Week2_김희숙_예습과제.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### CHAPTER 3\n",
    "# 분류\n",
    "### 지도 학습\n",
    "\n",
    "1. MNIST\n",
    "2. 이진 분류기 훈련\n",
    "3. 성능 측정\n",
    "4. 다중 분류\n",
    "5. 에러 분석\n",
    "6. 다중 레이블 분류\n",
    "7. 다중 출력 분류\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "고등학생과 미국 인구조사국 직원들이 손으로 쓴 70,000개의 작은 숫자 이미지를 모은 MNIST 데이터 셋을 사용하여 여러개의 분류 알고리즘을 작동시킨다."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#세팅\n",
    "import sys\n",
    "assert sys.version_info >= (3, 5)\n",
    "\n",
    "# 사이킷런 ≥0.20 필수\n",
    "import sklearn\n",
    "assert sklearn.__version__ >= \"0.20\"\n",
    "\n",
    "# 공통 모듈 임포트\n",
    "import numpy as np\n",
    "import os\n",
    "\n",
    "# 깔끔한 그래프 출력을 위해\n",
    "%matplotlib inline\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "mpl.rc('axes', labelsize=14)\n",
    "mpl.rc('xtick', labelsize=12)\n",
    "mpl.rc('ytick', labelsize=12)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## MNIST"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_keys(['data', 'target', 'frame', 'categories', 'feature_names', 'target_names', 'DESCR', 'details', 'url'])"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#사이킷런에서 제공하는 함수를 이용하여 MNIST 데이터셋 내려받기\n",
    "from sklearn.datasets import fetch_openml\n",
    "mnist = fetch_openml('mnist_784', version=1, as_frame=False)\n",
    "#매개변수: as_frame = True //판다스 데이터프레임 반환 \n",
    "mnist.keys()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 데이터셋을 설명하는 DESCR 키\n",
    "- 샘플이 하나의 행, 특성이 하나의 열로 구성된 배열을 가진 data 키\n",
    "- 레이블 배열을 가진 target 키"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(70000, 784)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X, y = mnist[\"data\"], mnist[\"target\"]\n",
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(70000,)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "784"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "28 * 28 #이미지는 28x28 픽셀"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "some_digit = X[0]\n",
    "some_digit_image = some_digit.reshape(28, 28)\n",
    "#샘플의 특성 벡터를 추출하여 28xx29 배열로 크기를 바꾸고 함수를 이용하여 그리기\n",
    "plt.imshow(some_digit_image, cmap=mpl.cm.binary)\n",
    "plt.axis(\"off\")\n",
    "\n",
    "#save_fig(\"some_digit_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'5'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#실제 레이블 확인\n",
    "y[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 문자열 레이블\n",
    "- 머신러닝 알고리즘에서의 사용을 위해 y를 정수로 변환"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = y.astype(np.uint8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "#MNIST 이미지 샘플"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_digit(data):\n",
    "    image = data.reshape(28, 28)\n",
    "    plt.imshow(image, cmap = mpl.cm.binary,\n",
    "               interpolation=\"nearest\")\n",
    "    plt.axis(\"off\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 숫자 그림을 위한 추가 함수\n",
    "def plot_digits(instances, images_per_row=10, **options):\n",
    "    size = 28\n",
    "    images_per_row = min(len(instances), images_per_row)\n",
    "    images = [instance.reshape(size,size) for instance in instances]\n",
    "    n_rows = (len(instances) - 1) // images_per_row + 1\n",
    "    row_images = []\n",
    "    n_empty = n_rows * images_per_row - len(instances)\n",
    "    images.append(np.zeros((size, size * n_empty)))\n",
    "    for row in range(n_rows):\n",
    "        rimages = images[row * images_per_row : (row + 1) * images_per_row]\n",
    "        row_images.append(np.concatenate(rimages, axis=1))\n",
    "    image = np.concatenate(row_images, axis=0)\n",
    "    plt.imshow(image, cmap = mpl.cm.binary, **options)\n",
    "    plt.axis(\"off\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 648x648 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(9,9))\n",
    "example_images = X[:100]\n",
    "plot_digits(example_images, images_per_row=10)\n",
    "#save_fig(\"more_digits_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**데이터를 조사하기 전에 항상 테스트 세트를 따로 만들어 떼어놓아야 함**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "#훈련세트와 테스트세트\n",
    "X_train, X_test, y_train, y_test = X[:60000], X[60000:], y[:60000], y[60000:]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 이진 분류기 훈련"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "#숫자 5만 식별해보기 #'5'와 '5 아님' 두 개의 클래스를 구분할 수 있는 이진 분류기\n",
    "y_train_5 = (y_train == 5) #5는 True이고, 다른 숫자는 모두 False\n",
    "y_test_5 = (y_test == 5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SGDClassifier(random_state=42)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#분류 모델을 하나 선택하여 훈련 시키기\n",
    "#사이킷런의 SGDClassifier를 사용하여 확률적 경사 하강법( SGD) 이용\n",
    "#SGD는 한 번에 하나씩 훈련 샘플을 독립적으로 처리\n",
    "\n",
    "from sklearn.linear_model import SGDClassifier\n",
    "\n",
    "sgd_clf = SGDClassifier(max_iter=1000, tol=1e-3, random_state=42) #SGDClassifier 모델 만들기\n",
    "sgd_clf.fit(X_train, y_train_5) #전체 훈련세트를 사용하여 훈련"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ True])"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#위에서 만든 모델을 이용하여 숫자 5의 이미지 감지\n",
    "sgd_clf.predict([some_digit])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 분류기가 이 이미지가 5를 나타낸다고 추측(True)함"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 성능 측정\n",
    "#### 분류기 평가"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### 교차검증을 사용한 정확도 측정"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9669\n",
      "0.91625\n",
      "0.96785\n"
     ]
    }
   ],
   "source": [
    "#사이킷런에서 제공하는 기능보다 교차 검증 과정을 더 많이 제어해야 할 때\n",
    "#교차 검증 직접 구현 \n",
    "from sklearn.model_selection import StratifiedKFold\n",
    "from sklearn.base import clone\n",
    "\n",
    "# shuffle=False가 기본값이기 때문에 random_state를 삭제하던지 shuffle=True로 지정하라는 경고가 발생합니다.\n",
    "# 0.24버전부터는 에러가 발생할 예정이므로 향후 버전을 위해 shuffle=True을 지정합니다.\n",
    "skfolds = StratifiedKFold(n_splits=3, random_state=42, shuffle=True)\n",
    "\n",
    "for train_index, test_index in skfolds.split(X_train, y_train_5):\n",
    "    clone_clf = clone(sgd_clf)\n",
    "    X_train_folds = X_train[train_index]\n",
    "    y_train_folds = y_train_5[train_index]\n",
    "    X_test_fold = X_train[test_index]\n",
    "    y_test_fold = y_train_5[test_index]\n",
    "\n",
    "    clone_clf.fit(X_train_folds, y_train_folds)\n",
    "    y_pred = clone_clf.predict(X_test_fold)\n",
    "    n_correct = sum(y_pred == y_test_fold)\n",
    "    print(n_correct / len(y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.95035, 0.96035, 0.9604 ])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#fold: 3, 모델: SGDClassifier, 예측 성능 지표: accuracy\n",
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "cross_val_score(sgd_clf, X_train, y_train_5, cv=3, scoring=\"accuracy\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 교차 검증 폴드에 대해 정확도가 95% 이상"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "#모든 이미지를 '5 아님' 클래스로 분류한느 더미 분류기 만들기\n",
    "from sklearn.base import BaseEstimator\n",
    "\n",
    "class Never5Classifier(BaseEstimator):\n",
    "    def fit(self, X, y=None):\n",
    "        pass\n",
    "    def predict(self, X):\n",
    "        return np.zeros((len(X), 1), dtype=bool)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.91125, 0.90855, 0.90915])"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#모델의 정확도 추측\n",
    "never_5_clf = Never5Classifier()\n",
    "cross_val_score(never_5_clf, X_train, y_train_5, cv=3, scoring=\"accuracy\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 90% 이상의 정확도\n",
    "- 이 예제는 정확도를 분류기의 성능 측정 지표로 선호하지 않는 이유를 보여줌\n",
    "- 특히 불균형한 데이터셋을 다룰 때(즉, 어떤 클래스가 다른 것보다 월등히 많은 경우) 더욱 그러함"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### 오차 행렬"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "#클래스 A의 샘플이 클래스 B로 분류된 횟수를 세는 것\n",
    "#즉, 분류기가 숫자 5의 이미지를 3으로 잘못 분류한 횟수를 알고 싶으면, 오차 행렬의 5행 3열을 보면 됨"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "#오차행렬을 만들기 위해선, 실제 타깃과 비교할 수 있도록 먼저 예측값을 만들어야 함\n",
    "from sklearn.model_selection import cross_val_predict\n",
    "\n",
    "### 테스트 세트로 예픅하면 안됨\n",
    "y_train_pred = cross_val_predict(sgd_clf, X_train, y_train_5, cv=3)\n",
    "#cross_val_predict: k-겹 교차 검증을 수행하지만 평가 점수를 반환하지 않고 각 테스트 폴드에서 얻은 예측을 반환함"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[53892,   687],\n",
       "       [ 1891,  3530]], dtype=int64)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "confusion_matrix(y_train_5, y_train_pred) #오차행렬 만들기"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 행은 실제 클래스를 나라태고 열은 예측한 클래스를 나타냄"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[54579,     0],\n",
       "       [    0,  5421]], dtype=int64)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train_perfect_predictions = y_train_5  # 완변한 분류기일 경우\n",
    "confusion_matrix(y_train_5, y_train_perfect_predictions)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 오차 행렬이 많은 정보를 제공해주지만 가금 더 요약된 지표가 필요할 때가 있음\n",
    "- 양성 예측의 정확도 살펴보기 -> 정밀도 \n",
    "- 분류기가 정확하게 감지한 양성 샘플의 비율 -> 재현율or민감도\n",
    "- 정밀도와 재현율은 함께 사용함"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " ![nn](https://mblogthumb-phinf.pstatic.net/MjAxOTA3MjNfNTIg/MDAxNTYzODYzNzI3OTk5.O3L8K5__en1f-CClSXf_NKi-zQbKkj5NVUaVaHT4_8Yg.740uyaCWkYHFpa41tz8PH3YP0340CxTWtyRgQ-a5Sskg.PNG.taewwon/3.PNG?type=w800)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 정밀도\n",
    " ![nn2](https://img1.daumcdn.net/thumb/R1280x0/?scode=mtistory2&fname=https%3A%2F%2Fblog.kakaocdn.net%2Fdn%2Fbkx8Fh%2FbtqUWtHvygX%2FpkVDXYIB9TtpK1Aq0rFeo0%2Fimg.png)\n",
    " \n",
    "- 재현율\n",
    " ![nn3](https://img1.daumcdn.net/thumb/R1280x0/?scode=mtistory2&fname=https%3A%2F%2Fblog.kakaocdn.net%2Fdn%2FbtEm2n%2FbtqUUprWiha%2FDz304PSuf6fpA7z7RnE9Z1%2Fimg.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### 정밀도와 재현율"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8370879772350012"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#정밀도와 재현율을 포함하여 분류기의 지표를 계산\n",
    "from sklearn.metrics import precision_score, recall_score\n",
    "\n",
    "precision_score(y_train_5, y_train_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8370879772350012"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#동일한 정밀도를 나타내는 코드\n",
    "cm = confusion_matrix(y_train_5, y_train_pred)\n",
    "cm[1, 1] / (cm[0, 1] + cm[1, 1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6511713705958311"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "recall_score(y_train_5, y_train_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6511713705958311"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#위 코드의 결과처럼 재현율을 나타내는 코드\n",
    "cm[1, 1] / (cm[1, 0] + cm[1, 1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![nn4](https://img1.daumcdn.net/thumb/R1280x0/?scode=mtistory2&fname=https%3A%2F%2Fblog.kakaocdn.net%2Fdn%2FedsXg1%2FbtqUUqjZ1x4%2FRu9sW4q0dkaW4ZkLkFWCe0%2Fimg.png)\n",
    "- F점수: 정밀도와 재현율의 조화 평균"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7325171197343846"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import f1_score\n",
    "\n",
    "f1_score(y_train_5, y_train_pred) #F점수를 계산하기 위해 f1_score() 호출"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7325171197343847"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#위 코드의 결과처럼 F점수를 나타내는 코드\n",
    "cm[1, 1] / (cm[1, 1] + (cm[1, 0] + cm[0, 1]) / 2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 정밀도와 재현율이 비슷한 분류기에서는 F점수가 높음\n",
    "- 정밀도를 올리면 재현율이 줄고, 정밀도를 줄이면 재현율이 올라감\n",
    "- 이를 정밀도/재현율 트레이드오프 라고 함"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### 정밀도/재현율 트레이드오프"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![nn5](https://blog.kakaocdn.net/dn/cULrDu/btqEYH1R8G2/klkjPvgekm24UtriVsQik0/img.jpg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 결정 함수를 사용하여 각 샘플의 점수를 계산\n",
    "- 이 점수가 임계값보다 크면 샘플을 양성 클래스에 할당\n",
    "- 그렇지 않으면, 음성 클래스에 할당\n",
    "\n",
    "<br>\n",
    "- 사이킷런에서 임계값을 직접 지정할 수는 없음\n",
    "- 예측에 사용한 점수는 확인할 수 있음"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2164.22030239])"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#분류기의 predict() 메서드 대신 decision_function() 이용하여 각 샘플의 점수 확인 \n",
    "y_scores = sgd_clf.decision_function([some_digit])\n",
    "y_scores"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 이 점수를 기반으로 원하는 임곗값을 정해 예측을 만들수 있음"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "threshold = 0 #임계값을 0으로 정함\n",
    "y_some_digit_pred = (y_scores > threshold)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ True])"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_some_digit_pred"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 임계값이 0이므로 위 코드는 predict() 메서드와 같은 결과를 반환"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([False])"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "threshold = 8000 #임계값을 8000으로 높임\n",
    "y_some_digit_pred = (y_scores > threshold)\n",
    "y_some_digit_pred"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 임계값을 높이면 재현율은 감소\n",
    "- 즉, 이미지가 실제로 숫자 5이고 임계값이 0일 때는 분류기가 이를 감지했지만, 임계값이 8000으로 높아지면 이를 놓침"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### 적절한 임꼐값 정하기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "#먼저 cross_val_predict() 함수를 이용하여 훈련세트에 있는 모든 샘플의 점수를 구해야 함\n",
    "#단, 이번에는 예측 결과가 아니라 결정 점수를 반환 받아야 함\n",
    "y_scores = cross_val_predict(sgd_clf, X_train, y_train_5, cv=3,\n",
    "                             method=\"decision_function\") #결정 점수 반환"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### 이 점수와 precision_recall_curve() 함수를 사용하여 가능한 모든 임계값에 대해 정밀도와 재현율 계산하기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import precision_recall_curve\n",
    "\n",
    "precisions, recalls, thresholds = precision_recall_curve(y_train_5, y_scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#맷플롯립을 이용하여 임계값의 함수로 정밀도와 재현율 그리기\n",
    "def plot_precision_recall_vs_threshold(precisions, recalls, thresholds):\n",
    "    plt.plot(thresholds, precisions[:-1], \"b--\", label=\"Precision\", linewidth=2)\n",
    "    plt.plot(thresholds, recalls[:-1], \"g-\", label=\"Recall\", linewidth=2)\n",
    "    plt.legend(loc=\"center right\", fontsize=16) #범례 추가\n",
    "    plt.xlabel(\"Threshold\", fontsize=16)        #임계값을 표시하고\n",
    "    plt.grid(True)                             #그리드 추가\n",
    "    plt.axis([-50000, 50000, 0, 1])            #축 범위 지정\n",
    "\n",
    "\n",
    "\n",
    "recall_90_precision = recalls[np.argmax(precisions >= 0.90)]\n",
    "threshold_90_precision = thresholds[np.argmax(precisions >= 0.90)]\n",
    "\n",
    "\n",
    "plt.figure(figsize=(8, 4))                                                                  \n",
    "plot_precision_recall_vs_threshold(precisions, recalls, thresholds)\n",
    "plt.plot([threshold_90_precision, threshold_90_precision], [0., 0.9], \"r:\")                \n",
    "plt.plot([-50000, threshold_90_precision], [0.9, 0.9], \"r:\")                               \n",
    "plt.plot([-50000, threshold_90_precision], [recall_90_precision, recall_90_precision], \"r:\")\n",
    "plt.plot([threshold_90_precision], [0.9], \"ro\")                                          \n",
    "plt.plot([threshold_90_precision], [recall_90_precision], \"ro\")                        \n",
    "#save_fig(\"precision_recall_vs_threshold_plot\")                                             \n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 정밀도 곡선이 재현울 곡선보다 더 울퉁불퉁한 이유: 이는 임계값을 올리더라도 정밀도가 가끔 낮아질 때가 있기 때문"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(y_train_pred == (y_scores > 0)).all()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_precision_vs_recall(precisions, recalls):\n",
    "    plt.plot(recalls, precisions, \"b-\", linewidth=2)\n",
    "    plt.xlabel(\"Recall\", fontsize=16)\n",
    "    plt.ylabel(\"Precision\", fontsize=16)\n",
    "    plt.axis([0, 1, 0, 1])\n",
    "    plt.grid(True)\n",
    "\n",
    "plt.figure(figsize=(8, 6))\n",
    "plot_precision_vs_recall(precisions, recalls)\n",
    "plt.plot([recall_90_precision, recall_90_precision], [0., 0.9], \"r:\")\n",
    "plt.plot([0.0, recall_90_precision], [0.9, 0.9], \"r:\")\n",
    "plt.plot([recall_90_precision], [0.9], \"ro\")\n",
    "#save_fig(\"precision_vs_recall_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 재현율에 대한 정밀도 곡선(임계값은 이전 그래프와 동일:0.4799852425751706)\n",
    "- 재현율 80% 근처에서 정밀도 급격하게 감소\n",
    "- 이 하강점 직전을 정밀도/재현율 트레이드오프로 선택하는 것이 좋음(ex. 정밀도 60% 지점)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4799852425751706"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "recall_90_precision"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### 정밀도 90% 달성 목표"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "#최소한 90% 정밀도가 되는 가장 낮은 임계값 찾을 수 있음\n",
    "#np.argmax(): 최대값의 첫번째 인덱스를 반환 #여기서는 첫번째 True 값을 의미\n",
    "threshold_90_precision = thresholds[np.argmax(precisions >= 0.90)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3370.0194991439557"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "threshold_90_precision"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "#훈련세트에 대한 예측 만들기\n",
    "y_train_pred_90 = (y_scores >= threshold_90_precision)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9000345901072293"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#이 예측에 대한 정밀도\n",
    "precision_score(y_train_5, y_train_pred_90)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4799852425751706"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#이 예측에 대한 재현율\n",
    "recall_score(y_train_5, y_train_pred_90)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 정밀도가 90%인 분류기 만들었음\n",
    "- 정밀도를 높이려면 충분히 큰 임계값을 지정, 단 재현율이 너무 낮다면 높은 정밀도의 분류기는 유용하지 않음"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### ROC 곡선"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 수신기 조작  특성(ROC) 곡선도 이진 분류에서 널리 사용하는 도구\n",
    "- ROC 곡선은 거짓양성비율(FPR)에 대한 진짜양성비율(TPR=재현율) 곡선임 *(FPR: 양성으로 잘못 분류된 음성 샘플의 비율)*\n",
    "- FPR = 1 - TNR(진짜음성비율, 특이도)  \n",
    "- ROC 그래프는 <민감도(재현율)에 대한 1-특이도> 그래프 라고도 함"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import roc_curve\n",
    "\n",
    "fpr, tpr, thresholds = roc_curve(y_train_5, y_scores) #roc_curve() 함수를 사용하여 여러 임곅밧에서 TPR과 FPR을 계산"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#맷플롯립을 사용해 TPR에 대한 FPR 곡선을 나타낼 수 있음\n",
    "def plot_roc_curve(fpr, tpr, label=None):\n",
    "    plt.plot(fpr, tpr, linewidth=2, label=label)\n",
    "    plt.plot([0, 1], [0, 1], 'k--') # 대각 점선\n",
    "    plt.axis([0, 1, 0, 1])                                    \n",
    "    plt.xlabel('False Positive Rate (Fall-Out)', fontsize=16) \n",
    "    plt.ylabel('True Positive Rate (Recall)', fontsize=16)    \n",
    "    plt.grid(True)                                            \n",
    "\n",
    "plt.figure(figsize=(8, 6))                                    \n",
    "plot_roc_curve(fpr, tpr)\n",
    "fpr_90 = fpr[np.argmax(tpr >= recall_90_precision)]           \n",
    "plt.plot([fpr_90, fpr_90], [0., recall_90_precision], \"r:\")   \n",
    "plt.plot([0.0, fpr_90], [recall_90_precision, recall_90_precision], \"r:\")  \n",
    "plt.plot([fpr_90], [recall_90_precision], \"ro\")               \n",
    "#save_fig(\"roc_curve_plot\")                                   \n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 모든 가능한 임계값에서 진짜양성비율에 대한 거짓양성비율을 나타낸 ROC곡선\n",
    "- 붉은 점은 선택한 비율의 지점(43.68%재현율)\n",
    "- 재현율이 높을수록 분류기가 만드는 거짓양성이 늘어남\n",
    "- 점선은 완전한 랜덤 분류기의 ROC 곡선\n",
    "- 좋은 분류기는 이 점선에서 최대한 멀리 떨어져 있어야 함(왼쪽 위 모서리)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**곡선아래의 면적(AUC)를 측정하면 분류기들 비교할 수 있음**<br>\n",
    "**완벽한 분류기는 ROC의 AUC가 1이고, 완전한 랜덤 분류기는 0.5임**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9604938554008616"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#roc_auc_score(): ROC의 AUC를 계산\n",
    "from sklearn.metrics import roc_auc_score\n",
    "\n",
    "roc_auc_score(y_train_5, y_scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "'''\n",
    "#TIP\n",
    "ROC 곡선이 정밀도/재현율(PR) 곡선과 비슷해서 어떤 것을 사용해야할까\n",
    "양성 클래스가 드물거나 거짓음성보다 거짓양성이 더 중요할 때, 성능 개선 여지가 얼마나 되는지 중심 -> PR곡선\n",
    "그 외 경우 -> ROC 곡선\n",
    "'''"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "#RandomForestClassifier을 훈련시켜 ROC곡선과 ROC AUC 점수 비교\n",
    "\n",
    "#훈련 세트의 샘플에 대한 점수 얻기\n",
    "#predict_proba(): 샘플이 행, 클래스가 열이고 샘플이 주어진 클래스에 속할 확률을 담은 배열을 반환\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "forest_clf = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "y_probas_forest = cross_val_predict(forest_clf, X_train, y_train_5, cv=3,\n",
    "                                    method=\"predict_proba\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_scores_forest = y_probas_forest[:, 1] # 점수 = 양성 클래스의 확률\n",
    "fpr_forest, tpr_forest, thresholds_forest = roc_curve(y_train_5,y_scores_forest) \n",
    "#roc_curve(): 레이블과 점수를 기대. 점수대신 클래스 확률을 전달 할 수 있음"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#비교를 위해 첫번째 ROC곡선도 함께 그림\n",
    "recall_for_forest = tpr_forest[np.argmax(fpr_forest >= fpr_90)]\n",
    "\n",
    "plt.figure(figsize=(8, 6))\n",
    "plt.plot(fpr, tpr, \"b:\", linewidth=2, label=\"SGD\")\n",
    "plot_roc_curve(fpr_forest, tpr_forest, \"Random Forest\")\n",
    "plt.plot([fpr_90, fpr_90], [0., recall_90_precision], \"r:\")\n",
    "plt.plot([0.0, fpr_90], [recall_90_precision, recall_90_precision], \"r:\")\n",
    "plt.plot([fpr_90], [recall_90_precision], \"ro\")\n",
    "plt.plot([fpr_90, fpr_90], [0., recall_for_forest], \"r:\")\n",
    "plt.plot([fpr_90], [recall_for_forest], \"ro\")\n",
    "plt.grid(True)\n",
    "plt.legend(loc=\"lower right\", fontsize=16)\n",
    "#save_fig(\"roc_curve_comparison_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- ROC 곡선 비교: 랜덤 포레스트 분류기가 SGD 분류기보다 훨씬 좋음\n",
    "- 랜덤 포레스트의 ROC 곡선이 왼쪽 위 모서리에 더 가까워진 AUC 값이 크기 때문"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9983436731328145"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "roc_auc_score(y_train_5, y_scores_forest)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- ROC AUC 점수가 훨씬 높음"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9905083315756169"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#정밀도 점수 계산\n",
    "y_train_pred_forest = cross_val_predict(forest_clf, X_train, y_train_5, cv=3)\n",
    "precision_score(y_train_5, y_train_pred_forest)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8662608374838591"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#재현율 점수 계산\n",
    "recall_score(y_train_5, y_train_pred_forest)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 다중 분류\n",
    "\n",
    "#### 둘 이상의 클래스 구별"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "OvR(One-versus-the-rest)전략 orOvA(One-versus-all)\n",
    "- 특정 숫자 하나만 구분하는 숫자별 이진 분류기 10개를(0-9까지) 훈련시켜서 클래스가 10개인 숫자 이미지 분류 시스템을 만듦\n",
    "- 이미지를 분류할 때 각 분류기의 결정 점수 중에서 가장 높은 것을 클래스로 선택\n",
    "\n",
    "OvV(One-versus-one)전략\n",
    "- 0과 1 구별, 0과 2 구별, 1과 2 구별 등과 같이 각 숫자의 조합마다 이진 분류기를 훈련시키는 것\n",
    "- 클래스가 N개라면 분류기는 Nx(N-1)/2개가 필요함\n",
    "- 즉, MNIST 문제에서 45개의 분류기를 훈련시켜야 함\n",
    "이미지 하나를 분류하려면 45개 분류기 모두를 통과시켜서 가장 많이 양성으로 분류된 크래스를 선택함<br>OvO전략의 주요 장점은 각 분류기의 훈련에 전체 훈련 세트 중 구별할 두 클래스에 해당하는 샘플만 필요\n",
    "<br>\n",
    "<br>\n",
    "- 서포트 벡터 머신같은 알고리즘은 훈련 세트의 크기에 민감해서 큰 훈련 세트에서 몇개의 분류기를 훈련시키는 것보다 작은 훈련 세트에서 많은 분류기를 훈련시키는 쪽이 빠르므로 OvO를 선호\n",
    "- 하지만 대부분의 이진분류 알고리즘에서는 OvR을 선호 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([5], dtype=uint8)"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#이진분류 알고리즘을 선택하면 사이킷런이 알고리즘에 따라 자동으로 OvR 또는 OvO 실행\n",
    "from sklearn.svm import SVC #서포트벡터머신분류기 테스트\n",
    "\n",
    "svm_clf = SVC(gamma=\"auto\", random_state=42)\n",
    "svm_clf.fit(X_train[:1000], y_train[:1000]) # y_train_5이 아니라 y_train입니다\n",
    "svm_clf.predict([some_digit])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 5를 구별한 타깃 클래스(y_train_5)대신 0~9까지의 원래 타깃 클래스(y_train)을 사용해 SVC를 훈련시킴\n",
    "- 사이킷런이 OvO 전략을 사용하여 45개의 이진 분류기를 훈련시킴\n",
    "- 각각의 결정 점수를 얻어 점수가 갖아 높은 클래스를 선택함"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 2.81585438,  7.09167958,  3.82972099,  0.79365551,  5.8885703 ,\n",
       "         9.29718395,  1.79862509,  8.10392157, -0.228207  ,  4.83753243]])"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#decision_function(): 샘플당 10개의 점수를 반환\n",
    "#이 점수는 클래스마다 하나씩\n",
    "some_digit_scores = svm_clf.decision_function([some_digit])\n",
    "some_digit_scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.argmax(some_digit_scores) #가장 높은 점수의 클래스 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=uint8)"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svm_clf.classes_  #클래스의 인덱스"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svm_clf.classes_[5] #인덱스 5에 해당하는 클래스 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([5], dtype=uint8)"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#SVC 기반으로 OvR전략을 사용하는 다중 분류기 만들기\n",
    "from sklearn.multiclass import OneVsRestClassifier\n",
    "ovr_clf = OneVsRestClassifier(SVC(gamma=\"auto\", random_state=42))\n",
    "ovr_clf.fit(X_train[:1000], y_train[:1000])\n",
    "ovr_clf.predict([some_digit])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(ovr_clf.estimators_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([3], dtype=uint8)"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#훈련시키기\n",
    "sgd_clf.fit(X_train, y_train)\n",
    "sgd_clf.predict([some_digit])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- SGD 분류기는 직접 샘플을 다중 클래스로 분류할 수 있기 때문에 별도로 사이킷런의 OvR이나 OvO를 적용할 필요가 없음"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-31893.03095419, -34419.69069632,  -9530.63950739,\n",
       "          1823.73154031, -22320.14822878,  -1385.80478895,\n",
       "        -26188.91070951, -16147.51323997,  -4604.35491274,\n",
       "        -12050.767298  ]])"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#SGD분류기가 클래스마다 부여한 점수 확인\n",
    "#decision_function(): 클래스마다 하나의 값을 반환\n",
    "sgd_clf.decision_function([some_digit])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.87365, 0.85835, 0.8689 ])"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#분류기 평가 -> 교차 검증\n",
    "#cross_val_score() 함수를 사용해 SGDClassifier의 정확도 평가\n",
    "cross_val_score(sgd_clf, X_train, y_train, cv=3, scoring=\"accuracy\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 모든 테스트 fold에서 84% 이상을 얻었음\n",
    "- 성능을 더 높일 여지가 있음\n",
    "- 간단하게 입력의 스케일을 조정하면 정확도를 89% 이상으로 높일 수 있음"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.8983, 0.891 , 0.9018])"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "scaler = StandardScaler()\n",
    "X_train_scaled = scaler.fit_transform(X_train.astype(np.float64)) #입력의 스케일 조정  *2장 참고\n",
    "cross_val_score(sgd_clf, X_train_scaled, y_train, cv=3, scoring=\"accuracy\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 에러 분석"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 실제 프로젝트라면 머신러닝 프러젝트 체크리스트의 단계를 따를 것\n",
    "- 데이터 준비 단계에서 가능한 선택 사항을 탐색하고,\n",
    "- 여러 모델을 시도하고,\n",
    "- 가장 좋은 몇 개를 골라\n",
    "- CridSearchCV를 사용해 하이퍼파라미터를 세밀하게 튜닝하고,\n",
    "- 가능한 한 자동화 함"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "가능성이 높은 모델을 하나 찾았다고 가정하고 이 모델의 성능을 향상 시킬 방법 찾기\n",
    "- 방법1. 에러의 종류를 분석"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### 오차 행렬 살펴보기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[5577,    0,   22,    5,    8,   43,   36,    6,  225,    1],\n",
       "       [   0, 6400,   37,   24,    4,   44,    4,    7,  212,   10],\n",
       "       [  27,   27, 5220,   92,   73,   27,   67,   36,  378,   11],\n",
       "       [  22,   17,  117, 5227,    2,  203,   27,   40,  403,   73],\n",
       "       [  12,   14,   41,    9, 5182,   12,   34,   27,  347,  164],\n",
       "       [  27,   15,   30,  168,   53, 4444,   75,   14,  535,   60],\n",
       "       [  30,   15,   42,    3,   44,   97, 5552,    3,  131,    1],\n",
       "       [  21,   10,   51,   30,   49,   12,    3, 5684,  195,  210],\n",
       "       [  17,   63,   48,   86,    3,  126,   25,   10, 5429,   44],\n",
       "       [  25,   18,   30,   64,  118,   36,    1,  179,  371, 5107]],\n",
       "      dtype=int64)"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#cross_val_predict()를 이용하여 예측을 만들고 confusion_matrix() 호출\n",
    "y_train_pred = cross_val_predict(sgd_clf, X_train_scaled, y_train, cv=3)\n",
    "conf_mx = confusion_matrix(y_train, y_train_pred)\n",
    "conf_mx"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [],
   "source": [
    "#오차행렬을 맷플롯립의 matshow() 함수를 사용해 이미지로 표현\n",
    "def plot_confusion_matrix(matrix):\n",
    "    \"\"\"If you prefer color and a colorbar\"\"\"\n",
    "    fig = plt.figure(figsize=(8,8))\n",
    "    ax = fig.add_subplot(111)\n",
    "    cax = ax.matshow(matrix)\n",
    "    fig.colorbar(cax)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 288x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.matshow(conf_mx, cmap=plt.cm.gray)\n",
    "#save_fig(\"confusion_matrix_plot\", tight_layout=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 이 오차 행렬은 대부분의 이미지가 올바르게 분류되었음을 나타내는 주대각선에 있으므로 매우 좋아 보임\n",
    "- 숫자 5는 다른 숫자 보다 조금 더 어두워보임\n",
    "- 이는 데이터셋에 숫자 5의 이미지가 적거나 분류기가 숫자 5를 다른 숫자만큼 잘 분류하지 못한다는 뜻 *(배열에서 가장 큰 값은 흰색으로, 가장 작은 값은 검은색으로 정규화되어 그려짐)*\n",
    "<br>\n",
    "<br>\n",
    "**그래프의 에러 부분에 초점**\n",
    "- 오차 행렬의 각 값을 대응되는 클래스의 이미지 개수로 나누어(에러의 절대 개수가 아님) 에러 비율을 비교함(개수로 비교하면 이미지가 많은 클래스가 상대적으로 나쁘게 보임)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [],
   "source": [
    "row_sums = conf_mx.sum(axis=1, keepdims=True)\n",
    "norm_conf_mx = conf_mx / row_sums #각 값을 대응되는 클래스의 이미지 개수로 나눔"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 288x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#다른 항목은 그대로 유지하고 주대각선만 0으로 채워 그래프 그림\n",
    "np.fill_diagonal(norm_conf_mx, 0)\n",
    "plt.matshow(norm_conf_mx, cmap=plt.cm.gray)\n",
    "#save_fig(\"confusion_matrix_errors_plot\", tight_layout=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 분류기가 만든 에러가 확실히 보임\n",
    "- 행은 실제 클래스를 나타내고 열은 예측한 클래스를 나타냄\n",
    "- 클래스 8의 열이 상당히 밝으므로 많은 이미지가 8로 잘못 분류되었음을 암시\n",
    "- 하지만 클래스 8의 행은 나쁘지 않음\n",
    "- 이는 실제 8이 적절히 8로 분류되었다는 것을 의미\n",
    "- 오차 행렬은 반드시 대칭인 것은 아님\n",
    "- 3과 5가 서로 많이 혼동되고 있는 것도 볼 수 있음\n",
    "\n",
    "**8로 잘못 분류되는 것을 줄이려면?**\n",
    "- 8처럼 보이는(하지만 실제 8은 아닌) 숫자의 훈련 데이터를 더 많이 모아서 실제 8과 구분하도록 분류기를 학습시킬 수 있음\n",
    "- 또는 분류기에 도움 될 만한 특성을 더 찾아볼 수 있음\n",
    "- Ex. 동심원의 수를 세는 알고리즘( 8은 2개, 6은 1개, 5는 0개)\n",
    "- 또는 동심원 같은 어떤 패턴이 드러나도록 이미지를 전처리 해볼수 있음"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### 에러 해결을 위해 3과 5의 샘플을 그려보기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#plot_digits(): 맷플롯립의 imshow() 함수를 사용하는 함수\n",
    "cl_a, cl_b = 3, 5\n",
    "X_aa = X_train[(y_train == cl_a) & (y_train_pred == cl_a)]\n",
    "X_ab = X_train[(y_train == cl_a) & (y_train_pred == cl_b)]\n",
    "X_ba = X_train[(y_train == cl_b) & (y_train_pred == cl_a)]\n",
    "X_bb = X_train[(y_train == cl_b) & (y_train_pred == cl_b)]\n",
    "\n",
    "plt.figure(figsize=(8,8))\n",
    "plt.subplot(221); plot_digits(X_aa[:25], images_per_row=5)\n",
    "plt.subplot(222); plot_digits(X_ab[:25], images_per_row=5)\n",
    "plt.subplot(223); plot_digits(X_ba[:25], images_per_row=5)\n",
    "plt.subplot(224); plot_digits(X_bb[:25], images_per_row=5)\n",
    "#save_fig(\"error_analysis_digits_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 왼쪽의 5x5 블록 두 개는 3으로 분류된 이미지이고 오른쪽 5x5 블록 두 개는 5로 분류된 이미지\n",
    "- 분류기가 잘못 분류한 숫자 중 일부는 정말 잘못 쓰여 있음(왼쪽 아래 블록과 오른쪽 위 블록)\n",
    "- 분류기가 실수한 이유 -> 선형 모델인 SGDClassifier를 사용했기 때문\n",
    "- 선형 분류기는 클래스마다 픽셀에 가중치를 할당하고 새로운 이미지에 대해 단순히 픽셀 강도의 가중치 합을 클래스의 점수로 계산함\n",
    "- 따라서 3과 5는 몇 개의 픽셀만 다르기 때문에 모델이 쉽게 혼동 #이미지의 위치, 회전 방향에 민감\n",
    "- 에러를 줄이는 한가지 방법은 이미지를 중앙에 위치시키고 회전되어 있지 않도록 전처리 하는 것"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 다중 레이블 분류\n",
    "\n",
    "#### 샘플마다 여러 개의 클래스를 출력\n",
    "-  여러 개의 이진 꼬리표 출력"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier()"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#각 숫자 이미지에 두개의 타깃 레이블이 담긴 y_multilabel배열을 만듦\n",
    "#첫번째 숫자가 큰값(7,8,9)인지 나타내고\n",
    "#두번째 숫자가 홀수인지 나타냄\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "y_train_large = (y_train >= 7) #큰수체크\n",
    "y_train_odd = (y_train % 2 == 1) #홀수체크\n",
    "y_multilabel = np.c_[y_train_large, y_train_odd] \n",
    "\n",
    "knn_clf = KNeighborsClassifier() #KNeighborsClassifier 인스턴스 만듦\n",
    "knn_clf.fit(X_train, y_multilabel) #다중 타깃 배열을 사용하여 훈련"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[False,  True]])"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knn_clf.predict([some_digit])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 예측 결과 두개의 레이블 출력\n",
    "- 숫자 5는 크지않고(False), 홀수(True) 임"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.976410265560605"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#각 레이블의 F1 점수를 구하고 간단하게 평균 점수를 계산\n",
    "y_train_knn_pred = cross_val_predict(knn_clf, X_train, y_multilabel, cv=3)\n",
    "f1_score(y_multilabel, y_train_knn_pred, average=\"macro\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 이 코드는 모든 레이블의 가중치가 같다고 가정한 것\n",
    "- 사진이 수가 많은 특정 이미지에 분류기의 점수에 더 높은 가중치를 주려면 레이블에 클래스의 지지도를 가중치로 주면 됨(지지도: 타깃 레이블이 속한 샘플 수)\n",
    "- 즉, 위의 코드에서 average=\"weighted\" 설정"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 다중 출력 분류\n",
    "\n",
    "#### 다중 출력 다중 클래스 분류 or 다중 출력 분류\n",
    "- 다중 레이블 분류에서 한 레이블이 다중 클래스가 될 수 있도록 일반화 한 것 *(즉, 값을 두개 이상 가질 수 있음)*\n",
    "<br>\n",
    "<br>\n",
    "**이미지의 답음을 제거하는 시스템**\n",
    "- 잡음이 많은 숫자 이미지를 입력 받고 깨끗한 숫자 이미지를 MNIST 이미지처럼 픽셀의 강도를 담은 배열로 출력\n",
    "- 분류기의 출력이 다중 레이블(픽셀당 한 레이블)이고 각 레이블은 값을 여러개 가짐(0-255)\n",
    "- 픽셀 강도 예측은 분류보다 회귀와 비슷\n",
    "- 샘플마다 클래스와 값을 모두 포함하는 다중 레이블이 출력되는 시스템도 가능"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [],
   "source": [
    "#MNIST 이미지에서 추출한 훈련 세트와 테스트 세트에 넘파이의 randint() 함수를 사용하여\n",
    "#픽셀 강도에 잡음을 추가\n",
    "#타깃 이미지는 원본 이미지가 될 것\n",
    "noise = np.random.randint(0, 100, (len(X_train), 784))\n",
    "X_train_mod = X_train + noise\n",
    "noise = np.random.randint(0, 100, (len(X_test), 784))\n",
    "X_test_mod = X_test + noise\n",
    "y_train_mod = X_train\n",
    "y_test_mod = X_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "some_index = 0\n",
    "plt.subplot(121); plot_digit(X_test_mod[some_index])\n",
    "plt.subplot(122); plot_digit(y_test_mod[some_index])\n",
    "#save_fig(\"noisy_digit_example_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- 왼쪽은 잡음이 섞인 입력 이미지, 오른쪽은 깨끗한 타깃 이미\n",
    "- 분류기를 훈련시켜 이 이미지를 깨끗하게 만들기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "knn_clf.fit(X_train_mod, y_train_mod)\n",
    "clean_digit = knn_clf.predict([X_test_mod[some_index]])\n",
    "plot_digit(clean_digit)\n",
    "#save_fig(\"cleaned_digit_example_plot\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.8.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}