def get_model(choice='lr', class_weight=None):
if choice == 'svc':
model = svc(verbose=1, class_weight=class_weight, n_jobs=-1)
elif choice == 'lsvc':
model = lsvc(class_weight=class_weight, n_jobs=-1)
elif choice == 'knn':
model = KNeighborsClassifier()
elif choice == 'msvm':
model = MulticlassSVM(C=0.1,
tol=0.01,
max_iter=100,
random_state=0,
verbose=1)
elif choice == 'gnb':
model = gnb(class_weight=class_weight)
elif choice == 'gpc':
model = gpc(class_weight=class_weight)
elif choice == 'sgdc':
model = sgdc(class_weight=class_weight)
elif choice == 'rf':
model = rf(class_weight=class_weight)
# elif choice == 'vw':
# model = vw()
else:
model = lr(class_weight=class_weight)
return model
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
sex = 'F'
scaler = StandardScaler()
data_partial = data[data['Sex'] == sex].drop('Sex', axis=1)
# corr_matrix_f, corr_matrix_m = data_f.corr(), data_m.corr()
# plot_corr_matrices(corr_matrix_f, corr_matrix_m)
y = data_partial['EmoState']
X = scaler.fit_transform(data_partial.drop('EmoState', axis=1))
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=71)
models = (('DTC', dtc()), ('SVM', svc(C=10)), ('KNN', knc(n_neighbors=10)),
('SGDC', sgdc()), ('GNBC', gnbc()), ('MLPC',
mlpc(max_iter=1000,
learning_rate='adaptive')))
results = []
names = []
seed = 13
scoring = 'accuracy'
for name, model in models:
kfold = model_selection.KFold(n_splits=10, random_state=seed, shuffle=True)
cv_results = model_selection.cross_val_score(model,
X_train,
y_train,
cv=kfold,
scoring=scoring)
results.append(cv_results)
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