{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Incidence de la mortalité des femmes fumeuses et non fumeuses" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Partie 1" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "%matplotlib inline\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "import isoweek" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "data_url = \"https://gitlab.inria.fr/learninglab/mooc-rr/mooc-rr-ressources/-/raw/master/module3/Practical_session/Subject6_smoking.csv?inline=false\"\n", "data_file = \"mortalite_femmes_fumeuses_ou_non.csv\"\n", "\n", "import os\n", "import urllib.request\n", "if not os.path.exists(data_file):\n", " urllib.request.urlretrieve(data_url, data_file)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Représentation du CSV étudié :" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
SmokerStatusAge
0YesAlive21.0
1YesAlive19.3
2NoDead57.5
3NoAlive47.1
4YesAlive81.4
5NoAlive36.8
6NoAlive23.8
7YesDead57.5
8YesAlive24.8
9YesAlive49.5
10YesAlive30.0
11NoDead66.0
12YesAlive49.2
13NoAlive58.4
14NoDead60.6
15NoAlive25.1
16NoAlive43.5
17NoAlive27.1
18NoAlive58.3
19YesAlive65.7
20NoDead73.2
21YesAlive38.3
22NoAlive33.4
23YesDead62.3
24NoAlive18.0
25NoAlive56.2
26YesAlive59.2
27NoAlive25.8
28NoDead36.9
29NoAlive20.2
............
1284YesDead36.0
1285YesAlive48.3
1286NoAlive63.1
1287NoAlive60.8
1288YesDead39.3
1289NoAlive36.7
1290NoAlive63.8
1291NoDead71.3
1292NoAlive57.7
1293NoAlive63.2
1294NoAlive46.6
1295YesDead82.4
1296YesAlive38.3
1297YesAlive32.7
1298NoAlive39.7
1299YesDead60.0
1300NoDead71.0
1301NoAlive20.5
1302NoAlive44.4
1303YesAlive31.2
1304YesAlive47.8
1305YesAlive60.9
1306NoDead61.4
1307YesAlive43.0
1308NoAlive42.1
1309YesAlive35.9
1310NoAlive22.3
1311YesDead62.1
1312NoDead88.6
1313NoAlive39.1
\n", "

1314 rows × 3 columns

\n", "
" ], "text/plain": [ " Smoker Status Age\n", "0 Yes Alive 21.0\n", "1 Yes Alive 19.3\n", "2 No Dead 57.5\n", "3 No Alive 47.1\n", "4 Yes Alive 81.4\n", "5 No Alive 36.8\n", "6 No Alive 23.8\n", "7 Yes Dead 57.5\n", "8 Yes Alive 24.8\n", "9 Yes Alive 49.5\n", "10 Yes Alive 30.0\n", "11 No Dead 66.0\n", "12 Yes Alive 49.2\n", "13 No Alive 58.4\n", "14 No Dead 60.6\n", "15 No Alive 25.1\n", "16 No Alive 43.5\n", "17 No Alive 27.1\n", "18 No Alive 58.3\n", "19 Yes Alive 65.7\n", "20 No Dead 73.2\n", "21 Yes Alive 38.3\n", "22 No Alive 33.4\n", "23 Yes Dead 62.3\n", "24 No Alive 18.0\n", "25 No Alive 56.2\n", "26 Yes Alive 59.2\n", "27 No Alive 25.8\n", "28 No Dead 36.9\n", "29 No Alive 20.2\n", "... ... ... ...\n", "1284 Yes Dead 36.0\n", "1285 Yes Alive 48.3\n", "1286 No Alive 63.1\n", "1287 No Alive 60.8\n", "1288 Yes Dead 39.3\n", "1289 No Alive 36.7\n", "1290 No Alive 63.8\n", "1291 No Dead 71.3\n", "1292 No Alive 57.7\n", "1293 No Alive 63.2\n", "1294 No Alive 46.6\n", "1295 Yes Dead 82.4\n", "1296 Yes Alive 38.3\n", "1297 Yes Alive 32.7\n", "1298 No Alive 39.7\n", "1299 Yes Dead 60.0\n", "1300 No Dead 71.0\n", "1301 No Alive 20.5\n", "1302 No Alive 44.4\n", "1303 Yes Alive 31.2\n", "1304 Yes Alive 47.8\n", "1305 Yes Alive 60.9\n", "1306 No Dead 61.4\n", "1307 Yes Alive 43.0\n", "1308 No Alive 42.1\n", "1309 Yes Alive 35.9\n", "1310 No Alive 22.3\n", "1311 Yes Dead 62.1\n", "1312 No Dead 88.6\n", "1313 No Alive 39.1\n", "\n", "[1314 rows x 3 columns]" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data = pd.read_csv(data_file, encoding = 'iso-8859-1', error_bad_lines=False)\n", "raw_data" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
SmokerStatusAge
\n", "
" ], "text/plain": [ "Empty DataFrame\n", "Columns: [Smoker, Status, Age]\n", "Index: []" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data[raw_data.isnull().any(axis=1)]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Aucune ligne vide dans le csv." ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "No 732\n", "Yes 582\n", "Name: Smoker, dtype: int64" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tableau = raw_data['Smoker'].value_counts()\n", "tableau" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "On représente ici le nombre total de femmes vivantes et décédées sur la période en fonction de leur habitude de tabagisme." ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
SmokerStatusNombre
0NoAlive502
1NoDead230
2YesAlive443
3YesDead139
\n", "
" ], "text/plain": [ " Smoker Status Nombre\n", "0 No Alive 502\n", "1 No Dead 230\n", "2 Yes Alive 443\n", "3 Yes Dead 139" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tableau = raw_data.groupby(['Smoker', 'Status']).size().reset_index(name='Nombre')\n", "tableau" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "On calcule maintenant le taux de mortalité des femmes fumeuses et non fumeuses." ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Le taux de mortalité des fumeuses est de 0.23883161512027493\n", "Le taux de mortalité des non fumeuses est de 0.31420765027322406\n" ] } ], "source": [ "def calcul_taux_mortalite(smoker):\n", " nb_femmes_mortes = raw_data[(raw_data['Smoker'] == smoker) & (raw_data['Status'] == 'Dead')].shape[0]\n", " nb_femmes = (raw_data['Smoker'] == smoker).sum()\n", " return nb_femmes_mortes / nb_femmes\n", "\n", "taux_mortalite_fumeuses = calcul_taux_mortalite('Yes')\n", "taux_mortalite_non_fumeuses = calcul_taux_mortalite('No')\n", "\n", "print(f\"Le taux de mortalité des fumeuses est de {taux_mortalite_fumeuses}\")\n", "print(f\"Le taux de mortalité des non fumeuses est de {taux_mortalite_non_fumeuses}\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "On calcule ensuite l'intervale de confiance de ces taux de mortalité." ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "L'intervale de confiance du taux de mortalité des fumeuses est (0.20419201440918022, 0.27347121583136963)\n", "L'intervale de confiance du taux de mortalité des non fumeuses est (0.28057994394817404, 0.3478353565982741)\n" ] } ], "source": [ "import statsmodels.api as sm\n", "\n", "def intervale_confiance(smoker):\n", " n = (raw_data['Smoker'] == smoker).sum()\n", " p = calcul_taux_mortalite(smoker)\n", " # Intervalle de confiance à 95%\n", " intevaleC = sm.stats.proportion_confint(count=int(n * p), nobs=n, alpha=0.05, method='normal')\n", " return intevaleC\n", "\n", "intervale_fumeuses = intervale_confiance('Yes')\n", "intervale_non_fumeuses = intervale_confiance('No')\n", "\n", "print(f\"L'intervale de confiance du taux de mortalité des fumeuses est {intervale_fumeuses}\")\n", "print(f\"L'intervale de confiance du taux de mortalité des non fumeuses est {intervale_non_fumeuses}\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "On fait ensuite une répresentation graphique de nos données." ] }, { "cell_type": "code", "execution_count": 67, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", " \n", "status_fumeur = ['No', 'Yes'] \n", "valeur_mortalite = [taux_mortalite_non_fumeuses, taux_mortalite_fumeuses]\n", "min_intervaleC = [intervale_non_fumeuses[0], intervale_fumeuses[0]]\n", "max_intervaleC = [intervale_non_fumeuses[1], intervale_fumeuses[1]]\n", "\n", "plt.bar(status_fumeur, valeur_mortalite, yerr=[min_intervaleC, max_intervaleC], capsize=5)\n", "plt.title('Taux de mortalité par statut de fumeur')\n", "plt.ylabel('Taux de mortalité')\n", "plt.xlabel('Statut de fumeur')\n", "plt.ylim(0, 1)\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Le résultat est étrange car le taux de mortalité des femmes fumeuses est supérieur à celui des femmes non fumeuses, ce qui est incohérent par rapport à nos connaissances sur les conséquences de l'usage du tabac. Nous avons sûrement oublié de prendre en compte une donnée essentielle." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Partie 2" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "On reprend donc l'analyse précédente en prenant en compte des périodes d'âges : \n", " *18-34 ans, 35-54 ans, 55-64 ans, plus de 65 ans*" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
SmokerStatusNombre
Age Groupe
18-34NoAlive213
18-34NoDead6
18-34YesAlive174
18-34YesDead5
35-54NoAlive180
35-54NoDead19
35-54YesAlive198
35-54YesDead41
55-64NoAlive80
55-64NoDead39
55-64YesAlive64
55-64YesDead51
65+NoAlive29
65+NoDead166
65+YesAlive7
65+YesDead42
\n", "
" ], "text/plain": [ " Smoker Status Nombre\n", "Age Groupe \n", "18-34 No Alive 213\n", "18-34 No Dead 6\n", "18-34 Yes Alive 174\n", "18-34 Yes Dead 5\n", "35-54 No Alive 180\n", "35-54 No Dead 19\n", "35-54 Yes Alive 198\n", "35-54 Yes Dead 41\n", "55-64 No Alive 80\n", "55-64 No Dead 39\n", "55-64 Yes Alive 64\n", "55-64 Yes Dead 51\n", "65+ No Alive 29\n", "65+ No Dead 166\n", "65+ Yes Alive 7\n", "65+ Yes Dead 42" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "bins = [18, 34, 54, 64, 100]\n", "labels = ['18-34', '35-54', '55-64', '65+']\n", "raw_data['Age Groupe'] = pd.cut(raw_data['Age'], bins=bins, labels=labels, right=False)\n", "\n", "tableau = raw_data.groupby(['Smoker', 'Status', 'Age Groupe']).size().reset_index(name='Nombre')\n", "tableau_trie = tableau.set_index('Age Groupe').sort_index()\n", "tableau_trie" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "On calcule le taux de mortalité en fonction de ces périodes d'âges." ] }, { "cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Le taux de mortalité des fumeuses de 18 à 34 ans est de 0.00859106529209622\n", "Le taux de mortalité des non fumeuses de 18 à 34 ans est de 0.00819672131147541\n", "\n", "Le taux de mortalité des fumeuses de 35 à 54 ans est de 0.06701030927835051\n", "Le taux de mortalité des non fumeuses de 35 à 54 ans est de 0.025956284153005466\n", "\n", "Le taux de mortalité des fumeuses de 55 à 64 ans est de 0.08762886597938144\n", "Le taux de mortalité des non fumeuses de 55 à 64 ans est de 0.05327868852459016\n", "\n", "Le taux de mortalité des fumeuses de 65 ans et plus est de 0.07216494845360824\n", "Le taux de mortalité des non fumeuses de 65 ans et plus est de 0.22540983606557377\n", "\n" ] } ], "source": [ "def calcul_taux_mortalite_periode(smoker, age_min, age_max=200):\n", " nb_femmes_mortes = raw_data[(raw_data['Smoker'] == smoker) & (raw_data['Status'] == 'Dead') & (raw_data['Age']>=age_min) & (raw_data['Age']|z| [0.025 0.975]\n", "------------------------------------------------------------------------------\n", "const -6.7955 0.479 -14.174 0.000 -7.735 -5.856\n", "Age 0.1073 0.008 13.742 0.000 0.092 0.123\n", "==============================================================================\n", " Logit Regression Results \n", "==============================================================================\n", "Dep. Variable: Death No. Observations: 582\n", "Model: Logit Df Residuals: 580\n", "Method: MLE Df Model: 1\n", "Date: Mon, 11 Nov 2024 Pseudo R-squ.: 0.2492\n", "Time: 17:09:20 Log-Likelihood: -240.21\n", "converged: True LL-Null: -319.94\n", " LLR p-value: 1.477e-36\n", "==============================================================================\n", " coef std err z P>|z| [0.025 0.975]\n", "------------------------------------------------------------------------------\n", "const -5.5081 0.466 -11.814 0.000 -6.422 -4.594\n", "Age 0.0890 0.009 10.203 0.000 0.072 0.106\n", "==============================================================================\n" ] } ], "source": [ "# Modèle pour les non-fumeurs \n", "non_fumeurs = raw_data[raw_data['Smoker'] == 'No']\n", "X_ns = sm.add_constant(non_fumeurs['Age']) \n", "y_ns = non_fumeurs['Death']\n", "model_ns = sm.Logit(y_ns, X_ns).fit()\n", "\n", "# Modèle pour les fumeurs \n", "fumeurs = raw_data[raw_data['Smoker'] == 'Yes']\n", "X_s = sm.add_constant(fumeurs['Age'])\n", "y_s = fumeurs['Death']\n", "model_s = sm.Logit(y_s, X_s).fit()\n", "\n", "print(model_ns.summary())\n", "print(model_s.summary())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "On modélise ensuite la régression logique à l'aide d'un graphique." ] }, { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "import numpy as np \n", "\n", "tranche_age = np.linspace(18, 85, 100)\n", " \n", "pred_ns = model_ns.predict(sm.add_constant(age_range))\n", "pred_s = model_s.predict(sm.add_constant(age_range))\n", "\n", "# Calculer les intervalles de confiance \n", "int_conf_ns = intervale_confiance('No')\n", "int_conf_s = intervale_confiance('Yes')\n", "\n", "# Prédire les probabilités et les intervalles de confiance pour les non-fumeurs \n", "lower_bound_ns = model_ns.predict(sm.add_constant(tranche_age)) - 1.96 * np.sqrt(pred_ns * (1 - pred_ns) / len(non_fumeurs))\n", "upper_bound_ns = model_ns.predict(sm.add_constant(tranche_age)) + 1.96 * np.sqrt(pred_ns * (1 - pred_ns) / len(non_fumeurs))\n", "\n", "# Prédire les probabilités et les intervalles de confiance pour les fumeurs \n", "lower_bound_s = model_s.predict(sm.add_constant(tranche_age)) - 1.96 * np.sqrt(pred_s * (1 - pred_s) / len(fumeurs))\n", "upper_bound_s = model_s.predict(sm.add_constant(tranche_age)) + 1.96 * np.sqrt(pred_s * (1 - pred_s) / len(fumeurs))\n", "\n", "plt.figure(figsize=(10, 6))\n", "plt.plot(tranche_age, pred_ns, label='Probabilité de décès (non-fumeurs)', color='blue')\n", "plt.fill_between(age_range, lower_bound_ns, upper_bound_ns, color='blue', alpha=0.2)\n", "plt.plot(tranche_age, pred_s, label='Probabilité de décès (fumeurs)', color='red')\n", "plt.fill_between(age_range, lower_bound_s, upper_bound_s, color='red', alpha=0.2)\n", "plt.title('Régression logistique : Probabilité de décès en fonction de l\\'âge')\n", "plt.xlabel('Âge')\n", "plt.ylabel('Probabilité de décès')\n", "plt.legend()\n", "plt.ylim(0, 1)\n", "plt.grid()\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Ces régressions vous permettent de conclure que la nocivité du tabagisme influe particulièrement sur le taux de mortalité des femmes de 18 à 65 ans. Les femmes fumeuses ont ainsi plus de chance de mourir jeune que les femmes non fumeuses. Cependant, ce phénomène s'inverse pour les femmes de plus de 65 ans, celui pourrait être dû à l'infériorité numérique des femmes fumeuses de plus de 65 ans par rapport au femmes fumeuses." ] } ], "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 }