nlp-lab/Jonas_Solutions/Exercise01_JonasWeinz.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 inline \n",
    "#inline for publishing on github. For jupyter lab set ipympl here\n",
    "\n",
    "import nltk\n",
    "import pprint\n",
    "#from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.feature_extraction import DictVectorizer\n",
    "from sklearn.pipeline import Pipeline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* download data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package treebank to /home/jonas/nltk_data...\n",
      "[nltk_data]   Package treebank is already up-to-date!\n",
      "[nltk_data] Downloading package brown to /home/jonas/nltk_data...\n",
      "[nltk_data]   Package brown is already up-to-date!\n",
      "[nltk_data] Downloading package punkt to /home/jonas/nltk_data...\n",
      "[nltk_data]   Package punkt is already up-to-date!\n",
      "[nltk_data] Downloading package averaged_perceptron_tagger to\n",
      "[nltk_data]     /home/jonas/nltk_data...\n",
      "[nltk_data]   Package averaged_perceptron_tagger is already up-to-\n",
      "[nltk_data]       date!\n",
      "[nltk_data] Downloading package tagsets to /home/jonas/nltk_data...\n",
      "[nltk_data]   Package tagsets is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nltk.download('treebank')\n",
    "nltk.download('brown')\n",
    "nltk.download('punkt')\n",
    "nltk.download('averaged_perceptron_tagger')\n",
    "nltk.download('tagsets')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## implementing own classifiers"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* writing an own feature funtion"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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": 4,
   "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": 5,
   "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": [
    "* Train classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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": 7,
   "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": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "def model_01(X,y,tX,ty, max_size=10000):\n",
    "    #classifier = DecisionTreeClassifier(criterion='entropy')\n",
    "    model01_clf = train_classifier(X,y,MLPClassifier(hidden_layer_sizes=(100,), learning_rate='adaptive'),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": 9,
   "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": 10,
   "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": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "P1.1\n",
      "start training…\n",
      "training done\n",
      "Accuracy:  0.9156644543140875\n",
      "P1.2\n",
      "P1.3\n",
      "P1.4\n",
      "start training…\n",
      "training done\n",
      "Accuracy:  0.8418517269617997\n",
      "P1.5\n",
      "P1.6\n",
      "\n",
      "All Performances:\n",
      "{'P1.1': 0.9156644543140875,\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': 0.8418517269617997,\n",
      " 'P1.5': 0.615540247603449,\n",
      " 'P1.6 -- bi_model': 0.09186376993111421,\n",
      " 'P1.6 -- def_model': 0.1209595837949805,\n",
      " 'P1.6 -- regexp_model': 0.19683029047641987,\n",
      " 'P1.6 -- tri_model': 0.05867334650031312,\n",
      " 'P1.6 -- uni_model': 0.8026879907509996}\n"
     ]
    }
   ],
   "source": [
    "# dictionary containing all performances\n",
    "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",
    "# running performances 1.1 - 1.6\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 p6.items():\n",
    "    performances[\"P1.6 -- \" + k] = v\n",
    "\n",
    "    \n",
    "print(\"\\nAll Performances:\")\n",
    "pprint.pprint(performances)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f9611a7b588>"
      ]
     },
     "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.ylabel(\"performance\")\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "----\n",
    "## Task 2\n",
    "\n",
    "* the file `ru_syntagrus-ud-train-uncommented.conllu` is generated from the file `ru_syntagrus-ud-train.conllu` located here: https://github.com/UniversalDependencies/UD_Russian-SynTagRus. Changes to the original file:\n",
    "    * removed commentaries (lines with leading `#`)\n",
    "    * removed spaces in in long numbers (eg: `100 000` → `100000`)\n",
    "* to generate this file just run:\n",
    "    ```\n",
    "    curl https://raw.githubusercontent.com/UniversalDependencies/UD_Russian-SynTagRus/master/ru_syntagrus-ud-train.conllu | grep -v \\# | tr -d ' ' > ru_syntagrus-ud-train-uncommented.conllu\n",
    "    ```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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",
    "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": 14,
   "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": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "P2.1\n",
      "start training…\n",
      "training done\n",
      "Accuracy:  0.7951261788284127\n",
      "0.7951261788284127\n"
     ]
    }
   ],
   "source": [
    "print(\"P2.1\")\n",
    "performances2 = {}\n",
    "performances2['P2.1'] = model_01(X3,y3,tX3,ty3, max_size=5000) # 10000 here consumes too much memory on my laptop\n",
    "print(performances2['P2.1'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Model 05, Performance 2.2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "# write russian text out to file:\n",
    "f = open(\"ru_text.txt\", 'w')\n",
    "for word_features in tX3:\n",
    "    f.write(word_features['word'] + \" \")\n",
    "    if word_features['word'] == '.':    \n",
    "        f.write(\"\\n\") #new sentence → new line\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",
    "    ```\n",
    "    mkdir -p ~/src\n",
    "    cd ~/src\n",
    "    git clone https://github.com/jacopofar/RDRPOSTagger-python-3.git\n",
    "    ```\n",
    "* adjust `RDRPOS_TAGGER_PATH` to match with the download location"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys, os\n",
    "\n",
    "# remember current working directory\n",
    "cwd = os.getcwd()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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 = os.environ['HOME'] + \"/src/RDRPOSTagger-python-3/pSCRDRtagger/\"\n",
    "\n",
    "sys.path.insert(0, RDRPOS_TAGGER_PATH)\n",
    "\n",
    "# change current working directory to RDRPOSTagger repo\n",
    "os.chdir(RDRPOS_TAGGER_PATH)\n",
    "\n",
    "import RDRPOSTagger as model05_tagger \n",
    "\n",
    "# train tagger (copied from RDRPOSTagger.py):\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",
    "# change back to our cwd\n",
    "os.chdir(cwd)\n",
    "\n",
    "# run trained tagger\n",
    "r.tagRawCorpus(DICT, \"ru_text.txt\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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",
    "        w,t = splits.rsplit('/',1) # use last occurence of '/' to split.\n",
    "        tagged_words.append((w,t))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "score_2_2 = sum((1 if tagged_words[i][1] == ty3[i] else 0)for i in range(len(tagged_words))) / len(tagged_words)\n",
    "performances2['P2.2'] = score_2_2\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Results of performance 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'P2.1': 0.7951261788284127, 'P2.2': 0.8884973715119793}\n"
     ]
    }
   ],
   "source": [
    "pprint.pprint(performances2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f9611a0ed68>"
      ]
     },
     "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.ylabel(\"performance\")\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
}