diff --git a/Jonas_Solutions/Exercise01.ipynb b/Jonas_Solutions/Exercise01.ipynb index 5c27fba..8e67e89 100644 --- a/Jonas_Solutions/Exercise01.ipynb +++ b/Jonas_Solutions/Exercise01.ipynb @@ -225,19 +225,9 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 7, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "start training…\n", - "training done\n", - "Accuracy: 0.768551324916413\n" - ] - } - ], + "outputs": [], "source": [ "def model_01(X,y,tX,ty, max_size=1000):\n", " #classifier = DecisionTreeClassifier(criterion='entropy')\n", @@ -255,17 +245,9 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 8, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "0.8936074654423873\n" - ] - } - ], + "outputs": [], "source": [ "def model_02(tX,ty):\n", " m2_y = nltk.pos_tag([w['word'] for w in tX])\n", @@ -283,7 +265,7 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -292,9 +274,9 @@ " 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_sents) * cut)\n", - " train_sents = corpus_sents[:size]\n", - " test_sents = corpus_sents[size:]\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", @@ -320,24 +302,139 @@ }, { "cell_type": "code", - "execution_count": 41, + "execution_count": 10, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "P1.1\n", + "start training…\n", + "training done\n", + "Accuracy: 0.7712959728529368\n", + "P1.2\n", + "P1.3\n", + "P1.4\n", + "start training…\n", + "training done\n", + "Accuracy: 0.6410882090489463\n", + "P1.5\n", + "P1.6\n", + "{'P1.1': 0.7712959728529368,\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': 0.6410882090489463,\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": [ - "accs_p1 = [0] * 3\n", - "names_p1 = [\"P1.1\", \"P1.2\", \"P1.3\"]\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()\n", - "brown_sents = nltk.corpus.brown.sents()\n", + "brown_tagged = nltk.corpus.brown.tagged_sents()#(categories='news')\n", + "brown_sents = nltk.corpus.brown.sents()#(categories='news')\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" + " 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": "80f8a41746b340f09c5d16a3071c7384", + "version_major": 2, + "version_minor": 0 + }, + "text/html": [ + "

Failed to display Jupyter Widget of type FigureCanvasNbAgg.

\n", + "

\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 Jupyter\n", + " Widgets Documentation for setup instructions.\n", + "

\n", + "

\n", + " If you're reading this message in another frontend (for example, a static\n", + " rendering on GitHub or NBViewer),\n", + " it may mean that your frontend doesn't currently support widgets.\n", + "

\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" ] }, {