Exercice sur le traitement de données

traitement-données.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### Exercice 2 : La course d'athlétisme"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "data = [48.65, 49.20, 50, 50.12, 50.13, 50.45, 51, 51.80, 51.85, 51.90,\n        52.05, 52.20, 52.60, 53.28, 54.80]\nresults = pd.Series(data)\nresults.describe()",
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 2,
          "data": {
            "text/plain": "count    15.000000\nmean     51.335333\nstd       1.621793\nmin      48.650000\n25%      50.125000\n50%      51.800000\n75%      52.125000\nmax      54.800000\ndtype: float64"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "étendue = results.max() - results.min()\nmoyenne = round(results.mean(), 2)\nmédiane = results.median()",
      "execution_count": 3,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "part_lents = len(results[results < 52.50]) / len(results) * 100\nprint(f'{part_lents}% de coureurs ont mis moins de  52,50 secondes pour le 400m')",
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": "80.0% de coureurs ont mis moins de  52,50 secondes pour le 400m\n",
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### Exercice 3"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "intervals = pd.interval_range(start=0, end=120, freq=30, closed='left')\neffectifs = [106, 671 - (106 + 235 + 144), 235, 144]\ntemps_travail = pd.DataFrame({'Durée de travail (mn)': intervals,\n                              'Centre de classe' : intervals.mid,\n                              'Effectifs': effectifs})\ntemps_travail['Fréquences (%)'] = round(temps_travail['Effectifs'] / sum(effectifs) * 100, 0)\ntemps_travail",
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 5,
          "data": {
            "text/plain": "  Durée de travail (mn)  Centre de classe  Effectifs  Fréquences (%)\n0               [0, 30)              15.0        106            16.0\n1              [30, 60)              45.0        186            28.0\n2              [60, 90)              75.0        235            35.0\n3             [90, 120)             105.0        144            21.0",
            "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>Durée de travail (mn)</th>\n      <th>Centre de classe</th>\n      <th>Effectifs</th>\n      <th>Fréquences (%)</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>[0, 30)</td>\n      <td>15.0</td>\n      <td>106</td>\n      <td>16.0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>[30, 60)</td>\n      <td>45.0</td>\n      <td>186</td>\n      <td>28.0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>[60, 90)</td>\n      <td>75.0</td>\n      <td>235</td>\n      <td>35.0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>[90, 120)</td>\n      <td>105.0</td>\n      <td>144</td>\n      <td>21.0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "moyenne = round(np.average(temps_travail['Centre de classe'], weights=temps_travail['Effectifs']), 0)\nprint(f'Un élève passe en moyenne {moyenne} minutes par jour pour faire ses devoirs.')",
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": "Un élève passe en moyenne 64.0 minutes par jour pour faire ses devoirs.\n",
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### Exercice 4"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "age_intervals = pd.interval_range(start=0, end= 90, freq=10, closed='left')\neffectifs = [27, 45, 48, 39, 42, 36, 33, 24, 6]\nskieurs = pd.DataFrame({'Âge': age_intervals,\n                        'Centre de classe': age_intervals.mid,\n                        'Effectifs': effectifs})\nskieurs['Eff. cumulés croissants'] = skieurs['Effectifs'].cumsum()\nskieurs",
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 7,
          "data": {
            "text/plain": "        Âge  Centre de classe  Effectifs  Eff. cumulés croissants\n0   [0, 10)               5.0         27                       27\n1  [10, 20)              15.0         45                       72\n2  [20, 30)              25.0         48                      120\n3  [30, 40)              35.0         39                      159\n4  [40, 50)              45.0         42                      201\n5  [50, 60)              55.0         36                      237\n6  [60, 70)              65.0         33                      270\n7  [70, 80)              75.0         24                      294\n8  [80, 90)              85.0          6                      300",
            "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>Âge</th>\n      <th>Centre de classe</th>\n      <th>Effectifs</th>\n      <th>Eff. cumulés croissants</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>[0, 10)</td>\n      <td>5.0</td>\n      <td>27</td>\n      <td>27</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>[10, 20)</td>\n      <td>15.0</td>\n      <td>45</td>\n      <td>72</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>[20, 30)</td>\n      <td>25.0</td>\n      <td>48</td>\n      <td>120</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>[30, 40)</td>\n      <td>35.0</td>\n      <td>39</td>\n      <td>159</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>[40, 50)</td>\n      <td>45.0</td>\n      <td>42</td>\n      <td>201</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>[50, 60)</td>\n      <td>55.0</td>\n      <td>36</td>\n      <td>237</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>[60, 70)</td>\n      <td>65.0</td>\n      <td>33</td>\n      <td>270</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>[70, 80)</td>\n      <td>75.0</td>\n      <td>24</td>\n      <td>294</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>[80, 90)</td>\n      <td>85.0</td>\n      <td>6</td>\n      <td>300</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "age_moyen = np.average(skieurs['Centre de classe'], weights=skieurs['Effectifs'])\nprint(f\"L'âge moyen des skieurs est de {age_moyen} ans.\")",
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "text": "L'âge moyen des skieurs est de 39.0 ans.\n",
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "jeunes_skieurs = skieurs[skieurs['Âge'].apply(lambda i: i.overlaps(pd.Interval(left=0, right=20, closed='left')))]\npercent = sum(jeunes_skieurs['Effectifs']) / sum(skieurs['Effectifs']) * 100\nprint(f\"La fréquence en pourcentage de skieurs ayant moins de 20 ans est de  {percent} %\")",
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": "La fréquence en pourcentage de skieurs ayant moins de 20 ans est de  24.0 %\n",
          "name": "stdout"
        }
      ]
    }
  ],
  "metadata": {
    "interpreter": {
      "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3 (ipykernel)",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.9.10",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "traitement-données.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}