def classification_within_modality(dataFrame, categoria, exposure):
'''
'''
dataFrame_result = []
loo = LeaveOneOut()
pbar = tqdm(total=loo.get_n_splits(dataFrame))
for ind, pearson in dataFrame.groupby('people'):
X = pearson.drop(['trial', 'group', 'people'], 1)
y = pearson['group']
loo = LeaveOneOut()
for train_index, test_index in loo.split(X):
X_train, X_test = X.iloc[train_index], X.iloc[test_index]
y_train, y_test = y.iloc[train_index], y.iloc[test_index]
#Normalize
train_mean = average(X_train, axis=0)
X_train_without_mean = subtract(X_train, train_mean)
X_test_without_mean = subtract(X_test, train_mean)
clf = GaussianNB()
clf.class_prior_ = [(1 / 6), (1 / 6), (1 / 6), (1 / 6), (1 / 6),
(1 / 6)]
pca_ = PCA(random_state=42, svd_solver='full', n_components=0.99)
pca = pca_.fit(X_train_without_mean)
X_train_pca = pca.transform(X_train_without_mean)
X_test_pca = pca.transform(X_test_without_mean)
clf = clf.fit(X_train_pca, y_train)
y_pred = clf.predict(X_test_pca)
dataFrame_result.append(
[ind, y_pred, y_test.values, categoria, exposure])
pbar.update(1)
return dataFrame_result
def deserialize_gaussian_nb(model_dict):
model = GaussianNB(model_dict['params'])
model.classes_ = np.array(model_dict['classes_'])
model.class_count_ = np.array(model_dict['class_count_'])
model.class_prior_ = np.array(model_dict['class_prior_'])
model.theta_ = np.array(model_dict['theta_'])
model.sigma_ = np.array(model_dict['sigma_'])
model.epsilon_ = model_dict['epsilon_']
return model
def NB_predict():
X = json.loads(request.form['X'])
params = json.loads(request.form['params'])
clf = GaussianNB()
clf.class_prior_ = np.array(params['class_prior'])
clf.class_count_ = np.array(params['class_count'])
clf.theta_ = np.array(params['theta'])
clf.sigma_ = np.array(params['sigma'])
clf.classes_ = np.array(params['classes'])
y = clf.predict(X)
return jsonify(pred=y.tolist())
def classification_across_modality(dataFrame1, dataFrame2, inp, exp):
dataFrame_result = []
for (ind_1, pearson_1), (ind_2, pearson_2) in list(
zip(dataFrame1.groupby('people'), dataFrame2.groupby('people'))):
X_train = pearson_1.drop(['trial', 'group', 'people'], 1)
y_train = pearson_1['group']
X_test = pearson_2.drop(['trial', 'group', 'people'], 1)
y_test = pearson_2['group']
#Normalize
train_mean = average(X_train, axis=0)
X_train_without_mean = subtract(X_train, train_mean)
X_test_without_mean = subtract(X_test, train_mean)
clf = GaussianNB()
clf.class_prior_ = [(1 / 6), (1 / 6), (1 / 6), (1 / 6), (1 / 6),
(1 / 6)]
pca_ = PCA(random_state=42, svd_solver='full', n_components=0.99)
pca = pca_.fit(X_train_without_mean)
X_train_pca = pca.transform(X_train_without_mean)
X_test_pca = pca.transform(X_test_without_mean)
clf = clf.fit(X_train_pca, y_train)
y_pred = clf.predict(X_test_pca)
for y_i_pred, y_i_test in list(zip(y_pred, y_test.values)):
dataFrame_result.append([ind_1, y_i_pred, y_i_test, inp, exp])
return dataFrame_result
# coding: utf8 # 在scikit-learn中，提供了3中朴素贝叶斯分类算法：GaussianNB(高斯朴素贝叶斯)、MultinomialNB(多项式朴素贝叶斯)、BernoulliNB(伯努利朴素贝叶斯) import numpy as np from sklearn.naive_bayes import GaussianNB, MultinomialNB, BernoulliNB X = np.asarray([[-1, -1], [-2, -2], [-3, -3], [-4, -4], [-5, -5], [1, 1], [2, 2], [3, 3]]) y = np.asarray([1, 1, 1, 1, 1, 2, 2, 2]) clf = GaussianNB() clf.class_prior_ = [0.675, 0.325] clf.fit(X, y) print(clf.predict([[-1, -1], [2,3]]))
tailles = np.concatenate( (taille_h,taille_f) )
poids = np.concatenate( (poids_h,poids_f) )
data = np.column_stack( (tailles,poids) )
gnb.fit(data, classes)
#######
# MAP
#######
y_pred=gnb.predict(data)
p_err, err=computeNaif(y_pred,classes)
print("Prédiction MAP", gnb.class_prior_ , "% d'erreurs :" , p_err*100, "soit", err ,"/", len(y_pred))
#######
# ML
#######
gnb.class_prior_ = [0.48,0.52]
y_pred=gnb.predict(data)
p_err, err=computeNaif(y_pred,classes)
print("Prédiction ML", gnb.class_prior_ , "% d'erreurs :" , p_err*100, "soit", err ,"/", len(y_pred))
#######
# Naif
#######
gnb.class_prior_ = [0.5,0.5]
y_pred=gnb.predict(data)
p_err, err=computeNaif(y_pred,classes)
print("Prédiction Naif", gnb.class_prior_ , "% d'erreurs :" , p_err*100, "soit", err ,"/", len(y_pred))
#######
# Twice
#######
# replace missing (-1) values for distance with max int size
imp = Imputer(-1)
train_feats = imp.fit_transform(train_feats)
# train_feats[train_feats == -1] = sys.maxsize
print_stars()
print('Multinomial Naive Bayes')
mnb = MultinomialNB(class_prior=[0.9, 0.1])
_, _, _, mnb_probs = train_test_print(mnb, train_feats, test_feats,
train_mask, test_mask)
print_stars()
print('Gaussian Naive Bayes')
gnb = GaussianNB()
gnb.class_prior_ = [0.9, 0.1]
_, _, _, gnb_probs = train_test_print(gnb, train_feats, test_feats,
train_mask, test_mask)
print_stars()
print('Naive Bayes with Square Kernel')
gnb2 = GaussianNB()
gnb2.class_prior_ = [0.9, 0.1]
test_prods = pairwise_products(test_feats)
train_prods = pairwise_products(train_feats)
_, _, _, gnb2_probs = train_test_print(gnb2, train_prods, test_prods,
train_mask, test_mask)
print_stars()
print('K-Nearest Neighbors, k = 25')
knn = KNeighborsClassifier(n_neighbors=25, weights='distance')
print(f"Classification Accuracy: {accuracy}")
""" ROC CURVE 1"""
fpr, tpr, thresholds = metrics.roc_curve(testY, prediction)
roc_auc = metrics.auc(fpr, tpr)
print('ROC_AUC = ', roc_auc)
display = metrics.RocCurveDisplay(fpr=fpr, tpr=tpr, roc_auc=roc_auc , estimator_name= None)
display.plot()
plt.show()
"""CHANGING PRIORS TO 0.1 AND 0.9"""
classifier.class_prior_ = [0.1,0.9]
prediction = classifier.predict(testX)
prediction_train = classifier.predict(trainX)
print(classification_report(prediction_train,trainY))
print(classification_report(prediction,testY))
"""CONFUSION MATRICIES"""
# Train Accuracy
cm = confusion_matrix(trainY, prediction_train)
plt.figure(figsize=(5, 5))
ax = sns.heatmap(cm, annot=True, fmt="d")
plt.ylabel('True Values')
plt.xlabel('Predicted Values')
accuracy = accuracy_score(trainY, prediction_train)
# replace missing (-1) values for distance with max int size
imp = Imputer(-1)
train_feats = imp.fit_transform(train_feats)
# train_feats[train_feats == -1] = sys.maxsize
print_stars()
print('Multinomial Naive Bayes')
mnb = MultinomialNB(class_prior=[0.9, 0.1])
_, _, _, mnb_probs = train_test_print(
mnb, train_feats, test_feats, train_mask, test_mask)
print_stars()
print('Gaussian Naive Bayes')
gnb = GaussianNB()
gnb.class_prior_ = [0.9, 0.1]
_, _, _, gnb_probs = train_test_print(
gnb, train_feats, test_feats, train_mask, test_mask)
print_stars()
print('Naive Bayes with Square Kernel')
gnb2 = GaussianNB()
gnb2.class_prior_ = [0.9, 0.1]
test_prods = pairwise_products(test_feats)
train_prods = pairwise_products(train_feats)
_, _, _, gnb2_probs = train_test_print(
gnb2, train_prods, test_prods, train_mask, test_mask)
print_stars()
print('K-Nearest Neighbors, k = 25')
knn = KNeighborsClassifier(n_neighbors=25, weights='distance')
