import numpy as np X_train = np.loadtxt('ressources/SY32_P20_TD02_data_X_train.csv', ndmin=2) Y_train = np.loadtxt('ressources/SY32_P20_TD02_data_y_train.csv') X_test = np.loadtxt('ressources/SY32_P20_TD02_data_X_test.csv', ndmin=2) from ressources.catClassifier import CatClassifierMultiDim clf = CatClassifierMultiDim() clf.fit(X_train,Y_train) print(clf.h_hat) print(clf.d_hat) print(clf.z_hat) from ressources.catClassifierPlot import plotCatClassifier plotCatClassifier(clf)

from ressources.catClassifier import CatClassifierBoost list_K = [3,10,20,30,40] list_err = [] for k in list_K: clf = CatClassifierBoost() clf.fit(X_train,Y_train,k) plotCatClassifier(clf) list_err.append(np.mean(clf.predict(X_train) != Y_train)) print(list_err[-1])

from sklearn.model_selection import StratifiedKFold skf = StratifiedKFold(n_splits=10) list_K = [3,10,20,30,40] list_err = [] for k in list_K: list_err_k=[] for train,val in skf.split(X_train,Y_train): clf = CatClassifierBoost() clf.fit(X_train[train],Y_train[train],k) list_err_k.append(np.mean(clf.predict(X_train[val]) != Y_train[val])) list_err.append(np.mean(list_err_k)) print(list_err[-1])

best_k = 1 best_err = np.Inf list_err = [] for k in list_K: list_err_k=[] for train,val in skf.split(X_train,Y_train): clf = CatClassifierBoost() clf.fit(X_train[train],Y_train[train],k) list_err_k.append(np.mean(clf.predict(X_train[val]) != Y_train[val])) list_err.append(np.mean(list_err_k)) # print(list_err[-1]) if list_err[-1] < best_err: best_err = list_err[-1] best_k = k print('Meilleur k: {}'.format(k)) y_test = clf.predict(X_test) np.savetxt('y_test.txt',y_test,fmt ='%d')