lafrite
/
2017-2018
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
2017-2018/Notes/DNB blanc 1.ipynb

1085 lines
388 KiB
Plaintext
Raw Normal View History

Start analyse DNB blanc 1 scores
2018-04-10 11:22:39 +00:00
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from math import ceil\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"%matplotlib inline\n",
"from pprint import pprint"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Analyse des résultats du DNB blanc 1"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"gene = [str(i) for i in range(301, 305)] + [str(i) for i in range(309, 312)]\n",
"pro = [str(i) for i in range(305, 309)] + [\"312\"]\n",
"coeff = {\n",
" \"Français\": 100,\n",
" \"HG\": 50,\n",
" \"Maths\": 100,\n",
" \"SVT\": 25,\n",
" \"Physique\": 25,\n",
" \"Techno\": 25\n",
"}\n",
"matieres = list(coeff.keys())\n",
"norm_matieres = [\"_\"+m for m in matieres]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"sheets_gene = pd.read_excel(\"./DNB blanc 1.xls\",\n",
" sheetname=gene,\n",
" skiprows=[0],\n",
" parse_cols=\"B,C,E,G,I,K,M\",\n",
" )\n",
"sheets_pro = pd.read_excel(\"./DNB blanc 1.xls\",\n",
" sheetname=pro,\n",
" header=1,\n",
" parse_cols=\"B,C,E,G,I,K,M\",\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def orderedDict2df(sheets):\n",
" dfs = []\n",
" for tribe, df in sheets.items():\n",
" df['classe'] = tribe\n",
" dfs.append(df)\n",
" return pd.concat(dfs)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"gene_df = orderedDict2df(sheets_gene)\n",
"pro_df = orderedDict2df(sheets_pro)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>Français: /100</th>\n",
" <th>HG: /50</th>\n",
" <th>Maths: /100</th>\n",
" <th>SVT: /25</th>\n",
" <th>Phys. : /25</th>\n",
" <th>Techno: /25</th>\n",
" <th>classe</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>ABDALLAH Faouzia</td>\n",
" <td>38</td>\n",
" <td>22</td>\n",
" <td>28</td>\n",
" <td>16.5</td>\n",
" <td>11</td>\n",
" <td>11.5</td>\n",
" <td>301</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>ABDALLAH Sarati</td>\n",
" <td>49</td>\n",
" <td>23</td>\n",
" <td>39</td>\n",
" <td>11.5</td>\n",
" <td>15</td>\n",
" <td>13.5</td>\n",
" <td>301</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ABDOU SOUFFE Momed</td>\n",
" <td>64</td>\n",
" <td>41</td>\n",
" <td>89</td>\n",
" <td>25</td>\n",
" <td>19</td>\n",
" <td>18.5</td>\n",
" <td>301</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>ABDOUL-KADER Sinina</td>\n",
" <td>61.5</td>\n",
" <td>33</td>\n",
" <td>52</td>\n",
" <td>15.5</td>\n",
" <td>16</td>\n",
" <td>18.5</td>\n",
" <td>301</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>ALI Aïda</td>\n",
" <td>54</td>\n",
" <td>43</td>\n",
" <td>50</td>\n",
" <td>17.5</td>\n",
" <td>14</td>\n",
" <td>19.5</td>\n",
" <td>301</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 Français: /100 HG: /50 Maths: /100 SVT: /25 \\\n",
"0 ABDALLAH Faouzia 38 22 28 16.5 \n",
"1 ABDALLAH Sarati 49 23 39 11.5 \n",
"2 ABDOU SOUFFE Momed 64 41 89 25 \n",
"3 ABDOUL-KADER Sinina 61.5 33 52 15.5 \n",
"4 ALI Aïda 54 43 50 17.5 \n",
"\n",
" Phys. : /25 Techno: /25 classe \n",
"0 11 11.5 301 \n",
"1 15 13.5 301 \n",
"2 19 18.5 301 \n",
"3 16 18.5 301 \n",
"4 14 19.5 301 "
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gene_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Nom</th>\n",
" <th>Français</th>\n",
" <th>HG</th>\n",
" <th>Maths</th>\n",
" <th>SVT</th>\n",
" <th>Physique</th>\n",
" <th>Techno</th>\n",
" <th>Classe</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>ABDALLAH Faouzia</td>\n",
" <td>38</td>\n",
" <td>22</td>\n",
" <td>28</td>\n",
" <td>16.5</td>\n",
" <td>11</td>\n",
" <td>11.5</td>\n",
" <td>301</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>ABDALLAH Sarati</td>\n",
" <td>49</td>\n",
" <td>23</td>\n",
" <td>39</td>\n",
" <td>11.5</td>\n",
" <td>15</td>\n",
" <td>13.5</td>\n",
" <td>301</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ABDOU SOUFFE Momed</td>\n",
" <td>64</td>\n",
" <td>41</td>\n",
" <td>89</td>\n",
" <td>25</td>\n",
" <td>19</td>\n",
" <td>18.5</td>\n",
" <td>301</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>ABDOUL-KADER Sinina</td>\n",
" <td>61.5</td>\n",
" <td>33</td>\n",
" <td>52</td>\n",
" <td>15.5</td>\n",
" <td>16</td>\n",
" <td>18.5</td>\n",
" <td>301</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>ALI Aïda</td>\n",
" <td>54</td>\n",
" <td>43</td>\n",
" <td>50</td>\n",
" <td>17.5</td>\n",
" <td>14</td>\n",
" <td>19.5</td>\n",
" <td>301</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Nom Français HG Maths SVT Physique Techno Classe\n",
"0 ABDALLAH Faouzia 38 22 28 16.5 11 11.5 301\n",
"1 ABDALLAH Sarati 49 23 39 11.5 15 13.5 301\n",
"2 ABDOU SOUFFE Momed 64 41 89 25 19 18.5 301\n",
"3 ABDOUL-KADER Sinina 61.5 33 52 15.5 16 18.5 301\n",
"4 ALI Aïda 54 43 50 17.5 14 19.5 301"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gene_df.columns = [\"Nom\", \"Français\", \"HG\", \"Maths\", \"SVT\", \"Physique\", \"Techno\", \"Classe\"]\n",
"gene_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Nom</th>\n",
" <th>Français</th>\n",
" <th>HG</th>\n",
" <th>Maths</th>\n",
" <th>SVT</th>\n",
" <th>Physique</th>\n",
" <th>Techno</th>\n",
" <th>Classe</th>\n",
" <th>_Français</th>\n",
" <th>_HG</th>\n",
" <th>_Maths</th>\n",
" <th>_SVT</th>\n",
" <th>_Physique</th>\n",
" <th>_Techno</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>ABDALLAH Faouzia</td>\n",
" <td>38.0</td>\n",
" <td>22.0</td>\n",
" <td>28.0</td>\n",
" <td>16.5</td>\n",
" <td>11.0</td>\n",
" <td>11.5</td>\n",
" <td>301</td>\n",
" <td>0.380</td>\n",
" <td>0.44</td>\n",
" <td>0.28</td>\n",
" <td>0.66</td>\n",
" <td>0.44</td>\n",
" <td>0.46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>ABDALLAH Sarati</td>\n",
" <td>49.0</td>\n",
" <td>23.0</td>\n",
" <td>39.0</td>\n",
" <td>11.5</td>\n",
" <td>15.0</td>\n",
" <td>13.5</td>\n",
" <td>301</td>\n",
" <td>0.490</td>\n",
" <td>0.46</td>\n",
" <td>0.39</td>\n",
" <td>0.46</td>\n",
" <td>0.60</td>\n",
" <td>0.54</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ABDOU SOUFFE Momed</td>\n",
" <td>64.0</td>\n",
" <td>41.0</td>\n",
" <td>89.0</td>\n",
" <td>25.0</td>\n",
" <td>19.0</td>\n",
" <td>18.5</td>\n",
" <td>301</td>\n",
" <td>0.640</td>\n",
" <td>0.82</td>\n",
" <td>0.89</td>\n",
" <td>1.00</td>\n",
" <td>0.76</td>\n",
" <td>0.74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>ABDOUL-KADER Sinina</td>\n",
" <td>61.5</td>\n",
" <td>33.0</td>\n",
" <td>52.0</td>\n",
" <td>15.5</td>\n",
" <td>16.0</td>\n",
" <td>18.5</td>\n",
" <td>301</td>\n",
" <td>0.615</td>\n",
" <td>0.66</td>\n",
" <td>0.52</td>\n",
" <td>0.62</td>\n",
" <td>0.64</td>\n",
" <td>0.74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>ALI Aïda</td>\n",
" <td>54.0</td>\n",
" <td>43.0</td>\n",
" <td>50.0</td>\n",
" <td>17.5</td>\n",
" <td>14.0</td>\n",
" <td>19.5</td>\n",
" <td>301</td>\n",
" <td>0.540</td>\n",
" <td>0.86</td>\n",
" <td>0.50</td>\n",
" <td>0.70</td>\n",
" <td>0.56</td>\n",
" <td>0.78</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Nom Français HG Maths SVT Physique Techno Classe \\\n",
"0 ABDALLAH Faouzia 38.0 22.0 28.0 16.5 11.0 11.5 301 \n",
"1 ABDALLAH Sarati 49.0 23.0 39.0 11.5 15.0 13.5 301 \n",
"2 ABDOU SOUFFE Momed 64.0 41.0 89.0 25.0 19.0 18.5 301 \n",
"3 ABDOUL-KADER Sinina 61.5 33.0 52.0 15.5 16.0 18.5 301 \n",
"4 ALI Aïda 54.0 43.0 50.0 17.5 14.0 19.5 301 \n",
"\n",
" _Français _HG _Maths _SVT _Physique _Techno \n",
"0 0.380 0.44 0.28 0.66 0.44 0.46 \n",
"1 0.490 0.46 0.39 0.46 0.60 0.54 \n",
"2 0.640 0.82 0.89 1.00 0.76 0.74 \n",
"3 0.615 0.66 0.52 0.62 0.64 0.74 \n",
"4 0.540 0.86 0.50 0.70 0.56 0.78 "
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"for m, coef in coeff.items():\n",
" gene_df[m] = pd.to_numeric(gene_df[m], errors='coerce')\n",
" gene_df[\"_\"+m] = gene_df[m]/coef\n",
"gene_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"gene_df = gene_df = gene_df.assign(\n",
" total = gene_df[matieres].sum(1),\n",
" maximum = 325\n",
")\n",
"gene_df = gene_df.assign(\n",
" normalisee = gene_df[\"total\"]/gene_df[\"maximum\"]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Nom</th>\n",
" <th>Français</th>\n",
" <th>HG</th>\n",
" <th>Maths</th>\n",
" <th>SVT</th>\n",
" <th>Physique</th>\n",
" <th>Techno</th>\n",
" <th>Classe</th>\n",
" <th>_Français</th>\n",
" <th>_HG</th>\n",
" <th>_Maths</th>\n",
" <th>_SVT</th>\n",
" <th>_Physique</th>\n",
" <th>_Techno</th>\n",
" <th>maximum</th>\n",
" <th>total</th>\n",
" <th>normalisee</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>ABDALLAH Faouzia</td>\n",
" <td>38.0</td>\n",
" <td>22.0</td>\n",
" <td>28.0</td>\n",
" <td>16.5</td>\n",
" <td>11.0</td>\n",
" <td>11.5</td>\n",
" <td>301</td>\n",
" <td>0.380</td>\n",
" <td>0.44</td>\n",
" <td>0.28</td>\n",
" <td>0.66</td>\n",
" <td>0.44</td>\n",
" <td>0.46</td>\n",
" <td>325</td>\n",
" <td>127.0</td>\n",
" <td>0.390769</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>ABDALLAH Sarati</td>\n",
" <td>49.0</td>\n",
" <td>23.0</td>\n",
" <td>39.0</td>\n",
" <td>11.5</td>\n",
" <td>15.0</td>\n",
" <td>13.5</td>\n",
" <td>301</td>\n",
" <td>0.490</td>\n",
" <td>0.46</td>\n",
" <td>0.39</td>\n",
" <td>0.46</td>\n",
" <td>0.60</td>\n",
" <td>0.54</td>\n",
" <td>325</td>\n",
" <td>151.0</td>\n",
" <td>0.464615</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ABDOU SOUFFE Momed</td>\n",
" <td>64.0</td>\n",
" <td>41.0</td>\n",
" <td>89.0</td>\n",
" <td>25.0</td>\n",
" <td>19.0</td>\n",
" <td>18.5</td>\n",
" <td>301</td>\n",
" <td>0.640</td>\n",
" <td>0.82</td>\n",
" <td>0.89</td>\n",
" <td>1.00</td>\n",
" <td>0.76</td>\n",
" <td>0.74</td>\n",
" <td>325</td>\n",
" <td>256.5</td>\n",
" <td>0.789231</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>ABDOUL-KADER Sinina</td>\n",
" <td>61.5</td>\n",
" <td>33.0</td>\n",
" <td>52.0</td>\n",
" <td>15.5</td>\n",
" <td>16.0</td>\n",
" <td>18.5</td>\n",
" <td>301</td>\n",
" <td>0.615</td>\n",
" <td>0.66</td>\n",
" <td>0.52</td>\n",
" <td>0.62</td>\n",
" <td>0.64</td>\n",
" <td>0.74</td>\n",
" <td>325</td>\n",
" <td>196.5</td>\n",
" <td>0.604615</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>ALI Aïda</td>\n",
" <td>54.0</td>\n",
" <td>43.0</td>\n",
" <td>50.0</td>\n",
" <td>17.5</td>\n",
" <td>14.0</td>\n",
" <td>19.5</td>\n",
" <td>301</td>\n",
" <td>0.540</td>\n",
" <td>0.86</td>\n",
" <td>0.50</td>\n",
" <td>0.70</td>\n",
" <td>0.56</td>\n",
" <td>0.78</td>\n",
" <td>325</td>\n",
" <td>198.0</td>\n",
" <td>0.609231</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Nom Français HG Maths SVT Physique Techno Classe \\\n",
"0 ABDALLAH Faouzia 38.0 22.0 28.0 16.5 11.0 11.5 301 \n",
"1 ABDALLAH Sarati 49.0 23.0 39.0 11.5 15.0 13.5 301 \n",
"2 ABDOU SOUFFE Momed 64.0 41.0 89.0 25.0 19.0 18.5 301 \n",
"3 ABDOUL-KADER Sinina 61.5 33.0 52.0 15.5 16.0 18.5 301 \n",
"4 ALI Aïda 54.0 43.0 50.0 17.5 14.0 19.5 301 \n",
"\n",
" _Français _HG _Maths _SVT _Physique _Techno maximum total \\\n",
"0 0.380 0.44 0.28 0.66 0.44 0.46 325 127.0 \n",
"1 0.490 0.46 0.39 0.46 0.60 0.54 325 151.0 \n",
"2 0.640 0.82 0.89 1.00 0.76 0.74 325 256.5 \n",
"3 0.615 0.66 0.52 0.62 0.64 0.74 325 196.5 \n",
"4 0.540 0.86 0.50 0.70 0.56 0.78 325 198.0 \n",
"\n",
" normalisee \n",
"0 0.390769 \n",
"1 0.464615 \n",
"2 0.789231 \n",
"3 0.604615 \n",
"4 0.609231 "
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gene_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<matplotlib.axes._subplots.AxesSubplot at 0x7fd710b74ac8>"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAW4AAAD8CAYAAABXe05zAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nVsouCgCQrzC4zWyPpNs
"text/plain": [
"<matplotlib.figure.Figure at 0x7fd7108b2fd0>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"gene_df[\"total\"].hist(bins=150)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Français</th>\n",
" <th>HG</th>\n",
" <th>Maths</th>\n",
" <th>SVT</th>\n",
" <th>Physique</th>\n",
" <th>Techno</th>\n",
" <th>_Français</th>\n",
" <th>_HG</th>\n",
" <th>_Maths</th>\n",
" <th>_SVT</th>\n",
" <th>_Physique</th>\n",
" <th>_Techno</th>\n",
" <th>maximum</th>\n",
" <th>total</th>\n",
" <th>normalisee</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>179.000000</td>\n",
" <td>180.000000</td>\n",
" <td>179.000000</td>\n",
" <td>179.000000</td>\n",
" <td>179.000000</td>\n",
" <td>179.000000</td>\n",
" <td>179.000000</td>\n",
" <td>180.000000</td>\n",
" <td>179.000000</td>\n",
" <td>179.000000</td>\n",
" <td>179.000000</td>\n",
" <td>179.000000</td>\n",
" <td>188.0</td>\n",
" <td>180.000000</td>\n",
" <td>180.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>45.474860</td>\n",
" <td>22.427778</td>\n",
" <td>34.597765</td>\n",
" <td>12.740223</td>\n",
" <td>10.522346</td>\n",
" <td>12.709497</td>\n",
" <td>0.454749</td>\n",
" <td>0.448556</td>\n",
" <td>0.345978</td>\n",
" <td>0.509609</td>\n",
" <td>0.420894</td>\n",
" <td>0.508380</td>\n",
" <td>325.0</td>\n",
" <td>137.827778</td>\n",
" <td>0.424085</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>15.803416</td>\n",
" <td>9.165170</td>\n",
" <td>17.255359</td>\n",
" <td>5.063457</td>\n",
" <td>4.919812</td>\n",
" <td>5.013686</td>\n",
" <td>0.158034</td>\n",
" <td>0.183303</td>\n",
" <td>0.172554</td>\n",
" <td>0.202538</td>\n",
" <td>0.196792</td>\n",
" <td>0.200547</td>\n",
" <td>0.0</td>\n",
" <td>46.713537</td>\n",
" <td>0.143734</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>2.000000</td>\n",
" <td>0.000000</td>\n",
" <td>1.000000</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>2.500000</td>\n",
" <td>0.020000</td>\n",
" <td>0.000000</td>\n",
" <td>0.010000</td>\n",
" <td>0.080000</td>\n",
" <td>0.080000</td>\n",
" <td>0.100000</td>\n",
" <td>325.0</td>\n",
" <td>13.000000</td>\n",
" <td>0.040000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>37.250000</td>\n",
" <td>14.750000</td>\n",
" <td>23.000000</td>\n",
" <td>9.000000</td>\n",
" <td>6.000000</td>\n",
" <td>8.500000</td>\n",
" <td>0.372500</td>\n",
" <td>0.295000</td>\n",
" <td>0.230000</td>\n",
" <td>0.360000</td>\n",
" <td>0.240000</td>\n",
" <td>0.340000</td>\n",
" <td>325.0</td>\n",
" <td>106.000000</td>\n",
" <td>0.326154</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>47.000000</td>\n",
" <td>22.500000</td>\n",
" <td>30.000000</td>\n",
" <td>12.000000</td>\n",
" <td>10.000000</td>\n",
" <td>12.500000</td>\n",
" <td>0.470000</td>\n",
" <td>0.450000</td>\n",
" <td>0.300000</td>\n",
" <td>0.480000</td>\n",
" <td>0.400000</td>\n",
" <td>0.500000</td>\n",
" <td>325.0</td>\n",
" <td>136.000000</td>\n",
" <td>0.418462</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>55.250000</td>\n",
" <td>28.250000</td>\n",
" <td>42.500000</td>\n",
" <td>16.000000</td>\n",
" <td>14.000000</td>\n",
" <td>16.500000</td>\n",
" <td>0.552500</td>\n",
" <td>0.565000</td>\n",
" <td>0.425000</td>\n",
" <td>0.640000</td>\n",
" <td>0.560000</td>\n",
" <td>0.660000</td>\n",
" <td>325.0</td>\n",
" <td>169.500000</td>\n",
" <td>0.521538</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>88.000000</td>\n",
" <td>43.000000</td>\n",
" <td>90.000000</td>\n",
" <td>25.000000</td>\n",
" <td>24.000000</td>\n",
" <td>23.500000</td>\n",
" <td>0.880000</td>\n",
" <td>0.860000</td>\n",
" <td>0.900000</td>\n",
" <td>1.000000</td>\n",
" <td>0.960000</td>\n",
" <td>0.940000</td>\n",
" <td>325.0</td>\n",
" <td>261.000000</td>\n",
" <td>0.803077</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Français HG Maths SVT Physique Techno \\\n",
"count 179.000000 180.000000 179.000000 179.000000 179.000000 179.000000 \n",
"mean 45.474860 22.427778 34.597765 12.740223 10.522346 12.709497 \n",
"std 15.803416 9.165170 17.255359 5.063457 4.919812 5.013686 \n",
"min 2.000000 0.000000 1.000000 2.000000 2.000000 2.500000 \n",
"25% 37.250000 14.750000 23.000000 9.000000 6.000000 8.500000 \n",
"50% 47.000000 22.500000 30.000000 12.000000 10.000000 12.500000 \n",
"75% 55.250000 28.250000 42.500000 16.000000 14.000000 16.500000 \n",
"max 88.000000 43.000000 90.000000 25.000000 24.000000 23.500000 \n",
"\n",
" _Français _HG _Maths _SVT _Physique _Techno \\\n",
"count 179.000000 180.000000 179.000000 179.000000 179.000000 179.000000 \n",
"mean 0.454749 0.448556 0.345978 0.509609 0.420894 0.508380 \n",
"std 0.158034 0.183303 0.172554 0.202538 0.196792 0.200547 \n",
"min 0.020000 0.000000 0.010000 0.080000 0.080000 0.100000 \n",
"25% 0.372500 0.295000 0.230000 0.360000 0.240000 0.340000 \n",
"50% 0.470000 0.450000 0.300000 0.480000 0.400000 0.500000 \n",
"75% 0.552500 0.565000 0.425000 0.640000 0.560000 0.660000 \n",
"max 0.880000 0.860000 0.900000 1.000000 0.960000 0.940000 \n",
"\n",
" maximum total normalisee \n",
"count 188.0 180.000000 180.000000 \n",
"mean 325.0 137.827778 0.424085 \n",
"std 0.0 46.713537 0.143734 \n",
"min 325.0 13.000000 0.040000 \n",
"25% 325.0 106.000000 0.326154 \n",
"50% 325.0 136.000000 0.418462 \n",
"75% 325.0 169.500000 0.521538 \n",
"max 325.0 261.000000 0.803077 "
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gene_df.describe()"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<matplotlib.axes._subplots.AxesSubplot at 0x7fd7108bc208>"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD9CAYAAABHnDf0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nlpHUANwEnA00A22Smkc
"text/plain": [
"<matplotlib.figure.Figure at 0x7fd7108c4f98>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"gene_df[norm_matieres].boxplot()"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from pandas.plotting import scatter_matrix"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7fd705b06c50>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd7052fec18>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd7057ef208>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd70576f3c8>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd70577f400>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd70577f358>],\n",
" [<matplotlib.axes._subplots.AxesSubplot object at 0x7fd705687ba8>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd705605240>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd7055655c0>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd705563278>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd7054c0ba8>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd70547af98>],\n",
" [<matplotlib.axes._subplots.AxesSubplot object at 0x7fd70540f518>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd705420550>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704f7d358>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704ed6a20>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704e490b8>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704e2d438>],\n",
" [<matplotlib.axes._subplots.AxesSubplot object at 0x7fd704da60f0>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704d05a20>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704d41e10>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704c54390>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704c62320>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd706534c18>],\n",
" [<matplotlib.axes._subplots.AxesSubplot object at 0x7fd7069245c0>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704b6b1d0>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704b42a90>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704ab4128>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704a114a8>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704990160>],\n",
" [<matplotlib.axes._subplots.AxesSubplot object at 0x7fd70496fa90>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd70492de80>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd7048be400>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd70484e438>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd70478c160>,\n",
" <matplotlib.axes._subplots.AxesSubplot object at 0x7fd704768908>]], dtype=object)"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA3YAAANgCAYAAABgIvoLAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\neg2JTJ52x9rHkru3bmx
"text/plain": [
"<matplotlib.figure.Figure at 0x7fd70d281b38>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"scatter_matrix(gene_df[matieres], alpha=0.5, figsize=(15, 15), diagonal='kde')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"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
}