13. naive_bayes (수정).ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 라이브러리 불러오기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 데이터셋 만들기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "col = ['장르', '재미있는', '연인', '사랑', '맹렬한', '빠른', '총격', '날으는']\n",
    "\n",
    "genre = ['코미디', '액션', '코미디', '액션', '액션']\n",
    "V1 = [1, 0, 2, 1, 0]\n",
    "V2 = [1, 0, 1, 0, 0]\n",
    "V3 = [2, 0, 0, 0, 1]\n",
    "V4 = [0, 1, 0, 1, 0]\n",
    "V5 = [0, 1, 1, 0, 1]\n",
    "V6 = [0, 1, 0, 2, 1]\n",
    "V7 = [0, 0, 1, 0, 1]\n",
    "\n",
    "dic = {'장르':genre, 'V1':V1, 'V2':V2, 'V3':V3, 'V4':V4, 'V5':V5, 'V6':V6, 'V7':V7}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'장르': ['코미디', '액션', '코미디', '액션', '액션'],\n",
       " 'V1': [1, 0, 2, 1, 0],\n",
       " 'V2': [1, 0, 1, 0, 0],\n",
       " 'V3': [2, 0, 0, 0, 1],\n",
       " 'V4': [0, 1, 0, 1, 0],\n",
       " 'V5': [0, 1, 1, 0, 1],\n",
       " 'V6': [0, 1, 0, 2, 1],\n",
       " 'V7': [0, 0, 1, 0, 1]}"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "dic2 = pd.DataFrame(dic)\n",
    "dic2.columns = col"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['장르', '재미있는', '연인', '사랑', '맹렬한', '빠른', '총격', '날으는'], dtype='object')"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dic2.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>장르</th>\n",
       "      <th>재미있는</th>\n",
       "      <th>연인</th>\n",
       "      <th>사랑</th>\n",
       "      <th>맹렬한</th>\n",
       "      <th>빠른</th>\n",
       "      <th>총격</th>\n",
       "      <th>날으는</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>코미디</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>액션</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>코미디</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>액션</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>액션</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    장르  재미있는  연인  사랑  맹렬한  빠른  총격  날으는\n",
       "0  코미디     1   1   2    0   0   0    0\n",
       "1   액션     0   0   0    1   1   1    0\n",
       "2  코미디     2   1   0    0   1   0    1\n",
       "3   액션     1   0   0    1   0   2    0\n",
       "4   액션     0   0   1    0   1   1    1"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dic2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 0보다 큰 경우 'yes'로 반환하는 사용자 정의 함수를 생성"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert(x):\n",
    "    if x>0:\n",
    "        return 1\n",
    "    else:\n",
    "        return 0\n",
    "# convert(1) -> yes\n",
    "# convert(0) -> 'no'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'yes'"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "convert(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'no'"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "convert(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    1\n",
       "1    0\n",
       "2    1\n",
       "3    1\n",
       "4    0\n",
       "Name: 재미있는, dtype: int64"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dic2['재미있는'].apply(convert)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['재미있는', '연인', '사랑', '맹렬한', '빠른', '총격', '날으는'], dtype='object')"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dic2.columns[1:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "for x in dic2.columns[1:]: dic2[x]=dic2[x].apply(convert)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>장르</th>\n",
       "      <th>재미있는</th>\n",
       "      <th>연인</th>\n",
       "      <th>사랑</th>\n",
       "      <th>맹렬한</th>\n",
       "      <th>빠른</th>\n",
       "      <th>총격</th>\n",
       "      <th>날으는</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>코미디</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>액션</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>코미디</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>액션</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>액션</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    장르  재미있는  연인  사랑  맹렬한  빠른  총격  날으는\n",
       "0  코미디     1   1   1    0   0   0    0\n",
       "1   액션     0   0   0    1   1   1    0\n",
       "2  코미디     1   1   0    0   1   0    1\n",
       "3   액션     1   0   0    1   0   1    0\n",
       "4   액션     0   0   1    0   1   1    1"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dic2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 가능하면 list comprehension, apply를 쓸 것 for문은 최대한 자제"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### R에서는 문자를 factor로 바꿔주면 들어가는데\n",
    "#### python에서는 숫자가 아니면 안들어감 ... 면접 때 알고리즘 설명 가능해야"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 정규분포를 따르는 경우는 거의 없음, 대부분 multinomial Naive Bayes (다항분포)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## in gaussian ... \n",
    "## parameter : 사전 확률, 매우 작은 수만큼 추가 가능 \n",
    "## attribute : 모델을 만들고 . 뒤에 각 class에서 관찰된 횟수 추가 가능"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 나이브베이즈 모델 적용(Laplace 적용x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\anaconda\\lib\\site-packages\\sklearn\\naive_bayes.py:512: UserWarning: alpha too small will result in numeric errors, setting alpha = 1.0e-10\n",
      "  'setting alpha = %.1e' % _ALPHA_MIN)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "MultinomialNB(alpha=0)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "\n",
    "# alpha : laplace 추정기, default 1\n",
    "# class_prior : 사전확률 직접 정의 \n",
    "# 사전 확률 : 구분하고 싶은 최종 확률\n",
    "## comedy가 5개중 2개, action이 5개중 3개 -> 어떤 단어 B를 뽑았을 때 A인 경우\n",
    "## 사전 확률을 곱해줘서 사전 확률에 따른 그 단어의 확률을 구함 (사후 확률)\n",
    "# fit_prior : 사전확률 적합, default True\n",
    "\n",
    "model = MultinomialNB(alpha=0)\n",
    "model.fit(dic2.iloc[:, 1:], dic2['장르']) # dic2.iloc : 숫자로 데이터 프레임의 행렬 접근, 장르 : 알고 싶은 것"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### attribute"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# alpha : alpha값 확인\n",
    "model.alpha"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['액션', '코미디'], dtype='<U3')"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# classes_ : 클래스 이름\n",
    "# 학습 시켜준 이후에\n",
    "model.classes_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([3., 2.])"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# class_count_ : 클래스 개수 반환\n",
    "model.class_count_\n",
    "# action 3 comedy 2 exist"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1., 0., 1., 2., 2., 3., 1.],\n",
       "       [2., 2., 1., 0., 1., 0., 1.]])"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# feature_count_ : 각 클래스별 단어 개수 등장 횟수\n",
    "model.feature_count_ # 위에껀 action에서 나타나는 단어 개수, 아래껀 comedy에서 나타나는 단어 개수"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.6, 0.4])"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# class_log_prior_ : class별 log를 씌운 사전확률\n",
    "# log_e_1.33 에 e를 씌우면 1.33\n",
    "# 수학적 모듈 np\n",
    "np.exp(model.class_log_prior_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1.00000000e-01, 1.00000000e-11, 1.00000000e-01, 2.00000000e-01,\n",
       "        2.00000000e-01, 3.00000000e-01, 1.00000000e-01],\n",
       "       [2.85714286e-01, 2.85714286e-01, 1.42857143e-01, 1.42857143e-11,\n",
       "        1.42857143e-01, 1.42857143e-11, 1.42857143e-01]])"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# feature_log_prob_ : 단어별 log를 씌운 사후확률\n",
    "np.exp(model.feature_log_prob_)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## '재미있는 맹렬한 빠른' 단어가 나올경우"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['장르', '재미있는', '연인', '사랑', '맹렬한', '빠른', '총격', '날으는'], dtype='object')"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dic2.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "# test set 만들기\n",
    "test = np.array([1, 0, 0, 1, 1, 0, 0])#reshape(1,-1) # 재미있는 맹렬한 빠른\n",
    "# 머신러닝에서는 list말고 array로 넣을 것\n",
    "# (-1,1) : 행을 1열로 하라 -> 7행"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7,)"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1, 0, 0, 1, 1, 0, 0]])"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test = np.array([1, 0, 0, 1, 1, 0, 0]).reshape(1,-1)\n",
    "test # 대괄호 2개"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['액션'], dtype='<U3')"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 예측\n",
    "model.predict(test)\n",
    "# reshape (차원 변경)하라 -> (1, -1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1.00000000e+00, 9.71817298e-11]])"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 확률 확인\n",
    "model.predict_proba(test)\n",
    "# 거의 1에 가까움 -> action"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 나이브베이즈 모델 적용(Laplace 적용o)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MultinomialNB(alpha=1)"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "\n",
    "model = MultinomialNB(alpha=1)\n",
    "model.fit(dic2.iloc[:, 1:], dic2['장르'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['액션'], dtype='<U3')"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 예측\n",
    "model.predict(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.71536991, 0.28463009]])"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 확률 확인\n",
    "model.predict_proba(test)\n",
    "# 확률이 좀 낮아짐 - 학습이 극단적이면 안됨"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 데이터 불러오기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "wine = pd.read_csv(\"./input/wine.csv\")\n",
    "\n",
    "wine['grade'] = ['Good' if x in range(3,7) else 'Best' for x in wine['quality']]\n",
    "\n",
    "x_data = wine.drop(['quality', 'grade'], axis=1)\n",
    "y_data = wine['grade']\n",
    "\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# scaler 생성\n",
    "standard_scaler = StandardScaler()\n",
    "\n",
    "# scaler 학습\n",
    "standard_scaler.fit(x_data)\n",
    "\n",
    "# scaler 적용\n",
    "wine_scaled = standard_scaler.transform(x_data)\n",
    "\n",
    "# 최종 데이터프레임 만들기\n",
    "x_data = pd.DataFrame(wine_scaled, columns=x_data.columns)\n",
    "\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(x_data, y_data, test_size = 0.2, random_state = 321)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "col = ['장르', '재미있는', '연인', '사랑', '맹렬한', '빠른', '총격', '날으는']\n",
    "\n",
    "genre = ['코미디', '액션', '코미디', '액션', '액션']\n",
    "V1 = [1, 0, 2, 1, 0]\n",
    "V2 = [1, 0, 1, 0, 0]\n",
    "V3 = [2, 0, 0, 0, 1]\n",
    "V4 = [0, 1, 0, 1, 0]\n",
    "V5 = [0, 1, 1, 0, 1]\n",
    "V6 = [0, 1, 0, 2, 1]\n",
    "V7 = [0, 0, 1, 0, 1]\n",
    "\n",
    "dic = {'장르':genre, 'V1':V1, 'V2':V2, 'V3':V3, 'V4':V4, 'V5':V5, 'V6':V6, 'V7':V7}\n",
    "\n",
    "\n",
    "data = pd.DataFrame(dic)\n",
    "data.columns = col\n",
    "\n",
    "\n",
    "def convert(x):\n",
    "    if x > 0:\n",
    "        return 1\n",
    "    else:\n",
    "        return 0\n",
    "    \n",
    "\n",
    "for i in data.columns[1:]:\n",
    "    data[i] = data[i].apply(convert)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "data=pd.read_csv('./input/HouseVotes84.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 결측치 채우기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "202"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 결측치가 있는 행만 불러오기\n",
    "temp = data.isna().sum(axis=1)\n",
    "len(temp[temp!=0].index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "data.fillna('y', inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## n이면 0, y면 1 적용"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert(x):\n",
    "    if x == 'n':\n",
    "        return 0\n",
    "    else:\n",
    "        return 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in data.columns[1:]:\n",
    "    data[i]=data[i].apply(convert)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Class</th>\n",
       "      <th>V1</th>\n",
       "      <th>V2</th>\n",
       "      <th>V3</th>\n",
       "      <th>V4</th>\n",
       "      <th>V5</th>\n",
       "      <th>V6</th>\n",
       "      <th>V7</th>\n",
       "      <th>V8</th>\n",
       "      <th>V9</th>\n",
       "      <th>V10</th>\n",
       "      <th>V11</th>\n",
       "      <th>V12</th>\n",
       "      <th>V13</th>\n",
       "      <th>V14</th>\n",
       "      <th>V15</th>\n",
       "      <th>V16</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>republican</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>republican</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>democrat</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>democrat</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>democrat</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>429</td>\n",
       "      <td>republican</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>430</td>\n",
       "      <td>democrat</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>431</td>\n",
       "      <td>republican</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>432</td>\n",
       "      <td>republican</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>433</td>\n",
       "      <td>republican</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>434 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          Class  V1  V2  V3  V4  V5  V6  V7  V8  V9  V10  V11  V12  V13  V14  \\\n",
       "0    republican   0   1   0   1   1   1   0   0   0    1    1    1    1    1   \n",
       "1    republican   0   1   0   1   1   1   0   0   0    0    0    1    1    1   \n",
       "2      democrat   1   1   1   1   1   1   0   0   0    0    1    0    1    1   \n",
       "3      democrat   0   1   1   0   1   1   0   0   0    0    1    0    1    0   \n",
       "4      democrat   1   1   1   0   1   1   0   0   0    0    1    1    1    1   \n",
       "..          ...  ..  ..  ..  ..  ..  ..  ..  ..  ..  ...  ...  ...  ...  ...   \n",
       "429  republican   0   0   1   1   1   1   0   0   1    1    0    1    1    1   \n",
       "430    democrat   0   0   1   0   0   0   1   1   1    1    0    0    0    0   \n",
       "431  republican   0   1   0   1   1   1   0   0   0    0    1    1    1    1   \n",
       "432  republican   0   0   0   1   1   1   1   1   1    1    0    1    1    1   \n",
       "433  republican   0   1   0   1   1   1   0   0   0    1    0    1    1    1   \n",
       "\n",
       "     V15  V16  \n",
       "0      0    1  \n",
       "1      0    1  \n",
       "2      0    0  \n",
       "3      0    1  \n",
       "4      1    1  \n",
       "..   ...  ...  \n",
       "429    0    1  \n",
       "430    0    1  \n",
       "431    0    1  \n",
       "432    0    1  \n",
       "433    1    0  \n",
       "\n",
       "[434 rows x 17 columns]"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## train test 분리"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "\n",
    "# random seed 설정하기\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_data=data.iloc[:, 1:] # 2번째 column부터 끝까지\n",
    "y_data=data['Class'] # 종속변수"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "# train, test set분리\n",
    "X_train, X_test, y_train, y_test = train_test_split(x_data, y_data, test_size=0.3, random_state=7) \n",
    "# 100개 중에 30개를 뽑는데 seed 값에 따라 뽑히는 값이 다름"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 나이브베이즈 모델 적용"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "\n",
    "model = MultinomialNB(alpha=1)\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# test 데이터로 예측\n",
    "model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 정확도 확인\n",
    "sum(y_pred==y_test)/len(y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# random forest ... decision tree가 주알고리즘"
   ]
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}