1. Importez le fichier « iris_data.csv » dans un dataframe intitulé « iris »

import pandas as pd
iris = pd.read_csv("iris_data.csv", sep=",")

2. Affichez les 5 premières lignes du dataframe « iris »

iris.head()

	sepal_length	sepal_width	petal_length	petal_width	species
0	5.1	3.5	1.4	0.2	setosa
1	4.9	3.0	1.4	0.2	setosa
2	4.7	3.2	1.3	0.2	setosa
3	4.6	3.1	1.5	0.2	setosa
4	5.0	3.6	1.4	0.2	setosa

3. Combien le dataframe compte t-il de lignes et de colonnes ?

iris.shape

(150, 5)

La dataframe iris compte 5 variables et 150 individus

4. Quelles sont les variables explicatives ? Quelle est la variable cible ?

La variable cible est: "species".

Les variables explicatives sont: "sepal_length, sepal_width, petal_length et petal_width

5. Séparez les variables explicatives dans un objet « X » et la variable cible dans un objet « y ». Vous pourrez utiliser le script suivant :

X = iris.loc[:, "sepal_length":"petal_width"]
y = iris["species"]

6. Nous allons à présent constituer un échantillon d’apprentissage et un échantillon de test pour notre modèle. Entrez les commandes suivantes :

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.35)

7. Nous allons instancier un modèle de classification de type KNN en utilisant 3 comme nombre de voisins

from sklearn.neighbors import KNeighborsClassifier

# Instanciation du modèle
modele1 = KNeighborsClassifier(n_neighbors=3)

8. Entrainez le modèle sur les données d’apprentissage

modele1.fit(X_train, y_train)

KNeighborsClassifier(n_neighbors=3)

9. En utilisant le modèle entrainé, faites la prédiction sur les données de test, et stockez le résultat dans un objet « y_pred »

y_pred = modele1.predict(X_test)

10. Affichez le contenu de l’objet « y_pred »

y_pred

array(['versicolor', 'virginica', 'versicolor', 'versicolor', 'setosa',
       'versicolor', 'setosa', 'versicolor', 'setosa', 'virginica',
       'versicolor', 'setosa', 'setosa', 'virginica', 'virginica',
       'setosa', 'virginica', 'versicolor', 'versicolor', 'versicolor',
       'setosa', 'virginica', 'versicolor', 'setosa', 'setosa',
       'versicolor', 'versicolor', 'versicolor', 'versicolor', 'setosa',
       'versicolor', 'virginica', 'virginica', 'virginica', 'virginica',
       'virginica', 'virginica', 'setosa', 'setosa', 'virginica',
       'setosa', 'virginica', 'setosa', 'setosa', 'setosa', 'setosa',
       'setosa', 'virginica', 'setosa', 'versicolor', 'versicolor',
       'setosa', 'setosa'], dtype=object)

11. En utilisant les prédictions et la réalité (y_test), affichez la matrice de confusion

from sklearn.metrics import confusion_matrix
confusion_matrix(y_test,y_pred)

array([[21,  0,  0],
       [ 0, 16,  1],
       [ 0,  1, 14]], dtype=int64)

12. Affichez l’efficacité du modèle.

from sklearn.metrics import accuracy_score
accuracy_score(y_test,y_pred)

0.9622641509433962

(21+16+14)/(21+16+14+1+1)

0.9622641509433962

13. Chargez les données « data_breast_cancer.csv » dans un dataframe.

cancer = pd.read_csv("data_breast_cancer.csv")

cancer.head()

	id	diagnosis	radius_mean	texture_mean	perimeter_mean	area_mean	smoothness_mean	compactness_mean	concavity_mean	concave points_mean	...	texture_worst	perimeter_worst	area_worst	smoothness_worst	compactness_worst	concavity_worst	concave points_worst	symmetry_worst	fractal_dimension_worst	Unnamed: 32
0	842302	M	17.99	10.38	122.80	1001.0	0.11840	0.27760	0.3001	0.14710	...	17.33	184.60	2019.0	0.1622	0.6656	0.7119	0.2654	0.4601	0.11890	NaN
1	842517	M	20.57	17.77	132.90	1326.0	0.08474	0.07864	0.0869	0.07017	...	23.41	158.80	1956.0	0.1238	0.1866	0.2416	0.1860	0.2750	0.08902	NaN
2	84300903	M	19.69	21.25	130.00	1203.0	0.10960	0.15990	0.1974	0.12790	...	25.53	152.50	1709.0	0.1444	0.4245	0.4504	0.2430	0.3613	0.08758	NaN
3	84348301	M	11.42	20.38	77.58	386.1	0.14250	0.28390	0.2414	0.10520	...	26.50	98.87	567.7	0.2098	0.8663	0.6869	0.2575	0.6638	0.17300	NaN
4	84358402	M	20.29	14.34	135.10	1297.0	0.10030	0.13280	0.1980	0.10430	...	16.67	152.20	1575.0	0.1374	0.2050	0.4000	0.1625	0.2364	0.07678	NaN

5 rows × 33 columns

14. En suivant les étapes nécessaires comme ci-dessus (échantillonnage, instanciation, évaluation), concevez deux modèles permettant de prédire la gravité d’une tumeur.

--> Séparation variable cible/variables prédictives

X = cancer.loc[:,'radius_mean':'fractal_dimension_worst']
y=cancer['diagnosis']

--> Echantillonnage

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)

--> Chargement et instanciation des modèles

from sklearn.neighbors import KNeighborsClassifier
modele_knn = KNeighborsClassifier(n_neighbors=3)

from sklearn.linear_model import LogisticRegression
modele_reg_log = LogisticRegression(max_iter=5000)

--> Entrainement des modèles

modele_knn.fit(X_train, y_train)
modele_reg_log.fit(X_train, y_train)

LogisticRegression(max_iter=5000)

--> Prédictions

pred_knn = modele_knn.predict(X_test)
pred_reg_log = modele_reg_log.predict(X_test)

pred_knn

array(['M', 'B', 'B', 'M', 'B', 'B', 'M', 'M', 'B', 'M', 'B', 'B', 'M',
       'M', 'B', 'M', 'M', 'B', 'B', 'B', 'B', 'M', 'B', 'B', 'B', 'B',
       'M', 'M', 'B', 'B', 'M', 'B', 'M', 'B', 'B', 'B', 'M', 'B', 'M',
       'B', 'B', 'M', 'B', 'B', 'B', 'B', 'B', 'M', 'M', 'B', 'M', 'M',
       'M', 'B', 'M', 'M', 'B', 'M', 'B', 'B', 'B', 'B', 'M', 'M', 'M',
       'B', 'M', 'M', 'B', 'B', 'B', 'B', 'B', 'B', 'M', 'B', 'M', 'B',
       'B', 'M', 'B', 'M', 'B', 'B', 'B', 'B', 'M', 'B', 'M', 'M', 'M',
       'M', 'M', 'B', 'M', 'B', 'B', 'B', 'B', 'B', 'M', 'B', 'B', 'B',
       'B', 'B', 'M', 'B', 'B', 'M', 'B', 'M', 'M', 'B', 'B', 'B', 'B',
       'B', 'B', 'B', 'B', 'B', 'B', 'B', 'M', 'B', 'B', 'B', 'B', 'B',
       'B', 'B', 'M', 'B', 'B', 'M', 'M', 'B', 'B', 'M', 'B', 'M', 'M'],
      dtype=object)

pred_reg_log

array(['M', 'B', 'B', 'M', 'B', 'B', 'M', 'M', 'B', 'M', 'B', 'B', 'M',
       'M', 'B', 'M', 'M', 'B', 'B', 'B', 'B', 'M', 'B', 'B', 'B', 'B',
       'M', 'M', 'B', 'B', 'M', 'B', 'M', 'B', 'M', 'B', 'M', 'M', 'B',
       'B', 'B', 'M', 'B', 'M', 'B', 'B', 'B', 'M', 'B', 'B', 'B', 'M',
       'M', 'B', 'M', 'M', 'B', 'M', 'B', 'B', 'B', 'B', 'M', 'M', 'M',
       'B', 'M', 'M', 'B', 'B', 'B', 'B', 'B', 'B', 'M', 'B', 'M', 'B',
       'B', 'M', 'B', 'M', 'M', 'B', 'B', 'B', 'M', 'B', 'M', 'M', 'M',
       'M', 'M', 'B', 'M', 'B', 'B', 'B', 'B', 'B', 'M', 'M', 'B', 'B',
       'B', 'B', 'M', 'B', 'B', 'B', 'B', 'M', 'M', 'B', 'B', 'B', 'B',
       'B', 'B', 'B', 'B', 'B', 'B', 'B', 'M', 'B', 'B', 'M', 'B', 'B',
       'B', 'B', 'M', 'B', 'B', 'M', 'M', 'B', 'B', 'M', 'B', 'M', 'M'],
      dtype=object)

--> matrice de confusion

confusion_matrix(y_test, pred_knn)

array([[82,  1],
       [ 8, 52]], dtype=int64)

confusion_matrix(y_test, pred_reg_log)

array([[82,  1],
       [ 6, 54]], dtype=int64)

--> Efficacité

accuracy_score(y_test, pred_knn)

0.9370629370629371

accuracy_score(y_test, pred_reg_log)

0.951048951048951

--> Proba

pred_proba_knn = modele_knn.predict_proba(X_test)

pred_proba_knn

array([[0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.66666667, 0.33333333],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.33333333, 0.66666667],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.66666667, 0.33333333],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.66666667, 0.33333333],
       [0.33333333, 0.66666667],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.33333333, 0.66666667],
       [1.        , 0.        ],
       [0.33333333, 0.66666667],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.33333333, 0.66666667],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.66666667, 0.33333333],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.33333333, 0.66666667],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.66666667, 0.33333333],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.33333333, 0.66666667],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.66666667, 0.33333333],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.33333333, 0.66666667],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.66666667, 0.33333333],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.66666667, 0.33333333],
       [1.        , 0.        ],
       [0.66666667, 0.33333333],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [1.        , 0.        ],
       [0.        , 1.        ],
       [0.        , 1.        ]])

pred_proba_reg_log = modele_reg_log.predict_proba(X_test)

pred_proba_reg_log

array([[1.58570398e-06, 9.99998414e-01],
       [9.97729191e-01, 2.27080940e-03],
       [9.99353267e-01, 6.46732792e-04],
       [3.50792062e-10, 1.00000000e+00],
       [5.13338197e-01, 4.86661803e-01],
       [9.99995551e-01, 4.44947030e-06],
       [1.24334106e-03, 9.98756659e-01],
       [3.09770654e-09, 9.99999997e-01],
       [9.99630564e-01, 3.69436078e-04],
       [7.36306901e-03, 9.92636931e-01],
       [9.99979306e-01, 2.06937603e-05],
       [9.99049022e-01, 9.50977587e-04],
       [9.08804143e-11, 1.00000000e+00],
       [1.29509037e-02, 9.87049096e-01],
       [9.35444560e-01, 6.45554404e-02],
       [4.08117984e-13, 1.00000000e+00],
       [1.43085504e-03, 9.98569145e-01],
       [9.93007993e-01, 6.99200694e-03],
       [9.99558359e-01, 4.41641325e-04],
       [9.99579889e-01, 4.20111213e-04],
       [9.97983556e-01, 2.01644428e-03],
       [1.11464910e-03, 9.98885351e-01],
       [9.99999282e-01, 7.17849294e-07],
       [9.99511009e-01, 4.88990569e-04],
       [9.88617371e-01, 1.13826293e-02],
       [7.47205755e-01, 2.52794245e-01],
       [1.58210612e-06, 9.99998418e-01],
       [7.22159358e-04, 9.99277841e-01],
       [9.95976818e-01, 4.02318210e-03],
       [9.99490400e-01, 5.09599965e-04],
       [1.21661914e-06, 9.99998783e-01],
       [9.96881683e-01, 3.11831660e-03],
       [7.06964516e-03, 9.92930355e-01],
       [9.93429161e-01, 6.57083879e-03],
       [3.64909006e-01, 6.35090994e-01],
       [9.99939950e-01, 6.00503896e-05],
       [6.70412248e-03, 9.93295878e-01],
       [1.95344046e-01, 8.04655954e-01],
       [9.27697000e-01, 7.23029996e-02],
       [9.89157785e-01, 1.08422146e-02],
       [9.99570437e-01, 4.29563258e-04],
       [1.18580853e-02, 9.88141915e-01],
       [9.98235624e-01, 1.76437639e-03],
       [4.83236274e-01, 5.16763726e-01],
       [9.98847334e-01, 1.15266553e-03],
       [9.98211977e-01, 1.78802267e-03],
       [9.59709791e-01, 4.02902094e-02],
       [1.25040044e-02, 9.87495996e-01],
       [5.22130239e-01, 4.77869761e-01],
       [9.97510241e-01, 2.48975873e-03],
       [7.40221868e-01, 2.59778132e-01],
       [3.11532846e-02, 9.68846715e-01],
       [3.35890846e-08, 9.99999966e-01],
       [9.94061745e-01, 5.93825500e-03],
       [5.56928355e-03, 9.94430716e-01],
       [2.46274036e-06, 9.99997537e-01],
       [9.90885375e-01, 9.11462464e-03],
       [4.87069974e-02, 9.51293003e-01],
       [7.26195193e-01, 2.73804807e-01],
       [9.50089969e-01, 4.99100315e-02],
       [9.94412968e-01, 5.58703245e-03],
       [9.98425732e-01, 1.57426843e-03],
       [7.76038648e-03, 9.92239614e-01],
       [7.57397125e-07, 9.99999243e-01],
       [5.22451369e-06, 9.99994775e-01],
       [9.89003499e-01, 1.09965011e-02],
       [4.80143543e-02, 9.51985646e-01],
       [4.71385394e-02, 9.52861461e-01],
       [9.99774714e-01, 2.25285540e-04],
       [9.99260983e-01, 7.39016969e-04],
       [9.99469501e-01, 5.30498785e-04],
       [9.97025216e-01, 2.97478381e-03],
       [9.93825212e-01, 6.17478761e-03],
       [9.85669937e-01, 1.43300635e-02],
       [2.99837734e-06, 9.99997002e-01],
       [9.99802277e-01, 1.97723394e-04],
       [2.62257489e-08, 9.99999974e-01],
       [9.99057213e-01, 9.42786838e-04],
       [9.63352603e-01, 3.66473966e-02],
       [2.48757078e-04, 9.99751243e-01],
       [9.97513777e-01, 2.48622322e-03],
       [4.43024068e-04, 9.99556976e-01],
       [1.18026326e-01, 8.81973674e-01],
       [9.99766346e-01, 2.33654185e-04],
       [9.61558338e-01, 3.84416623e-02],
       [9.83615094e-01, 1.63849059e-02],
       [5.10859791e-06, 9.99994891e-01],
       [9.58016902e-01, 4.19830978e-02],
       [4.79157752e-02, 9.52084225e-01],
       [3.43725048e-13, 1.00000000e+00],
       [1.94809110e-04, 9.99805191e-01],
       [1.13770183e-08, 9.99999989e-01],
       [4.04487590e-03, 9.95955124e-01],
       [9.99596411e-01, 4.03588743e-04],
       [1.76655584e-02, 9.82334442e-01],
       [9.99006188e-01, 9.93811623e-04],
       [7.89226049e-01, 2.10773951e-01],
       [9.10505256e-01, 8.94947438e-02],
       [9.96749470e-01, 3.25052998e-03],
       [9.99982793e-01, 1.72074796e-05],
       [1.77635684e-15, 1.00000000e+00],
       [4.58170705e-02, 9.54182930e-01],
       [9.68718952e-01, 3.12810484e-02],
       [9.84469687e-01, 1.55303134e-02],
       [9.96506048e-01, 3.49395157e-03],
       [9.97012723e-01, 2.98727685e-03],
       [1.35246856e-02, 9.86475314e-01],
       [8.86478631e-01, 1.13521369e-01],
       [9.99988451e-01, 1.15486279e-05],
       [8.67322439e-01, 1.32677561e-01],
       [9.90403927e-01, 9.59607292e-03],
       [1.23647947e-03, 9.98763521e-01],
       [6.10622664e-14, 1.00000000e+00],
       [9.96959631e-01, 3.04036869e-03],
       [9.99545441e-01, 4.54559056e-04],
       [9.99995450e-01, 4.54957037e-06],
       [9.23948232e-01, 7.60517683e-02],
       [9.99709917e-01, 2.90082676e-04],
       [9.99990823e-01, 9.17704762e-06],
       [9.99915937e-01, 8.40631544e-05],
       [9.99986734e-01, 1.32662289e-05],
       [9.98336038e-01, 1.66396172e-03],
       [9.99961765e-01, 3.82347230e-05],
       [9.13803387e-01, 8.61966127e-02],
       [5.71515191e-09, 9.99999994e-01],
       [9.99692738e-01, 3.07261980e-04],
       [9.99032059e-01, 9.67941259e-04],
       [2.46956525e-01, 7.53043475e-01],
       [9.97768102e-01, 2.23189754e-03],
       [9.82422696e-01, 1.75773039e-02],
       [8.41075141e-01, 1.58924859e-01],
       [9.82059450e-01, 1.79405499e-02],
       [1.53836229e-07, 9.99999846e-01],
       [9.97198586e-01, 2.80141386e-03],
       [9.99905151e-01, 9.48489308e-05],
       [7.78652349e-07, 9.99999221e-01],
       [1.06505702e-06, 9.99998935e-01],
       [9.98816528e-01, 1.18347197e-03],
       [9.86061473e-01, 1.39385269e-02],
       [1.63169142e-03, 9.98368309e-01],
       [9.87330105e-01, 1.26698949e-02],
       [1.04133699e-02, 9.89586630e-01],
       [5.36966027e-10, 9.99999999e-01]])