2.NLP_PREP/2.2.sklearn.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2.2 Sklearn\n",
    "\n",
    "* 데이터 불러오기\n",
    "* 2.2.1. 싸이킷-런 데이터 분리\n",
    "* 2.2.2. 싸이킷-런 지도 학습\n",
    "* 2.2.3. 싸이킷-런 비지도 학습\n",
    "* 2.2.4. 싸이킷-런 특징 추출"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sklearn\n",
    "sklearn.__version__"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 데이터 불러오기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_iris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "iris_dataset = load_iris()\n",
    "print(\"iris_dataset key: {}\".format(iris_dataset.keys()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(iris_dataset['data'])\n",
    "print(\"shape of data: {}\". format(iris_dataset['data'].shape))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(iris_dataset['feature_names'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(iris_dataset['target'])\n",
    "print(iris_dataset['target_names'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(iris_dataset['DESCR'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.2.1. 싸이킷-런 데이터 분리"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "target = iris_dataset['target']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_input, test_input, train_label, test_label = train_test_split(iris_dataset['data'],\n",
    "                                                                    target,\n",
    "                                                                    test_size = 0.25,\n",
    "                                                                    random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"shape of train_input: {}\".format(train_input.shape))\n",
    "print(\"shape of test_input: {}\".format(test_input.shape))\n",
    "print(\"shape of train_label: {}\".format(train_label.shape))\n",
    "print(\"shape of test_label: {}\".format(test_label.shape))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.2.2. 싸이킷-런 지도 학습"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "knn = KNeighborsClassifier(n_neighbors = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "knn.fit(train_input, train_label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "new_input = np.array([[6.1, 2.8, 4.7, 1.2]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "knn.predict(new_input)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict_label = knn.predict(test_input)\n",
    "print(predict_label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print('test accuracy {:.2f}'.format(np.mean(predict_label == test_label)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.2.3. 싸이킷-런 비지도 학습"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.cluster import KMeans\n",
    "k_means = KMeans(n_clusters=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "k_means.fit(train_input)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "k_means.labels_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"0 cluster:\", train_label[k_means.labels_ == 0])\n",
    "print(\"1 cluster:\", train_label[k_means.labels_ == 1])\n",
    "print(\"2 cluster:\", train_label[k_means.labels_ == 2])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "new_input  = np.array([[6.1, 2.8, 4.7, 1.2]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "prediction = k_means.predict(new_input)\n",
    "print(prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict_cluster = k_means.predict(test_input)\n",
    "print(predict_cluster)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "np_arr = np.array(predict_cluster)\n",
    "np_arr[np_arr==0], np_arr[np_arr==1], np_arr[np_arr==2] = 3, 4, 5\n",
    "np_arr[np_arr==3] = 1\n",
    "np_arr[np_arr==4] = 0\n",
    "np_arr[np_arr==5] = 2\n",
    "predict_label = np_arr.tolist()\n",
    "print(predict_label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print('test accuracy {:.2f}'.format(np.mean(predict_label == test_label)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.2.4. 싸이킷-런 특징 추출\n",
    "\n",
    "* CountVectorizer\n",
    "* TfidfVectorizer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### CountVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "text_data = ['나는 배가 고프다', '내일 점심 뭐먹지', '내일 공부 해야겠다', '점심 먹고 공부 해야지']\n",
    "\n",
    "count_vectorizer = CountVectorizer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "count_vectorizer.fit(text_data)\n",
    "print(count_vectorizer.vocabulary_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sentence = [text_data[0]] # ['나는 배가 고프다']\n",
    "print(count_vectorizer.transform(sentence).toarray())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### TfidfVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import TfidfVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "text_data = ['나는 배가 고프다', '내일 점심 뭐먹지', '내일 공부 해야겠다', '점심 먹고 공부 해야지']\n",
    "tfidf_vectorizer = TfidfVectorizer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tfidf_vectorizer.fit(text_data)\n",
    "print(tfidf_vectorizer.vocabulary_)\n",
    "\n",
    "sentence = [text_data[3]] # ['점심 먹고 공부 해야지']\n",
    "print(tfidf_vectorizer.transform(text_data).toarray())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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
}