Skip to content

Instantly share code, notes, and snippets.

@maxkleiner
Created November 5, 2020 11:18
Show Gist options
  • Save maxkleiner/bf22872692f33366d0531c51e00225ca to your computer and use it in GitHub Desktop.
Save maxkleiner/bf22872692f33366d0531c51e00225ca to your computer and use it in GitHub Desktop.
sentimenttree2.ipynb
Display the source blob
Display the rendered blob
Raw
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "sentimenttree2.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyOErW7zdlgktKLnj1ommNat",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/maxkleiner/bf22872692f33366d0531c51e00225ca/sentimenttree2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "pggupr0A9oOx"
},
"source": [
"# Sentiment Tree Classifier 2"
]
},
{
"cell_type": "code",
"metadata": {
"id": "04EukN1I80cD",
"outputId": "1803d74e-3288-4fc6-8f42-435178f18239",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 644
}
},
"source": [
"# use a preclassifier dtree with high recall and then a second \n",
"# classifier SVC to sort false positives out!\n",
"# use SVC as classifier and dtree to plot decision\n",
"\n",
"from sklearn import tree\n",
"from sklearn.feature_extraction.text import CountVectorizer\n",
"from sklearn import svm\n",
"from sklearn.metrics import confusion_matrix\n",
"from sklearn.metrics import classification_report\n",
"\n",
"#https://ritza.co/showcase/repl.it/introduction-to-machine-learning-with-python-and-repl-it.html\n",
"\n",
"positive_texts = [\n",
" \"we love you\",\n",
" \"they love us\",\n",
" \"you are good\",\n",
" \"he is good\",\n",
" \"they love max\"\n",
"]\n",
"\n",
"negative_texts = [\n",
" \"we hate you\",\n",
" \"they hate us\",\n",
" \"you are bad\",\n",
" \"he is bad\",\n",
" \"we hate max\"\n",
"]\n",
"\n",
"test_texts = [\n",
" \"they love bad max\", # this is labeled as positive !\n",
" \"they are good\",\n",
" \"why do you hate mary\",\n",
" \"they are almost always good\",\n",
" \"we are very bad\"\n",
"]\n",
"\n",
"print('testset: ',test_texts)\n",
"\n",
"training_texts = negative_texts + positive_texts\n",
"training_labels = [\"neg\"] * len(negative_texts) + [\"pos\"] * len(positive_texts)\n",
"#print(training_labels)\n",
"\n",
"#mapping the words to numbers (bag of words)\n",
"vectorizer = CountVectorizer()\n",
"vectorizer.fit(training_texts)\n",
"print('vocabulary: ',vectorizer.vocabulary_)\n",
"\n",
"#vectorizer.fit(test_texts)\n",
"#print(vectorizer.vocabulary_)\n",
"\n",
"#You can join all lines and then use split: \n",
"print('unique words:',set(\" \".join(test_texts).split()))\n",
"#print(set([wo for line in test_texts for wo in line.split()]))\n",
"\n",
"training_vectors = vectorizer.transform(training_texts)\n",
"testing_vectors = vectorizer.transform(test_texts)\n",
"\n",
"classifier = tree.DecisionTreeClassifier()\n",
"classifier.fit(training_vectors, training_labels)\n",
"predictions = classifier.predict(testing_vectors)\n",
"print('predict: ',predictions)\n",
"#print('testset: ',test_texts)\n",
"\n",
"#!pip install StringIO\n",
"\n",
"import pydotplus\n",
"\n",
"try:\n",
" from StringIO import StringIO\n",
"except ImportError:\n",
" from io import StringIO\n",
"#import StringIO\n",
"\n",
"#http://www.webgraphviz.com/\n",
"tree.export_graphviz(\n",
" classifier,\n",
" out_file='maxtree.dot',\n",
" feature_names=vectorizer.get_feature_names(),\n",
")\n",
"\n",
"dotfile = StringIO()\n",
"tree.export_graphviz(classifier, out_file=dotfile)\n",
"graph=pydotplus.graph_from_dot_data(dotfile.getvalue())\n",
"graph.write_png(\"sentimentdtree2.png\")\n",
"\n",
"# https://stackoverflow.com/questions/35286540/display-an-image-with-python\n",
"# %pylab inline\n",
"import matplotlib.pyplot as plt\n",
"import matplotlib.image as mpimg\n",
"img = mpimg.imread('sentimentdtree2.png')\n",
"imgplot = plt.imshow(img)\n",
"plt.show()\n",
"\n",
"# Create a linear SVM classifier\n",
"clf = svm.SVC(kernel='linear')\n",
"# Train & learn classifier\n",
"clf.fit(training_vectors, training_labels)\n",
"\n",
"# Make predictions on unseen test data\n",
"clf_predictions = clf.predict(testing_vectors)\n",
"print('predict SVC: ',clf_predictions)\n",
"test_labels=['pos','pos','neg','pos','neg']\n",
"print(\"Accuracy: {}%\".format(clf.score(testing_vectors,test_labels)*100))\n",
"\n",
"y_test = test_labels\n",
"y_pred = clf_predictions\n",
"\n",
"print('actual:',y_test)\n",
"print('predic:',y_pred)\n",
"\n",
"print('confusion matrix - classification report \\n')\n",
"print(confusion_matrix(y_test, y_pred))\n",
"print(classification_report(y_test, y_pred))"
],
"execution_count": 25,
"outputs": [
{
"output_type": "stream",
"text": [
"testset: ['they love bad max', 'they are good', 'why do you hate mary', 'they are almost always good', 'we are very bad']\n",
"vocabulary: {'we': 10, 'hate': 3, 'you': 11, 'they': 8, 'us': 9, 'are': 0, 'bad': 1, 'he': 4, 'is': 5, 'max': 7, 'love': 6, 'good': 2}\n",
"unique words: {'love', 'good', 'max', 'are', 'mary', 'almost', 'very', 'you', 'bad', 'hate', 'we', 'always', 'they', 'why', 'do'}\n",
"predict: ['pos' 'pos' 'neg' 'pos' 'neg']\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
},
{
"output_type": "stream",
"text": [
"predict SVC: ['neg' 'pos' 'neg' 'pos' 'neg']\n",
"Accuracy: 80.0%\n",
"actual: ['pos', 'pos', 'neg', 'pos', 'neg']\n",
"predic: ['neg' 'pos' 'neg' 'pos' 'neg']\n",
"confusion matrix - classification report \n",
"\n",
"[[2 0]\n",
" [1 2]]\n",
" precision recall f1-score support\n",
"\n",
" neg 0.67 1.00 0.80 2\n",
" pos 1.00 0.67 0.80 3\n",
"\n",
" accuracy 0.80 5\n",
" macro avg 0.83 0.83 0.80 5\n",
"weighted avg 0.87 0.80 0.80 5\n",
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "kJizsOWqG8kv"
},
"source": [
""
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "fRVScZB4-uDt"
},
"source": [
"![image.png](data:image/png;base64,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)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ZWnuFOm--XX5"
},
"source": [
"Because love or hate has 3 counts as discriminator in training set its easier to decide than good and bad with 2 ocurrences.\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "LG5br5Vu95Ac"
},
"source": [
"![image.png](data:image/png;base64,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)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "zJcRJ6-_9Q_r"
},
"source": [
"# Sentiment Tree Classifier with Support Vector Machine and Decision Tree Graph"
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment