import pandas as pd import numpy as np import sklearn.metrics as metrics import matplotlib.pyplot as plt df=pd.read_csv("Vins.csv")

df["Classe"]=np.where(df['quality']>= 7, 1, 0)

df.head()

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split( df.drop(['Classe','quality'], axis=1), df['Classe'], test_size=0.33, random_state=42 )

from sklearn import tree

clf = tree.DecisionTreeClassifier(max_depth=6) clf = clf.fit(X_train, y_train) # tree.plot_tree(clf)

clf.score(X_test,y_test) #premiere eval du modele (precision)

y_test_pred=clf.predict(X_test)

from sklearn.metrics import confusion_matrix conf_matrix=confusion_matrix(y_test, y_test_pred) conf_matrix

#on associe les valeurs a des variables vn,fp=conf_matrix[0] fn,vp=conf_matrix[1]

#precision rappel from sklearn.metrics import recall_score from sklearn.metrics import precision_score precision=precision_score(y_test, y_test_pred) recall=recall_score(y_test, y_test_pred) print("precision:",precision,"\nrecall:",recall)

print("precision: ", vp/(vp+fp)) print("recall", vp/(vp+fn))

specificity=vn/(vn+fp) print(specificity) sensibility=vp/(vp+fn) print(sensibility)

probas=clf.predict_proba(X_test) plt.hist(probas)

y_score = clf.predict_proba(X_test) #Calcul des points de la courbe ROC fpr, tpr, thresholds = metrics.roc_curve(y_test, y_score[:,-1]) #false positive rate, true positive rate, ensemble des seuils #Affichage de la courbe ROC plt.plot(fpr, tpr) metrics.auc(fpr, tpr)

u_s_list=[] v_s_list=[] probas=clf.predict_proba(X_test) # probas score=probas[:,1] step = 0.1 x_val = np.arange(0,1,step) print(x_val) for s in x_val: pred_seuil = np.where(score > s, 1, score) pred_seuil = np.where(score <= s, 0, score) # pred_seuil vp = 0 fp = 0 vn = 0 fn = 0 for i in range(0,len(pred_seuil)-1): if pred_seuil[i]==1 and list(y_test)[i]==1: vp+=1 elif pred_seuil[i]==1 and list(y_test)[i]==0: fp+=1 elif pred_seuil[i]==0 and list(y_test)[i]==1: fn+=1 elif pred_seuil[i]==0 and list(y_test)[i]==0: vn+=1 u_s=(vp+fp)/(vp+fn+fp+vn) v_s=vp/(vp+fn) u_s_list+=[u_s] v_s_list+=[v_s] print(s) print(u_s,v_s) print(vp,fp,"\n",fn,vn,"\n")

plt.plot(v_s_list[::-1]) plt.title("Courbe lift a reverse ")

clf = tree.DecisionTreeClassifier(max_depth=6) clf = clf.fit(pd.concat([X_train, X_test]), pd.concat([y_train, y_test])) tree.plot_tree(clf)

from sklearn.model_selection import KFold kf = KFold(n_splits=4) X = np.array(df.drop(['Classe','quality'], axis=1)) y = np.array(df['Classe']) kf.get_n_splits(X) print(kf) print(kf.get_n_splits(X))

fig = plt.figure() ax = plt.subplot(111) i=0 auc_list = [] for train_index, test_index in kf.split(X): # print("TRAIN:", train_index, "TEST:", test_index) X_train, X_test = X[train_index], X[test_index] y_train, y_test = y[train_index], y[test_index] #modèle predictif clf = tree.DecisionTreeClassifier(max_depth=6) clf = clf.fit(X_train, y_train) # tree.plot_tree(clf) y_score = clf.predict_proba(X_test) #Calcul des points de la courbe ROC fpr, tpr, thresholds = metrics.roc_curve(y_test, y_score[:,-1]) #false positive rate, true positive rate, ensemble des seuils #Affichage de la courbe ROC plt.plot(fpr, tpr, label=i) i=i+1 #Calcul de l'air sur la courbe print("AUC de ",i," : ",metrics.auc(fpr, tpr)) auc_list += [metrics.auc(fpr, tpr)] ax.legend() plt.show() mean_auc = sum(auc_list)/kf.get_n_splits(X)

print("précision avec l'AUC moyen", mean_auc)

ecart_type=0 for val in auc_list: ecart_type += (val-mean_auc)**2 ecart_type = (1/kf.get_n_splits(X)) * ecart_type print("Robustesse avec écart type : ", ecart_type)

clf = tree.DecisionTreeClassifier(max_depth=6) clf = clf.fit(X,y) # tree.plot_tree(clf)

X_train, X_test, y_train, y_test = train_test_split( df.drop(['Classe','quality'], axis=1), df['Classe'], test_size=0.33, random_state=42 )

from sklearn.linear_model import LinearRegression from sklearn.neural_network import MLPClassifier from sklearn.neighbors import KNeighborsClassifier from sklearn.linear_model import Perceptron from sklearn.ensemble import RandomForestClassifier from sklearn.experimental import enable_halving_search_cv # noqa from sklearn.model_selection import HalvingGridSearchCV fig = plt.figure(figsize=(10,10)) ax = plt.subplot(111) model_list = [tree.DecisionTreeClassifier(max_depth=6), tree.DecisionTreeClassifier(max_depth=4), tree.DecisionTreeClassifier(max_depth=3), RandomForestClassifier(max_depth=5,random_state=0), LinearRegression(), MLPClassifier(solver='lbfgs', alpha=1e-5, hidden_layer_sizes=(5, 2), random_state=1), MLPClassifier(solver='lbfgs', alpha=1e-5, hidden_layer_sizes=(100,), random_state=1), Perceptron(max_iter=40, eta0=0.1, random_state=0), KNeighborsClassifier(n_neighbors=3), KNeighborsClassifier(n_neighbors=6)] i=0 auc_list = [] for m in model_list: #modèle predictif model = m.fit(X_train, y_train) try: y_score = model.predict_proba(X_test) #Calcul des points de la courbe ROC fpr, tpr, thresholds = metrics.roc_curve(y_test, y_score[:,-1]) #false positive rate, true positive rate, ensemble des seuils except: fpr, tpr, thresholds = metrics.roc_curve(y_test, model.predict(X_test)) #false positive rate, true positive rate, ensemble des seuils #Affichage de la courbe ROC plt.plot(fpr, tpr, label=m) i=i+1 #Calcul de l'air sur la courbe print("AUC de ",m," : ",metrics.auc(fpr, tpr)) auc_list += [metrics.auc(fpr, tpr)] ax.legend() plt.show() mean_auc = sum(auc_list)/kf.get_n_splits(X)

param_grid = {'max_depth': [3, 5, 10], 'min_samples_split': [2, 5, 10]} base_estimator = RandomForestClassifier(random_state=0) sh = HalvingGridSearchCV(base_estimator, param_grid, cv=5, factor=2, resource='n_estimators', max_resources=30).fit(X, y) print(sh.best_estimator_)