\n",
       "  If you're reading this message in another frontend (for example, a static\n",
       "  rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
       "  it may mean that your frontend doesn't currently support widgets.\n",
       "</p>\n"
      ],
      "text/plain": [
       "FigureCanvasNbAgg()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "#weights = clf.named_steps['classifier'].feature_importances_\n",
    "#labels = clf.named_steps['vectorizer'].get_feature_names()\n",
    "\n",
    "#sort\n",
    "#weights, labels = (list(t) for t in zip(*sorted(zip(weights, labels))))\n",
    "\n",
    "fig_1, ax_1 = plt.subplots()\n",
    "plt.bar(np.arange(len(performances)), performances.values())\n",
    "plt.xticks(np.arange(len(performances)), performances.keys(), rotation=30, ha='right')\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "----\n",
    "## Task 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "WORDS = 'words'   #: column type for words\n",
    "POS = 'pos'       #: column type for part-of-speech tags\n",
    "TREE = 'tree'     #: column type for parse trees\n",
    "CHUNK = 'chunk'   #: column type for chunk structures\n",
    "NE = 'ne'         #: column type for named entities\n",
    "SRL = 'srl'       #: column type for semantic role labels\n",
    "IGNORE = 'ignore' #: column type for column that should be ignored\n",
    "train_path = \"./ru_syntagrus-ud-train.conllu\"\n",
    "ru_corp = nltk.corpus.ConllCorpusReader(root=\"./\", \n",
    "                              fileids=[\"ru_syntagrus-ud-train-uncommented.conllu\"],\n",
    "                              columntypes=[IGNORE, WORDS, IGNORE, POS],\n",
    "                                       encoding='utf-8')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "ru_tagged = ru_corp.tagged_sents()\n",
    "\n",
    "\n",
    "\n",
    "X3,y3,tX3,ty3 = create_training_and_test_set(annotated_sentences=ru_tagged, \n",
    "                                         relative_cutoff=0.8)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Model 04, Performance 2.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "P2.1\n",
      "start training…\n",
      "training done\n",
      "Accuracy:  0.7079014288483687\n",
      "0.7079014288483687\n"
     ]
    }
   ],
   "source": [
    "print(\"P2.1\")\n",
    "performances2 = {}\n",
    "performances2['P2.1'] = model_01(X3,y3,tX3,ty3, max_size=1000)\n",
    "print(performances2['P2.1'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Model 05, Performance 2.2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# write russian text out to file:\n",
    "f = open(\"ru_text.txt\", 'w')\n",
    "for sentence in ru_tagged:\n",
    "    for word, tag in sentence:\n",
    "        f.write(word + \" \")\n",
    "    f.write(\"\\n\")\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* download the python 3 fork of the rdrpos-tagger: https://github.com/jacopofar/RDRPOSTagger-python-3\n",
    "* adjust `RDRPOS_TAGGER_PATH` to match with the download location"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/home/jonas/Dokumente/gitRepos/NLP-LAB/Jonas_Solutions\n"
     ]
    }
   ],
   "source": [
    "import sys, os\n",
    "\n",
    "dir_path = os.getcwd()\n",
    "print(dir_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Node', '__builtins__', '__cached__', '__doc__', '__file__', '__loader__', '__name__', '__package__', '__spec__', 'tabStr']\n",
      "('\\nOutput file:', 'ru_text.txt.TAGGED')\n"
     ]
    }
   ],
   "source": [
    "RDRPOS_TAGGER_PATH = r\"/home/jonas/src/RDRPOSTagger-python-3/pSCRDRtagger/\"\n",
    "\n",
    "sys.path.insert(0, RDRPOS_TAGGER_PATH)\n",
    "os.chdir(RDRPOS_TAGGER_PATH)\n",
    "\n",
    "import RDRPOSTagger as model05_tagger \n",
    "\n",
    "r = model05_tagger.RDRPOSTagger()\n",
    "r.constructSCRDRtreeFromRDRfile(\"../Models/UniPOS/UD_Russian-SynTagRus/train.UniPOS.RDR\")\n",
    "DICT = model05_tagger.readDictionary(\"../Models/UniPOS/UD_Russian-SynTagRus/train.UniPOS.DICT\")\n",
    "\n",
    "os.chdir(dir_path)\n",
    "\n",
    "r.tagRawCorpus(DICT, \"ru_text.txt\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "tagged_words = []\n",
    "f = open(\"ru_text.txt.TAGGED\", 'r')\n",
    "for line in f:\n",
    "    for splits in line.split():\n",
    "        cmp = splits.rsplit('/',1)\n",
    "        if len(cmp) != 2:\n",
    "            print(\"error parsing: \", cmp)\n",
    "        else:\n",
    "            w,t = cmp\n",
    "            tagged_words.append((w,t))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "score_2_2 = 0\n",
    "i = 0\n",
    "for sent in ru_tagged:\n",
    "    for tagged_w in sent:\n",
    "        if tagged_w[1] == tagged_words[i][1]:\n",
    "            score_2_2 += 1\n",
    "        i += 1\n",
    "performances2['P2.2'] = score_2_2 / len(tagged_words)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Results of performance 2.2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'P2.1': 0.7079014288483687, 'P2.2': 0.8899716702179293}\n"
     ]
    }
   ],
   "source": [
    "pprint.pprint(performances2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "aeb29243e58d49b8942122ceec03fab5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/html": [
       "<p>Failed to display Jupyter Widget of type <code>FigureCanvasNbAgg</code>.</p>\n",
       "<p>\n",
       "  If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
       "  that the widgets JavaScript is still loading. If this message persists, it\n",
       "  likely means that the widgets JavaScript library is either not installed or\n",
       "  not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
       "  Widgets Documentation</a> for setup instructions.\n",
       "</p>\n",
       "<p>\n",
       "  If you're reading this message in another frontend (for example, a static\n",
       "  rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
       "  it may mean that your frontend doesn't currently support widgets.\n",
       "</p>\n"
      ],
      "text/plain": [
       "FigureCanvasNbAgg()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig_2, ax_2 = plt.subplots()\n",
    "plt.bar(np.arange(len(performances2)), performances2.values())\n",
    "plt.xticks(np.arange(len(performances2)), performances2.keys(), rotation=30, ha='right')\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}