def classification(self, metric, folds, alphas, graph):
size = 1.3 * self.report_width // 10
models = {}
models["K nearest neighbors classifier K2"] = knnc(n_neighbors=2)
models["K nearest neighbors classifier K5"] = knnc(n_neighbors=5)
models["K nearest neighbors classifier K10"] = knnc(n_neighbors=10)
models["Decision tree classifier"] = dtc()
models["Logistic classifier"] = logitc()
models["SVM classifier with RBF kernel"] = svc(gamma='scale')
models["SVM classifier with linear kernel"] = svc(kernel='linear')
models["Gaussian naive bayes"] = gnbc()
models["Bernoulli naive bayes"] = bnbc()
models["SGD classifier"] = sgdc(max_iter=10000)
models["Random forest classifier"] = rfc(n_estimators=100)
models["Gradient boosting classifier"] = gbc()
self.models = models
print('\n')
print(self.report_width * '*', '\n*')
print('* CLASSIFICATION RESULTS - BEFORE PARAMETERS BOOSTING \n*')
kf = StratifiedKFold(n_splits=folds, shuffle=True)
results = []
names = []
for model_name in models:
cv_scores = cross_val_score(models[model_name], self.Xt_train, self.yt_train.values.ravel(), cv=kf, error_score=np.nan)
results.append(cv_scores)
names.append(model_name)
print(self.report_width * '*', '')
report = pd.DataFrame({'Classifier': names, 'Score': results})
report['Score (avg)'] = report.Score.apply(lambda x: x.mean())
report['Score (std)'] = report.Score.apply(lambda x: x.std())
report['Score (VC)'] = 100 * report['Score (std)'] / report['Score (avg)']
report.sort_values(by='Score (avg)', inplace=True, ascending=False)
report.drop('Score', axis=1, inplace=True)
display(report)
print('\n')
if graph:
fig, ax = plt.subplots(figsize=(size, 0.5 * size))
plt.title('Classifier Comparison')
#ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.xticks(rotation=45)
plt.subplots_adjust(hspace=0.0)
plt.show()
return None
def classification(file, X, Y, x, y):
# lab_enc = prep.LabelEncoder()
# Y = lab_enc.fit_transform(Y)
# y = lab_enc.fit_transform(y)
param = []
acc = []
for i in it.product(n_neighbors, weights, algorithm, leaf_size):
for m in metric:
# print(*i,m)
if m == 'minkowski':
for j in p:
# print('p=',j)
knn = knnc(*i, p=j, metric=m)
knn.fit(X, Y)
acc.append(knn.score(x, y))
param.append([*i, m, j])
else:
knn = knnc(*i, metric=m)
knn.fit(X, Y)
acc.append(knn.score(x, y))
param.append([*i, m])
_results(file, acc, param)
def classification(self, metric, folds, printt=True, graph=False):
size = self.graph_width
if len(self.y.iloc[:,0].unique()) > 2:
struct = 'multiclass'
else:
struct = 'binary'
# significant model setup differences should be list as different models
models = {}
models["Linear discriminant analysis"] = ldac()
models["Nearest centroid classifier euclidian"] = ncc(metric='euclidean')
models["Nearest centroid classifier manhattan"] = ncc(metric='manhattan')
models["K nearest neighbors classifier K2"] = knnc(n_neighbors=2)
models["K nearest neighbors classifier K5"] = knnc(n_neighbors=5)
models["K nearest neighbors classifier K10"] = knnc(n_neighbors=10)
models["Decision tree classifier"] = dtc()
models["Gaussian naive bayes"] = gnbc()
models["Bernoulli naive bayes"] = bnbc(binarize=0.5)
models["Multinomial naive bayes"] = mnbc()
models["SGD classifier"] = sgdc(max_iter=10000)
models["Ridge classifier"] = rc()
if len(self.Xt_train) < 10000:
models["SVM classifier RBF"] = svc(gamma='scale')
models["SVM classifier Linear"] = svc(kernel='linear')
models["SVM classifier Poly"] = svc(kernel='poly')
if self.Xt_train.shape[0] < 10000 or self.Xt_train.shape[1] < 5:
models["Gradient boosting classifier"] = gbc()
models["Random forest classifier"] = rfc(n_estimators=100)
if struct == 'multiclass':
models["Logistic classifier multinomial"] = logitc(multi_class='multinomial', solver='lbfgs')
models["Logistic classifier auto"] = logitc(multi_class='auto')
models["Logistic One vs Rest"] = ovrc(logitc())
models["Logistic One vs One"] = ovoc(logitc())
if struct == 'binary':
models["Logistic classifier"] = logitc(max_iter=2000)
self.models = models
kf = StratifiedKFold(n_splits=folds, shuffle=True)
results = []
names = []
et = []
for model_name in models:
start = time.time()
cv_scores = cross_val_score(models[model_name], self.Xt_train, self.yt_train, cv=kf, scoring=metric, error_score=np.nan)
results.append(cv_scores)
names.append(model_name)
et.append((time.time() - start))
#print(model_name, time.time() - start)
report = pd.DataFrame({'Model': names, 'Score': results, 'Elapsed Time': et})
report['Score (avg)'] = report.Score.apply(lambda x: x.mean())
report['Score (std)'] = report.Score.apply(lambda x: x.std())
report['Score (VC)'] = 100 * report['Score (std)'] / report['Score (avg)']
report.sort_values(by='Score (avg)', inplace=True, ascending=False)
report.drop('Score', axis=1, inplace=True)
report.reset_index(inplace=True, drop=True)
self.report_performance = report
if printt:
print('\n')
print(self.report_width * '*', '\n*')
print('* CLASSIFICATION RESULTS - BEFORE PARAMETERS BOOSTING \n*')
print(self.report_width * '*', '')
print(report)
print('\n')
if graph:
fig, ax = plt.subplots(figsize=(size, 0.5 * size))
plt.title('Classifier Comparison')
#ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.xticks(rotation=45)
plt.subplots_adjust(hspace=0.0, bottom=0.25)
self.graphs_model.append(fig)
plt.show()
return None
train, test = train_test_split(data_mod, test_size=0.2)
# X = diabetes[['Pregnancies','Glucose','BloodPressure','SkinThickness','Insulin','BMI','DiabetesPedigreeFunction','Age']]
# y = diabetes[['Outcome']]
# X_train, X_test, y_train, y_test = train_test_split(X, y, random_state = 2)
print(data_mod.shape)
print(train.shape)
print(test.shape)
features = [
'Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'BMI', 'Age',
'Insulin', 'DiabetesPedigreeFunction'
]
target = 'Outcome'
classifiers = [knnc(), dtc(), SVC(gamma='auto'), SVC(kernel='linear'), gnb()]
classifier_names = [
'K nearest neighbors', 'Decision Tree Classifier',
'SVM classifier with RBF kernel', 'SVM classifier with linear kernel',
'Gaussian Naive Bayes'
]
for clf, clf_name in zip(classifiers, classifier_names):
cv_scores = cross_val_score(clf, train[features], train[target], cv=5)
print(clf_name, ' mean accuracy: ', round(cv_scores.mean() * 100, 3),
'% std: ', round(cv_scores.var() * 100, 3), '%')
final_model_smv_lin = SVC(kernel='linear',
probability=True).fit(train[features], train[target])
# final_model_gnb = gnb().fit(train[features], train[target])
]
target = ['defects']
# print(df)
# print(df.shape)
# print(train[features].shape)
# print(train[target].shape)
# print(train[target].values.ravel().shape)
# # print(test.shape)
# Y = train[target].values.reshape(train[target].shape[0])
# print(Y)
classifiers = [knnc(), dtc(), SVC(), SVC(kernel='linear'), gnb()]
classifier_names = [
'K nearest neighbors', 'Decision Tree Classifier',
'SVM classifier with RBF kernel', 'SVM classifier with linear kernel',
'Gaussian Naive Bayes'
]
# for clf, clf_name in zip(classifiers, classifier_names):
# cv_scores = cross_val_score(clf, train[features], train[target], cv=5)
# print(clf_name, ' mean accuracy: ', round(cv_scores.mean()*100, 3), \
# '% std: ', round(cv_scores.var()*100, 3),'%')
# final_model_smv_lin = SVC(kernel='linear').fit(train[features], Y)
final_model_gnb = gnb().fit(train[features], train[target])