From 2c625f7f9220b42a5baccd7e6a7673090300039c Mon Sep 17 00:00:00 2001 From: Jonas Weinz Date: Wed, 2 May 2018 17:59:50 +0200 Subject: [PATCH] I'm Blue, dabedi dabedei... --- Jonas_Solutions/Exercise01.ipynb | 165 +++++++++++++++---------------- 1 file changed, 82 insertions(+), 83 deletions(-) diff --git a/Jonas_Solutions/Exercise01.ipynb b/Jonas_Solutions/Exercise01.ipynb index 095e2b0..5c27fba 100644 --- a/Jonas_Solutions/Exercise01.ipynb +++ b/Jonas_Solutions/Exercise01.ipynb @@ -205,24 +205,14 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Exercises:" + "## Exercise 01:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "### Exercise 01\n" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "metadata": {}, - "outputs": [], - "source": [ - "accs = [0] * 5\n", - "names = [\"M1\", \"M2\", \"M3\", \"M4\", \"M5\"]\n" + "### Performance 1\n" ] }, { @@ -235,7 +225,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 17, "metadata": {}, "outputs": [ { @@ -243,20 +233,17 @@ "output_type": "stream", "text": [ "start training…\n", - "training done\n" + "training done\n", + "Accuracy: 0.768551324916413\n" ] } ], "source": [ - "annotated_sent = nltk.corpus.treebank.tagged_sents()\n", - "\n", - "X,y,tX,ty = create_training_and_test_set(annotated_sentences=annotated_sent, \n", - " relative_cutoff=0.8)\n", - "\n", - "#classifier = DecisionTreeClassifier(criterion='entropy')\n", - "from sklearn.neural_network import MLPClassifier\n", - "model01_clf = train_classifier(X,y,MLPClassifier(),max_size=10000)\n", - "accs[0] = test_classifier(clf=clf, tX=tX, ty=ty)" + "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=1000)\n", + " return test_classifier(clf=model01_clf, tX=tX, ty=ty)" ] }, { @@ -268,77 +255,89 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 30, "metadata": {}, "outputs": [ { - "data": { - "text/plain": [ - "0" - ] - }, - "execution_count": 13, - "metadata": {}, - "output_type": "execute_result" + "name": "stdout", + "output_type": "stream", + "text": [ + "0.8936074654423873\n" + ] } ], "source": [ - "accs[1]" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "'\\nimport matplotlib.pyplot as plt\\nimport numpy as np\\n\\nweights = clf.named_steps[\\'classifier\\'].feature_importances_\\nlabels = clf.named_steps[\\'vectorizer\\'].get_feature_names()\\n\\n#sort\\nweights, 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(weights)), weights)\\n#plt.xticks(np.arange(len(weights)), labels, rotation=90)\\n#plt.show()\\n\\nprint(\"Most important features:\")\\npprint.pprint(list(reversed(labels[-20:])))\\nprint(\"with weights: \")\\npprint.pprint(list(reversed(weights[-20:])))\\n'" - ] - }, - "execution_count": 8, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "'''\n", - "import matplotlib.pyplot as plt\n", - "import numpy as np\n", - "\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(weights)), weights)\n", - "#plt.xticks(np.arange(len(weights)), labels, rotation=90)\n", - "#plt.show()\n", - "\n", - "print(\"Most important features:\")\n", - "pprint.pprint(list(reversed(labels[-20:])))\n", - "print(\"with weights: \")\n", - "pprint.pprint(list(reversed(weights[-20:])))\n", - "'''" + "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": [ - "```\n", - "from sklearn import tree\n", - "import graphviz\n", - "dot_data = tree.export_graphviz(clf.named_steps['classifier'], out_file='test',\n", - " feature_names=labels,\n", - " filled=True, rounded=True, \n", - " special_characters=True)\n", - "#graph = graphviz.Source(dot_data)\n", - "#graph\n", - "```" + "#### Model 03" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "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_sents) * cut)\n", + " train_sents = corpus_sents[:size]\n", + " test_sents = corpus_sents[size:]\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": 41, + "metadata": {}, + "outputs": [], + "source": [ + "accs_p1 = [0] * 3\n", + "names_p1 = [\"P1.1\", \"P1.2\", \"P1.3\"]\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", + "\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" ] }, { @@ -365,7 +364,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.3" + "version": "3.6.5" } }, "nbformat": 4,