{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "<p style=\"font-family: Arial; font-size:2.2em;color:purple; font-style:bold\">\n",
    "\n",
    "Karar Ağaçları (Decision Tree) Kullanarak Hava Durumu \n",
    "Sınıflandırması <br><br>\n",
    "scikit-learn\n",
    "<br><br>\n",
    "</p>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "Günlük Hava Durumu Analizi</p>\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "\n",
    "Gerekli Kütüphanelerin İçe Aktarılması<br></p>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>\n",
       ".output {\n",
       "    flex-direction: row;\n",
       "}\n",
       "</style>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from IPython.display import Image, display,HTML\n",
    "CSS = \"\"\"\n",
    ".output {\n",
    "    flex-direction: row;\n",
    "}\n",
    "\"\"\"\n",
    "HTML('<style>{}</style>'.format(CSS))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "\n",
    "CSV Dosyası ile Pandas DataFrame oluşturma<br></p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "url='https://raw.githubusercontent.com/cagriemreakin/Machine-Learning/master/classification/weather/daily_weather.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv(url)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\">Hakkında</p>\n",
    "<br>\n",
    "San Diego,California eyaletine ait 2011 - 2014 arasındaki hava durumu değerleridir.Meteroloji binasındaki sensorler tarafında sıcaklık, basınç ve nemdeğerleri kayıt yaz-kış bütün mevsimler için kayıt altına alınmıştır.\n",
    "<br><br>\n",
    "Şimdi bu değerleri kullanark hava durumu için analiz yapalım."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['number', 'air_pressure_9am', 'air_temp_9am', 'avg_wind_direction_9am',\n",
       "       'avg_wind_speed_9am', 'max_wind_direction_9am', 'max_wind_speed_9am',\n",
       "       'rain_accumulation_9am', 'rain_duration_9am', 'relative_humidity_9am',\n",
       "       'relative_humidity_3pm'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "Dataset içindeki değerlerin açıklaması:\n",
    "\n",
    "* **number:** satır sayısı\n",
    "* **air_pressure_9am:** 8:55 to 9:04 arasındaki ortalama basınç (*Unit: hectopascals*)\n",
    "* **air_temp_9am:** 8:55 to 9:04 arasındaki ortalama sıcaklık (*Unit: degrees Fahrenheit*)\n",
    "* **air_wind_direction_9am:** 8:55 to 9:04 arasındaki ortalama rüzgar yönü (*Unit: degrees, with 0 means coming from the North, and increasing clockwise*)\n",
    "* **air_wind_speed_9am:** 8:55 to 9:04 arasındaki ortalama rüzgar hızı (*Unit: miles per hour*)\n",
    "* ** max_wind_direction_9am:** 8:55 to 9:04 arasındaki ortalama kuvvetli rüzgar (*Unit: degrees, with 0 being North and increasing clockwise*)\n",
    "* **max_wind_speed_9am:** 8:55 to 9:04 arasındaki ortalama kuvvetli rüzgar hızı (*Unit: miles per hour*)\n",
    "* **rain_accumulation_9am:** 24 saatlik yağmur miktarı (*Unit: millimeters*)\n",
    "* **rain_duration_9am:**24 saat içindeki yağmur yağma süresi(*Unit: seconds*)\n",
    "* **relative_humidity_9am:**Ortalama bağıl nem 8:55  ila 9:04 arasındaki . (*Unit: percent*)\n",
    "* **relative_humidity_3pm:** Ortalama bağıl nem 2:55  ila 3:04 arasındak (*Unit: percent *)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>number</th>\n",
       "      <th>air_pressure_9am</th>\n",
       "      <th>air_temp_9am</th>\n",
       "      <th>avg_wind_direction_9am</th>\n",
       "      <th>avg_wind_speed_9am</th>\n",
       "      <th>max_wind_direction_9am</th>\n",
       "      <th>max_wind_speed_9am</th>\n",
       "      <th>rain_accumulation_9am</th>\n",
       "      <th>rain_duration_9am</th>\n",
       "      <th>relative_humidity_9am</th>\n",
       "      <th>relative_humidity_3pm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>918.060000</td>\n",
       "      <td>74.822000</td>\n",
       "      <td>271.100000</td>\n",
       "      <td>2.080354</td>\n",
       "      <td>295.400000</td>\n",
       "      <td>2.863283</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>42.420000</td>\n",
       "      <td>36.160000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>917.347688</td>\n",
       "      <td>71.403843</td>\n",
       "      <td>101.935179</td>\n",
       "      <td>2.443009</td>\n",
       "      <td>140.471548</td>\n",
       "      <td>3.533324</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>24.328697</td>\n",
       "      <td>19.426597</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>923.040000</td>\n",
       "      <td>60.638000</td>\n",
       "      <td>51.000000</td>\n",
       "      <td>17.067852</td>\n",
       "      <td>63.700000</td>\n",
       "      <td>22.100967</td>\n",
       "      <td>0.00</td>\n",
       "      <td>20.0</td>\n",
       "      <td>8.900000</td>\n",
       "      <td>14.460000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>920.502751</td>\n",
       "      <td>70.138895</td>\n",
       "      <td>198.832133</td>\n",
       "      <td>4.337363</td>\n",
       "      <td>211.203341</td>\n",
       "      <td>5.190045</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>12.189102</td>\n",
       "      <td>12.742547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>921.160000</td>\n",
       "      <td>44.294000</td>\n",
       "      <td>277.800000</td>\n",
       "      <td>1.856660</td>\n",
       "      <td>136.500000</td>\n",
       "      <td>2.863283</td>\n",
       "      <td>8.90</td>\n",
       "      <td>14730.0</td>\n",
       "      <td>92.410000</td>\n",
       "      <td>76.740000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5</td>\n",
       "      <td>915.300000</td>\n",
       "      <td>78.404000</td>\n",
       "      <td>182.800000</td>\n",
       "      <td>9.932014</td>\n",
       "      <td>189.000000</td>\n",
       "      <td>10.983375</td>\n",
       "      <td>0.02</td>\n",
       "      <td>170.0</td>\n",
       "      <td>35.130000</td>\n",
       "      <td>33.930000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>6</td>\n",
       "      <td>915.598868</td>\n",
       "      <td>70.043304</td>\n",
       "      <td>177.875407</td>\n",
       "      <td>3.745587</td>\n",
       "      <td>186.606696</td>\n",
       "      <td>4.589632</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10.657422</td>\n",
       "      <td>21.385657</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>7</td>\n",
       "      <td>918.070000</td>\n",
       "      <td>51.710000</td>\n",
       "      <td>242.400000</td>\n",
       "      <td>2.527742</td>\n",
       "      <td>271.600000</td>\n",
       "      <td>3.646212</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>80.470000</td>\n",
       "      <td>74.920000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>8</td>\n",
       "      <td>920.080000</td>\n",
       "      <td>80.582000</td>\n",
       "      <td>40.700000</td>\n",
       "      <td>4.518619</td>\n",
       "      <td>63.000000</td>\n",
       "      <td>5.883152</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>29.580000</td>\n",
       "      <td>24.030000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>9</td>\n",
       "      <td>915.010000</td>\n",
       "      <td>47.498000</td>\n",
       "      <td>163.100000</td>\n",
       "      <td>4.943637</td>\n",
       "      <td>195.900000</td>\n",
       "      <td>6.576604</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>88.600000</td>\n",
       "      <td>68.050000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   number  air_pressure_9am  air_temp_9am  avg_wind_direction_9am  \\\n",
       "0       0        918.060000     74.822000              271.100000   \n",
       "1       1        917.347688     71.403843              101.935179   \n",
       "2       2        923.040000     60.638000               51.000000   \n",
       "3       3        920.502751     70.138895              198.832133   \n",
       "4       4        921.160000     44.294000              277.800000   \n",
       "5       5        915.300000     78.404000              182.800000   \n",
       "6       6        915.598868     70.043304              177.875407   \n",
       "7       7        918.070000     51.710000              242.400000   \n",
       "8       8        920.080000     80.582000               40.700000   \n",
       "9       9        915.010000     47.498000              163.100000   \n",
       "\n",
       "   avg_wind_speed_9am  max_wind_direction_9am  max_wind_speed_9am  \\\n",
       "0            2.080354              295.400000            2.863283   \n",
       "1            2.443009              140.471548            3.533324   \n",
       "2           17.067852               63.700000           22.100967   \n",
       "3            4.337363              211.203341            5.190045   \n",
       "4            1.856660              136.500000            2.863283   \n",
       "5            9.932014              189.000000           10.983375   \n",
       "6            3.745587              186.606696            4.589632   \n",
       "7            2.527742              271.600000            3.646212   \n",
       "8            4.518619               63.000000            5.883152   \n",
       "9            4.943637              195.900000            6.576604   \n",
       "\n",
       "   rain_accumulation_9am  rain_duration_9am  relative_humidity_9am  \\\n",
       "0                   0.00                0.0              42.420000   \n",
       "1                   0.00                0.0              24.328697   \n",
       "2                   0.00               20.0               8.900000   \n",
       "3                   0.00                0.0              12.189102   \n",
       "4                   8.90            14730.0              92.410000   \n",
       "5                   0.02              170.0              35.130000   \n",
       "6                   0.00                0.0              10.657422   \n",
       "7                   0.00                0.0              80.470000   \n",
       "8                   0.00                0.0              29.580000   \n",
       "9                   0.00                0.0              88.600000   \n",
       "\n",
       "   relative_humidity_3pm  \n",
       "0              36.160000  \n",
       "1              19.426597  \n",
       "2              14.460000  \n",
       "3              12.742547  \n",
       "4              76.740000  \n",
       "5              33.930000  \n",
       "6              21.385657  \n",
       "7              74.920000  \n",
       "8              24.030000  \n",
       "9              68.050000  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Veri işlemenin ilk adımı temiz bir veri elde etmektir.Hücredeki boş (null)değerler hesaplamaların yanlış olmasına sebep olabilir.Satırlardaki boş değerleri bulalım."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>number</th>\n",
       "      <th>air_pressure_9am</th>\n",
       "      <th>air_temp_9am</th>\n",
       "      <th>avg_wind_direction_9am</th>\n",
       "      <th>avg_wind_speed_9am</th>\n",
       "      <th>max_wind_direction_9am</th>\n",
       "      <th>max_wind_speed_9am</th>\n",
       "      <th>rain_accumulation_9am</th>\n",
       "      <th>rain_duration_9am</th>\n",
       "      <th>relative_humidity_9am</th>\n",
       "      <th>relative_humidity_3pm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>16</td>\n",
       "      <td>917.890000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>169.200000</td>\n",
       "      <td>2.192201</td>\n",
       "      <td>196.800000</td>\n",
       "      <td>2.930391</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>48.990000</td>\n",
       "      <td>51.190000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>111</th>\n",
       "      <td>111</td>\n",
       "      <td>915.290000</td>\n",
       "      <td>58.820000</td>\n",
       "      <td>182.600000</td>\n",
       "      <td>15.613841</td>\n",
       "      <td>189.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>21.500000</td>\n",
       "      <td>29.690000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>177</th>\n",
       "      <td>177</td>\n",
       "      <td>915.900000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>183.300000</td>\n",
       "      <td>4.719943</td>\n",
       "      <td>189.900000</td>\n",
       "      <td>5.346287</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>29.260000</td>\n",
       "      <td>46.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>262</th>\n",
       "      <td>262</td>\n",
       "      <td>923.596607</td>\n",
       "      <td>58.380598</td>\n",
       "      <td>47.737753</td>\n",
       "      <td>10.636273</td>\n",
       "      <td>67.145843</td>\n",
       "      <td>13.671423</td>\n",
       "      <td>0.000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>17.990876</td>\n",
       "      <td>16.461685</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>277</th>\n",
       "      <td>277</td>\n",
       "      <td>920.480000</td>\n",
       "      <td>62.600000</td>\n",
       "      <td>194.400000</td>\n",
       "      <td>2.751436</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.869906</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>52.580000</td>\n",
       "      <td>54.030000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>334</th>\n",
       "      <td>334</td>\n",
       "      <td>916.230000</td>\n",
       "      <td>75.740000</td>\n",
       "      <td>149.100000</td>\n",
       "      <td>2.751436</td>\n",
       "      <td>187.500000</td>\n",
       "      <td>4.183078</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1480.000000</td>\n",
       "      <td>31.880000</td>\n",
       "      <td>32.900000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>358</th>\n",
       "      <td>358</td>\n",
       "      <td>917.440000</td>\n",
       "      <td>58.514000</td>\n",
       "      <td>55.100000</td>\n",
       "      <td>10.021491</td>\n",
       "      <td>NaN</td>\n",
       "      <td>12.705819</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>13.880000</td>\n",
       "      <td>25.930000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>361</th>\n",
       "      <td>361</td>\n",
       "      <td>920.444946</td>\n",
       "      <td>65.801845</td>\n",
       "      <td>49.823346</td>\n",
       "      <td>21.520177</td>\n",
       "      <td>61.886944</td>\n",
       "      <td>25.549112</td>\n",
       "      <td>NaN</td>\n",
       "      <td>40.364018</td>\n",
       "      <td>12.278715</td>\n",
       "      <td>7.618649</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>381</th>\n",
       "      <td>381</td>\n",
       "      <td>918.480000</td>\n",
       "      <td>66.542000</td>\n",
       "      <td>90.900000</td>\n",
       "      <td>3.467257</td>\n",
       "      <td>89.400000</td>\n",
       "      <td>4.406772</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>20.640000</td>\n",
       "      <td>14.350000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>409</th>\n",
       "      <td>409</td>\n",
       "      <td>NaN</td>\n",
       "      <td>67.853833</td>\n",
       "      <td>65.880616</td>\n",
       "      <td>4.328594</td>\n",
       "      <td>78.570923</td>\n",
       "      <td>5.216734</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>18.487385</td>\n",
       "      <td>20.356594</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>517</th>\n",
       "      <td>517</td>\n",
       "      <td>920.570000</td>\n",
       "      <td>53.600000</td>\n",
       "      <td>100.100000</td>\n",
       "      <td>4.697574</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.285801</td>\n",
       "      <td>4.712</td>\n",
       "      <td>14842.000000</td>\n",
       "      <td>79.880000</td>\n",
       "      <td>84.530000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>519</th>\n",
       "      <td>519</td>\n",
       "      <td>916.250000</td>\n",
       "      <td>55.670000</td>\n",
       "      <td>176.400000</td>\n",
       "      <td>6.666081</td>\n",
       "      <td>188.200000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>72.550000</td>\n",
       "      <td>74.390000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>546</th>\n",
       "      <td>546</td>\n",
       "      <td>NaN</td>\n",
       "      <td>42.746000</td>\n",
       "      <td>251.100000</td>\n",
       "      <td>12.929513</td>\n",
       "      <td>274.400000</td>\n",
       "      <td>17.604718</td>\n",
       "      <td>14.627</td>\n",
       "      <td>7825.000000</td>\n",
       "      <td>87.870000</td>\n",
       "      <td>70.770000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>620</th>\n",
       "      <td>620</td>\n",
       "      <td>921.200000</td>\n",
       "      <td>56.786000</td>\n",
       "      <td>192.300000</td>\n",
       "      <td>9.551734</td>\n",
       "      <td>201.400000</td>\n",
       "      <td>11.005745</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>59.790000</td>\n",
       "      <td>77.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>625</th>\n",
       "      <td>625</td>\n",
       "      <td>912.400000</td>\n",
       "      <td>50.774000</td>\n",
       "      <td>171.600000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>181.400000</td>\n",
       "      <td>4.831790</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>86.840000</td>\n",
       "      <td>64.740000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>656</th>\n",
       "      <td>656</td>\n",
       "      <td>920.830000</td>\n",
       "      <td>66.344000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>15.457255</td>\n",
       "      <td>189.400000</td>\n",
       "      <td>16.486248</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>23.770000</td>\n",
       "      <td>51.630000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>670</th>\n",
       "      <td>670</td>\n",
       "      <td>910.920000</td>\n",
       "      <td>48.362000</td>\n",
       "      <td>156.500000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>177.500000</td>\n",
       "      <td>16.128337</td>\n",
       "      <td>4.970</td>\n",
       "      <td>10560.000000</td>\n",
       "      <td>80.560000</td>\n",
       "      <td>88.220000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>672</th>\n",
       "      <td>672</td>\n",
       "      <td>922.448945</td>\n",
       "      <td>72.863773</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.682370</td>\n",
       "      <td>214.196160</td>\n",
       "      <td>4.849450</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>16.753670</td>\n",
       "      <td>17.804720</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>705</th>\n",
       "      <td>705</td>\n",
       "      <td>911.900000</td>\n",
       "      <td>59.072000</td>\n",
       "      <td>199.800000</td>\n",
       "      <td>1.275056</td>\n",
       "      <td>239.500000</td>\n",
       "      <td>1.834291</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>77.630000</td>\n",
       "      <td>59.130000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>731</th>\n",
       "      <td>731</td>\n",
       "      <td>922.970166</td>\n",
       "      <td>51.391847</td>\n",
       "      <td>33.810942</td>\n",
       "      <td>NaN</td>\n",
       "      <td>59.290089</td>\n",
       "      <td>11.111555</td>\n",
       "      <td>0.000</td>\n",
       "      <td>4.735034</td>\n",
       "      <td>34.807753</td>\n",
       "      <td>18.418179</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>737</th>\n",
       "      <td>737</td>\n",
       "      <td>917.895130</td>\n",
       "      <td>76.804690</td>\n",
       "      <td>104.771020</td>\n",
       "      <td>1.632705</td>\n",
       "      <td>97.178763</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>13.771311</td>\n",
       "      <td>16.792455</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>788</th>\n",
       "      <td>788</td>\n",
       "      <td>917.923442</td>\n",
       "      <td>73.249717</td>\n",
       "      <td>42.101739</td>\n",
       "      <td>4.132698</td>\n",
       "      <td>64.284969</td>\n",
       "      <td>5.345258</td>\n",
       "      <td>0.000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.939692</td>\n",
       "      <td>18.793825</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>840</th>\n",
       "      <td>840</td>\n",
       "      <td>918.043767</td>\n",
       "      <td>NaN</td>\n",
       "      <td>181.774042</td>\n",
       "      <td>0.964376</td>\n",
       "      <td>185.618601</td>\n",
       "      <td>1.570007</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>11.911222</td>\n",
       "      <td>18.154358</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>848</th>\n",
       "      <td>848</td>\n",
       "      <td>915.250000</td>\n",
       "      <td>37.562000</td>\n",
       "      <td>246.500000</td>\n",
       "      <td>11.587349</td>\n",
       "      <td>258.700000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.171</td>\n",
       "      <td>2891.000000</td>\n",
       "      <td>91.000000</td>\n",
       "      <td>90.780000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>861</th>\n",
       "      <td>861</td>\n",
       "      <td>919.065408</td>\n",
       "      <td>NaN</td>\n",
       "      <td>172.303728</td>\n",
       "      <td>2.639600</td>\n",
       "      <td>193.058141</td>\n",
       "      <td>3.326949</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>12.497839</td>\n",
       "      <td>13.438518</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>869</th>\n",
       "      <td>869</td>\n",
       "      <td>NaN</td>\n",
       "      <td>45.104000</td>\n",
       "      <td>259.000000</td>\n",
       "      <td>3.265932</td>\n",
       "      <td>275.000000</td>\n",
       "      <td>4.026492</td>\n",
       "      <td>0.000</td>\n",
       "      <td>80.000000</td>\n",
       "      <td>85.270000</td>\n",
       "      <td>90.260000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>998</th>\n",
       "      <td>998</td>\n",
       "      <td>914.140000</td>\n",
       "      <td>71.240000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.722444</td>\n",
       "      <td>232.900000</td>\n",
       "      <td>2.326418</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24.200000</td>\n",
       "      <td>41.380000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1031</th>\n",
       "      <td>1031</td>\n",
       "      <td>922.669195</td>\n",
       "      <td>NaN</td>\n",
       "      <td>47.946284</td>\n",
       "      <td>7.969686</td>\n",
       "      <td>65.770066</td>\n",
       "      <td>10.262337</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>18.920805</td>\n",
       "      <td>19.641841</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1035</th>\n",
       "      <td>1035</td>\n",
       "      <td>919.670000</td>\n",
       "      <td>77.576000</td>\n",
       "      <td>171.800000</td>\n",
       "      <td>6.554234</td>\n",
       "      <td>191.000000</td>\n",
       "      <td>8.164831</td>\n",
       "      <td>0.000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>56.860000</td>\n",
       "      <td>50.650000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1063</th>\n",
       "      <td>1063</td>\n",
       "      <td>917.300185</td>\n",
       "      <td>65.790001</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.879553</td>\n",
       "      <td>222.498226</td>\n",
       "      <td>2.692862</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>14.972668</td>\n",
       "      <td>20.966267</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1066</th>\n",
       "      <td>1066</td>\n",
       "      <td>919.564869</td>\n",
       "      <td>73.726732</td>\n",
       "      <td>68.704694</td>\n",
       "      <td>3.551777</td>\n",
       "      <td>102.571616</td>\n",
       "      <td>4.861315</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>11.657314</td>\n",
       "      <td>17.331823</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      number  air_pressure_9am  air_temp_9am  avg_wind_direction_9am  \\\n",
       "16        16        917.890000           NaN              169.200000   \n",
       "111      111        915.290000     58.820000              182.600000   \n",
       "177      177        915.900000           NaN              183.300000   \n",
       "262      262        923.596607     58.380598               47.737753   \n",
       "277      277        920.480000     62.600000              194.400000   \n",
       "334      334        916.230000     75.740000              149.100000   \n",
       "358      358        917.440000     58.514000               55.100000   \n",
       "361      361        920.444946     65.801845               49.823346   \n",
       "381      381        918.480000     66.542000               90.900000   \n",
       "409      409               NaN     67.853833               65.880616   \n",
       "517      517        920.570000     53.600000              100.100000   \n",
       "519      519        916.250000     55.670000              176.400000   \n",
       "546      546               NaN     42.746000              251.100000   \n",
       "620      620        921.200000     56.786000              192.300000   \n",
       "625      625        912.400000     50.774000              171.600000   \n",
       "656      656        920.830000     66.344000                     NaN   \n",
       "670      670        910.920000     48.362000              156.500000   \n",
       "672      672        922.448945     72.863773                     NaN   \n",
       "705      705        911.900000     59.072000              199.800000   \n",
       "731      731        922.970166     51.391847               33.810942   \n",
       "737      737        917.895130     76.804690              104.771020   \n",
       "788      788        917.923442     73.249717               42.101739   \n",
       "840      840        918.043767           NaN              181.774042   \n",
       "848      848        915.250000     37.562000              246.500000   \n",
       "861      861        919.065408           NaN              172.303728   \n",
       "869      869               NaN     45.104000              259.000000   \n",
       "998      998        914.140000     71.240000                     NaN   \n",
       "1031    1031        922.669195           NaN               47.946284   \n",
       "1035    1035        919.670000     77.576000              171.800000   \n",
       "1063    1063        917.300185     65.790001                     NaN   \n",
       "1066    1066        919.564869     73.726732               68.704694   \n",
       "\n",
       "      avg_wind_speed_9am  max_wind_direction_9am  max_wind_speed_9am  \\\n",
       "16              2.192201              196.800000            2.930391   \n",
       "111            15.613841              189.000000                 NaN   \n",
       "177             4.719943              189.900000            5.346287   \n",
       "262            10.636273               67.145843           13.671423   \n",
       "277             2.751436                     NaN            3.869906   \n",
       "334             2.751436              187.500000            4.183078   \n",
       "358            10.021491                     NaN           12.705819   \n",
       "361            21.520177               61.886944           25.549112   \n",
       "381             3.467257               89.400000            4.406772   \n",
       "409             4.328594               78.570923            5.216734   \n",
       "517             4.697574                     NaN            6.285801   \n",
       "519             6.666081              188.200000                 NaN   \n",
       "546            12.929513              274.400000           17.604718   \n",
       "620             9.551734              201.400000           11.005745   \n",
       "625                  NaN              181.400000            4.831790   \n",
       "656            15.457255              189.400000           16.486248   \n",
       "670                  NaN              177.500000           16.128337   \n",
       "672             3.682370              214.196160            4.849450   \n",
       "705             1.275056              239.500000            1.834291   \n",
       "731                  NaN               59.290089           11.111555   \n",
       "737             1.632705               97.178763                 NaN   \n",
       "788             4.132698               64.284969            5.345258   \n",
       "840             0.964376              185.618601            1.570007   \n",
       "848            11.587349              258.700000                 NaN   \n",
       "861             2.639600              193.058141            3.326949   \n",
       "869             3.265932              275.000000            4.026492   \n",
       "998             1.722444              232.900000            2.326418   \n",
       "1031            7.969686               65.770066           10.262337   \n",
       "1035            6.554234              191.000000            8.164831   \n",
       "1063            1.879553              222.498226            2.692862   \n",
       "1066            3.551777              102.571616            4.861315   \n",
       "\n",
       "      rain_accumulation_9am  rain_duration_9am  relative_humidity_9am  \\\n",
       "16                    0.000           0.000000              48.990000   \n",
       "111                   0.000           0.000000              21.500000   \n",
       "177                   0.000           0.000000              29.260000   \n",
       "262                   0.000                NaN              17.990876   \n",
       "277                   0.000           0.000000              52.580000   \n",
       "334                     NaN        1480.000000              31.880000   \n",
       "358                   0.000           0.000000              13.880000   \n",
       "361                     NaN          40.364018              12.278715   \n",
       "381                     NaN           0.000000              20.640000   \n",
       "409                   0.000           0.000000              18.487385   \n",
       "517                   4.712       14842.000000              79.880000   \n",
       "519                   0.000           0.000000              72.550000   \n",
       "546                  14.627        7825.000000              87.870000   \n",
       "620                     NaN           0.000000              59.790000   \n",
       "625                   0.000           0.000000              86.840000   \n",
       "656                   0.000           0.000000              23.770000   \n",
       "670                   4.970       10560.000000              80.560000   \n",
       "672                   0.000           0.000000              16.753670   \n",
       "705                     NaN           0.000000              77.630000   \n",
       "731                   0.000           4.735034              34.807753   \n",
       "737                   0.000           0.000000              13.771311   \n",
       "788                   0.000                NaN               6.939692   \n",
       "840                   0.000           0.000000              11.911222   \n",
       "848                   3.171        2891.000000              91.000000   \n",
       "861                   0.000           0.000000              12.497839   \n",
       "869                   0.000          80.000000              85.270000   \n",
       "998                   0.000           0.000000              24.200000   \n",
       "1031                  0.000           0.000000              18.920805   \n",
       "1035                  0.000                NaN              56.860000   \n",
       "1063                  0.000           0.000000              14.972668   \n",
       "1066                    NaN           0.000000              11.657314   \n",
       "\n",
       "      relative_humidity_3pm  \n",
       "16                51.190000  \n",
       "111               29.690000  \n",
       "177               46.500000  \n",
       "262               16.461685  \n",
       "277               54.030000  \n",
       "334               32.900000  \n",
       "358               25.930000  \n",
       "361                7.618649  \n",
       "381               14.350000  \n",
       "409               20.356594  \n",
       "517               84.530000  \n",
       "519               74.390000  \n",
       "546               70.770000  \n",
       "620               77.750000  \n",
       "625               64.740000  \n",
       "656               51.630000  \n",
       "670               88.220000  \n",
       "672               17.804720  \n",
       "705               59.130000  \n",
       "731               18.418179  \n",
       "737               16.792455  \n",
       "788               18.793825  \n",
       "840               18.154358  \n",
       "848               90.780000  \n",
       "861               13.438518  \n",
       "869               90.260000  \n",
       "998               41.380000  \n",
       "1031              19.641841  \n",
       "1035              50.650000  \n",
       "1063              20.966267  \n",
       "1066              17.331823  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "data[data.isnull().any(axis=1)] "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "\n",
    "Gereksiz Veri'den Kurtulalım<br><br></p>\n",
    "\n",
    "Kaç tane satır sayısına ihtiyacımız olmadığı için silelim."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "del data['number']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "boş değerleri pandas dropna fonksiyonunu kullanarak silelim"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1064\n"
     ]
    }
   ],
   "source": [
    "silmeden_once = data.shape[0]\n",
    "print(silmeden_once)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "data = data.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1064\n",
      "None\n"
     ]
    }
   ],
   "source": [
    "sildikten_sonra = data.shape[0]\n",
    "print(print(sildikten_sonra))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "\n",
    "Temizleme işleminden sonra kalan satır sayısı?<br><br></p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "silmeden_once - sildikten_sonra"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\">\n",
    "Sınıflandırma İşlemi<br><br></p>\n",
    "İkili sistemde sınıflandırma relative_humidity_3pm (saat 3'teki nispi nem miktarı) to 0 or 1.<br>\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0       1\n",
      "1       0\n",
      "2       0\n",
      "3       0\n",
      "4       1\n",
      "5       1\n",
      "6       0\n",
      "7       1\n",
      "8       0\n",
      "9       1\n",
      "10      1\n",
      "11      1\n",
      "12      1\n",
      "13      1\n",
      "14      0\n",
      "15      0\n",
      "17      0\n",
      "18      1\n",
      "19      0\n",
      "20      0\n",
      "21      1\n",
      "22      0\n",
      "23      1\n",
      "24      0\n",
      "25      1\n",
      "26      1\n",
      "27      1\n",
      "28      1\n",
      "29      1\n",
      "30      1\n",
      "       ..\n",
      "1064    1\n",
      "1065    1\n",
      "1067    1\n",
      "1068    1\n",
      "1069    1\n",
      "1070    1\n",
      "1071    1\n",
      "1072    0\n",
      "1073    1\n",
      "1074    1\n",
      "1075    0\n",
      "1076    0\n",
      "1077    1\n",
      "1078    0\n",
      "1079    1\n",
      "1080    0\n",
      "1081    0\n",
      "1082    1\n",
      "1083    1\n",
      "1084    1\n",
      "1085    1\n",
      "1086    1\n",
      "1087    1\n",
      "1088    1\n",
      "1089    1\n",
      "1090    1\n",
      "1091    1\n",
      "1092    1\n",
      "1093    1\n",
      "1094    0\n",
      "Name: high_humidity_label, Length: 1064, dtype: int32\n"
     ]
    }
   ],
   "source": [
    "clean_data = data.copy() #temizlediğimiz veri setini kopyaladık\n",
    "clean_data['high_humidity_label'] = (clean_data['relative_humidity_3pm'] > 24.99)*1 #nem oranı 24.99'dan büyük olanları 1 olarak işaretle\n",
    "print(clean_data['high_humidity_label'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "\n",
    "Sonucu  'y' de sakla.\n",
    "<br><br></p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "y=clean_data[['high_humidity_label']].copy()\n",
    "#y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    36.160000\n",
       "1    19.426597\n",
       "2    14.460000\n",
       "3    12.742547\n",
       "4    76.740000\n",
       "Name: relative_humidity_3pm, dtype: float64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clean_data['relative_humidity_3pm'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>high_humidity_label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   high_humidity_label\n",
       "0                    1\n",
       "1                    0\n",
       "2                    0\n",
       "3                    0\n",
       "4                    1"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.head() # 25 ve büyük değerler için 1 olarak işaretlendi"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "\n",
    "Saat 3'teki Nem miktarını bulmak için Saat 9'daki sensor değerlerini kullanalım\n",
    "<br><br></p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "morning_features = ['air_pressure_9am','air_temp_9am','avg_wind_direction_9am','avg_wind_speed_9am',\n",
    "        'max_wind_direction_9am','max_wind_speed_9am','rain_accumulation_9am',\n",
    "        'rain_duration_9am']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = clean_data[morning_features].copy()# morning features'ın içindeki indeklere göre cleandata değerlerini Z' e kopyalam işelemi"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['air_pressure_9am', 'air_temp_9am', 'avg_wind_direction_9am',\n",
       "       'avg_wind_speed_9am', 'max_wind_direction_9am', 'max_wind_speed_9am',\n",
       "       'rain_accumulation_9am', 'rain_duration_9am'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['high_humidity_label'], dtype='object')"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "\n",
    "\n",
    "Test ve Eğitim(Train) Kümeleri Oluşturma \n",
    "\n",
    "<br><br></p>\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Hatırlatma: Eğitim Evresi\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmQAAAGHCAYAAAAeKU4NAAAAAXNSR0IArs4c6QAAAARnQU1BAACx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\n/pTHTt22ewAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "display(Image(filename=\"C:\\\\Users\\\\ceakn\\\\Desktop\\\\site-resimler\\\\class_apply.png\", embed=True))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=324)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Yukarıdaki kodun amacı daha önceki yazımda anlattığım test ve eğitim veri setini oluşturmaktır.Yukarıdaki kodda test için veri setinin %33 ü ayrılmıştır."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "#type(X_train)\n",
    "#type(X_test)\n",
    "#type(y_train)\n",
    "#type(y_test)\n",
    "#X_train.head()\n",
    "#y_train.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "\n",
    "Fit on Train Set\n",
    "<br><br></p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,\n",
       "            max_features=None, max_leaf_nodes=10, min_impurity_split=1e-07,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, presort=False, random_state=0,\n",
       "            splitter='best')"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "humidity_classifier = DecisionTreeClassifier(max_leaf_nodes=10, random_state=0) # 10 adet leaf node' a izin verdik ve ağacı oluşturduk.\n",
    "humidity_classifier.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sklearn.tree.tree.DecisionTreeClassifier"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(humidity_classifier)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "\n",
    "Test Kümesinden Çıkarım Yapma\n",
    "\n",
    "<br><br></p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions = humidity_classifier.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 1, 1, 1, 1, 0, 0, 0, 1])"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "456     0\n",
       "845     0\n",
       "693     1\n",
       "259     1\n",
       "723     1\n",
       "224     1\n",
       "300     1\n",
       "442     0\n",
       "585     1\n",
       "1057    1\n",
       "Name: high_humidity_label, dtype: int32"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test['high_humidity_label'][:10]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Yukarıdaki değerlere bakarsanız 2 değeriin farklı olduğunu görebilirsiniz."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"font-family: Arial; font-size:1.75em;color:purple; font-style:bold\"><br>\n",
    "\n",
    "Başarı Oranını Hesaplama\n",
    "<br><br></p>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.81534090909090906"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_true = y_test, y_pred = predictions)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "% 81 başarı"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}