{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Etude des donnees du confinement\n",
    "\n",
    "\n",
    "## lecture de fichier csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/home/jovyan/work/module2/exo4\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "mypath=os.getcwd()\n",
    "print(mypath)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "C'est là qu'on est"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "hideOutput": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['exercice_python_en.org',\n",
       " 'exercice_fr.ipynb',\n",
       " 'exercice.ipynb',\n",
       " 'exercice_fr.Rmd',\n",
       " 'exercice_python_fr.org',\n",
       " 'exercice_R_en.org',\n",
       " 'exercice_R_fr.org',\n",
       " 'exercice_en.Rmd',\n",
       " 'exercice_en.ipynb',\n",
       " '.ipynb_checkpoints',\n",
       " 'donnees.csv']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.listdir(mypath)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/home/jovyan/work/module2/exo4/*.csv\n"
     ]
    }
   ],
   "source": [
    "print(mypath + \"/*.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['donnees.csv']\n"
     ]
    }
   ],
   "source": [
    "import glob\n",
    "csvlist = [f for f in glob.glob(\"*.csv\")]\n",
    "print(csvlist)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "donnees.csv\n"
     ]
    }
   ],
   "source": [
    "filename=csvlist[0]\n",
    "print(filename)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "scrolled": true
   },
   "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>date</th>\n",
       "      <th>sport</th>\n",
       "      <th>durée</th>\n",
       "      <th>FC moy</th>\n",
       "      <th>FC max</th>\n",
       "      <th>intensité ressentie</th>\n",
       "      <th>Unnamed: 7</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>-----</td>\n",
       "      <td>-----</td>\n",
       "      <td>------</td>\n",
       "      <td>------</td>\n",
       "      <td>-------</td>\n",
       "      <td>-------------------</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>18/03/2020</td>\n",
       "      <td>vélo</td>\n",
       "      <td>1:09:16</td>\n",
       "      <td>128</td>\n",
       "      <td>176</td>\n",
       "      <td>facile</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>19/03/2020</td>\n",
       "      <td>vélo</td>\n",
       "      <td>2:29:58</td>\n",
       "      <td>151</td>\n",
       "      <td>188</td>\n",
       "      <td>mod+</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>20/03/2020</td>\n",
       "      <td>vélo</td>\n",
       "      <td>0:44:05</td>\n",
       "      <td>144</td>\n",
       "      <td>176</td>\n",
       "      <td>facile</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>25/03/2020</td>\n",
       "      <td>crossfit</td>\n",
       "      <td>0:51:25</td>\n",
       "      <td>128</td>\n",
       "      <td>182</td>\n",
       "      <td>mod+</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0         date       sport      durée    FC moy    FC max   \\\n",
       "0         NaN         -----      -----      ------   ------    -------   \n",
       "1         NaN   18/03/2020        vélo    1:09:16       128       176    \n",
       "2         NaN   19/03/2020        vélo    2:29:58       151       188    \n",
       "3         NaN   20/03/2020        vélo    0:44:05       144       176    \n",
       "4         NaN   25/03/2020    crossfit    0:51:25       128       182    \n",
       "\n",
       "    intensité ressentie   Unnamed: 7  \n",
       "0   -------------------          NaN  \n",
       "1                facile          NaN  \n",
       "2                mod+            NaN  \n",
       "3                facile          NaN  \n",
       "4                  mod+          NaN  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "variable = pd.read_csv(r\"/home/jovyan/work/module2/exo4/donnees.csv\",sep=';')\n",
    "variable.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>sport</th>\n",
       "      <th>durée</th>\n",
       "      <th>FC moy</th>\n",
       "      <th>FC max</th>\n",
       "      <th>intensité ressentie</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>18/03/2020</td>\n",
       "      <td>vélo</td>\n",
       "      <td>1:09:16</td>\n",
       "      <td>128</td>\n",
       "      <td>176</td>\n",
       "      <td>facile</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>19/03/2020</td>\n",
       "      <td>vélo</td>\n",
       "      <td>2:29:58</td>\n",
       "      <td>151</td>\n",
       "      <td>188</td>\n",
       "      <td>mod+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>20/03/2020</td>\n",
       "      <td>vélo</td>\n",
       "      <td>0:44:05</td>\n",
       "      <td>144</td>\n",
       "      <td>176</td>\n",
       "      <td>facile</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>25/03/2020</td>\n",
       "      <td>crossfit</td>\n",
       "      <td>0:51:25</td>\n",
       "      <td>128</td>\n",
       "      <td>182</td>\n",
       "      <td>mod+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>26/03/2020</td>\n",
       "      <td>vélo</td>\n",
       "      <td>0:45:29</td>\n",
       "      <td>162</td>\n",
       "      <td>193</td>\n",
       "      <td>mod++</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date      sport     durée   FC moy   FC max  intensité ressentie \n",
       "0  18/03/2020       vélo   1:09:16       128      176              facile \n",
       "1  19/03/2020       vélo   2:29:58       151      188              mod+   \n",
       "2  20/03/2020       vélo   0:44:05       144      176              facile \n",
       "3  25/03/2020   crossfit   0:51:25       128      182                mod+ \n",
       "4  26/03/2020       vélo   0:45:29       162      193               mod++ "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "variable = pd.read_csv(r\"/home/jovyan/work/module2/exo4/donnees.csv\",sep=';',header=0,usecols=[1,2,3,4,5,6],skiprows=[1],skipinitialspace=1)\n",
    "variable.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "hideOutput": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[['18/03/2020 ' 'vélo ' '1:09:16 ' 128 176 'facile ']\n",
      " ['19/03/2020 ' 'vélo ' '2:29:58 ' 151 188 'mod+   ']\n",
      " ['20/03/2020 ' 'vélo ' '0:44:05 ' 144 176 'facile ']\n",
      " ['25/03/2020 ' 'crossfit ' '0:51:25 ' 128 182 'mod+ ']\n",
      " ['26/03/2020 ' 'vélo ' '0:45:29 ' 162 193 'mod++ ']\n",
      " ['30/03/2020 ' 'cap ' '0:39:04 ' 158 189 'mod++ ']\n",
      " ['30/03/2020 ' 'crossfit ' '0:29:14 ' 130 169 'mod+ ']\n",
      " ['31/03/2020 ' 'vélo ' '0:41:52 ' 156 181 'mod+ ']\n",
      " ['01/04/2020 ' 'vélo ' '0:39:06 ' 168 190 'mod++ ']]\n"
     ]
    }
   ],
   "source": [
    "mat=variable.values\n",
    "print(mat)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "9\n"
     ]
    }
   ],
   "source": [
    "[nrows,ncols]=mat.shape\n",
    "print(nrows)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['18/03/2020 ', '19/03/2020 ', '20/03/2020 ', '25/03/2020 ',\n",
       "       '26/03/2020 ', '30/03/2020 ', '30/03/2020 ', '31/03/2020 ',\n",
       "       '01/04/2020 '], dtype=object)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mat[:,0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'18/03/2020 '"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mat[0,0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "datetime.datetime(2020, 3, 18, 0, 0)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from datetime import datetime, date, time, timezone\n",
    "datetime.strptime(mat[0,0],\"%d/%m/%Y \")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}