15. clustering.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 필요한 라이브러리 불러오기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 거리 계산하는 함수 만들기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "25.0"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## seaborn module을 이용한 iris 내장 데이터 불러오기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "      <th>species</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>145</td>\n",
       "      <td>6.7</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.3</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>146</td>\n",
       "      <td>6.3</td>\n",
       "      <td>2.5</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>147</td>\n",
       "      <td>6.5</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>148</td>\n",
       "      <td>6.2</td>\n",
       "      <td>3.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.3</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>149</td>\n",
       "      <td>5.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>150 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     sepal_length  sepal_width  petal_length  petal_width    species\n",
       "0             5.1          3.5           1.4          0.2     setosa\n",
       "1             4.9          3.0           1.4          0.2     setosa\n",
       "2             4.7          3.2           1.3          0.2     setosa\n",
       "3             4.6          3.1           1.5          0.2     setosa\n",
       "4             5.0          3.6           1.4          0.2     setosa\n",
       "..            ...          ...           ...          ...        ...\n",
       "145           6.7          3.0           5.2          2.3  virginica\n",
       "146           6.3          2.5           5.0          1.9  virginica\n",
       "147           6.5          3.0           5.2          2.0  virginica\n",
       "148           6.2          3.4           5.4          2.3  virginica\n",
       "149           5.9          3.0           5.1          1.8  virginica\n",
       "\n",
       "[150 rows x 5 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 데이터 분할"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 데이터 표준화 진행"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>-0.900681</td>\n",
       "      <td>1.019004</td>\n",
       "      <td>-1.340227</td>\n",
       "      <td>-1.315444</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>-1.143017</td>\n",
       "      <td>-0.131979</td>\n",
       "      <td>-1.340227</td>\n",
       "      <td>-1.315444</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>-1.385353</td>\n",
       "      <td>0.328414</td>\n",
       "      <td>-1.397064</td>\n",
       "      <td>-1.315444</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>-1.506521</td>\n",
       "      <td>0.098217</td>\n",
       "      <td>-1.283389</td>\n",
       "      <td>-1.315444</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>-1.021849</td>\n",
       "      <td>1.249201</td>\n",
       "      <td>-1.340227</td>\n",
       "      <td>-1.315444</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>145</td>\n",
       "      <td>1.038005</td>\n",
       "      <td>-0.131979</td>\n",
       "      <td>0.819596</td>\n",
       "      <td>1.448832</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>146</td>\n",
       "      <td>0.553333</td>\n",
       "      <td>-1.282963</td>\n",
       "      <td>0.705921</td>\n",
       "      <td>0.922303</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>147</td>\n",
       "      <td>0.795669</td>\n",
       "      <td>-0.131979</td>\n",
       "      <td>0.819596</td>\n",
       "      <td>1.053935</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>148</td>\n",
       "      <td>0.432165</td>\n",
       "      <td>0.788808</td>\n",
       "      <td>0.933271</td>\n",
       "      <td>1.448832</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>149</td>\n",
       "      <td>0.068662</td>\n",
       "      <td>-0.131979</td>\n",
       "      <td>0.762758</td>\n",
       "      <td>0.790671</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>150 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     sepal_length  sepal_width  petal_length  petal_width\n",
       "0       -0.900681     1.019004     -1.340227    -1.315444\n",
       "1       -1.143017    -0.131979     -1.340227    -1.315444\n",
       "2       -1.385353     0.328414     -1.397064    -1.315444\n",
       "3       -1.506521     0.098217     -1.283389    -1.315444\n",
       "4       -1.021849     1.249201     -1.340227    -1.315444\n",
       "..            ...          ...           ...          ...\n",
       "145      1.038005    -0.131979      0.819596     1.448832\n",
       "146      0.553333    -1.282963      0.705921     0.922303\n",
       "147      0.795669    -0.131979      0.819596     1.053935\n",
       "148      0.432165     0.788808      0.933271     1.448832\n",
       "149      0.068662    -0.131979      0.762758     0.790671\n",
       "\n",
       "[150 rows x 4 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## kmeans 모델"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KMeans(n_clusters=3, random_state=311)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.cluster import KMeans\n",
    "\n",
    "# n_clusters : cluster 개수\n",
    "# n_init :초기값 설정 횟수\n",
    "# max_iter : k-means 최대 반복 횟수\n",
    "# 현재 sklearn에서 kmeans는 유클리디안 거리만 제공\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KMeans(n_clusters=3, random_state=311)"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 모델 학습\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "40    setosa\n",
       "34    setosa\n",
       "44    setosa\n",
       "22    setosa\n",
       "18    setosa\n",
       "45    setosa\n",
       "10    setosa\n",
       "7     setosa\n",
       "30    setosa\n",
       "49    setosa\n",
       "24    setosa\n",
       "31    setosa\n",
       "16    setosa\n",
       "2     setosa\n",
       "38    setosa\n",
       "Name: species, dtype: object"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 0번 군집 확인 \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "114     virginica\n",
       "122     virginica\n",
       "139     virginica\n",
       "148     virginica\n",
       "144     virginica\n",
       "118     virginica\n",
       "100     virginica\n",
       "117     virginica\n",
       "104     virginica\n",
       "103     virginica\n",
       "58     versicolor\n",
       "70     versicolor\n",
       "125     virginica\n",
       "Name: species, dtype: object"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 1번 군집 확인\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "57     versicolor\n",
       "113     virginica\n",
       "123     virginica\n",
       "92     versicolor\n",
       "66     versicolor\n",
       "63     versicolor\n",
       "121     virginica\n",
       "83     versicolor\n",
       "99     versicolor\n",
       "88     versicolor\n",
       "96     versicolor\n",
       "81     versicolor\n",
       "119     virginica\n",
       "98     versicolor\n",
       "90     versicolor\n",
       "78     versicolor\n",
       "53     versicolor\n",
       "Name: species, dtype: object"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 2번 군집 확인\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 실제 군집 진행"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KMeans(n_clusters=3, random_state=311)"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-0.05021989, -0.88337647,  0.34773781,  0.2815273 ],\n",
       "       [-1.01457897,  0.85326268, -1.30498732, -1.25489349],\n",
       "       [ 1.13597027,  0.08842168,  0.99615451,  1.01752612]])"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# cluster_centers_ : column별 중앙값 변화\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "139.82049635974968"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# inertia_ : TSS(Total Sum of Squares)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# n_iter_ : 반복 횟수\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 2, 2, 2, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 2,\n",
       "       0, 0, 0, 0, 2, 0, 0, 0, 0, 2, 2, 2, 0, 0, 0, 0, 0, 0, 0, 2, 2, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 2, 2, 2, 0, 2, 2, 2,\n",
       "       2, 2, 2, 0, 0, 2, 2, 2, 2, 0, 2, 0, 2, 0, 2, 2, 0, 2, 2, 2, 2, 2,\n",
       "       2, 0, 0, 2, 2, 2, 0, 2, 2, 2, 0, 2, 2, 2, 0, 2, 2, 0])"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# labels_ : 라벨\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 데이터프레임에 column 추가\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cluster</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>5.801887</td>\n",
       "      <td>2.673585</td>\n",
       "      <td>4.369811</td>\n",
       "      <td>1.413208</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>5.006000</td>\n",
       "      <td>3.428000</td>\n",
       "      <td>1.462000</td>\n",
       "      <td>0.246000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>6.780851</td>\n",
       "      <td>3.095745</td>\n",
       "      <td>5.510638</td>\n",
       "      <td>1.972340</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         sepal_length  sepal_width  petal_length  petal_width\n",
       "cluster                                                      \n",
       "0            5.801887     2.673585      4.369811     1.413208\n",
       "1            5.006000     3.428000      1.462000     0.246000\n",
       "2            6.780851     3.095745      5.510638     1.972340"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 군집해석\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "([<matplotlib.axis.XTick at 0x1e6ec7ab948>,\n",
       "  <matplotlib.axis.XTick at 0x1e6ef507a88>,\n",
       "  <matplotlib.axis.XTick at 0x1e6ef512208>],\n",
       " <a list of 3 Text xticklabel objects>)"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 시각화\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## k값 찾기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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": [
    "# elbow 기법\n",
    "def elbow(x):\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 계층적 군집"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2880x1440 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "from scipy.cluster.hierarchy import linkage, dendrogram\n",
    "\n",
    "# 'complete' : 먼 거리\n",
    "# 'single' : 짧은 거리\n",
    "# 'average' : 평균 거리\n",
    "\n",
    "mergings = linkage(x_data,method='complete')\n",
    "\n",
    "plt.figure(figsize=(40,20))\n",
    "dendrogram(mergings,\n",
    "           leaf_rotation=90,\n",
    "           leaf_font_size=20,\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    66\n",
       "4    49\n",
       "3    24\n",
       "2    11\n",
       "Name: predict, dtype: int64"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from scipy.cluster.hierarchy import fcluster\n",
    "\n",
    "predict = pd.DataFrame(fcluster(mergings, 4, criterion='maxclust'))\n",
    "predict.columns=['predict']\n",
    "\n",
    "predict['predict'].value_counts()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}