diff --git a/.ipynb_checkpoints/Limpieza de datos-checkpoint.ipynb b/.ipynb_checkpoints/Limpieza de datos-checkpoint.ipynb
new file mode 100644
index 0000000..f40fe1c
--- /dev/null
+++ b/.ipynb_checkpoints/Limpieza de datos-checkpoint.ipynb	
@@ -0,0 +1,539 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.read_csv(\"measurements.csv\") #cargamos el csv."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "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>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "      <th>refill liters</th>\n",
+       "      <th>refill gas</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>28</td>\n",
+       "      <td>5</td>\n",
+       "      <td>26</td>\n",
+       "      <td>21,5</td>\n",
+       "      <td>12</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>45</td>\n",
+       "      <td>E10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>12</td>\n",
+       "      <td>4,2</td>\n",
+       "      <td>30</td>\n",
+       "      <td>21,5</td>\n",
+       "      <td>13</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>11,2</td>\n",
+       "      <td>5,5</td>\n",
+       "      <td>38</td>\n",
+       "      <td>21,5</td>\n",
+       "      <td>15</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>12,9</td>\n",
+       "      <td>3,9</td>\n",
+       "      <td>36</td>\n",
+       "      <td>21,5</td>\n",
+       "      <td>14</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>18,5</td>\n",
+       "      <td>4,5</td>\n",
+       "      <td>46</td>\n",
+       "      <td>21,5</td>\n",
+       "      <td>15</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  distance consume  speed temp_inside  temp_outside specials gas_type  AC  \\\n",
+       "0       28       5     26        21,5            12      NaN      E10   0   \n",
+       "1       12     4,2     30        21,5            13      NaN      E10   0   \n",
+       "2     11,2     5,5     38        21,5            15      NaN      E10   0   \n",
+       "3     12,9     3,9     36        21,5            14      NaN      E10   0   \n",
+       "4     18,5     4,5     46        21,5            15      NaN      E10   0   \n",
+       "\n",
+       "   rain  sun refill liters refill gas  \n",
+       "0     0    0            45        E10  \n",
+       "1     0    0           NaN        NaN  \n",
+       "2     0    0           NaN        NaN  \n",
+       "3     0    0           NaN        NaN  \n",
+       "4     0    0           NaN        NaN  "
+      ]
+     },
+     "execution_count": 105,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Exploro la forma del dataset:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(388, 12)"
+      ]
+     },
+     "execution_count": 106,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Veo la naturaleza de los datos:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 107,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 388 entries, 0 to 387\n",
+      "Data columns (total 12 columns):\n",
+      " #   Column         Non-Null Count  Dtype \n",
+      "---  ------         --------------  ----- \n",
+      " 0   distance       388 non-null    object\n",
+      " 1   consume        388 non-null    object\n",
+      " 2   speed          388 non-null    int64 \n",
+      " 3   temp_inside    376 non-null    object\n",
+      " 4   temp_outside   388 non-null    int64 \n",
+      " 5   specials       93 non-null     object\n",
+      " 6   gas_type       388 non-null    object\n",
+      " 7   AC             388 non-null    int64 \n",
+      " 8   rain           388 non-null    int64 \n",
+      " 9   sun            388 non-null    int64 \n",
+      " 10  refill liters  13 non-null     object\n",
+      " 11  refill gas     13 non-null     object\n",
+      "dtypes: int64(5), object(7)\n",
+      "memory usage: 36.5+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Compruebo que no hay duplicados:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 108,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=df.drop_duplicates() #no hay duplicados."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 109,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(388, 12)"
+      ]
+     },
+     "execution_count": 109,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Compruebo dónde hay valores nulos:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 110,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "distance           0\n",
+       "consume            0\n",
+       "speed              0\n",
+       "temp_inside       12\n",
+       "temp_outside       0\n",
+       "specials         295\n",
+       "gas_type           0\n",
+       "AC                 0\n",
+       "rain               0\n",
+       "sun                0\n",
+       "refill liters    375\n",
+       "refill gas       375\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 110,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Relleno los nulos con \"Unkown\" al tratarse de variables categóricas:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 111,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "Int64Index: 388 entries, 0 to 387\n",
+      "Data columns (total 12 columns):\n",
+      " #   Column         Non-Null Count  Dtype \n",
+      "---  ------         --------------  ----- \n",
+      " 0   distance       388 non-null    object\n",
+      " 1   consume        388 non-null    object\n",
+      " 2   speed          388 non-null    int64 \n",
+      " 3   temp_inside    376 non-null    object\n",
+      " 4   temp_outside   388 non-null    int64 \n",
+      " 5   specials       93 non-null     object\n",
+      " 6   gas_type       388 non-null    object\n",
+      " 7   AC             388 non-null    int64 \n",
+      " 8   rain           388 non-null    int64 \n",
+      " 9   sun            388 non-null    int64 \n",
+      " 10  refill liters  13 non-null     object\n",
+      " 11  refill gas     13 non-null     object\n",
+      "dtypes: int64(5), object(7)\n",
+      "memory usage: 39.4+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 112,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['temp_inside'] = pd.to_numeric(df['temp_inside'],errors = 'coerce')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 113,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#relleno los Nan con la media de las temperaturas al ser una variable numérica:\n",
+    "df[\"temp_inside\"].fillna(df[\"temp_inside\"].mean(), inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 114,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#relleno los Nan de \"specials\" con \"Unkown\" al ser categórica:\n",
+    "df.specials.fillna((\"Unknown\"), inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 117,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#elimino las columnas de \"refill liters\" y \"refill gas\" por el alto porcentaje de Nans que contienen:\n",
+    "df.drop([\"refill liters\",\"refill gas\"], axis=1, inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 118,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "distance        0\n",
+       "consume         0\n",
+       "speed           0\n",
+       "temp_inside     0\n",
+       "temp_outside    0\n",
+       "specials        0\n",
+       "gas_type        0\n",
+       "AC              0\n",
+       "rain            0\n",
+       "sun             0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 118,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 120,
+   "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>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>215</th>\n",
+       "      <td>12,1</td>\n",
+       "      <td>4,4</td>\n",
+       "      <td>33</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>5</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>SP98</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    distance consume  speed  temp_inside  temp_outside specials gas_type  AC  \\\n",
+       "215     12,1     4,4     33    21.934911             5  Unknown     SP98   0   \n",
+       "\n",
+       "     rain  sun  \n",
+       "215     0    0  "
+      ]
+     },
+     "execution_count": 120,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.sample()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Guardo el dataset limpio:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 121,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv('measurementsclean.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ironhack",
+   "language": "python",
+   "name": "ironhack"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/.ipynb_checkpoints/Machine Learning- Predictions-checkpoint.ipynb b/.ipynb_checkpoints/Machine Learning- Predictions-checkpoint.ipynb
new file mode 100644
index 0000000..8d427b5
--- /dev/null
+++ b/.ipynb_checkpoints/Machine Learning- Predictions-checkpoint.ipynb	
@@ -0,0 +1,582 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split as tts\n",
+    "from sklearn import metrics\n",
+    "import numpy as np\n",
+    "from sklearn.linear_model import LinearRegression as LinReg\n",
+    "from sklearn.linear_model import Ridge, Lasso\n",
+    "from sklearn.linear_model import SGDRegressor\n",
+    "from sklearn.neighbors import KNeighborsRegressor\n",
+    "from sklearn.ensemble import GradientBoostingRegressor\n",
+    "from sklearn.svm import SVR\n",
+    "from sklearn.model_selection import cross_val_score as cvs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.read_csv(\"measurementsclean.csv\")"
+   ]
+  },
+  {
+   "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>Unnamed: 0</th>\n",
+       "      <th>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>26</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>12</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>30</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>13</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>11.2</td>\n",
+       "      <td>5.5</td>\n",
+       "      <td>38</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>12.9</td>\n",
+       "      <td>3.9</td>\n",
+       "      <td>36</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>14</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>4</td>\n",
+       "      <td>18.5</td>\n",
+       "      <td>4.5</td>\n",
+       "      <td>46</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Unnamed: 0  distance  consume  speed  temp_inside  temp_outside specials  \\\n",
+       "0           0      28.0      5.0     26    21.934911            12  Unknown   \n",
+       "1           1      12.0      4.2     30    21.934911            13  Unknown   \n",
+       "2           2      11.2      5.5     38    21.934911            15  Unknown   \n",
+       "3           3      12.9      3.9     36    21.934911            14  Unknown   \n",
+       "4           4      18.5      4.5     46    21.934911            15  Unknown   \n",
+       "\n",
+       "  gas_type  AC  rain  sun  \n",
+       "0      E10   0     0    0  \n",
+       "1      E10   0     0    0  \n",
+       "2      E10   0     0    0  \n",
+       "3      E10   0     0    0  \n",
+       "4      E10   0     0    0  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "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>distance</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>28.0</td>\n",
+       "      <td>26</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>12</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>12.0</td>\n",
+       "      <td>30</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>13</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>11.2</td>\n",
+       "      <td>38</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>12.9</td>\n",
+       "      <td>36</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>14</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>18.5</td>\n",
+       "      <td>46</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   distance  speed  temp_inside  temp_outside specials gas_type  AC  rain  sun\n",
+       "0      28.0     26    21.934911            12  Unknown      E10   0     0    0\n",
+       "1      12.0     30    21.934911            13  Unknown      E10   0     0    0\n",
+       "2      11.2     38    21.934911            15  Unknown      E10   0     0    0\n",
+       "3      12.9     36    21.934911            14  Unknown      E10   0     0    0\n",
+       "4      18.5     46    21.934911            15  Unknown      E10   0     0    0"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X = df.drop([\"Unnamed: 0\",\"consume\"], axis=1) \n",
+    "X.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y=df.consume"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Convierto las columnas categóricas a numéricas:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 388 entries, 0 to 387\n",
+      "Data columns (total 9 columns):\n",
+      " #   Column        Non-Null Count  Dtype  \n",
+      "---  ------        --------------  -----  \n",
+      " 0   distance      388 non-null    float64\n",
+      " 1   speed         388 non-null    int64  \n",
+      " 2   temp_inside   388 non-null    float64\n",
+      " 3   temp_outside  388 non-null    int64  \n",
+      " 4   specials      388 non-null    object \n",
+      " 5   gas_type      388 non-null    object \n",
+      " 6   AC            388 non-null    int64  \n",
+      " 7   rain          388 non-null    int64  \n",
+      " 8   sun           388 non-null    int64  \n",
+      "dtypes: float64(2), int64(5), object(2)\n",
+      "memory usage: 27.4+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "X.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['Unknown', 'AC rain', 'AC', 'rain', 'snow', 'AC snow',\n",
+       "       'half rain half sun', 'sun', 'AC sun', 'sun ac', 'ac', 'AC Sun',\n",
+       "       'ac rain'], dtype=object)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X.specials.unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dic_specials ={\"AC rain\":1,\n",
+    "               \"ac rain\":1,\n",
+    "                \"AC\":2,\n",
+    "                \"ac\":2,\n",
+    "                \"rain\":1,\n",
+    "                \"snow\":3,\n",
+    "                \"AC snow\":3,\n",
+    "                \"half rain half sun\":4,\n",
+    "                \"sun\": 5,\n",
+    "                \"AC sun\": 5,\n",
+    "                \"sun ac\": 5,\n",
+    "                \"AC Sun\":5,\n",
+    "                \"Unknown\":7} "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X.specials = X.specials.map(dic_specials)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['E10', 'SP98'], dtype=object)"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X[\"gas_type\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dicc_gas={\"E10\":0,\"SP98\":1}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X[\"gas_type\"] = X[\"gas_type\"].map(dicc_gas)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = tts(X,y, test_size=0.2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "models={\n",
+    "    'ridge': Ridge(),\n",
+    "    'lasso': Lasso(),\n",
+    "    'sgd': SGDRegressor(),\n",
+    "    'knn': KNeighborsRegressor(),\n",
+    "    'grad': GradientBoostingRegressor(),\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ENTRENANDO:  ridge\n",
+      "ENTRENANDO:  lasso\n",
+      "ENTRENANDO:  sgd\n",
+      "ENTRENANDO:  knn\n",
+      "ENTRENANDO:  grad\n"
+     ]
+    }
+   ],
+   "source": [
+    "for name, model in models.items():\n",
+    "    print(\"ENTRENANDO: \", name)\n",
+    "    model.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "------ridge------\n",
+      "MAE -  0.5915556390285266\n",
+      "MSE -  0.6332090689017884\n",
+      "RMSE -  0.7957443489600089\n",
+      "R2 -  -0.012519409694171424\n",
+      "------lasso------\n",
+      "MAE -  0.5863373677641668\n",
+      "MSE -  0.5938663515550878\n",
+      "RMSE -  0.7706272455312542\n",
+      "R2 -  0.05039072046668458\n",
+      "------sgd------\n",
+      "MAE -  2781777071543.0493\n",
+      "MSE -  2.41440185751784e+25\n",
+      "RMSE -  4913656334663.465\n",
+      "R2 -  -3.860697617263027e+25\n",
+      "------knn------\n",
+      "MAE -  0.46461538461538454\n",
+      "MSE -  0.3931897435897436\n",
+      "RMSE -  0.6270484379932252\n",
+      "R2 -  0.37127835555520505\n",
+      "------grad------\n",
+      "MAE -  0.4349697461504338\n",
+      "MSE -  0.4202707359577462\n",
+      "RMSE -  0.6482829135167347\n",
+      "R2 -  0.32797507429623884\n"
+     ]
+    }
+   ],
+   "source": [
+    "for name, model in models.items():\n",
+    "    y_pred = model.predict(X_test)\n",
+    "    print(f\"------{name}------\")\n",
+    "    print('MAE - ', metrics.mean_absolute_error(y_test, y_pred))\n",
+    "    print('MSE - ', metrics.mean_squared_error(y_test, y_pred))\n",
+    "    print('RMSE - ', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
+    "    print('R2 - ', metrics.r2_score(y_test, y_pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Modelo:  ridge Score:  -0.24517033785848322\n",
+      "Modelo:  lasso Score:  -0.28426366190194124\n",
+      "Modelo:  sgd Score:  -1.3318385155302547e+25\n",
+      "Modelo:  knn Score:  0.3493454625360017\n",
+      "Modelo:  grad Score:  0.40623622869965026\n"
+     ]
+    }
+   ],
+   "source": [
+    "for name, model in models.items():\n",
+    "    scores=cvs(model, X, y, scoring='r2', cv=5)\n",
+    "    print('Modelo: ', name, 'Score: ', np.mean(scores))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Me quedo con el modelo KNeighborsRegressor puesto que tiene el RMSE menor."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ironhack",
+   "language": "python",
+   "name": "ironhack"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/.ipynb_checkpoints/Visualizaciones-checkpoint.ipynb b/.ipynb_checkpoints/Visualizaciones-checkpoint.ipynb
new file mode 100644
index 0000000..6c763b6
--- /dev/null
+++ b/.ipynb_checkpoints/Visualizaciones-checkpoint.ipynb
@@ -0,0 +1,670 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Matplotlib inline para visualizar los gráficos de Matplotlib\n",
+    "%matplotlib inline\n",
+    "%config Inlinebackend.figure_format= 'retina'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Configuración para setear y que todas las fig de Seaborn salgan por defecto con este tamaño\n",
+    "# Se puede especificar el tamaño de cada figura\n",
+    "sns.set_context(\"poster\")\n",
+    "sns.set(rc={\"figure.figsize\": (12.,6.)})\n",
+    "sns.set_style(\"whitegrid\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.read_csv(\"measurementsclean.csv\") #cargamos el csv."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.drop([\"Unnamed: 0\"], axis=1, inplace=True)"
+   ]
+  },
+  {
+   "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>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>28.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>26</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>12</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>12.0</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>30</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>13</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>11.2</td>\n",
+       "      <td>5.5</td>\n",
+       "      <td>38</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>12.9</td>\n",
+       "      <td>3.9</td>\n",
+       "      <td>36</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>14</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>18.5</td>\n",
+       "      <td>4.5</td>\n",
+       "      <td>46</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   distance  consume  speed  temp_inside  temp_outside specials gas_type  AC  \\\n",
+       "0      28.0      5.0     26    21.934911            12  Unknown      E10   0   \n",
+       "1      12.0      4.2     30    21.934911            13  Unknown      E10   0   \n",
+       "2      11.2      5.5     38    21.934911            15  Unknown      E10   0   \n",
+       "3      12.9      3.9     36    21.934911            14  Unknown      E10   0   \n",
+       "4      18.5      4.5     46    21.934911            15  Unknown      E10   0   \n",
+       "\n",
+       "   rain  sun  \n",
+       "0     0    0  \n",
+       "1     0    0  \n",
+       "2     0    0  \n",
+       "3     0    0  \n",
+       "4     0    0  "
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['E10', 'SP98'], dtype=object)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[\"gas_type\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Comparamos la velocidad media que alcanza cada combustible:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = df.groupby(\"gas_type\").agg({\"speed\": \"mean\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df3=df2.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x432 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "barplot = sns.barplot(x=\"gas_type\", y=\"speed\", data=df3,ci=\"sd\", palette=\"magma\");"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_dist = df.groupby(\"gas_type\").agg({\"distance\": \"mean\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "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>distance</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>gas_type</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>E10</th>\n",
+       "      <td>21.096250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SP98</th>\n",
+       "      <td>18.639912</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "           distance\n",
+       "gas_type           \n",
+       "E10       21.096250\n",
+       "SP98      18.639912"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_dist"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Relación entre la velocidad y el consumo para ambos combustibles:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x432 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.scatterplot(x=\"speed\", y=\"consume\", hue=\"gas_type\",data=df);"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Estudio la correlación entre las diferentes variables:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "E10=df.loc[(df[\"gas_type\"]==\"E10\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "corrE10 = E10.corr()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "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>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>distance</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.172572</td>\n",
+       "      <td>0.633082</td>\n",
+       "      <td>0.137061</td>\n",
+       "      <td>0.158903</td>\n",
+       "      <td>0.045776</td>\n",
+       "      <td>-0.073315</td>\n",
+       "      <td>0.027364</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>consume</th>\n",
+       "      <td>-0.172572</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.233318</td>\n",
+       "      <td>-0.040842</td>\n",
+       "      <td>-0.322918</td>\n",
+       "      <td>0.043591</td>\n",
+       "      <td>0.248199</td>\n",
+       "      <td>-0.160503</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>speed</th>\n",
+       "      <td>0.633082</td>\n",
+       "      <td>-0.233318</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.014835</td>\n",
+       "      <td>0.091093</td>\n",
+       "      <td>0.125102</td>\n",
+       "      <td>-0.001633</td>\n",
+       "      <td>0.128376</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>temp_inside</th>\n",
+       "      <td>0.137061</td>\n",
+       "      <td>-0.040842</td>\n",
+       "      <td>-0.014835</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.386506</td>\n",
+       "      <td>0.428083</td>\n",
+       "      <td>0.091396</td>\n",
+       "      <td>0.171009</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>temp_outside</th>\n",
+       "      <td>0.158903</td>\n",
+       "      <td>-0.322918</td>\n",
+       "      <td>0.091093</td>\n",
+       "      <td>0.386506</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.048762</td>\n",
+       "      <td>-0.097756</td>\n",
+       "      <td>0.236743</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AC</th>\n",
+       "      <td>0.045776</td>\n",
+       "      <td>0.043591</td>\n",
+       "      <td>0.125102</td>\n",
+       "      <td>0.428083</td>\n",
+       "      <td>0.048762</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.336123</td>\n",
+       "      <td>0.171118</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>rain</th>\n",
+       "      <td>-0.073315</td>\n",
+       "      <td>0.248199</td>\n",
+       "      <td>-0.001633</td>\n",
+       "      <td>0.091396</td>\n",
+       "      <td>-0.097756</td>\n",
+       "      <td>0.336123</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.094916</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>sun</th>\n",
+       "      <td>0.027364</td>\n",
+       "      <td>-0.160503</td>\n",
+       "      <td>0.128376</td>\n",
+       "      <td>0.171009</td>\n",
+       "      <td>0.236743</td>\n",
+       "      <td>0.171118</td>\n",
+       "      <td>-0.094916</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "              distance   consume     speed  temp_inside  temp_outside  \\\n",
+       "distance      1.000000 -0.172572  0.633082     0.137061      0.158903   \n",
+       "consume      -0.172572  1.000000 -0.233318    -0.040842     -0.322918   \n",
+       "speed         0.633082 -0.233318  1.000000    -0.014835      0.091093   \n",
+       "temp_inside   0.137061 -0.040842 -0.014835     1.000000      0.386506   \n",
+       "temp_outside  0.158903 -0.322918  0.091093     0.386506      1.000000   \n",
+       "AC            0.045776  0.043591  0.125102     0.428083      0.048762   \n",
+       "rain         -0.073315  0.248199 -0.001633     0.091396     -0.097756   \n",
+       "sun           0.027364 -0.160503  0.128376     0.171009      0.236743   \n",
+       "\n",
+       "                    AC      rain       sun  \n",
+       "distance      0.045776 -0.073315  0.027364  \n",
+       "consume       0.043591  0.248199 -0.160503  \n",
+       "speed         0.125102 -0.001633  0.128376  \n",
+       "temp_inside   0.428083  0.091396  0.171009  \n",
+       "temp_outside  0.048762 -0.097756  0.236743  \n",
+       "AC            1.000000  0.336123  0.171118  \n",
+       "rain          0.336123  1.000000 -0.094916  \n",
+       "sun           0.171118 -0.094916  1.000000  "
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "corrE10"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x432 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "mascara = np.triu(np.ones_like(corr, dtype=bool)) \n",
+    "color_map = sns.diverging_palette(0, 10, as_cmap=True) \n",
+    "sns.heatmap(corrE10,  \n",
+    "            mask = mascara,\n",
+    "            cmap=color_map,\n",
+    "            square=True, \n",
+    "            linewidth=0.5,\n",
+    "            vmax=1,\n",
+    "            cbar_kws={\"shrink\": .5},\n",
+    "            annot=True);"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "SP98=df.loc[(df[\"gas_type\"]==\"SP98\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "corrSP98 = SP98.corr()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x432 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "mascara = np.triu(np.ones_like(corr, dtype=bool)) \n",
+    "color_map = sns.diverging_palette(0, 10, as_cmap=True) \n",
+    "sns.heatmap(corrSP98,  \n",
+    "            mask = mascara,\n",
+    "            cmap=\"viridis\",\n",
+    "            square=True, \n",
+    "            linewidth=0.5,\n",
+    "            vmax=1,\n",
+    "            cbar_kws={\"shrink\": .5},\n",
+    "            annot=True);"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Mostramos la distribución de la variable consumo para cada tipo de carburantes:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAuIAAAF5CAYAAADaqk8iAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAABcv0lEQVR4nO3dd3xUZcL28d+ZPpNeCEnovfcuKFVsiK5ldcX62ntX4HGtqFiQVUFXfVZXd8Vn1RULKqDSFBUQCyBIh0BCAiQBUqee94+QGBA1QpKTcn0/e3ZKJjPXzBnJNffc5xzDNE0TERERERGpVTarA4iIiIiINEYq4iIiIiIiFlARFxERERGxgIq4iIiIiIgFVMRFRERERCzgsDpAbYtEIhQVFeF0OjEMw+o4IiIiItJAmaZJMBgkKioKm+2X49+NrogXFRWxYcMGq2OIiIiISCPRsWNHYmJifnF9oyviTqcTKHtBXC6XxWmkOqxZs4bu3btbHUOqkdZpw6N12vBonTY8WqfVLxAIsGHDhor+ebhGV8TLp6O4XC7cbrfFaaS6aF02PFqnDY/WacOjddrwaJ3WjF+bDq2NNUVERERELKAiLiIiIiJiARVxERERERELqIiLiIiIiFhARVxERERExAIq4iIiIiIiFlARFxERERGxgIq4iIiIiIgFVMRFRERERCygIi4iIiIiYgEVcRERERERC6iIi4iIiIhYQEVcRERERMQCDqsDiDRExcXF/PDDD2RlZXHgwIGKZf/+/Xi9Xpo3b06zZs1o1qwZzZs3Jzk5GcMwrI4tIiIitUhFXKSaZGVlsWLFClasWMGaNWsIh8MAGDY7NocHw+7CNFxg7mHV6h+JhIMVv5uS0pQxY0YzatQomjZtatVTEBERkVqkIi5yDMLhMF999RVvvvkWW7duAcDuicMW1wFXdBp2byIYjl+MdpumiRkqJRI4QMR/gLzCncyaNYtZs2bRo0cPxowZw9ChQ3G73VY8LREREakFKuIiRyEUCrF48WLefPNNsrKysLtjcTftiyM6HZsr+nd/3zAMDKcXm9MLUU0hsQORYBHBfVtZu2Erq1dP59VXX+Oyyy5l+PDhmrYiIiLSAKmIi/wBkUiEzz77jFmz3mDv3j3YPQl4mh2HI6Y5hnFs2z7bnFG4m3THTO5GuDiH/XtWMW3aNObMmcNVV11Fx44dq+lZiIiISF2gIi5SRRkZGcyYMYN169Zh9ybhbX489uj0ah+tNgwDR1Qqdl8Kof3b2LRlNbfffjsjR47ksssuIyEhoVofT0RERKyhIi7yO/x+P2+++Sb//e9/MQ0HnrSBOOLa1Ph0EcOw4YxviyOmBYHctSxatJgVK77h9ttvo3///jX62CIiIlLzVMRFfsOqVat45plnyMnJwRHXGk9Kb2wOT61mMOxO3Cm9cMS1piTrKx544AHGjx/PpZdeitPprNUsIiIiUn1UxEWOIBQKMWvWLN56+23srmi8LUfiiLJ2t4J2dxzeVifi3/0977//PqtWrebuu++iefPmluYSERGRo6Mja4ocJicnh7vvvpu33noLZ1wbvK1PsryElzNsdjyp/fA2P56MnVncfPPNLFq0yOpYIiIichQ0Ii5Syeeff86zz87AHwjhaXYcztiWVkc6IkdMM2yekyjN+ppp06axfft2LrroImw2fbYWERGpL1TERYBgMMiLL77I3LlzsXuT8bYeXKX9gVvJ5vThbTkcf/a3vP3222zfvp077rgDn89ndTQRERGpAg2fSaOXm5vLpEmTmDt3Lq6kznhbjarzJbycYdhxp/bH3bQfK775htvvuIPs7GyrY4mIiEgVqIhLo7Zu3TpuvvkWNm7ajKfZUNwpvY/5wDy1zTAMXIkd8LYYTtau3dxy662sWbPG6lgiIiLyO+pX4xCpJqZp8vHHHzNp0iQKS8N4Wo7BGdvC6ljHxBGVirfVGEqDNu6556/aiFNERKSO0xxxaXRCoRAvvPACc+fOxRGdhid9CIbdZXWsamFzxeBtNZrSnUuZNm0au3fv5txzz63xgw+JiIjIH6ciLo1KYWEhjz76KKtWrcKV1AVXkx71birK7zHsbjwthlO6azn/+te/yMnJ4dprr8Xh0H/uIiIidYn+MkujkZWVxf0PPED2rmw8aYNwxrexOlKNMWx2POmDCTijmD9/Prt372bSpEnao4qIiEgd0rCGAkV+xZo1a7jtttvJ2Z2Lp+WIBl3CyxmGgTulJ+60AXz/ww/ceeed7Nmzx+pYIiIicpCKuDR4CxYs4J577qE0ZMPbagwOX4rVkWqVK74d3ubD2ZmZzW233c6mTZusjiQiIiKoiEsDZpom//nPf5g+fTqGJxlvqzHYXDFWx7KEIzoVT8tRFBQHuHviRJYvX251JBERkUZPRVwapHA4zIwZM/j3v/+NI7YVnhYnNJg9oxwtuyceT8sxRGxRTJkyhTlz5lgdSUREpFFTEZcGp6SkhIceeoj58+fjSuqKJ30whmG3OladYHN68bQchT06nRdeeIG///3vhEIhq2OJiIg0Siri0qDk5+czadIkVq78tuzQ7yk9tQ/twxg2B55mQ3EmdubDDz/k3nvv5cCBA1bHEhERaXRUxKXByM7O5s677mLr1u14mw/DldDe6kh1lmHY8DTtjSdtEGvW/Mitt97G9u3brY4lIiLSqKiIS4Owbds27rjzTvbszcfTcgSOmGZWR6oXnPFt8LYaRW7+AW6//Q5txCkiIlKLVMSl3tu+fTt33X03hUWBsvnP3mSrI9Urdm8ynlYnErb5eGjKFN544w3C4bDVsURERBo8FXGp11asWMFrr/2LQNiBp9Vo7O44qyPVSzanD0/LUThiWzFr1izuu+9+9u/fb3UsERGRBk1FXOqthQsXMmXKFHDG4mk5CpszyupI9Zphc+BJG4Q7dQCrVq/mxhtvYu3atVbHEhERabBUxKVe+vjjj3lq+nRs3mS8LUdic3isjtQgGIaBK6Ed3lZjOFAcZNKkSbz77ruYpml1NBERkQZHRVzqndmzZ/Pcc8/hiErD03w4ht1pdaQGx+5JwNvqRGxR6fzjH//ggQceID8/3+pYIiIiDYqKuNQbpmnyxhtv8PLLL+OIaYGn+VAMmw7UU1MMuwtPs6G4m/bl2+++5/rrb9BeVURERKqRirjUC6Zp8sorrzBr1iwccW3wNBuio2XWAsMwcCV2xNt6LMVBOw899BAzZ86ktLTU6mgiIiL1noq41HmRSIS///3vzJ49G2dCBzxpAzEMvXVrk90dh7fVGJyJnZk7dy433Xwz69evtzqWiIhIvaY2I3VaJBJh5syZfPTRRzgTO+Nu2leHrLeIYbPjadobb8uR7N67jzvvvJOXX34Zv99vdTQREZF6SUVc6qxwOMzTTz/N/PnzcSV1xZ3SSyW8DnBENcXb+mQccW2YPXu2dnMoIiJylFTEpU4Kh8M89dRTLFiwAFdyd9wpPVXC6xDD7sKTNhBvyxHszt3P3RMn8tJLL1FSUmJ1NBERkXpDRVzqnFAoxOOPP86SJUtwNemFu0l3qyPJr3BEpeJtczLO+Pa8//77XHvtdaxYscLqWCIiIvWCirjUKcFgkKlTp/Lll1/iTumDO7mL1ZHkdxg2J57UfnhbjWZfUZAHH3yQqVOnkpeXZ3U0ERGROk1FXOqMQCDAww8/zLJly3A37YsrqZPVkeQPcPia4G01Fldyd7786muuueZaPv74YyKRiNXRRERE6iQVcakTSktLefDBh1i5ciXu1P64EjtaHUmOgmGz427SHV/rkwjaonnuuee444472bRpk9XRRERE6hwVcbFcaWkpDzzwID/88D2etIG4EtpbHUmOkc0di6fFSDzpg9i8LYPbbruN559/nsLCQqujiYiI1Bkq4mKp4uJi7r3vPtasWYMnfTDO+LZWR5JqYhgGzrg2+NqciiO+PR999DFXXX01CxYswDRNq+OJiIhYTkVcLFNQUMD/3HMP69atw9NsCM641lZHkhpg2F14UvvhazOW4qCL6dOnc+edd7Jx40aro4mIiFhKRVwskZeXx913T2Tz5i14mw3DGdvS6khSw+yeBLytRuNJG8jGLdu57fbbeeaZZ9i3b5/V0URERCyhIi61Licnh7vuuovMrCw8zY/HEdPM6khSSwzDwBnfFl+bU3EmdOTTTz/jqquu5t133yUYDFodT0REpFapiEut2rlzJ3fddTd7cvPxNB+BIyrV6khiAcPuwtO0D742JxOwxfGPf/yDa6+7jqVLl2r+uIiINBoOqwNI47Fp0ybuvfc+iksDeFqMxO5JsDqSWMzmjsXb4gTCRdns3fMDU6dOpVOnzgwbNpR+/fpZHU9ERKRGqYhLrVi+fDmPPfYYYZx4WozC5o61OpLUEYZh4IhOwx7VlOD+rWzasob1639i3bp1XHjhhbRo0cLqiCIiIjVCRVxq3IcffsgLL7yA3ZOAp/nx2BxeqyNJHWQYNlzx7XDGtiSQu56vly3nq6++YsSIEZx//vmkp6dbHVFERKRaqYhLjYlEIrzyyiu8++67OKLT8TQbgmFzWh1L6jjD5sTdpDvOhPYEcn9i0eLPWbx4MaNHj+b8888nJSXF6ogiIiLVQkVcakRpaSlPPTWdr776EmdCB9xN+2AY2jZYqs7m8OBp2ptIYicCuev49NPP+OyzBYwYMZyzzjqLVq1aWR1RRETkmKiIS7XbuXMnjzzyKDt2ZOBO6YMzsSOGYVgdS+opm9OLJ7UvkaTOBHJ/YuGiJSxYsIABAwZw9tln07VrV72/RESkXlIRl2q1aNEinp0xg1DYwNtiOI7oNKsjSQNhc/rwpPbFTO5GIH8jK79bzYoVK+jYsSPjxo1j6NChuFwuq2OKiIhUmYq4VItAIMBLL73E3Llzsfua4G0xBJvTZ3UsaYAMhxt3k+64kjoT3LeVzds38NRTT/HCiy8y9sQTOfnkk7Vhp4iI1Asq4nLMtm/fzrRp09i6dSuupM64mvTUfHCpcYbNgSuxA86E9oSLc/Dnb+bdd99j9uzZ9OzZk1GjRjFkyBB8Pn0gFBGRuklFXI5aaWkp//nPf3jnnXfA5sSrw9WLBQzDwBGViiMqlUiwhOD+Lfz40xZWrVrFjJkzGTRwICNGjKBfv344ndprj4iI1B0q4nJUVq5cycyZz7Fnz24ccW1wp/TG5nBbHUsaOZvTizu5G2ZSVyIluQQPbOer5StZunQpXq+P/v37MXjwYPr27Ut0dLTVcUVEpJFTEZc/JCsri9de+xdLl36B3R2Ht+UoHFHar7PULYZhYPclY/clY5p9CBflEDyQwdKvV/D5559js9np3r0bAwcOpHfv3rRs2VJ7XhERkVqnIi5Vsn37dt58800+//xzMGy4mvTAldgZw2a3OprIbzIMG47oNBzRaZhmhEhJHqHCTH7csJ1Vq1YBEBsbR+/evejZsyc9e/YkNTVVxVxERGqcirj8pg0bNvDmm2+ybNkybHYnzsROOBM76TD1Ui8Zhq1ipBx6EQkUEi7eTXFRDku/WsGSJUsAiImNpUvnznTu3JlOnTrRvn17bfQpIiLVTkVcfiE7O5vFixezaPFidu7Ygc3hxpXcHVdiBwy75oFLw2FzRWNzReOMb4tpmkQCBwgX76akJJeVP/zE8uXLK27bpEkKbdq0pnXrsqVFixakpqbi8XgsfAYiIlKfWV7ER40ahcvlwu3+ueDNnDmT119/nXnz5pGZmckHH3xAx44dK36+detWJk6cyL59+4iPj+exxx6jdevWFqRvGMLhMBkZGfzwww8sXrKETRs3AmD3NcHdtB/OuNYYdu1tQho2wzCwu+Owu+MgoQMAZjhAuCSXcGke+f795K9az/IVK8A0K34vNi6e9LRU0tLSSElJISEhgYSEBBITE4mPjyc+Ph63262pLiIi8guWF3GAZ5555pCiDTB69GguvvhiJkyY8Ivb33fffVxwwQWcccYZvPfee9x777289tprtRW3XjNNkwMHDpCRkcFPP/3Ejz/+yNq16ygpKQbA4UnAldILZ2xLbM4oi9OKWMuwuyrml5czI2EigQNE/AeIBAspCRSyMSOPjVt2EA4UHfF+bDYbXp+PKF8U0dHR+HzeigEIl8uFy+XC6XRit9srFofDgd1uxzAMbDbb7y52u71Kp4cvhmEcspSLRCKYplmxhMPhXyyhUIhQKFRxvvJp5cU0TTIzM1m/fj2RSKTstT3sedntdpxOZ8VrUX7e4/Hg9XorTssXu13bp4hI/VcniviR9O/f/4jX5+bmsnbtWl555RUAxo0bx0MPPUReXh6JiYm1GbFeME2TDz74gE2bNrFz5052ZmZSUlxc8XO7Jw6bJw1PQhPs3mRsLu3SDcpet2D+JkKFWWCGauYxwkHMSBDD5qzdbxwMB46YdJzx7TVKexQMmx27JwG7J+EXPzPNCGbIjxkuxQyVYIZKiYT9EA4SiATwlwbJLSoG8wCYEQwzDGYY0wyDGSn7/Uik4rz8OpfLhdfrw+fzERUdRXRUVNn5Sqderxefr+w25ec9Hs8hi9vtxmbTAcjqGtM0CQaDR1wCgQDBYJBQKHTI9Uf6QBiJRCoW0zQrPggCh3z4PNIHV4fDgcPhqPiQXH6+8ofFX1v0b6tUVZ0o4jfddFPF1BS73V52gJhfsWvXLpo2bVoxGmK320lJSWHXrl0q4kewd+9eXnrpJWxOD4YzDps7HXdMDDZXLHZPIoZF+/4O7ttKcP8WSx67KiLBEsxgYY0+hsfjYewpY5k/fz6lxftq9LEOFy7aRSB3PTanNrot54xrizO+zTHdh2HYMJxecHqBXxb1P8o0TcA8OBWm0inmr/7MNE0wI7/4mUnkl/djmpgcnGZjVvwfYBz8n1HpsgGGDQwDA1uly7ay2x08j2E7WELKb2OU/f7B+yovKGal54JZvkQOfigJl30QiYQxIyGIhDDNEGYkWHb+4IfY4kiQosIguw8UQCQP4+BtzHCASLhmPkCL1KSLLrqIP//5z1bHkFpUJ4r4kaamSPUo//RvcyfhiGmGzRWL4YrRwXd+TyRY4w8xduxYrrzyyopvLWpdJAioiNdlRnmJPcLgWn0fb6t4bnDIk/m151X+AaOsmAcwIyHMcKCsmEcCFeXcDAchEsQWDhAJFZd9MxEs4ecPGdIwGRg2B9gcYNjLdq1r2DEqfUCs+NB40M8fQg9+eC3/AFjxQfDgh8BIiNp6/3z19dcq4o1MnSjif0RaWho5OTmEw2HsdjvhcJjdu3eTlpb2+7/cCMXHx9OuXXu2bt1KaWFmxfU2hxvDnXhwV25NsHuSanWf4M74Nsc8+liTAvkb8WevrNHHmD9/PqZp8sknn9To4/waV5MeuBLaW/LYjYUZCWOG/WUjueHgIYWxrFSGy6Y+meGyKSmUjwpHfmVUu/wy8IsRbgAT45CR859vc8gI+iEj5Bz8+c+5jUP+7+DouGE7eP7wEW8bJpUuU156jEq/Y1S+57LLRxqdP1iCMMMYHDwfCROJBMtGuKswXcfhcOD1+fBFRREVFU+UL71iakr5Uj4lxev1HjJP3+12V0w9KJ+WUD4dwWazVczbP3zOfWOdhrBy5Ur69esHULEtQfkUkMrTQsrPH2nqSPl2BuXTTMpPf236Sfn1h//s8O0Vfr58ME8kjBk5ODWl4vOf7ZCpKT8vP2+zUP4eKL98NMvh76XK24CUL+XvKa9XgyONTb0r4klJSXTp0oU5c+ZwxhlnMGfOHLp06aJpKb/C7Xbzt79NJxwOk5OTQ2ZmJpmZmWRkZLB23Toyd64Gyv7I2rxJOKKb4Yhtic3ZuPeZ7IwvK6ihgpqbIx4IB5kzdwGGzYPdF1Mjj3FEFXPE29XeYzZAphnBDBYTCRYRCRRiBguJBMtGYI2In0iolEjIX6X7Kvsj7TxYABzYHXYcdgc2ux1b+UaNdjt2W/kfbFvZPtHttl+UwiPNdf21DTXLl3Llc2Yrb6RZXq7Ki9TvbbB5yPlwmHCobGPN0tJSXC4XETOCGTEPPqdKG2vaHAfLsOuQObjlxbl8Y023210xD7x8qTwv3OnUHp6sUP7eKX8/aT2IVI1hmqal39cdafeFU6ZM4b333mP+/Pns3buXhIQE4uPj+fDDDwHYvHkzEydO5MCBA8TGxvLYY4/Rtm3bKj2e3+9nzZo1dO/e/ZDHbKwOHDjAunXrWLt2Ld99/z1bt5TN27b7UnDEtsQR00LTWKRRM00TM1RMpHQfYf8+Iv79mIH9RPwFh2xQabfbSUxMIikpsWL3hQkJCcTGxhIdHU1UVFTF4vV6K8qmy+VqFBsLVh49lYZB67Th0Tqtfr/XOy0v4rVNRfy3ZWVlsWTJEhYtWkxm5s6yUbfYVriTumBzx1odT6TGmeEA4dK8sv2Hl+RiluYeMrKdnNyEtm3b0KJFC9LS0khNTSU1NZXk5GTtUu836A98w6N12vBonVa/3+ud9W5qitSs9PR0zj//fM477zy2bdvG/PnzmTdvPkX7t+KIaYEruesRd9smUl+ZkSDh4j2EinIwi3cTKs2v+Fmz5s3p2uUE2rdvT5s2bWjVqpUOdS8iItVGRVyOyDAM2rRpw9VXX815553He++9x5w5cyjeOg9HdDqulN7YNUIu9ZBpmkT8+wkVZhIuyiZSkotpRrA7HHTp0oWePU6hc+fOdOjQgeho7VdfRERqjoq4/K74+HguueQSzj77bD788EP++847lGybizOxC66krrW6txWRo2GakbJR74JMIsVZhP1l+4hv1649ffoMp1evXnTp0kXT1UREpFapiEuVRUdHc9555zF27Fj+8Y9/sHjxYsIFGbia9sMRlWp1PJFDmKZJpDSX4P7thAt3EAmW4nA46NunD4MGDWLAgAHa25KIiFhKRVz+sISEBO644w7GjBnDjJkzyclYhCO2FZ7Ufhh2l9XxpJGLBAoJ7t9KuCCDsL8Ah8PB4IEDGT58OH379sXj8VgdUUREBFARl2PQu3dvnps5k7feeou33nqLkm25uNOHYPcmWR1NGhnTjBAqzCKYv4lwUTaGYdCzZy9GjBjOcccdpw0sRUSkTlIRl2PicrmYMGEC/fv359FHp5K3/TNcKb1xJnRotEebk9oTCZUQzN9MeP8WwsFiEhISOeWMCxg7dixJSfpAKCIidZuKuFSLTp068eyzz/DUU9P55psVhIv34EkboKkqUiMi/gME8tYTOrAN04zQt08fTjnlFAYMGKB9eYuISL2hIi7VJiYmhr/+9R5mz57Na6+9Rsn2fbibHa/dHEq1CZfkEshdR6hgJw6Hg5PGnsif/vQn0tPTrY4mIiLyh6mIS7Wy2WycffbZdO7cmYcfeYSijE9xpw/DEZVidTSpx8IluQT2rCZUlI3X5+OsP/+ZcePGkZCgg0uJiEj9pSIuNaJbt248NW0a9913P7t2LMKdNhBnXGurY0k9Ey7NLyvghVlER8dw7mWXcfLJJ2vjSxERaRBUxKXGpKamMm3ak0yZMoUff/yaSLCo7ABA2ohTfkfYf4DAnlWECnbi8/n4y0UXMW7cOBVwERFpUFTEpUZFR0fz0EMP8cwzz7Bo0SLMQCHutAEYhs3qaFIHRUKlBPasIbh/Mx63m3POP58zzjhDh5oXEZEGSUVcapzT6eS2226jadOm/Oc//8GMBPCkH4dh094tpIwZCZXtBSXvJzDDDBwwgJtuuom4uDiro4mIiNQYFXGpFYZhcOGFFxIXF8eLL75I6c4leJofj2HTW7AxM02T0IHtBPeuIhwoZtCgQVx66aXk5OSohIuISIOnFiS16vTTT8fn8/H0009TumMRnuYnaF/jjVS4JI/A7m8JFe+lbbt2XHXllXTr1g2AnJwci9OJiIjUPBVxqXWjR4/G4/HwxBNPUJKxEE+L4dgcHqtjSS0pmwe+iuC+LcTExnLZTTcxevRobDZtNyAiIo2LirhYYujQoXi9XqZMeZjSjAV4WozA5tQeMRoy04wQzN9EcO8aMEOceeaZnH/++URFRVkdTURExBIaghLL9O3bl4ceehCnEaB0x0IiwSKrI0kNCRfvpWTbJ/hzvqVH967MmDGDyy+/XCVcREQaNRVxsVS3bt2YMmUKLluY0oyFRAKFVkeSahQJ+SnNWkbx9k+J9RpMnDiRhx56kBYtWlgdTURExHIq4mK5Tp068cgjD+N2mGUj44ECqyPJMTJNk8C+zZRs/YhwwXbOOussXnjh7wwdOlQHdBIRETlIRVzqhPbt2zN16qN4XTZKMxYQ9h+wOpIcpbD/ACUZC/HvWkGnju145plnuOyyy/B6vVZHExERqVNUxKXOaNOmDVOnPkqU14l/x0LC/v1WR5I/wIyE8e9ZTcm2ubgp4sYbb2Tqo4/SqlUrq6OJiIjUSSriUqe0atWKqVOnEh3lpjRjIeHSfKsjSRWEivdQsm0egb0/cvyw4/n7359n7Nix2iWhiIjIb9BfSalzWrRoweOPPUZ8bBSlOxYRLsmzOpL8CjMSojT7W0q2f0ZCjJsHHniAO++8g4SEBKujiYiI1Hkq4lInpaen89hjU0mMj6V05yLCJblWR5LDhIpyKNk2l2D+Bk499VSee24mffv2tTqWiIhIvaEiLnVWamoqjz02leTEBEp3LCJUvMfqSEL5KPg3lGQsJDk+ikceeYRrr71WG2OKiIj8QSriUqelpKTw+OOP0TQlGf/OxYSKcqyO1KiFS3Ip2TaP4L7NjB8/nhkzZtCjRw+rY4mIiNRLKuJS5yUlJfHYY4+Rnp5G6c4lhAqzrI7U6JhmBP/eHynZ/hlx0S4eefhhrrzySjwej9XRRERE6i0VcakXEhISeGzqVNq0bk3pzi8IHthhdaRGIxIopCRjIYE9qxk2bCgzNQouIiJSLVTEpd6IjY3lkUcepnPnTpRmfklw31arIzV4wQM7KNk2H2ekkNtvv50777yT6Ohoq2OJiIg0CCriUq9ERUXx4IMP0qtXT0p3LSOQt9HqSA2SaYYpzf6W0syltGvbmhkznmXEiBE6PL2IiEg1UhGXesfj8XDvvfcycOBA/Dkr8e/9EdM0rY7VYESCRZRsX0gwfwPjx4/nscem0rRpU6tjiYiINDgq4lIvuVwuJk2axMiRIwnsWY0/51uV8WoQKtxVNhXFLOTuu+/myiuvxOl0Wh1LRESkQXJYHUDkaDkcDm655RZKS0v56quvMMMBPOkDMQy71dHqHdM0CeSuI7BnFS1btWLypEk0a9bM6lgiIiINmoq41Gs2m42xY8fSoUMHXnvtNUojATzNhmLY9NauKjMSonTXckIHMjjhhBO48cYbtVtCERGRWqC2IvWeYRice+65xMbGMnPmTEoyFuFpfjw2h9vqaHVeJFiMP/MLQqX5XHzxxZxzzjnaIFNERKSWqIhLg3HSSScRGxvL4088QWnGp3iaD8fm0q72fk24ZC/+zKU4bCaT7rmHgQMHWh1JRESkUdHGmtKgDBkyhIenTMHjMCnN+JRwSa7Vkeqk4P7tlGQsJCkhlmnTnlQJFxERsYCKuDQ4Xbt25cknnyAhPoaSjIWECjKtjlRnmKaJf++PlGZ9RefOnZg+/SlatWpldSwREZFGSUVcGqTmzZvz1LRptGndipKdXxDI32R1JMuZZgT/ruUE9qxm+PDhPDxlCrGxsVbHEhERabRUxKXBSkhIYOrUR+nXry/+7G8ozfkO04xYHcsSZjhA6Y7FBPdv5fzzz+f222/X/sFFREQspiIuDZrX6+Wvf/0rp512GsG89ZTuXIoZCVodq1ZFgkWUZHyGWbqXW265hQkTJmjPKCIiInWAirg0eHa7nWuuuYarr76acFEWJdsXEAkWWR2rVoRL8ijd/ikuI8gDDzzA6NGjrY4kIiIiB6mIS6Mxbtw47rvvPpyUUrq94e9RJVSQSUnGAhLionnyySfo1auX1ZFERESkEhVxaVT69et3cI8q0ZRkLCC4f6vVkWpEIG8jJTu/oG2b1jz11DRatmxpdSQRERE5jIq4NDqtWrXib9On061rF0qzllGa/W2D2YjTNCOU5nyHP2clAwb0Z+rUR0lISLA6loiIiByBirg0SnFxcUyZMoUzzjiDYP4GSjIWEQmVWh3rmJjhIKU7vyCYt57TTjuN//mf/8Hj8VgdS0RERH6Firg0Wna7nSuuuILbbrsNI5hP6fb59XbeeCRQQEnGp0SKs7n22mu55pprsNvtVscSERGR36AiLo3eyJEjeeLxx0mIjaIk4zMCeesxTdPqWFUWKsqhZPuneOxhHnroIU499VSrI4mIiEgVqIiLAO3bt+fpp//GgP798ed8R+nOz+v8VBXTNMs2ytyxiLSmTZg+/Sl69uxpdSwRERGpoj9UxJcuXcrkyZO55pprAFi9ejVfffVVjQQTqW2xsbHcc889Ze/v0t2UbptHqCjH6lhHZIYDlGZ+iT9nJf379eOpp6aRlpZmdSwRERH5A6pcxP/1r39x//3307p1a1asWAGAx+Ph6aefrrFwIrXNMAxOO+00nnrqKZo2SaQkYyH+3d9jRkJWR6sQLt5LybZ5RIoyufTSS/nrX/+Kz+ezOpaIiIj8QVUu4q+++iqvvPIKV111FTZb2a+1bduWrVsb5n6YpXFr06YNTz/9N8aOHUsg9ydKts0lVLjL0kymGcG/Zw3FGZ+RFB/NE088wdlnn13x36OIiIjUL46q3rCoqKjiq2/DMAAIhUI4nc6aSSZiMY/Hw4033siIESN4dsYMdu1YjCO2Je6mfbE5ane3gOHSfPw53xIu3sMJJwzn+uuv0yi4iIhIPVflobQBAwbw4osvHnLda6+9xqBBg6o9lEhd0qNHD2bOmMEFF1yAWZRFydaPCORtqJXpKpFQKaW7llO8dR4eWwm33nord9xxu0q4iIhIA1DlEfHyjdjeeustioqKOOmkk4iKiuKFF16oyXwidYLT6eQvf/kLxx9/PM899xyrV39LKG8djoSOOOPbY9ir95sh0wwTzNtIMHctmCHGjx/PX/7yF6Kjo6v1cURERMQ6VS7iKSkp/Pe//2X16tVkZmaSlpZGz549NT9VGpXmzZvz8MMPs2bNGv7znzf54YfvCeb9hCO+Pc6EDsc8ZSUSKCC4fxvhA9sIB4ro168fl19+OS1atKimZyAiIiJ1RZWLOEAkEiEYDAIQDofr1UFPRKqLYRj06NGDHj16sGHDBt58802WLVtGYO9a7N4k7NFpOKLTsbnjK7an+C1mOECoYGdZAS/ejWEY9O7dmzPPPJO+ffvWwjMSERERK1S5iP/0009cf/31BAIBmjZtSnZ2Nm63m5kzZ9K5c+eazChSZ3Xs2JF77rmHjIwMvvjiC5YvX87mzasJ7FmN3eXDcCVg2N0YDnfZqd2FGQ4SCRQQCRyAUCHhQDEAaWnpnHjOxYwcOZLk5GSLn5mIiIjUtCoX8cmTJzNhwgQuu+wyDMPANE3++c9/MnnyZN55552azChS57Vs2ZILLriACy64gPz8fFauXMmKFSvYsXMnB/bnUbivgHA4XHF7ny+K5s2b07x5d5o3b0737t3p3LlzlUbQRUREpGGochHftm0bl1xySUVRMAyDiy++mGeffbbGwonURwkJCYwZM4YxY8ZUXGeaJiUlJRw4cACv10tsbKxKt4iISCNX5S0thw8fzoIFCw65buHChYwYMaK6M4k0OIZh4PP5SE1NJS4uTiVcREREqj4iHg6HufXWW+nevTupqalkZ2ezZs0aRo8ezV133VVxu8cff7xGgoqIiIiINCRVLuIdO3akY8eOFZfbt2/PsGHDaiSUiIiIiEhDV+UifsMNN9RkDhERERGRRqXKc8TPPPNM/vnPf5Kbm1uTeUREREREGoUqF/HrrruOb775htGjR3PFFVfwwQcf4Pf7azKbiIiIiEiDVeUiPnbsWGbMmMGiRYsYPXo0s2bNYujQoUyaNImvvvqqJjOKiIiIiDQ4f+gQ9wDx8fH86U9/wufz8b//+7/Mnz+fb775BpvNxn333cdxxx1XEzlFRERERBqUKhdx0zT54osveO+991i0aBG9e/fmqquu4sQTT8Tj8TBv3jzuvPNOli5dWpN5RUREREQahCoX8WHDhpGQkMAZZ5zBnXfeSdOmTQ/5+UknncS///3vag8oIiIiItIQVbmI//3vf6dHjx6/eZt//etfxxxIRERERKQxqPLGmpdffvkRrx8yZEi1hRERERERaSyqXMSDweARr4tEItUaSERERESkMfjdqSkXXHABhmEQCASYMGHCIT/Lzs6mT58+NRZORERERKSh+t0ifu6552KaJqtXr+acc86puN4wDJKSkhg8eHCNBhQRERERaYh+t4j/6U9/AqBXr160a9fuN297//33c//991dLMBERERGRhqzKc8R/r4QDvP/++8cURkRERESksahyEa8K0zSr8+5ERERERBqsai3ihmFU592JiIiIiDRY1VrERURERESkajQ1RURERETEAtVaxMePH1+ddyciIiIi0mBVuYjPmTOHzZs3A7BlyxYmTJjARRddVHEdwAMPPFD9CUVEREREGqAqF/G//e1vxMXFAfD444/Ts2dPBg4cqPItIiIiInIUfveAPuXy8vJITk7G7/ezcuVKnnnmGRwOh46sKSIiIiJyFKpcxBMTE9m+fTsbNmygR48euFwuSkpKtIGmiIiIiMhRqHIRv+666zjrrLOw2+1Mnz4dgC+//JLOnTvXWDgRERERkYaqykX8rLPO4pRTTgHA6/UC0Lt3b5566qmaSSYiIiIi0oBVuYjDzwXcNE1M0yQhIaFGQomIiIiINHRVLuI5OTk8+OCDfPPNNxw4cOCQn61bt67ag4mIiIiINGRV3n3hfffdh9Pp5J///Cc+n4/Zs2czatQo7b5QREREROQoVHlE/LvvvmPhwoX4fD4Mw6Bz5848/PDDnH/++fz5z3+uyYwiIiIiIg1OlUfEbTYbDkdZb4+NjSUvLw+fz0dOTk6NhRMRERERaaiqPCLeq1cvFi9ezIknnsiwYcO45ZZb8Hg8dO/evSbziYiIiIg0SFUu4o8//njFwXsmT57Myy+/TFFREZdeemlNZRMRERERabCqXMRfeeWVX1zncrl4++23SU1N5fjjjyc5Oblaw4mIiIiINFRVniO+bds2XnrpJZYtW0ZGRgbLli3jf//3f1m3bh1vvPEGY8aMYcmSJTWZVURERESkwajyiHgkEmH69OmceOKJFdd9+umnzJkzhzfffJPZs2czbdo0TjjhhBoJKlLbiouL2bp1K5s3b2bz5s3s37+fcDhMOBwmFAoRCoUIh0K4PW5SU9NITU0lNTWVtLSy8/Hx8RiGYfXTEBERkTqqykX8iy+++MXh7EeOHMldd90FwPjx43nooYeqN51ILdq/fz+ff/4569atY/OmjWTtyq7YLiLa7SDWZWADbAbYDQObDRwGFOeZfLt1EwdKQ5iV7i8qykevXr3p3btsSUtLs+R5iYiISN1U5SLesmVL3njjDS688MKK6/7v//6Pli1bApCfn4/X663+hCI1KBwO89133/HJJ/NZtmw54XCYeI+D1Cg7I1r6SIt2khbtIMZl/937CkZM9peGySsNk18aZldhkB+/Xc6XX34JQNOUJvTu05c+ffowYMAAXC5XTT89ERERqcOqXMSnTJnCjTfeyEsvvUTTpk3JycnBbrfz7LPPArB161ZuvvnmGgsqUp2ys7P55JNP+PTTT8jLy8fnsjMw1U3vpl6aRlX5P4tDOG0GyT4Hyb6ff980TXJLwmzZF2DzvgMs+uwT5s2bR5TPx4iRIxkzZgzt2rXTFBYREZFGqMqNo1u3bsybN48ffviB3bt306RJE3r37o3T6QRgwIABDBgwoMaCilSH/fv38+9//5t58+YBJu0T3IzpEkfHRDcOW/WXYcP4uZwPTPcRNk227QvwfU4p8z7+iA8//JDWrVtx4oljGTFiBLGxsdWeQUREROqmPzT053Q66d+/f01lEakxoVCIjz76iFmvv05JSQkD0jwMbR5FnPv3p5xUJ7th0C7BTbsENyXBCGv2lPLd7ixeeuklXnnlZUaPHsM555xDampqreYSERGR2nd038GL1CPffvstL774ApmZWbSNd3Fy50RSjnL6SXXyOm0MSPcxIN1HdlGQb7JK+PST+XzyyScMHz6cc889lxYtWlgdU0RERGqI9W1EpIbk5uYyc+YMVqz4hkSfk790jadjoqtOzsdOjXIyroOTE1pG8VVmMV8sWcyiRQsZMuQ4/vznP9OuXTurI4qIiEg1UxGXBunbb7/lySefwF9czIltohmU7quROeDVLdZt56S2MQxrHsXXWcUsX/41X375JccddxyXXXaZpqyIiIg0ICri0qCEw2HeeOMN3nzzPzTxObm4dwJNfPXvbR7lsjG6dTTHNffxdWYxXy77muXLl3HGGWdy7rnnEhUVZXVEEREROUb1r6GI/Ir8/HyeePxxVq9ZQ++mHk5tF4vLXvdHwX+L12FjZKto+qV6+WxbIf/973/5ZP58LrzoIsaOHYvdXrsbm4qIiEj1sVkdQKQ6/PDDD9x04w38tG4tZ3aM5cyOcfW+hFcW67bzp05xXNU7kQSbn+eee44bb7yBH374wepoIiIicpQ0Ii713tdff828efNI9jm4sldCndgjSk1Jj3FyaY941uX6+WRbNvfccw8jR47k8ssvJy4uzup4IiIi8gc03MYiDV4kEuHVV19l7ty5dElyc2anWNz2hv8lj2EYdE320CHBzZIdRSxZvIhvVqzg/11+OaNHj66Te4URERGRX2r4rUUapGAwyPTp03nnnXcYkObl3C5xjaKEV+a0G4xuHc3VvRNJsAV4+umnmTx5Mjt37rQ6moiIiFRB42ou0iAUFxfz0IMPsmjRIka1iubUdjHYGvEocEqUg0t7xnN6+xg2rV/HjTfewP/93/8RCoWsjiYiIiK/QUVc6pX8/HwmT57EDz/8wBkdYjmhZZSmYgA2w6Bfmo8b+ibQOcHB66+/zm233sqWLVusjiYiIiK/QkVc6o1du3Zx1513krFtG+d3jaNPqtfqSHVOtMvOOZ3jOa9LHHt27eC2W29l1qxZBINBq6OJiIjIYVTEpV7IzMxk4t13cSBvL5d0j6djotvqSHVal2QP1/VJpFuyizfeeIPbbr2FTZs2WR1LREREKlERlzpvx44dTJo4EX9RAZf0iKd5rNPqSPWCz2njrE5x/KVrPLnZWdx+++3861//0ui4iIhIHaEiLnXajh07mDxpEoHiAi7pHk/TBryP8JrSKcnNdX0S6NnExZtvvsktN9+s0XEREZE6QEVc6qyMjAwmT5pIqLSQS7rHN+gD9dQ0r9PGmR3juKBbPPm7d2l0XEREpA5QEZc6afv27UyaOJFwabFKeDXqmOjmur4aHRcREakLVMSlztm2bRuTJk3EDJRwSfc4mvhUwquT1/HL0fHXXnuNQCBgdTQREZFGRUVc6pTt27czefIkjEApl/aII1klvMZ0TCybO94j2cVbb73FTTfeyI8//mh1LBERkUZDRVzqjB07dvA/kydDoJRLesSR5FUJr2lep40/dYrjwu7xFOXtZuLEicycOZOioiKro4mIiDR4KuJSJ+zcuZPJkyYR8RdxSXeV8NrWPsHNtX0TGNzMx7x5c7nuumtZtmyZ1bFEREQaNBVxsVxWVhb/M3kSwZJCLuoWr+koFnHbbZzcNobLeyXiDBQyZcoUpk6dSm5urtXRREREGiQVcbFUdnY2kydNwl9UwMXaO0qd0DzGyVW9EhjVKpplX33J1Vdfxdtvv61dHYqIiFQzFXGxTE5ODpMmTaS4YD8XdYvTwXrqELvN4ISWUVzXN5HWUQavvvoqN1x/PStXrrQ6moiISIOhIi6WyMnJYfKkSRTu38dF3eNIjdZh6+uiRK+Dv3SLZ0K3ePz793D//fczZcoUsrOzrY4mIiJS72kIUmrdrl27mDx5EkX793FRtzjSVcLrvA6JbtrEu/g6s5gl36zgupUrOX38eM455xxiYmKsjiciIlIvaURcalVWVhaTJk6kaP8+Lu4eR7MYlfD6wmEzGNYiiuv7JdIl0cHsd97hissv5z//+Q+lpaVWxxMREal3VMSl1uzcuZOJd99NSeF+LukeR5pGwuulOLedszrFcU3fJFp4I/z73//myisuZ86cOdqgU0RE5A9QEZdakZGRwaSJdxMoLuCS7vGaE94ANI0qmz9+ea8E4inlhRde4NprrmbevHkq5CIiIlWgIi41bvv27UyaOJFwaRGX9ojX3lEamBaxLi7pEc+F3eOxl+xjxowZ/L/LLuPtt9/WETpFRER+g4q41Kj169czaeJEzEAJl3SPp4kO1tMgGYZB+wQ3V/ZK4KLu8SQaJbz66qtcdtml/POf/yQvL8/qiCIiInWOWpHUmOXLl/PY1KlEOUwu7KHD1jcGhmHQLsFNuwQ3WQVBlu4s4p13/st7773L8cefwKmnnkqnTp0wDMPqqCIiIpZTM5IaMX/+fGbOnElqlJ0LusYT7bJbHUlqWXqMk3O7xJNXEuKrzGKWfr6YhQsX0rpVK0459VRGjBiBz+ezOqaIiIhlVMSlWpmmyf/93/8xa9Ys2iW4+XOXWNx2zYBqzBK9Dk5rH8uY1hFW7yllZXYWzz//PC+//A9GjBjJ2LFj6dChg0bJRUSk0VERl2oTDod5/vnnmTdvHr1SPIzvEIvdpnIlZdwOG/3TfPRL9ZJZGGLlrmIWfPoJ8+bNIz0tjZGjRjFixAhSU1OtjioiIlIrVMSlWhQXFzNt2jSWL1/OsBY+RreK1ginHJFhGDSPcdI8Jo6T2kZYu9fPqt25vP7667z++ut06tSJdu3a0b59e+Li4qyOKyIiUmNUxOWYbd++nUcfeYSsXVmc0i6GQema9ytV43HY6JvqpW+ql32lYdbsKWXVzi18tH49c+fOpUf37gwdNozBgweTkJBgdVwREZFqpSIux2ThwoXMnDEDpxHm4u4JtIl3WR1J6ql4j51hLaIY1iKK7MIgP+71s3bTOp5btYrnn3+eLl26MHToUI477jiSk5OtjisiInLMVMTlqAQCAV566SXmzp1LqzgX53ROIEZ7RpFqkhrtJDXayahWJruLw6zdW8q67Rt5ae1aXnrpJdq1a8vgwUMYNGgQrVu31jQoERGpl1TE5Q/Lzs7m0UcfYcuWrQxt7mNU62jsKkJSAwzDoGmUg6ZR0YxsBXuLQ6zL9bNhz05mHZxT3iQ5mUGDBzNo0CC6deuG0+m0OraIiEiVqIhLlZmmyWeffcb/vvQS4aCfv3SNp1OS2+pY0ogk+xwc73NwfIsoCgNhNuQF+Cn3AHM/+pA5c+bg9Xjo07cvAwYMoF+/fppXLiIidZqKuFRJRkYGz82cyY9r19Iy1sWfuiWQ4NFUFLFOtMtesaFnIGyyZZ+fjXkBVq9czpdffglAh/btGTBwIP3796ddu3bYbNqnvYiI1B0q4vKbSktLefPNN3nnv//FZTcY3yGW3k092DQVReoQl92gc5KHzkkeTNMkuyjEhjw/G3dn8MasTcyaNYu42Fj69utH//796dOnDzExMVbHFhGRRk5FXH7VN998w/PPPcfuPXvo3dTDia1jiHJpRFHqNsMwSIt2khbtZHhLKApE2LTPz6a8AMuWLmHhwoUYhkHHjh3p168fffr0oUOHDtjt+oZHRERql4q4HMI0TX744QfeeustVq1aRZMoJ5f2SKC1dkso9VSUy0avFC+9UrxETJOsghAb8/1sytrKG+vXM2vWLHxeLz179aJv37706dNHR/cUEZFaoSIuQNnh6b/++mvefustNm3eTIzbwdg20QxM9+HQYeqlgbAZBs1jnTSPdTKyFRQHI2zdF2DzvgA/ff8NX3/9NQApTZLp0bMX3bt3p0ePHjRt2tTi5CIi0hCpiDdywWCQhQsX8t+33yZr1y6SfE5O7xBDrxSvCrg0eD6njW5NPHRrUja3PK80zOb8AFv3FfDV54v47LPPAGiSnEyPnj3p1q0bnTp1okWLFtrwU0REjpmKeCMUCoX4/vvv+fzzz/n6q68oLikhLdrJuZ3j6JLs1oaY0igZhkGS10GS18HAdB8R02RPcZht+wNs21fAsi8Ws2DBAgC8Xg8dO3SkU+fOdOrUiQ4dOmhXiSIi8oepiDcS4XCYVatW8cUXX/Dl0qUUFhXhdtjonOiiZ7t42sa7dHRCkUpsFQcTcjDoYDHPKwmzsyDIzoIgmVvXsXr1KiJm2e3j4mJp06YtrVu3pk2bNrRu3ZoWLVroAEMiIvKraq2If/zxx7zwwguYponf76dbt25MmzaNUaNG4XK5cLlcRCIRrr32Wk477TTC4TBTp07lq6++IhgMMmrUKO666y4MwyASifDII4/w5ZdfYrfbSUlJ4ZFHHtE8zkqKi4tZv34969atY+3ataz/6SdK/X5cDhudElx0axVH+wS3pp+IVJHNMEj2OUj2Oejd1AtAIGyyqzBIVmGQnKIAuzf/yJpVPxA62M4Nw6BJchJp6emkpqaRnp5OamoqaWlpJCUlERMTow/AIiKNWK0U8d27d/PAAw8we/Zs0tLSME2TdevWVfz8mWeeoWPHjqxdu5bzzz+fIUOG8Mknn7BlyxZmz56NYRhcc801fPTRR5x22mksWLCAVatW8f777+NwOHj00Ud5/vnnuf/++2vj6dQpoVCInJwcMjMzycrKYufOnWxYv55t27djmiaGAU2jnPRIdNAmPo4OCW6cdv3hF6kOLrtBqzgXreJ+3qtQ+ODI+e6iELuLQ+SVFJK7ZR2b1v1IUSB8yO87HHYS4uNJTEomKSmJxMREYmNjiYqKIiYmhujoaGJiYoiKisLn8+HxePB4PNrVoohIA1ErRXzv3r04HA7i4+OBslGirl27/uJ2Xbt2JSoqip07d/LTTz8xZMiQiq91hw4dygcffMBpp50GQCAQwO/3Y7PZKCoqonnz5rXxVGpFOBympKSEkpISiouL2bdvX8WSn59fcborK4uc3buJRCIVv+tz2mkaZeeEFj5axDppHuPE49BGZVC2a8YVu0rYkOcnWD6foBb4QxFKQyYeh4G7lteF02bQKdFN/zSvRl5rid0waOJz0MTnoNthPysNRcgrDZNfEqYgEKEgEKYgUERBTgGbdm6hIBChJBg+4v1W5nDYcbvdeD0eXC4XDocTp8uJ0+nC6XRWLDabDbvdjsPhqDhvt9ux2Wy/WAzDqNLlytdXvs5ut2MYxhF/brPZ2LJlC+Fw+JDbABW3A35xWs40TUzTPORyJBIhEokccv7wJRwO/+7lI91X+eOVP+bhj394/vLTykv561z5NS8/X5Xl8PspP1/59auco/z6yhl/TeXn8muOtE4OX3eV/w5XXufyS5XfZ5Xfh+Xnj/Q+Bo74viy/v8MvVz49GoZhkJmZSVxcXMXlyu+rw/+bLT89/N+Kyv8mHP7e1/vjl2qliHfu3JmePXsyYsQIBg0aRN++fTnjjDN+sXHT119/jd/vp3Xr1nTr1o133nmHCy64AIBPP/2UAwcOADBq1CiWL1/OsGHD8Hg8tG3blnvvvbc2nsox2bp1K0888QSZmZm/ebvKxfpwNsMg2m0nymmQ4LbRvpmXJK/94OLA56y+ovd9Tgnf5ZRU2/1ZrcAfJq/011/bmuLxeBh70ljmz59PaVFprT/+pvwAX2UWEePWKOrR6NPUWzEV5Vh5HDbSo22kR//6vPGwaeIPmZSEIpQED56GIgTCZsUSjJSfFhMMFhEOQLjQxG9CccQkbELYhIgJEQ6emhAxTSImmIecNzEpu2xWutwYGQYYGAdPy6+rVG6h4rUxKXu9oLwU0Whft8oO/0BQdh0Vr5VhGMdUFuuqQ5/zz++Ncr/1d70xOdL7o/z6cjX1/khISODWW2+lV69eNXL/R6tWirjNZuO5555jw4YNrFixgk8//ZR//OMffPDBBwDcdNNNuN1uoqOjefbZZ4mNjeWss85ix44d/OUvfyE6OpqePXtW7OP3xx9/ZPPmzSxZsoSoqCgefvhhpk6dWufL+I8//siOHTv+8O8ZULHRWLLPQbTLRrTTRoLHTrzHrnneVeQPW/OP/9ixY7nyyisxTbPiPV/b/GETHdC9frAbBj6nUfah+lf6fzhiEoiYBA+W8nCkrMCHDp4PHSzZ4Yj5cwnn4PlIefE+WMj5uUSaB29rHrxt2DSJRMpLvVlR5itfDh+8z19cVzkDZbf5+YNB5Q8EZZehUsmtVGoNOKwYl523GQZ2A2y2g6eGgc0Ax8HLdpuBwzCw28peU7ut0s8MA7vt55/ZDA4uxi8er/wxK6so4IfljZg/r4vK6yQUgVCkbF2VX/75fPn1ZbepxS/rasTh3x6IVGbl+yM3N5cFCxY0ziJermPHjnTs2JEJEyZw6qmnsnz5cuDnOeKV2Ww2br31Vm699VYAXnrpJdq1awfA7NmzGTx4MDExZdVi/PjxTJ48uRafydE59dRT6datG36/n2AweMgSCAQqpqJUPi0qKiqblpKfx0/79uPfXXjIfdoMSPA6SXQbJPkcJHntpEY5SIt2HnNB712NI4F1wYqsYj7cXFDrjzt//nxM0+STTz6p9ccuN6JVNAPSfJY9vhxZKGJSeHCKStlphOJg2VSm8pHwkpBJaZhKI+IRwrXY1iq+di7/mtp28CtpjjCNxW5gGOXXG9gMG46D5/3+AF6vt+z2B39Wfn8GBlQaKas8anb4V/CYZllxN03CkTBmxCQSCZcV/fKv+yNhgpEI4fBhU1Ui5VMCDp2OUhPsh01TKfuK3o7DYcfuKjvvdZRPRXFgdzgqvsYvn0p0pKkph08HOHz6wOGv35H82nMu267oyNODDp+WYBgGu3fvJi0t7YhTnQ6finP4dJ0jTZU60m2PNN3h157/7z3v8uf4a0vl94ppmkecQhIOh39xvvLye9cf6fRIj3f4dJTDp6pUfi5HWrd/5H1deZ3v37+fuLi4Q17LI73GR3ofHv4erfxePny9Oiq93yuv98q3P3xK3a+9b35rOTxrbGxslV+X2lIrRTwnJ4esrCz69OkDQHZ2Nnl5eb85r9vv9xMIBIiJiSErK4s33niDZ599FoDmzZuzdOlSLr30UpxOJ4sXL6ZDhw618VSOic1mo02bNsd0HyUlJezbt4+8vLyKjTTLlp18m5lFIFgMgMNukB7tpGWMgxaxLlrEOqt12kp91D+t7EPF+lqfIx7k8/kfEu8wcMfV7q7sKuaIpzacD1T1ScQ02e+PkFcSIr80TF5JmLzSMPv8EQoCJkWB0BF/z+vxEB0dRXRsDAmxsURHR+P1evF6vbjd7oqNNt1uN263G6fTicPhOGR+ePkfuiPNPS4vM0f6w3n4H7DqsnLlSvr161dt91ddKheeyiXot+beHmnebHlJLH/9GoO6uk7l6Gmd1r5aKeKhUIhnn32WzMxMPB4PkUiEW2655YgbbJYrKCjgoosuqvgH7Y477qBbt7JNnyZMmMDGjRsZP348DoeDtLQ0Hnroodp4KpYr/2OclpZW8XqUi0Qi7N27l40bNx7cbeGPfLV5C1/sLCvnaTFOuiW56dbEQ4Kn8c0XNgyDAek+BqRrZFiql2maFAYj5BSFfl6Kw+wtDh0yeu10OGjatCnN26TRpEkTEhISSExMrNhjSkJCAjExMTgcOsRDbSkv0CIiVjDMRjaZy+/3s2bNGrp3747b7bY6To0rLS1l48aNrF27lmXLvmbjxk0ANItx0i25rJTHaSM+kT+kOBgh8+CBfXYWBMkuCh+ya8KkxATatG1Hy5YtSU9PJy0trWLf4Y1ltPRwGmlreLROGx6t0+r3e71Twy4NnMfjoUePHvTo0YPzzjuP7Oxsli5dypIli5m/ZSvztxbSOt7Fcc18dEjQ0TVFDmeaJntLyg51v+NAkMzCMLnFQaBsNLVVyxYMHdCZNm3a0KpVK1q3bl2x/YqIiMhvURFvZFJTUzn77LM5++yzycrK4vPPP2fuxx8z68dcmkY7GdbMS9cmHuwq5NJIVS7e2/YF2F4QptBfNpc7Pi6Wzj27clrHjnTu3Jn27dvj9Wr+vYiIHB0V8UYsPT2d8847j7POOoslS5bw9ltv8d/1mSzIKOa4ZmV7THFq14jSCBQEwmzZF2BLfoAt+0MUHCzeiQnx9B/Sm+7du9OjRw/S0tL0rZGIiFQbFXHB6XQyevRoRo4cybJly3jrrTf5cOMmluwo4aQ2UXRLdqt8SIMSiphs3x9gc36AzfuD5BSWTTWJiY6m98AB9OrVS8VbRERqnIq4VLDZbAwZMoTBgwezevVqXnn5Zd7+aTPfJbg4tV0MSV69XaT+yi8NszHPz6Z8P1v3hwiGI9jtdrp27cJJffrSp08f2rZt22g3phQRkdqnZiW/YBgGPXv25Mlp0/j444957dVXef7bPI5v4WNo8ygdyVPqhVDEJGN/gA35ATblB9l7cAPLpikpjD15AP369aNHjx54PB6Lk4qISGOlIi6/ym63M27cOIYMGcI//vG/LPz8C1bvCXBqu2jaxrusjifyC4WBMBvzAmzI87NlfxB/KILT4aB79+78aUBZ+U5PT9d0ExERqRNUxOV3JSUlcddddzNmzIk8N3Mmr63ezXHNfIxuHY1do+NiIdM02V0c4qdcPxvyAmQWlI16JybEM2L0CAYMKJvvrVFvERGpi1TEpcr69u3LzOee4+WXX+ajjz5iZ2GIczrFEqsDAkktCkdMth8Isj63lPX5QfaVlO3hpEOH9lx4xmAGDBhAmzZtNOotIiJ1noq4/CFut5trr72WLl26MGPGs7zwfT5nd4yhbULDP0qpWCcYNtm8z8/avX425AcpDYZxOp307t2HQYMGMWDAABITE62OKSIi8oeoiMtRGTFiBO3ateORhx/mX2syGdEqiuNbRGHTKKRUk0DYZGOen7V7S9m4L0ggFCEqysdxxw9n8ODB9OnTR1NORESkXlMRl6PWokULnpo+nZkzZ7Jw8WJ2HAhxVqdYfE7t/k2OTihisinfz+rdpWzIDxIMR4iNiWHk6BEcd9xx9OzZE4dD/2yJiEjDoL9ocky8Xi+333473bp148UXX+CV1fuY0DWOeI/mjUvVmKbJjgNBVu0u5cfcACXBMD6flxNPOplhw4bRtWtX7Ha9n0REpOFREZdjZhgGp5xyCs2aNWPKlId4edU+JnSLpWmU0+poUoft94f5NruEVXv85JeEcDmdDB4ylJEjRxKJRBg4cKDVEUVERGqUirhUm549e/LYY49z/3338vKqfZzfJY422t+4VBIxTTbnB/hmVwkb8v2AQa9ePbl05CgGDx6Mz+cDYOXKldYGFRERqQUq4lKt2rRpwxNPTuO+e+/l3z9m8aeOsXRvog3qGrvCQJhvs0v5dncp+0pCxMXGcs454xk7diypqalWxxMREbGEirhUu5SUFB5/4gkeevBB/vvTTxQGIgxu5rM6llhgb3GILzOL+WF3KeGISc8ePbj61FMZNGgQTqemLomISOOmIi41IiYmhoemTOHJJ59k7tdfUxSMMKpVlA6y0kjsPBBk6c4ifsr143A4GHvSyYwfP57mzZtbHU1ERKTOUBGXGuN2u5k4cSLPPfcc8+fPJ2KajGkdrTLeQJmmyab8AEt3FrNtf4Aon49z//xnxo0bR0JCgtXxRERE6hwVcalRdrud66+/Hrvdzscff0zEhLFtVMYbmu37A3y2vYiM/QGSEhO5/PI/MXbs2IqNL0VEROSXVMSlxtlsNq699lrsdjtz5swhYpqc3DZGZbwByC4M8tn2Ijbm+YmPi+O6665gzJgxmv8tIiJSBSriUisMw+Cqq67Cbrfz3nvvETHhlHYx2FTG66W8khALtxexZk8pPp+PSy65hHHjxumQ8yIiIn+AirjUGsMwuPzyy7Hb7bzzzjtETDitvcp4feIPRVicUcTXWSU4HA7OOfdczjrrLKKjo62OJiIiUu+oiEutMgyDSy+9FLvdzltvvUXENDm9Q6zKeB1nmiar95TyybZiCvwhxowZw0UXXURiYqLV0UREROotFXGpdYZhcNFFF2Gz2fjPf/6DzTAY115zxuuqXYVBPt5SSMb+AB3at+f+a6+lY8eOVscSERGp91TExRKGYTBhwgTC4TBvv/02NgNObacyXpeUhCIs2FbIN9klREdHc+ONVzNmzBhsNpvV0URERBoEFXGxjGEYXHzxxYTDYWbPno3NMDi5rXZtWBes21vKR1uKKAyEOe20cUyYMEHzwEVERKqZirhYyjAMLrvsMsLhMO+//z42Q/sZt9IBf5iPNxewLtdPm9atefDmm2nfvr3VsURERBokFXGxnGEYXHHFFYRCIT766CPsBozWEThrVcQ0+S67hE+2FRM2bFx66aWcccYZOBz6J0JERKSm6K+s1AmGYXDNNdcQiUSYO3cuNsNgZKsolfFakFsS4oONBWzbH6B79+7ceOONpKenWx1LRESkwVMRlzrDMAyuvfZaIpEI8+fPxwRGqYzXmIhpsjyrhM+2F+F0ubnxxhs58cQT9XqLiIjUEhVxqVNsNhvXX389QFkZN01NU6kBuSUh3ttYQMb+AP379+eGG24gKSnJ6lgiIiKNioq41DnlZdxmszF37lwiwIkq49Wi8ii4y+3h1luvZ+TIkXptRURELKAiLnWSzWbjuuuuw2az8dFHH2Ga2pvKsdIouIiISN2iIi51VvkGnDabjTlz5hAx0X7Gj0LENFmWVcyC7cUaBRcREalDVMSlTjMMg6uuugqbzcb777+PaZqc3C4Gm0pklewtLhsF33EgwIAB/bn+eo2Ci4iI1BUq4lLnle9n3Gaz8e6771IcMjmzYywOm8r4r4mYJl9lFrMwoxi3x8Ntt93AiBEjNAouIiJSh6iIS71gGAb/7//9P+Li4nj11VcpCkY4r0scHofN6mh1zu6iEO9vKmDngQCDBw3i2uuuIzEx0epYIiIichgVcak3DMPgnHPOITExkWeefpp/rt7HhG5xxLjsVkerE4IRk88ziliaWYzPF8Wdd97M8ccfr1FwERGROkpFXOqdUaNGERcXx6OPPsLLq/YxoWscyb7G/Vbesi/Ah5sLyS0OMnz4cK644gri4+OtjiUiIiK/Qd/rS73Ur18/HnnkUcIOLy+v2sfOgqDVkSxRFIwwe/1+XludjzMmkQcffJA77rhDJVxERKQeUBGXeqtjx4488eSTuKKieXX1Pn7IKbE6Uq2JmCbfZZcwc2Uea/YGOPfcc5kxcyZ9+vSxOpqIiIhUUeP+Pl/qvfT0dK644krmfvwxs3/8kW37A5zaLhanveHOi962P8D8rYVkFQTp3KkTN9x4I61atbI6loiIiPxBKuJS70VHRzPl4YeZNWsWb775JllFYc7tFNvg5o3nlYT4ZGsh63L9JCUmcvvtl3HCCSdgs+mLLRERkfqoYTUVabTsdjsXXXQRXbt2ZdqTT/LiD/mc3i6aHileq6Mds5JQhM8zili2qwSHw8mECRM488wz8Xg8VkcTERGRY6AiLg1Kv379eObZZ3n8scf4708/sX1/kBPbRuO2179R45JQhOVZxSzLKqUkFGbUqNFcdNFFOjKmiIhIA6EiLg1OcnIyjzz6KP/617945513WJ8fZExrHz2aeLDVg31qFwUifJ1VzPJdJfhDEfr378+ECRNo37691dFERESkGqmIS4PkcDi47LLLGDJkCC++8AKz129ixa5STm4bTfMYp9XxjuiAP8yXmcWszC4lFIkwZMhx/PnPf6Zdu3ZWRxMREZEaoCIuDVrnzp15cto0Fi5cyD9feYX//T6PXikeRreOJtZt/RE5I6bJln0Bvssu4ae8ACYGw4cP59xzz6VFixZWxxMREZEapCIuDZ7NZmP06NEMGTKEt956i3ffnc263Dx6pbjpm+olLbr2R8jzSkJ8n1PKD3v87C8NERMdzWnjTuL0008nNTW11vOIiIhI7VMRl0bD5/NxySWXMHbsWF5//XW+XLqUFbtKSI120qephx5NPPicNbNRp2ma7CkOs3mfn/W5AbbtD2AYBn379uHEE8cycOBAnM66OWVGREREaoaKuDQ6aWlp3HHHHRRecw2LFy9m/vx5fLx5K59sLaRzkosOCW7Sop0k+ezYj2HjzgP+MFv2BdiyL8DW/SEK/CEAmqWnc9H40YwaNYrk5OTqeloiIiJSz6iIS6MVHR3NaaedxmmnncaWLVv45JNPWLhwAWv2HADAabfRNMpOWpSDtGgnMS4bdgNsNqPs1Cg79YdN8kvDhy5+k8KDxTsmJpreAwfQp08fevXqRUpKipVPW0REROoIFXERoG3btlx99dVcccUVZGZmsnnz5rJl0ybWbNnMil0Hfvc+DMMgKTGRtFbpdE5NpUWLFvTq1YvWrVvr6JciIiLyCyriIpXY7XZatmxJy5YtGTlyJACRSITs7Gz2799PKBQiHA5XLKFQCJfLRVpaGikpKZrnLSIiIlWmIi7yO2w2G+np6aSnp1sdRURERBoQfV8uIiIiImIBFXEREREREQuoiIuIiIiIWEBFXERERETEAiriIiIiIiIWUBEXEREREbGAiriIiIiIiAVUxEVERERELKAiLiIiIiJiARVxERERERELqIiLiIiIiFhARVxERERExAIq4iIiIiIiFlARFxERERGxgIq4iIiIiIgFVMRFRERERCygIi4iIiIiYgEVcRERERERC6iIi4iIiIhYwGF1gNpmmiYAgUDA4iRSnfx+v9URpJppnTY8WqcNj9Zpw6N1Wr3K+2Z5/zycYf7aTxqogoICNmzYYHUMEREREWkkOnbsSExMzC+ub3RFPBKJUFRUhNPpxDAMq+OIiIiISANlmibBYJCoqChstl/OCG90RVxEREREpC7QxpoiIiIiIhZQERcRERERsYCKuIiIiIiIBVTERUREREQsoCIuIiIiImIBFXEREREREQuoiIuIiIiIWEBFXOq9GTNm0KlTJx0xtQHw+/3cd999jB07ltNPP52//vWvVkeSY7Rw4ULOPPNMzjjjDMaPH8/8+fOtjiR/0GOPPcaoUaN+8e/s1q1bOe+88zjppJM477zz2LZtm3Uh5Q850jrNz8/nyiuv5KSTTuL000/nhhtuIC8vz+KkDZ+KuNRrP/74I99//z3NmjWzOopUgyeeeAK32828efP44IMPuPnmm62OJMfANE3uuusuHn/8cd577z0ef/xx7r77biKRiNXR5A8YPXo0r7/++i/+nb3vvvu44IILmDdvHhdccAH33nuvRQnljzrSOjUMgyuuuKLi398WLVrw5JNPWpiycVARl3orEAjw4IMPcv/991sdRapBUVER7777LjfffDOGYQCQnJxscSo5VjabjYKCAgAKCgpISUk54mGepe7q378/aWlph1yXm5vL2rVrGTduHADjxo1j7dq1GkGtJ460TuPj4xk0aFDF5d69e5OVlVXb0Rodh9UBRI7W008/zfjx42nevLnVUaQa7Nixg/j4eGbMmMGyZcuIiori5ptvpn///lZHk6NkGAZ/+9vfuO666/D5fBQVFfHiiy9aHUuqwa5du2jatCl2ux0Au91OSkoKu3btIjEx0eJ0cqwikQhvvPEGo0aNsjpKg6dhCamXvvvuO9asWcMFF1xgdRSpJuFwmB07dtC1a1feeecd7rjjDm688UYKCwutjiZHKRQK8cILL/Dcc8+xcOFCnn/+eW655RaKioqsjiYiv+Ghhx7C5/Nx4YUXWh2lwVMRl3ppxYoVbN68mdGjRzNq1Ciys7O5/PLL+eKLL6yOJkcpLS0Nh8NR8VV3r169SEhIYOvWrRYnk6O1bt06du/eTb9+/QDo168fXq+XzZs3W5xMjlVaWho5OTmEw2Gg7IP07t27fzHdQeqfxx57jO3bt/O3v/1N08hqgV5hqZeuuuoqvvjiCxYsWMCCBQtITU3lH//4B8OGDbM6mhylxMREBg0axNKlS4GyPTLk5ubSqlUri5PJ0UpNTSU7O5stW7YAsHnzZnJzc2nZsqXFyeRYJSUl0aVLF+bMmQPAnDlz6NKli6al1HNPPfUUa9asYebMmbhcLqvjNAqGaZqm1SFEjtWoUaP4+9//TseOHa2OIsdgx44dTJ48mX379uFwOLjlllsYPny41bHkGLz//vu89NJLFRvg3nTTTYwZM8biVPJHTJkyhfnz57N3714SEhKIj4/nww8/ZPPmzUycOJEDBw4QGxvLY489Rtu2ba2OK1VwpHX6t7/9jXHjxtG6dWs8Hg8AzZs3Z+bMmRanbdhUxEVERERELKCpKSIiIiIiFlARFxERERGxgIq4iIiIiIgFVMRFRERERCygIi4iIiIiYgEVcRERERERC6iIi4iIiIhYQEVcRERERMQCKuIiIg3Arl27uOGGGxg8eDCDBg3iwQcfJBKJ8NxzzzFy5EiGDBnCXXfdRUFBAQA7d+6kU6dOzJ49mxEjRjBo0CCef/75ivtbtWoVZ511Fn379uW4447j0UcfBWDZsmWccMIJhzz2qFGj+PLLLwF49tlnuemmm7jjjjvo06cPp59+Olu3buWFF15gyJAhDB8+nC+++KLidwsKCpg8eTLDhg3j+OOPZ/r06YTD4Zp+uURE6gQVcRGRei4cDnP11VeTnp7OggULWLJkCaeeeirvvPMOs2fP5rXXXuPTTz+luLiYBx988JDfXblyJXPnzuXVV19l5syZbN68GYCHH36Yiy++mG+//ZZPPvmEU045pcp5Fi5cyBlnnMGKFSvo0qULl19+OZFIhCVLlnD99ddz7733Vtx24sSJOBwO5s+fz7vvvsvSpUt56623queFERGp41TERUTquVWrVrF7927uuusufD4fbreb/v3788EHH3DppZfSokULoqKiuO222/joo48IhUIVv3vDDTfg8Xjo3LkznTt35qeffgLA4XCQkZFBXl4eUVFR9O7du8p5+vfvz/HHH4/D4eDkk08mPz+fq666CqfTyamnnkpmZiYHDhxg7969LF68mMmTJ+Pz+UhKSuLSSy/lww8/rO6XSESkTnJYHUBERI7Nrl27SE9Px+E49J/03bt306xZs4rLzZo1IxQKkZubW3FdcnJyxXmv10txcTFQNiL+zDPPcMopp9C8eXNuuOEGRo4cWaU8SUlJFec9Hg8JCQnY7faKywDFxcXs3r2bUCjEsGHDKm4fiURIS0ur6lMXEanXVMRFROq5tLQ0du3aRSgUOqSMp6SkkJmZWXE5KysLh8NBUlIS2dnZv3mfrVu35qmnniISiTB//nxuuukmli1bhtfrpbS0tOJ24XCYvLy8o8qdmpqKy+Xi66+//sWHCBGRxkBTU0RE6rmePXvSpEkTpk2bRnFxMX6/n5UrVzJu3DheffVVduzYQVFREdOnT+eUU06pUul97733yMvLw2azERsbC4DNZqNNmzb4/X4WLVpEMBjk+eefJxAIHFXulJQUhg4dytSpUyksLCQSiZCRkcHy5cuP6v5EROobFXERkXrObrfz97//ne3btzNy5EhOOOEEPv74Y84++2zGjx/PhRdeyOjRo3G5XPz1r3+t0n1+/vnnnHbaafTp04eHH36Y6dOn4/F4iImJ4b777uOee+7hhBNOwOv1kpqaetTZH3/8cYLBIKeeeioDBgzgpptuYs+ePUd9fyIi9YlhmqZpdQgRERERkcZGI+IiIiIiIhZQERcRERERsYCKuIiIiIiIBVTERUREREQsoCIuIiIiImIBFXEREREREQuoiIuIiIiIWEBFXERERETEAiriIiIiIiIW+P+xd0QB2k5LIAAAAABJRU5ErkJggg==\n",
+      "text/plain": [
+       "<Figure size 864x432 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.violinplot(x=df.consume,y=df[\"gas_type\"]);"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ironhack",
+   "language": "python",
+   "name": "ironhack"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/Limpieza de datos.ipynb b/Limpieza de datos.ipynb
new file mode 100644
index 0000000..06bb15e
--- /dev/null
+++ b/Limpieza de datos.ipynb	
@@ -0,0 +1,749 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.read_csv(\"measurements.csv\") #cargamos el csv."
+   ]
+  },
+  {
+   "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>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "      <th>refill liters</th>\n",
+       "      <th>refill gas</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>28</td>\n",
+       "      <td>5</td>\n",
+       "      <td>26</td>\n",
+       "      <td>21,5</td>\n",
+       "      <td>12</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>45</td>\n",
+       "      <td>E10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>12</td>\n",
+       "      <td>4,2</td>\n",
+       "      <td>30</td>\n",
+       "      <td>21,5</td>\n",
+       "      <td>13</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>11,2</td>\n",
+       "      <td>5,5</td>\n",
+       "      <td>38</td>\n",
+       "      <td>21,5</td>\n",
+       "      <td>15</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>12,9</td>\n",
+       "      <td>3,9</td>\n",
+       "      <td>36</td>\n",
+       "      <td>21,5</td>\n",
+       "      <td>14</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>18,5</td>\n",
+       "      <td>4,5</td>\n",
+       "      <td>46</td>\n",
+       "      <td>21,5</td>\n",
+       "      <td>15</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  distance consume  speed temp_inside  temp_outside specials gas_type  AC  \\\n",
+       "0       28       5     26        21,5            12      NaN      E10   0   \n",
+       "1       12     4,2     30        21,5            13      NaN      E10   0   \n",
+       "2     11,2     5,5     38        21,5            15      NaN      E10   0   \n",
+       "3     12,9     3,9     36        21,5            14      NaN      E10   0   \n",
+       "4     18,5     4,5     46        21,5            15      NaN      E10   0   \n",
+       "\n",
+       "   rain  sun refill liters refill gas  \n",
+       "0     0    0            45        E10  \n",
+       "1     0    0           NaN        NaN  \n",
+       "2     0    0           NaN        NaN  \n",
+       "3     0    0           NaN        NaN  \n",
+       "4     0    0           NaN        NaN  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Exploro la forma del dataset:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(388, 12)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Veo la naturaleza de los datos y convierto a numéricos las dos primeras columnas (distancia y consumo):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 388 entries, 0 to 387\n",
+      "Data columns (total 12 columns):\n",
+      " #   Column         Non-Null Count  Dtype \n",
+      "---  ------         --------------  ----- \n",
+      " 0   distance       388 non-null    object\n",
+      " 1   consume        388 non-null    object\n",
+      " 2   speed          388 non-null    int64 \n",
+      " 3   temp_inside    376 non-null    object\n",
+      " 4   temp_outside   388 non-null    int64 \n",
+      " 5   specials       93 non-null     object\n",
+      " 6   gas_type       388 non-null    object\n",
+      " 7   AC             388 non-null    int64 \n",
+      " 8   rain           388 non-null    int64 \n",
+      " 9   sun            388 non-null    int64 \n",
+      " 10  refill liters  13 non-null     object\n",
+      " 11  refill gas     13 non-null     object\n",
+      "dtypes: int64(5), object(7)\n",
+      "memory usage: 36.5+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def replace_coma(x):\n",
+    "    return x.replace(\",\",\".\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lista_col=[\"distance\",\"consume\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for x in lista_col:\n",
+    "    df[x]=list(df[x].apply(replace_coma))\n",
+    "    df[x] = df[x].astype(float)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['temp_inside'] = pd.to_numeric(df['temp_inside'],errors = 'coerce')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "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>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "      <th>refill liters</th>\n",
+       "      <th>refill gas</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>28.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>26</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>12</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>45</td>\n",
+       "      <td>E10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>12.0</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>30</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>13</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>11.2</td>\n",
+       "      <td>5.5</td>\n",
+       "      <td>38</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>15</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>12.9</td>\n",
+       "      <td>3.9</td>\n",
+       "      <td>36</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>14</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>18.5</td>\n",
+       "      <td>4.5</td>\n",
+       "      <td>46</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>15</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   distance  consume  speed  temp_inside  temp_outside specials gas_type  AC  \\\n",
+       "0      28.0      5.0     26          NaN            12      NaN      E10   0   \n",
+       "1      12.0      4.2     30          NaN            13      NaN      E10   0   \n",
+       "2      11.2      5.5     38          NaN            15      NaN      E10   0   \n",
+       "3      12.9      3.9     36          NaN            14      NaN      E10   0   \n",
+       "4      18.5      4.5     46          NaN            15      NaN      E10   0   \n",
+       "\n",
+       "   rain  sun refill liters refill gas  \n",
+       "0     0    0            45        E10  \n",
+       "1     0    0           NaN        NaN  \n",
+       "2     0    0           NaN        NaN  \n",
+       "3     0    0           NaN        NaN  \n",
+       "4     0    0           NaN        NaN  "
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 388 entries, 0 to 387\n",
+      "Data columns (total 12 columns):\n",
+      " #   Column         Non-Null Count  Dtype  \n",
+      "---  ------         --------------  -----  \n",
+      " 0   distance       388 non-null    float64\n",
+      " 1   consume        388 non-null    float64\n",
+      " 2   speed          388 non-null    int64  \n",
+      " 3   temp_inside    169 non-null    float64\n",
+      " 4   temp_outside   388 non-null    int64  \n",
+      " 5   specials       93 non-null     object \n",
+      " 6   gas_type       388 non-null    object \n",
+      " 7   AC             388 non-null    int64  \n",
+      " 8   rain           388 non-null    int64  \n",
+      " 9   sun            388 non-null    int64  \n",
+      " 10  refill liters  13 non-null     object \n",
+      " 11  refill gas     13 non-null     object \n",
+      "dtypes: float64(3), int64(5), object(4)\n",
+      "memory usage: 36.5+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Compruebo que no hay duplicados:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=df.drop_duplicates() #no hay duplicados."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(388, 12)"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Compruebo dónde hay valores nulos:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "distance           0\n",
+       "consume            0\n",
+       "speed              0\n",
+       "temp_inside      219\n",
+       "temp_outside       0\n",
+       "specials         295\n",
+       "gas_type           0\n",
+       "AC                 0\n",
+       "rain               0\n",
+       "sun                0\n",
+       "refill liters    375\n",
+       "refill gas       375\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Relleno los nulos con \"Unkown\" al tratarse de variables categóricas:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "Int64Index: 388 entries, 0 to 387\n",
+      "Data columns (total 12 columns):\n",
+      " #   Column         Non-Null Count  Dtype  \n",
+      "---  ------         --------------  -----  \n",
+      " 0   distance       388 non-null    float64\n",
+      " 1   consume        388 non-null    float64\n",
+      " 2   speed          388 non-null    int64  \n",
+      " 3   temp_inside    169 non-null    float64\n",
+      " 4   temp_outside   388 non-null    int64  \n",
+      " 5   specials       93 non-null     object \n",
+      " 6   gas_type       388 non-null    object \n",
+      " 7   AC             388 non-null    int64  \n",
+      " 8   rain           388 non-null    int64  \n",
+      " 9   sun            388 non-null    int64  \n",
+      " 10  refill liters  13 non-null     object \n",
+      " 11  refill gas     13 non-null     object \n",
+      "dtypes: float64(3), int64(5), object(4)\n",
+      "memory usage: 39.4+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#relleno los Nan con la media de las temperaturas al ser una variable numérica:\n",
+    "df[\"temp_inside\"].fillna(df[\"temp_inside\"].mean(), inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#relleno los Nan de \"specials\" con \"Unkown\" al ser categórica:\n",
+    "df.specials.fillna((\"Unknown\"), inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#elimino las columnas de \"refill liters\" y \"refill gas\" por el alto porcentaje de Nans que contienen:\n",
+    "df.drop([\"refill liters\",\"refill gas\"], axis=1, inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "distance        0\n",
+       "consume         0\n",
+       "speed           0\n",
+       "temp_inside     0\n",
+       "temp_outside    0\n",
+       "specials        0\n",
+       "gas_type        0\n",
+       "AC              0\n",
+       "rain            0\n",
+       "sun             0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "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>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>57</th>\n",
+       "      <td>12.3</td>\n",
+       "      <td>6.2</td>\n",
+       "      <td>61</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>8</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>SP98</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    distance  consume  speed  temp_inside  temp_outside specials gas_type  AC  \\\n",
+       "57      12.3      6.2     61    21.934911             8  Unknown     SP98   0   \n",
+       "\n",
+       "    rain  sun  \n",
+       "57     0    0  "
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.sample()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Guardo el dataset limpio:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv('measurementsclean.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ironhack",
+   "language": "python",
+   "name": "ironhack"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/Machine Learning- Predictions.ipynb b/Machine Learning- Predictions.ipynb
new file mode 100644
index 0000000..8d427b5
--- /dev/null
+++ b/Machine Learning- Predictions.ipynb	
@@ -0,0 +1,582 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split as tts\n",
+    "from sklearn import metrics\n",
+    "import numpy as np\n",
+    "from sklearn.linear_model import LinearRegression as LinReg\n",
+    "from sklearn.linear_model import Ridge, Lasso\n",
+    "from sklearn.linear_model import SGDRegressor\n",
+    "from sklearn.neighbors import KNeighborsRegressor\n",
+    "from sklearn.ensemble import GradientBoostingRegressor\n",
+    "from sklearn.svm import SVR\n",
+    "from sklearn.model_selection import cross_val_score as cvs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.read_csv(\"measurementsclean.csv\")"
+   ]
+  },
+  {
+   "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>Unnamed: 0</th>\n",
+       "      <th>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>26</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>12</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>30</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>13</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>11.2</td>\n",
+       "      <td>5.5</td>\n",
+       "      <td>38</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>12.9</td>\n",
+       "      <td>3.9</td>\n",
+       "      <td>36</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>14</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>4</td>\n",
+       "      <td>18.5</td>\n",
+       "      <td>4.5</td>\n",
+       "      <td>46</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Unnamed: 0  distance  consume  speed  temp_inside  temp_outside specials  \\\n",
+       "0           0      28.0      5.0     26    21.934911            12  Unknown   \n",
+       "1           1      12.0      4.2     30    21.934911            13  Unknown   \n",
+       "2           2      11.2      5.5     38    21.934911            15  Unknown   \n",
+       "3           3      12.9      3.9     36    21.934911            14  Unknown   \n",
+       "4           4      18.5      4.5     46    21.934911            15  Unknown   \n",
+       "\n",
+       "  gas_type  AC  rain  sun  \n",
+       "0      E10   0     0    0  \n",
+       "1      E10   0     0    0  \n",
+       "2      E10   0     0    0  \n",
+       "3      E10   0     0    0  \n",
+       "4      E10   0     0    0  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "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>distance</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>28.0</td>\n",
+       "      <td>26</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>12</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>12.0</td>\n",
+       "      <td>30</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>13</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>11.2</td>\n",
+       "      <td>38</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>12.9</td>\n",
+       "      <td>36</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>14</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>18.5</td>\n",
+       "      <td>46</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   distance  speed  temp_inside  temp_outside specials gas_type  AC  rain  sun\n",
+       "0      28.0     26    21.934911            12  Unknown      E10   0     0    0\n",
+       "1      12.0     30    21.934911            13  Unknown      E10   0     0    0\n",
+       "2      11.2     38    21.934911            15  Unknown      E10   0     0    0\n",
+       "3      12.9     36    21.934911            14  Unknown      E10   0     0    0\n",
+       "4      18.5     46    21.934911            15  Unknown      E10   0     0    0"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X = df.drop([\"Unnamed: 0\",\"consume\"], axis=1) \n",
+    "X.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y=df.consume"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Convierto las columnas categóricas a numéricas:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 388 entries, 0 to 387\n",
+      "Data columns (total 9 columns):\n",
+      " #   Column        Non-Null Count  Dtype  \n",
+      "---  ------        --------------  -----  \n",
+      " 0   distance      388 non-null    float64\n",
+      " 1   speed         388 non-null    int64  \n",
+      " 2   temp_inside   388 non-null    float64\n",
+      " 3   temp_outside  388 non-null    int64  \n",
+      " 4   specials      388 non-null    object \n",
+      " 5   gas_type      388 non-null    object \n",
+      " 6   AC            388 non-null    int64  \n",
+      " 7   rain          388 non-null    int64  \n",
+      " 8   sun           388 non-null    int64  \n",
+      "dtypes: float64(2), int64(5), object(2)\n",
+      "memory usage: 27.4+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "X.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['Unknown', 'AC rain', 'AC', 'rain', 'snow', 'AC snow',\n",
+       "       'half rain half sun', 'sun', 'AC sun', 'sun ac', 'ac', 'AC Sun',\n",
+       "       'ac rain'], dtype=object)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X.specials.unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dic_specials ={\"AC rain\":1,\n",
+    "               \"ac rain\":1,\n",
+    "                \"AC\":2,\n",
+    "                \"ac\":2,\n",
+    "                \"rain\":1,\n",
+    "                \"snow\":3,\n",
+    "                \"AC snow\":3,\n",
+    "                \"half rain half sun\":4,\n",
+    "                \"sun\": 5,\n",
+    "                \"AC sun\": 5,\n",
+    "                \"sun ac\": 5,\n",
+    "                \"AC Sun\":5,\n",
+    "                \"Unknown\":7} "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X.specials = X.specials.map(dic_specials)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['E10', 'SP98'], dtype=object)"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X[\"gas_type\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dicc_gas={\"E10\":0,\"SP98\":1}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X[\"gas_type\"] = X[\"gas_type\"].map(dicc_gas)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = tts(X,y, test_size=0.2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "models={\n",
+    "    'ridge': Ridge(),\n",
+    "    'lasso': Lasso(),\n",
+    "    'sgd': SGDRegressor(),\n",
+    "    'knn': KNeighborsRegressor(),\n",
+    "    'grad': GradientBoostingRegressor(),\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ENTRENANDO:  ridge\n",
+      "ENTRENANDO:  lasso\n",
+      "ENTRENANDO:  sgd\n",
+      "ENTRENANDO:  knn\n",
+      "ENTRENANDO:  grad\n"
+     ]
+    }
+   ],
+   "source": [
+    "for name, model in models.items():\n",
+    "    print(\"ENTRENANDO: \", name)\n",
+    "    model.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "------ridge------\n",
+      "MAE -  0.5915556390285266\n",
+      "MSE -  0.6332090689017884\n",
+      "RMSE -  0.7957443489600089\n",
+      "R2 -  -0.012519409694171424\n",
+      "------lasso------\n",
+      "MAE -  0.5863373677641668\n",
+      "MSE -  0.5938663515550878\n",
+      "RMSE -  0.7706272455312542\n",
+      "R2 -  0.05039072046668458\n",
+      "------sgd------\n",
+      "MAE -  2781777071543.0493\n",
+      "MSE -  2.41440185751784e+25\n",
+      "RMSE -  4913656334663.465\n",
+      "R2 -  -3.860697617263027e+25\n",
+      "------knn------\n",
+      "MAE -  0.46461538461538454\n",
+      "MSE -  0.3931897435897436\n",
+      "RMSE -  0.6270484379932252\n",
+      "R2 -  0.37127835555520505\n",
+      "------grad------\n",
+      "MAE -  0.4349697461504338\n",
+      "MSE -  0.4202707359577462\n",
+      "RMSE -  0.6482829135167347\n",
+      "R2 -  0.32797507429623884\n"
+     ]
+    }
+   ],
+   "source": [
+    "for name, model in models.items():\n",
+    "    y_pred = model.predict(X_test)\n",
+    "    print(f\"------{name}------\")\n",
+    "    print('MAE - ', metrics.mean_absolute_error(y_test, y_pred))\n",
+    "    print('MSE - ', metrics.mean_squared_error(y_test, y_pred))\n",
+    "    print('RMSE - ', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
+    "    print('R2 - ', metrics.r2_score(y_test, y_pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Modelo:  ridge Score:  -0.24517033785848322\n",
+      "Modelo:  lasso Score:  -0.28426366190194124\n",
+      "Modelo:  sgd Score:  -1.3318385155302547e+25\n",
+      "Modelo:  knn Score:  0.3493454625360017\n",
+      "Modelo:  grad Score:  0.40623622869965026\n"
+     ]
+    }
+   ],
+   "source": [
+    "for name, model in models.items():\n",
+    "    scores=cvs(model, X, y, scoring='r2', cv=5)\n",
+    "    print('Modelo: ', name, 'Score: ', np.mean(scores))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Me quedo con el modelo KNeighborsRegressor puesto que tiene el RMSE menor."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ironhack",
+   "language": "python",
+   "name": "ironhack"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/Visualizaciones.ipynb b/Visualizaciones.ipynb
new file mode 100644
index 0000000..6c763b6
--- /dev/null
+++ b/Visualizaciones.ipynb
@@ -0,0 +1,670 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Matplotlib inline para visualizar los gráficos de Matplotlib\n",
+    "%matplotlib inline\n",
+    "%config Inlinebackend.figure_format= 'retina'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Configuración para setear y que todas las fig de Seaborn salgan por defecto con este tamaño\n",
+    "# Se puede especificar el tamaño de cada figura\n",
+    "sns.set_context(\"poster\")\n",
+    "sns.set(rc={\"figure.figsize\": (12.,6.)})\n",
+    "sns.set_style(\"whitegrid\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.read_csv(\"measurementsclean.csv\") #cargamos el csv."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.drop([\"Unnamed: 0\"], axis=1, inplace=True)"
+   ]
+  },
+  {
+   "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>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>specials</th>\n",
+       "      <th>gas_type</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>28.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>26</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>12</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>12.0</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>30</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>13</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>11.2</td>\n",
+       "      <td>5.5</td>\n",
+       "      <td>38</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>12.9</td>\n",
+       "      <td>3.9</td>\n",
+       "      <td>36</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>14</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>18.5</td>\n",
+       "      <td>4.5</td>\n",
+       "      <td>46</td>\n",
+       "      <td>21.934911</td>\n",
+       "      <td>15</td>\n",
+       "      <td>Unknown</td>\n",
+       "      <td>E10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   distance  consume  speed  temp_inside  temp_outside specials gas_type  AC  \\\n",
+       "0      28.0      5.0     26    21.934911            12  Unknown      E10   0   \n",
+       "1      12.0      4.2     30    21.934911            13  Unknown      E10   0   \n",
+       "2      11.2      5.5     38    21.934911            15  Unknown      E10   0   \n",
+       "3      12.9      3.9     36    21.934911            14  Unknown      E10   0   \n",
+       "4      18.5      4.5     46    21.934911            15  Unknown      E10   0   \n",
+       "\n",
+       "   rain  sun  \n",
+       "0     0    0  \n",
+       "1     0    0  \n",
+       "2     0    0  \n",
+       "3     0    0  \n",
+       "4     0    0  "
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['E10', 'SP98'], dtype=object)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[\"gas_type\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Comparamos la velocidad media que alcanza cada combustible:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = df.groupby(\"gas_type\").agg({\"speed\": \"mean\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df3=df2.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x432 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "barplot = sns.barplot(x=\"gas_type\", y=\"speed\", data=df3,ci=\"sd\", palette=\"magma\");"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_dist = df.groupby(\"gas_type\").agg({\"distance\": \"mean\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "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>distance</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>gas_type</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>E10</th>\n",
+       "      <td>21.096250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SP98</th>\n",
+       "      <td>18.639912</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "           distance\n",
+       "gas_type           \n",
+       "E10       21.096250\n",
+       "SP98      18.639912"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_dist"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Relación entre la velocidad y el consumo para ambos combustibles:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x432 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.scatterplot(x=\"speed\", y=\"consume\", hue=\"gas_type\",data=df);"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Estudio la correlación entre las diferentes variables:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "E10=df.loc[(df[\"gas_type\"]==\"E10\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "corrE10 = E10.corr()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "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>distance</th>\n",
+       "      <th>consume</th>\n",
+       "      <th>speed</th>\n",
+       "      <th>temp_inside</th>\n",
+       "      <th>temp_outside</th>\n",
+       "      <th>AC</th>\n",
+       "      <th>rain</th>\n",
+       "      <th>sun</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>distance</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.172572</td>\n",
+       "      <td>0.633082</td>\n",
+       "      <td>0.137061</td>\n",
+       "      <td>0.158903</td>\n",
+       "      <td>0.045776</td>\n",
+       "      <td>-0.073315</td>\n",
+       "      <td>0.027364</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>consume</th>\n",
+       "      <td>-0.172572</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.233318</td>\n",
+       "      <td>-0.040842</td>\n",
+       "      <td>-0.322918</td>\n",
+       "      <td>0.043591</td>\n",
+       "      <td>0.248199</td>\n",
+       "      <td>-0.160503</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>speed</th>\n",
+       "      <td>0.633082</td>\n",
+       "      <td>-0.233318</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.014835</td>\n",
+       "      <td>0.091093</td>\n",
+       "      <td>0.125102</td>\n",
+       "      <td>-0.001633</td>\n",
+       "      <td>0.128376</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>temp_inside</th>\n",
+       "      <td>0.137061</td>\n",
+       "      <td>-0.040842</td>\n",
+       "      <td>-0.014835</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.386506</td>\n",
+       "      <td>0.428083</td>\n",
+       "      <td>0.091396</td>\n",
+       "      <td>0.171009</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>temp_outside</th>\n",
+       "      <td>0.158903</td>\n",
+       "      <td>-0.322918</td>\n",
+       "      <td>0.091093</td>\n",
+       "      <td>0.386506</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.048762</td>\n",
+       "      <td>-0.097756</td>\n",
+       "      <td>0.236743</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AC</th>\n",
+       "      <td>0.045776</td>\n",
+       "      <td>0.043591</td>\n",
+       "      <td>0.125102</td>\n",
+       "      <td>0.428083</td>\n",
+       "      <td>0.048762</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.336123</td>\n",
+       "      <td>0.171118</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>rain</th>\n",
+       "      <td>-0.073315</td>\n",
+       "      <td>0.248199</td>\n",
+       "      <td>-0.001633</td>\n",
+       "      <td>0.091396</td>\n",
+       "      <td>-0.097756</td>\n",
+       "      <td>0.336123</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.094916</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>sun</th>\n",
+       "      <td>0.027364</td>\n",
+       "      <td>-0.160503</td>\n",
+       "      <td>0.128376</td>\n",
+       "      <td>0.171009</td>\n",
+       "      <td>0.236743</td>\n",
+       "      <td>0.171118</td>\n",
+       "      <td>-0.094916</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "              distance   consume     speed  temp_inside  temp_outside  \\\n",
+       "distance      1.000000 -0.172572  0.633082     0.137061      0.158903   \n",
+       "consume      -0.172572  1.000000 -0.233318    -0.040842     -0.322918   \n",
+       "speed         0.633082 -0.233318  1.000000    -0.014835      0.091093   \n",
+       "temp_inside   0.137061 -0.040842 -0.014835     1.000000      0.386506   \n",
+       "temp_outside  0.158903 -0.322918  0.091093     0.386506      1.000000   \n",
+       "AC            0.045776  0.043591  0.125102     0.428083      0.048762   \n",
+       "rain         -0.073315  0.248199 -0.001633     0.091396     -0.097756   \n",
+       "sun           0.027364 -0.160503  0.128376     0.171009      0.236743   \n",
+       "\n",
+       "                    AC      rain       sun  \n",
+       "distance      0.045776 -0.073315  0.027364  \n",
+       "consume       0.043591  0.248199 -0.160503  \n",
+       "speed         0.125102 -0.001633  0.128376  \n",
+       "temp_inside   0.428083  0.091396  0.171009  \n",
+       "temp_outside  0.048762 -0.097756  0.236743  \n",
+       "AC            1.000000  0.336123  0.171118  \n",
+       "rain          0.336123  1.000000 -0.094916  \n",
+       "sun           0.171118 -0.094916  1.000000  "
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "corrE10"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x432 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "mascara = np.triu(np.ones_like(corr, dtype=bool)) \n",
+    "color_map = sns.diverging_palette(0, 10, as_cmap=True) \n",
+    "sns.heatmap(corrE10,  \n",
+    "            mask = mascara,\n",
+    "            cmap=color_map,\n",
+    "            square=True, \n",
+    "            linewidth=0.5,\n",
+    "            vmax=1,\n",
+    "            cbar_kws={\"shrink\": .5},\n",
+    "            annot=True);"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "SP98=df.loc[(df[\"gas_type\"]==\"SP98\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "corrSP98 = SP98.corr()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x432 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "mascara = np.triu(np.ones_like(corr, dtype=bool)) \n",
+    "color_map = sns.diverging_palette(0, 10, as_cmap=True) \n",
+    "sns.heatmap(corrSP98,  \n",
+    "            mask = mascara,\n",
+    "            cmap=\"viridis\",\n",
+    "            square=True, \n",
+    "            linewidth=0.5,\n",
+    "            vmax=1,\n",
+    "            cbar_kws={\"shrink\": .5},\n",
+    "            annot=True);"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Mostramos la distribución de la variable consumo para cada tipo de carburantes:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x432 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.violinplot(x=df.consume,y=df[\"gas_type\"]);"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ironhack",
+   "language": "python",
+   "name": "ironhack"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/measurementsclean.csv b/measurementsclean.csv
new file mode 100644
index 0000000..714e34a
--- /dev/null
+++ b/measurementsclean.csv
@@ -0,0 +1,389 @@
+,distance,consume,speed,temp_inside,temp_outside,specials,gas_type,AC,rain,sun
+0,28.0,5.0,26,21.93491124260355,12,Unknown,E10,0,0,0
+1,12.0,4.2,30,21.93491124260355,13,Unknown,E10,0,0,0
+2,11.2,5.5,38,21.93491124260355,15,Unknown,E10,0,0,0
+3,12.9,3.9,36,21.93491124260355,14,Unknown,E10,0,0,0
+4,18.5,4.5,46,21.93491124260355,15,Unknown,E10,0,0,0
+5,8.3,6.4,50,21.93491124260355,10,Unknown,E10,0,0,0
+6,7.8,4.4,43,21.93491124260355,11,Unknown,E10,0,0,0
+7,12.3,5.0,40,21.93491124260355,6,Unknown,E10,0,0,0
+8,4.9,6.4,26,21.93491124260355,4,Unknown,E10,0,0,0
+9,11.9,5.3,30,21.93491124260355,9,Unknown,E10,0,0,0
+10,12.4,5.6,42,21.93491124260355,4,Unknown,E10,0,0,0
+11,11.8,4.6,38,21.93491124260355,0,Unknown,E10,0,0,0
+12,12.3,5.9,59,21.93491124260355,10,Unknown,E10,0,0,0
+13,24.7,5.1,58,21.93491124260355,12,Unknown,E10,0,0,0
+14,12.4,4.7,46,21.93491124260355,11,Unknown,E10,0,0,0
+15,17.3,5.1,24,21.93491124260355,5,Unknown,E10,0,0,0
+16,33.4,5.6,36,21.93491124260355,3,Unknown,E10,0,0,0
+17,11.8,5.1,32,21.93491124260355,3,Unknown,E10,0,0,0
+18,25.9,4.9,39,21.93491124260355,8,Unknown,E10,0,0,0
+19,11.8,4.7,40,21.93491124260355,4,Unknown,E10,0,0,0
+20,25.3,5.5,32,21.93491124260355,3,Unknown,E10,0,0,0
+21,14.2,5.9,38,21.93491124260355,1,Unknown,E10,0,0,0
+22,17.9,5.7,37,21.93491124260355,1,Unknown,E10,0,0,0
+23,11.8,4.7,36,21.93491124260355,1,Unknown,E10,0,0,0
+24,12.3,5.9,62,21.93491124260355,6,Unknown,E10,0,0,0
+25,12.4,4.1,57,21.93491124260355,9,Unknown,E10,0,0,0
+26,18.4,5.7,21,21.93491124260355,2,Unknown,E10,0,0,0
+27,18.4,5.8,28,21.93491124260355,3,Unknown,E10,0,0,0
+28,18.3,5.5,29,21.93491124260355,1,Unknown,E10,0,0,0
+29,18.4,5.7,35,21.93491124260355,4,Unknown,E10,0,0,0
+30,12.3,5.3,51,21.93491124260355,11,Unknown,E10,0,0,0
+31,11.8,5.0,29,21.93491124260355,10,Unknown,E10,0,0,0
+32,12.3,5.6,58,21.93491124260355,8,Unknown,E10,0,0,0
+33,32.6,4.8,40,21.93491124260355,7,Unknown,E10,0,0,0
+34,19.0,4.3,36,21.93491124260355,7,Unknown,E10,0,0,0
+35,12.1,5.7,36,21.93491124260355,8,Unknown,E10,0,0,0
+36,20.0,5.2,37,21.93491124260355,4,Unknown,E10,0,0,0
+37,4.9,7.4,26,21.93491124260355,6,Unknown,E10,0,0,0
+38,11.8,4.8,23,21.93491124260355,9,Unknown,E10,0,0,0
+39,12.3,6.5,58,21.93491124260355,7,Unknown,E10,0,0,0
+40,12.4,4.0,55,21.93491124260355,7,AC rain,E10,1,1,0
+41,4.5,5.0,29,21.93491124260355,7,AC,E10,1,0,0
+42,11.7,4.6,37,21.93491124260355,6,Unknown,E10,0,0,0
+43,10.2,4.3,44,21.93491124260355,7,Unknown,E10,0,0,0
+44,5.4,3.3,32,21.93491124260355,7,Unknown,SP98,0,0,0
+45,2.0,9.9,21,21.93491124260355,4,Unknown,SP98,0,0,0
+46,14.2,5.1,32,21.93491124260355,7,Unknown,SP98,0,0,0
+47,16.0,4.9,25,21.93491124260355,8,Unknown,SP98,0,0,0
+48,11.8,4.9,25,21.93491124260355,11,Unknown,SP98,0,0,0
+49,27.3,4.7,36,21.93491124260355,10,Unknown,SP98,0,0,0
+50,11.8,5.1,29,21.93491124260355,5,rain,SP98,0,1,0
+51,10.6,4.9,63,21.93491124260355,6,Unknown,SP98,0,0,0
+52,11.6,4.2,61,21.93491124260355,7,Unknown,SP98,0,0,0
+53,13.1,6.1,46,21.93491124260355,6,rain,SP98,0,1,0
+54,6.1,6.4,28,21.93491124260355,8,Unknown,SP98,0,0,0
+55,153.5,4.9,82,21.93491124260355,3,rain,SP98,0,1,0
+56,11.8,4.9,24,21.93491124260355,7,Unknown,SP98,0,0,0
+57,12.3,6.2,61,21.93491124260355,8,Unknown,SP98,0,0,0
+58,12.4,4.2,57,21.93491124260355,8,Unknown,SP98,0,0,0
+59,12.3,5.7,52,21.93491124260355,8,rain,SP98,0,1,0
+60,2.9,7.9,18,21.93491124260355,9,AC rain,SP98,1,1,0
+61,2.1,12.2,23,21.93491124260355,9,Unknown,SP98,1,1,0
+62,9.8,5.8,24,21.93491124260355,6,Unknown,SP98,0,0,0
+63,6.8,5.3,26,21.93491124260355,6,Unknown,SP98,0,0,0
+64,12.4,5.4,24,21.93491124260355,7,Unknown,SP98,0,0,0
+65,12.4,4.7,57,21.93491124260355,8,Unknown,SP98,0,0,0
+66,11.8,4.6,41,21.93491124260355,6,Unknown,SP98,0,0,0
+67,12.3,5.4,55,21.93491124260355,8,Unknown,SP98,0,0,0
+68,14.0,4.3,40,21.93491124260355,8,Unknown,SP98,0,0,0
+69,11.8,4.5,37,21.93491124260355,4,AC,SP98,1,0,0
+70,12.3,5.2,55,21.93491124260355,12,Unknown,SP98,0,0,0
+71,2.0,6.2,20,21.93491124260355,10,Unknown,SP98,0,0,0
+72,13.9,5.1,29,21.93491124260355,6,Unknown,SP98,0,0,0
+73,9.7,3.9,42,21.93491124260355,8,Unknown,SP98,0,0,0
+74,11.6,5.0,25,21.93491124260355,6,Unknown,SP98,0,0,0
+75,14.2,5.4,38,21.93491124260355,7,Unknown,SP98,0,0,0
+76,11.8,4.5,39,21.93491124260355,6,Unknown,SP98,0,0,0
+77,24.8,5.1,50,21.93491124260355,9,Unknown,SP98,0,0,0
+78,12.4,4.7,56,21.93491124260355,7,Unknown,SP98,0,0,0
+79,34.8,4.0,28,20.0,4,Unknown,SP98,0,0,0
+80,14.2,5.4,36,20.0,6,Unknown,SP98,0,0,0
+81,5.2,4.5,39,20.0,10,Unknown,SP98,0,0,0
+82,10.5,3.6,42,20.0,10,Unknown,SP98,0,0,0
+83,12.3,5.2,57,20.0,10,Unknown,SP98,0,0,0
+84,11.8,4.9,25,20.0,11,Unknown,SP98,0,0,0
+85,12.3,6.2,58,20.0,11,rain,SP98,0,1,0
+86,13.2,4.3,51,20.0,11,rain,SP98,0,1,0
+87,13.0,5.0,45,20.0,11,rain,SP98,0,1,0
+88,12.9,5.1,32,20.0,11,Unknown,SP98,0,0,0
+89,13.9,5.6,22,20.0,8,Unknown,SP98,0,0,0
+90,11.8,4.3,37,20.0,6,Unknown,SP98,0,0,0
+91,12.2,5.8,60,20.0,11,Unknown,SP98,0,0,0
+92,12.5,4.0,51,20.0,13,Unknown,SP98,0,0,0
+93,12.4,4.7,43,21.93491124260355,10,Unknown,SP98,0,0,0
+94,11.8,5.9,21,20.0,9,AC rain,SP98,1,1,0
+95,11.8,5.3,52,21.93491124260355,11,Unknown,SP98,0,0,0
+96,12.5,4.2,57,20.0,11,Unknown,SP98,0,0,0
+97,15.7,5.3,33,21.93491124260355,9,Unknown,SP98,0,0,0
+98,12.9,5.7,35,21.93491124260355,9,Unknown,SP98,0,0,0
+99,6.4,4.4,37,21.93491124260355,10,Unknown,SP98,0,0,0
+100,5.3,4.1,34,21.93491124260355,9,Unknown,SP98,0,0,0
+101,26.2,5.8,71,21.0,8,AC rain,SP98,1,1,0
+102,18.8,5.0,62,21.93491124260355,9,rain,SP98,0,1,0
+103,4.9,6.9,25,21.0,12,rain,SP98,0,1,0
+104,12.4,5.4,18,21.0,11,AC rain,SP98,1,1,0
+105,22.9,5.3,45,21.93491124260355,7,Unknown,SP98,0,0,0
+106,162.7,5.5,75,23.0,1,Unknown,SP98,0,0,0
+107,4.9,6.5,26,21.0,1,Unknown,SP98,0,0,0
+108,11.8,4.7,36,21.0,4,Unknown,SP98,0,0,0
+109,16.6,5.1,56,21.0,7,Unknown,SP98,0,0,0
+110,12.4,5.7,37,21.0,7,Unknown,SP98,0,0,0
+111,15.9,5.4,25,21.0,7,Unknown,SP98,0,0,0
+112,5.1,8.7,21,21.93491124260355,5,Unknown,SP98,0,0,0
+113,22.4,4.9,66,21.93491124260355,7,Unknown,SP98,0,0,0
+114,31.1,4.7,42,21.93491124260355,7,Unknown,SP98,0,0,0
+115,4.9,6.3,27,21.93491124260355,3,Unknown,SP98,0,0,0
+116,11.8,5.1,26,23.0,4,rain,SP98,0,1,0
+117,22.9,6.0,42,23.0,4,rain,SP98,0,1,0
+118,12.4,4.6,38,23.0,1,snow,SP98,0,1,0
+119,12.9,5.8,40,23.0,4,Unknown,SP98,0,0,0
+120,11.8,5.1,43,23.0,0,Unknown,SP98,0,0,0
+121,12.2,5.8,58,23.0,2,Unknown,SP98,0,0,0
+122,24.8,4.6,55,23.0,3,Unknown,SP98,0,0,0
+123,14.2,5.6,24,23.0,8,Unknown,SP98,0,0,0
+124,11.8,4.6,38,23.0,0,snow,SP98,0,1,0
+125,12.2,6.3,57,23.0,0,snow,SP98,0,1,0
+126,24.7,5.5,56,25.0,1,Unknown,SP98,0,0,0
+127,6.8,4.3,46,24.0,2,Unknown,SP98,0,0,0
+128,17.3,5.6,37,21.93491124260355,1,Unknown,SP98,0,0,0
+129,11.8,4.3,44,21.93491124260355,-3,Unknown,SP98,0,0,0
+130,15.9,5.7,46,21.93491124260355,5,Unknown,SP98,0,0,0
+131,5.1,6.4,39,21.93491124260355,4,Unknown,SP98,0,0,0
+132,16.1,4.5,33,21.93491124260355,6,Unknown,SP98,0,0,0
+133,11.8,4.5,43,21.93491124260355,3,Unknown,SP98,0,0,0
+134,4.2,6.0,26,21.93491124260355,5,Unknown,SP98,0,0,0
+135,17.4,5.1,30,21.93491124260355,5,Unknown,SP98,0,0,0
+136,23.5,6.0,25,21.93491124260355,5,rain,SP98,0,1,0
+137,11.8,4.5,38,21.93491124260355,5,rain,SP98,0,1,0
+138,12.3,6.1,61,21.93491124260355,10,rain,SP98,0,1,0
+139,16.1,5.4,24,21.93491124260355,7,rain,E10,0,1,0
+140,11.8,4.3,40,21.93491124260355,10,rain,E10,0,1,0
+141,12.3,5.4,58,21.93491124260355,13,Unknown,E10,0,0,0
+142,12.4,4.3,49,21.93491124260355,17,Unknown,E10,0,0,0
+143,7.0,5.2,25,21.93491124260355,17,Unknown,E10,0,0,0
+144,11.8,4.1,37,21.93491124260355,10,Unknown,E10,0,0,0
+145,20.1,4.4,41,21.93491124260355,18,Unknown,E10,0,0,0
+146,20.8,4.5,45,21.93491124260355,10,Unknown,E10,0,0,0
+147,1.7,10.8,14,21.93491124260355,10,rain,E10,0,1,0
+148,35.9,4.7,45,21.93491124260355,12,Unknown,E10,0,0,0
+149,36.9,4.8,52,21.93491124260355,5,Unknown,E10,0,0,0
+150,16.8,4.0,46,21.93491124260355,8,Unknown,E10,0,0,0
+151,9.9,5.0,28,21.93491124260355,9,Unknown,E10,0,0,0
+152,22.9,4.6,61,21.93491124260355,7,rain,E10,0,1,0
+153,17.3,5.0,61,21.93491124260355,6,AC rain,E10,1,1,0
+154,11.8,4.3,37,21.93491124260355,7,Unknown,E10,0,0,0
+155,36.6,5.2,80,21.93491124260355,7,rain,E10,0,1,0
+156,44.9,4.7,62,21.93491124260355,8,Unknown,E10,0,0,0
+157,11.8,4.2,34,21.93491124260355,9,rain,E10,0,1,0
+158,21.6,5.3,44,21.93491124260355,9,rain,E10,0,1,0
+159,39.4,5.3,60,21.93491124260355,9,rain,E10,0,1,0
+160,5.1,8.1,39,21.93491124260355,4,Unknown,E10,0,0,0
+161,26.6,4.8,38,21.93491124260355,7,Unknown,E10,0,0,0
+162,53.2,5.1,71,21.93491124260355,2,Unknown,E10,0,0,0
+163,18.9,4.4,53,21.93491124260355,2,Unknown,E10,0,0,0
+164,43.5,5.0,80,21.93491124260355,3,Unknown,E10,0,0,0
+165,6.1,6.3,26,21.93491124260355,5,Unknown,E10,0,0,0
+166,16.4,4.8,49,21.93491124260355,5,Unknown,E10,0,0,0
+167,12.3,6.1,40,21.93491124260355,6,Unknown,E10,0,0,0
+168,21.1,4.6,36,21.93491124260355,8,Unknown,E10,0,0,0
+169,21.1,4.8,43,21.93491124260355,7,Unknown,E10,0,0,0
+170,22.7,4.7,55,21.93491124260355,6,Unknown,E10,0,0,0
+171,44.4,4.8,38,21.93491124260355,8,Unknown,E10,0,0,0
+172,35.8,4.4,51,21.93491124260355,6,Unknown,E10,0,0,0
+173,11.8,4.9,44,21.93491124260355,0,Unknown,E10,0,0,0
+174,26.2,4.9,42,21.93491124260355,6,Unknown,E10,0,0,0
+175,40.6,4.4,44,21.0,3,Unknown,E10,0,0,0
+176,12.4,5.3,38,21.0,-5,Unknown,E10,0,0,0
+177,14.1,5.3,47,21.0,-3,Unknown,E10,0,0,0
+178,58.7,4.8,75,21.0,0,Unknown,E10,0,0,0
+179,16.2,5.2,29,21.0,0,Unknown,E10,0,0,0
+180,12.3,4.9,50,21.93491124260355,0,Unknown,E10,0,0,0
+181,12.3,7.1,52,21.93491124260355,0,AC snow,E10,1,1,0
+182,12.4,5.2,51,21.93491124260355,1,Unknown,E10,0,0,0
+183,31.8,4.7,59,21.93491124260355,3,Unknown,E10,0,0,0
+184,12.3,5.1,55,21.93491124260355,8,Unknown,E10,0,0,0
+185,51.6,5.0,73,21.93491124260355,12,Unknown,E10,0,0,0
+186,38.6,4.6,44,21.93491124260355,10,Unknown,E10,0,0,0
+187,12.3,4.8,41,21.93491124260355,7,Unknown,E10,0,0,0
+188,81.2,4.4,69,22.0,13,Unknown,E10,0,0,0
+189,130.3,4.6,85,22.0,12,Unknown,E10,0,0,0
+190,67.2,4.3,67,22.0,18,Unknown,E10,0,0,0
+191,43.7,4.7,44,22.0,9,half rain half sun,SP98,0,1,0
+192,12.1,4.2,43,22.0,4,Unknown,SP98,0,0,0
+193,56.1,4.8,82,22.0,13,Unknown,SP98,0,0,0
+194,39.0,4.1,61,22.0,16,Unknown,SP98,0,0,0
+195,11.8,4.5,41,21.93491124260355,13,Unknown,SP98,0,0,0
+196,38.5,4.8,63,21.93491124260355,14,Unknown,SP98,0,0,0
+197,28.2,4.6,54,21.93491124260355,14,Unknown,SP98,0,0,0
+198,2.9,7.4,24,21.93491124260355,14,Unknown,SP98,0,0,0
+199,6.1,5.6,24,21.93491124260355,13,Unknown,SP98,0,0,0
+200,19.6,4.9,43,21.93491124260355,13,Unknown,SP98,0,0,0
+201,22.2,3.8,42,21.93491124260355,15,Unknown,SP98,0,0,0
+202,13.6,4.5,44,19.0,18,Unknown,SP98,0,0,0
+203,12.6,4.1,33,21.93491124260355,17,Unknown,SP98,0,0,0
+204,8.7,5.3,28,21.93491124260355,12,AC rain,SP98,1,1,0
+205,7.9,4.7,31,21.93491124260355,12,AC,SP98,1,0,0
+206,2.4,9.0,26,20.0,10,Unknown,SP98,0,0,0
+207,4.9,6.3,26,20.0,10,Unknown,SP98,0,0,0
+208,18.1,3.6,36,20.0,19,Unknown,SP98,0,0,0
+209,25.9,3.7,39,20.0,21,Unknown,SP98,0,0,0
+210,1.3,11.5,21,20.0,10,Unknown,SP98,0,0,0
+211,14.1,5.0,22,20.0,12,Unknown,SP98,0,0,0
+212,13.4,5.5,31,20.0,9,Unknown,SP98,0,0,0
+213,6.4,4.7,33,20.0,8,Unknown,SP98,0,0,0
+214,12.9,4.5,42,20.0,13,Unknown,SP98,0,0,0
+215,12.1,4.4,33,21.93491124260355,5,Unknown,SP98,0,0,0
+216,15.7,4.1,32,21.93491124260355,13,Unknown,SP98,0,0,0
+217,16.2,4.4,26,21.93491124260355,11,Unknown,SP98,0,0,0
+218,12.8,4.6,22,21.93491124260355,12,Unknown,SP98,0,0,0
+219,19.0,4.4,58,21.93491124260355,17,sun,SP98,0,0,1
+220,29.0,4.0,27,21.93491124260355,12,Unknown,SP98,0,0,0
+221,12.1,5.0,32,21.93491124260355,9,Unknown,SP98,0,0,0
+222,12.3,5.2,55,21.93491124260355,10,Unknown,SP98,0,0,0
+223,24.8,4.0,56,21.93491124260355,11,Unknown,SP98,0,0,0
+224,12.9,5.1,34,21.93491124260355,8,rain,SP98,0,1,0
+225,11.8,4.5,39,21.93491124260355,3,Unknown,SP98,0,0,0
+226,31.4,4.6,62,21.93491124260355,11,Unknown,SP98,0,0,0
+227,19.0,5.1,53,21.93491124260355,4,rain,SP98,0,1,0
+228,13.0,5.7,38,21.93491124260355,3,AC rain,SP98,1,1,0
+229,11.8,4.8,42,21.93491124260355,2,Unknown,SP98,0,0,0
+230,13.0,6.2,32,21.93491124260355,4,Unknown,SP98,0,0,0
+231,11.8,5.0,43,21.93491124260355,1,Unknown,SP98,0,0,0
+232,27.1,5.0,69,21.93491124260355,8,Unknown,SP98,0,0,0
+233,5.2,4.6,38,21.93491124260355,8,Unknown,SP98,0,0,0
+234,19.0,4.5,29,21.93491124260355,10,Unknown,E10,0,0,0
+235,12.4,4.8,38,21.93491124260355,1,Unknown,E10,0,0,0
+236,25.2,5.0,55,21.93491124260355,9,Unknown,E10,0,0,0
+237,14.3,4.8,36,21.93491124260355,10,Unknown,E10,0,0,0
+238,11.8,4.6,40,21.93491124260355,2,Unknown,E10,0,0,0
+239,16.9,4.5,48,21.93491124260355,9,sun,E10,0,0,1
+240,12.4,4.6,55,21.93491124260355,11,sun,E10,0,0,1
+241,17.4,4.4,36,21.93491124260355,12,sun,E10,0,0,1
+242,9.2,5.7,33,21.93491124260355,8,rain,E10,0,1,0
+243,12.3,5.8,54,21.93491124260355,10,rain,E10,0,1,0
+244,13.0,5.9,32,21.93491124260355,10,Unknown,E10,0,0,0
+245,11.8,6.1,16,21.93491124260355,6,rain,E10,0,1,0
+246,13.0,5.7,37,21.93491124260355,11,rain,E10,0,1,0
+247,12.3,5.0,42,21.93491124260355,10,Unknown,E10,0,0,0
+248,12.3,5.2,57,21.93491124260355,15,sun,E10,0,0,1
+249,12.5,4.3,57,21.93491124260355,16,sun,E10,0,0,1
+250,31.5,4.1,30,21.93491124260355,16,sun,E10,0,0,1
+251,11.8,4.4,42,21.93491124260355,8,Unknown,E10,0,0,0
+252,24.9,4.5,53,21.93491124260355,14,Unknown,E10,0,0,0
+253,17.0,3.9,46,21.93491124260355,14,sun,E10,0,0,1
+254,2.0,8.1,20,21.93491124260355,14,Unknown,E10,0,0,0
+255,11.8,4.4,33,21.93491124260355,8,Unknown,E10,0,0,0
+256,7.4,5.0,31,21.93491124260355,12,Unknown,E10,0,0,0
+257,12.4,4.7,55,21.93491124260355,14,sun,E10,0,0,1
+258,2.0,6.0,22,21.93491124260355,14,Unknown,E10,0,0,0
+259,14.0,5.0,41,21.93491124260355,8,Unknown,E10,0,0,0
+260,25.7,5.0,45,21.93491124260355,7,Unknown,E10,0,0,0
+261,24.5,3.9,50,21.93491124260355,15,sun,E10,0,0,1
+262,11.8,4.5,28,21.93491124260355,12,Unknown,E10,0,0,0
+263,4.1,5.4,24,21.93491124260355,13,Unknown,E10,0,0,0
+264,4.2,5.6,29,22.0,17,Unknown,E10,0,0,0
+265,4.2,3.9,29,22.0,18,sun,E10,0,0,1
+266,16.0,4.0,40,22.0,10,Unknown,E10,0,0,0
+267,22.9,4.0,29,21.93491124260355,21,Unknown,E10,0,0,0
+268,16.0,3.8,42,21.93491124260355,8,Unknown,E10,0,0,0
+269,15.4,4.5,50,22.0,14,Unknown,E10,0,0,0
+270,16.0,3.8,41,22.0,12,Unknown,E10,0,0,0
+271,4.2,5.6,32,22.0,18,Unknown,E10,0,0,0
+272,101.9,5.2,75,22.0,18,Unknown,E10,0,0,0
+273,93.9,4.8,88,23.0,18,AC sun,E10,1,0,1
+274,25.7,4.9,50,22.0,10,rain,SP98,0,1,0
+275,16.0,4.1,40,22.0,10,Unknown,SP98,0,0,0
+276,16.1,4.5,32,22.0,19,Unknown,SP98,0,0,0
+277,16.0,4.4,40,22.0,7,AC rain,SP98,1,1,0
+278,16.0,4.5,41,22.0,11,Unknown,SP98,0,0,0
+279,24.7,4.5,26,22.0,10,Unknown,SP98,0,0,0
+280,16.0,3.9,42,22.0,8,Unknown,SP98,0,0,0
+281,15.4,4.6,43,22.0,16,Unknown,SP98,0,0,0
+282,16.0,3.8,40,22.0,8,Unknown,SP98,0,0,0
+283,32.1,4.5,50,22.0,16,Unknown,SP98,0,0,0
+284,25.9,4.4,40,22.0,14,Unknown,SP98,0,0,0
+285,48.6,4.3,44,22.0,12,Unknown,SP98,0,0,0
+286,37.2,4.0,45,22.0,20,sun,SP98,0,0,1
+287,28.8,3.9,35,22.0,15,sun,SP98,0,0,1
+288,6.7,5.0,30,22.0,17,Unknown,SP98,0,0,0
+289,7.4,4.1,25,22.0,18,sun,SP98,0,0,1
+290,17.3,4.1,22,22.0,25,sun,SP98,0,0,1
+291,6.6,5.6,43,22.0,16,Unknown,SP98,0,0,0
+292,14.3,4.1,26,22.0,20,Unknown,SP98,0,0,0
+293,13.3,4.6,33,22.0,18,Unknown,SP98,0,0,0
+294,8.3,4.9,26,22.0,23,Unknown,SP98,0,0,0
+295,12.7,4.5,39,22.0,27,sun,SP98,0,0,1
+296,16.5,4.1,47,22.0,14,Unknown,SP98,0,0,0
+297,20.6,4.1,38,22.0,21,Unknown,SP98,0,0,0
+298,16.3,4.5,58,22.0,16,Unknown,SP98,0,0,0
+299,18.7,4.2,65,25.0,18,sun ac,SP98,1,0,1
+300,36.5,3.9,54,23.0,18,sun,SP98,0,0,1
+301,19.0,5.0,35,22.0,15,sun ac,SP98,1,0,1
+302,16.6,4.4,46,22.0,5,ac,SP98,1,0,0
+303,29.9,4.5,32,22.0,18,ac,SP98,1,0,0
+304,16.0,3.8,42,22.0,11,Unknown,SP98,0,0,0
+305,21.1,5.1,33,22.0,10,rain,SP98,0,1,0
+306,16.0,3.9,40,22.0,10,Unknown,SP98,0,0,0
+307,11.9,5.3,34,22.0,13,Unknown,SP98,0,0,0
+308,10.1,4.2,35,22.0,16,Unknown,SP98,0,0,0
+309,31.9,4.3,33,22.0,16,Unknown,SP98,0,0,0
+310,18.7,4.0,60,22.0,13,Unknown,SP98,0,0,0
+311,10.8,4.7,48,22.0,17,sun,SP98,0,0,1
+312,19.8,4.0,56,22.0,17,sun,SP98,0,0,1
+313,11.3,4.3,38,22.0,17,Unknown,SP98,0,0,0
+314,11.5,5.3,53,22.0,15,Unknown,SP98,0,0,0
+315,21.4,5.2,51,22.0,13,Unknown,SP98,0,0,0
+316,32.0,4.9,53,22.0,15,Unknown,SP98,0,0,0
+317,41.9,4.7,53,22.0,14,Unknown,SP98,0,0,0
+318,211.0,4.6,80,22.0,20,Unknown,SP98,0,0,0
+319,216.1,5.3,90,22.0,21,sun,SP98,0,0,1
+320,25.5,3.6,27,22.0,27,sun,SP98,0,0,1
+321,16.6,4.2,52,22.0,15,rain,SP98,0,1,0
+322,25.9,4.1,43,22.0,24,Unknown,SP98,0,0,0
+323,16.5,4.0,48,22.0,15,Unknown,SP98,0,0,0
+324,22.1,3.9,29,22.0,26,Unknown,SP98,0,0,0
+325,16.6,3.7,49,22.0,17,Unknown,E10,0,0,0
+326,15.4,4.5,43,22.0,24,Unknown,E10,0,0,0
+327,16.5,3.9,43,22.0,17,Unknown,E10,0,0,0
+328,15.4,5.1,21,22.0,24,Unknown,E10,0,0,0
+329,18.4,4.2,59,22.0,24,Unknown,E10,0,0,0
+330,39.5,4.2,58,22.0,25,Unknown,E10,0,0,0
+331,21.5,4.8,47,25.0,27,AC Sun,E10,1,0,1
+332,4.8,4.7,26,25.0,18,Unknown,E10,0,0,0
+333,100.9,4.7,87,21.93491124260355,22,Unknown,E10,0,0,0
+334,129.7,4.6,58,24.0,21,ac,E10,0,0,0
+335,16.6,3.8,43,21.93491124260355,16,Unknown,E10,0,0,0
+336,15.4,4.2,50,21.93491124260355,21,Unknown,E10,0,0,0
+337,16.0,3.7,45,22.0,17,Unknown,E10,0,0,0
+338,16.0,4.2,41,22.0,15,Unknown,E10,0,0,0
+339,15.4,4.1,45,22.0,24,Unknown,E10,0,0,0
+340,16.0,4.0,43,22.0,16,Unknown,E10,0,0,0
+341,21.0,3.8,37,22.0,21,Unknown,E10,0,0,0
+342,15.4,3.8,47,22.0,24,Unknown,E10,0,0,0
+343,16.0,3.8,42,22.0,17,Unknown,E10,0,0,0
+344,16.1,5.1,30,25.0,16,ac rain,E10,1,1,0
+345,16.0,4.0,42,22.0,15,Unknown,E10,0,0,0
+346,15.4,4.8,40,22.0,18,Unknown,E10,0,0,0
+347,17.2,3.9,35,22.0,16,Unknown,E10,0,0,0
+348,16.6,4.6,50,22.0,25,Unknown,E10,0,0,0
+349,18.3,4.3,46,22.0,16,Unknown,SP98,0,0,0
+350,16.1,4.8,36,22.0,18,rain,SP98,0,1,0
+351,16.0,4.1,46,22.0,17,Unknown,SP98,0,0,0
+352,16.3,4.0,35,22.0,23,Unknown,SP98,0,0,0
+353,16.0,3.7,44,22.0,16,Unknown,SP98,0,0,0
+354,18.3,4.3,46,22.0,23,Unknown,SP98,0,0,0
+355,4.5,5.2,23,22.0,23,sun,SP98,0,0,1
+356,17.0,4.2,48,22.0,16,Unknown,SP98,0,0,0
+357,6.1,5.0,35,21.93491124260355,18,Unknown,SP98,0,0,0
+358,6.1,5.0,33,22.0,24,sun,SP98,0,0,1
+359,17.3,4.2,36,22.0,22,Unknown,SP98,0,0,0
+360,6.0,4.8,27,22.0,17,Unknown,SP98,0,0,0
+361,16.0,4.1,45,22.0,15,Unknown,SP98,0,0,0
+362,15.4,4.9,55,22.0,18,Unknown,SP98,0,0,0
+363,15.4,4.3,39,22.0,23,Unknown,SP98,0,0,0
+364,16.0,3.9,35,22.0,18,Unknown,SP98,0,0,0
+365,15.4,4.5,52,22.0,26,Unknown,SP98,0,0,0
+366,16.6,4.1,48,21.93491124260355,30,sun ac,SP98,1,0,1
+367,15.4,5.0,48,21.93491124260355,31,ac,SP98,1,0,0
+368,16.0,4.0,43,22.0,21,ac,SP98,1,0,0
+369,15.4,4.5,42,22.0,30,Unknown,SP98,0,0,0
+370,16.0,3.6,43,22.0,19,Unknown,SP98,0,0,0
+371,20.9,4.1,33,22.0,21,Unknown,SP98,0,0,0
+372,32.1,3.9,47,22.0,26,Unknown,SP98,0,0,0
+373,15.3,6.6,16,24.0,27,ac,SP98,1,0,0
+374,28.5,4.0,44,25.0,23,ac,SP98,1,0,0
+375,11.9,3.7,33,25.0,19,Unknown,SP98,0,0,0
+376,14.5,4.3,36,25.0,22,Unknown,SP98,0,0,0
+377,16.6,4.1,49,22.0,26,sun,SP98,0,0,1
+378,16.2,4.4,39,21.93491124260355,17,ac,SP98,1,0,0
+379,16.7,3.8,44,21.93491124260355,23,sun,SP98,0,0,1
+380,8.3,5.0,52,21.93491124260355,27,Unknown,SP98,0,0,0
+381,5.5,3.7,33,21.93491124260355,28,sun,SP98,0,0,1
+382,13.6,3.7,33,21.93491124260355,28,sun,SP98,0,0,1
+383,16.0,3.7,39,21.93491124260355,18,Unknown,SP98,0,0,0
+384,16.1,4.3,38,25.0,31,AC,SP98,1,0,0
+385,16.0,3.8,45,25.0,19,Unknown,SP98,0,0,0
+386,15.4,4.6,42,25.0,31,AC,SP98,1,0,0
+387,14.7,5.0,25,25.0,30,AC,SP98,1,0,0