{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Train Naive Bayesian Classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "classifier = MultinomialNB(alpha = 0.01).fit(train_tfidf_features, train_labels)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Test prediction with toy data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0. 0. 0. ... 0. 0. 0.]\n",
      " [0. 0. 0. ... 0. 0. 0.]]\n"
     ]
    }
   ],
   "source": [
    "docs_new = ['Doing business in China', 'New cold war with China']\n",
    "new_counts = vectorizer.transform(docs_new)\n",
    "new_tfidf = transformer.transform(new_counts)\n",
    "print(new_tfidf.toarray())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[3 3]\n",
      "['BenjaminKangLim' 'BenjaminKangLim']\n",
      "[[0.09206076 0.06376814 0.13749245 0.60536409 0.10131456]\n",
      " [0.13577759 0.07320687 0.09476922 0.59473204 0.10151428]]\n"
     ]
    }
   ],
   "source": [
    "toy_predicted = classifier.predict(new_tfidf)\n",
    "\n",
    "print(toy_predicted)\n",
    "print(label_encoder.inverse_transform(toy_predicted))\n",
    "print(classifier.predict_proba(new_tfidf))"
   ]
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}