Merge branch 'jonas'
This commit is contained in:
		| @ -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" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
| @ -235,28 +225,15 @@ | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "code", | ||||
|    "execution_count": 9, | ||||
|    "execution_count": 7, | ||||
|    "metadata": {}, | ||||
|    "outputs": [ | ||||
|     { | ||||
|      "name": "stdout", | ||||
|      "output_type": "stream", | ||||
|      "text": [ | ||||
|       "start training…\n", | ||||
|       "training done\n" | ||||
|      ] | ||||
|     } | ||||
|    ], | ||||
|    "outputs": [], | ||||
|    "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)" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
| @ -266,79 +243,198 @@ | ||||
|     "#### Model 02" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "code", | ||||
|    "execution_count": 13, | ||||
|    "metadata": {}, | ||||
|    "outputs": [ | ||||
|     { | ||||
|      "data": { | ||||
|       "text/plain": [ | ||||
|        "0" | ||||
|       ] | ||||
|      }, | ||||
|      "execution_count": 13, | ||||
|      "metadata": {}, | ||||
|      "output_type": "execute_result" | ||||
|     } | ||||
|    ], | ||||
|    "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" | ||||
|     } | ||||
|    ], | ||||
|    "outputs": [], | ||||
|    "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": 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": [ | ||||
|     { | ||||
|      "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": [ | ||||
|     "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", | ||||
|     "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": "80f8a41746b340f09c5d16a3071c7384", | ||||
|        "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" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
| @ -365,7 +461,7 @@ | ||||
|    "name": "python", | ||||
|    "nbconvert_exporter": "python", | ||||
|    "pygments_lexer": "ipython3", | ||||
|    "version": "3.6.3" | ||||
|    "version": "3.6.5" | ||||
|   } | ||||
|  }, | ||||
|  "nbformat": 4, | ||||
|  | ||||
		Reference in New Issue
	
	Block a user