for row in x_tester:
for var in row:
if var not in new_x_tester:
new_x_tester[var] = []
new_x_tester[var].append(row[var])
#print(new_x_tester)
t = clf.classifier.predict_proba(new_x_tester)
results_y = []
predicted_y = []
for t, i in enumerate(t):
print(y_tester[t], i[1]*100)
results_y.append(y_tester[t])
predicted_y.append(i[1]*100)
mean_abs_err, mean_squ_err, r2score, kl_divergence = regressionMetrics(results_y, predicted_y)
printer.regressionEvaluation(mean_abs_err, mean_squ_err, r2score, kl_divergence, "Regression Evaluation")
# coefs = clf.classifier.named_steps['classifier'].coef_
# feature_names = clf.classifier.named_steps['feats'].get_params()['transformer_list'][0][1].named_steps['feature'].get_feature_names()
# coef_dict = {}
# for coef, feat in zip(coefs,feature_names):
# coef_dict[feat] = coef
#print(coef_dict)
# print(coef_dict)
# for word in coef_dict:
# print(len(coef_dict[word]))
class SVM:
X_train = []
Y_train = []
X_development = []
Y_development = []
X_test = []
Y_predicted = []
labels = []
features = []
def __init__(self, data, predict_method, show_fitting):
self.X_train = data.X_train
self.Y_train = data.Y_train
self.X_development = data.X_development
self.Y_development = data.Y_development
self.X_test = data.X_test
self.labels = data.labels
self.predict_method = predict_method
self.show_fitting = show_fitting
def classify(self, features, classifier=None):
feature_union = ('feats', FeatureUnion(features))
if classifier == None:
classifier = SGDClassifier(loss='hinge',
random_state=42,
max_iter=50,
tol=None)
self.classifier = Pipeline([feature_union, ('classifier', classifier)])
print(self.classifier)
self.printer = Printer('Model Fitting', self.show_fitting)
self.classifier.fit(self.X_train, self.Y_train)
self.printer.duration()
def evaluate(self):
if self.X_development:
self.Y_development_predicted = self.classifier.predict(
self.X_development)
print(self.X_development)
#print(self.classifier.predict_proba(self.X_development))
#print(self.Y_development[:20], self.Y_development_predicted[:20])
if self.X_test:
self.Y_test_predicted = self.classifier.predict(self.X_test)
if self.predict_method == 'classification':
self.accuracy, self.precision, self.recall, self.f1score = classificationMetrics(
self.Y_development, self.Y_development_predicted, self.labels)
elif self.predict_method == 'regression':
# self.Y_development_predicted = self.classifier.score(self.X_development, self.Y_development)
# print(self.Y_development_predicted)
self.mean_abs_err, self.mean_squ_err, self.r2score, self.kl_divergence = regressionMetrics(
self.Y_development, self.Y_development_predicted, self.labels)
def printBasicEvaluation(self):
if self.predict_method == 'classification':
self.printer.evaluation(self.accuracy, self.precision, self.recall,
self.f1score, "Classification Evaluation")
elif self.predict_method == 'regression':
self.printer.regressionEvaluation(self.mean_abs_err,
self.mean_squ_err, self.r2score,
self.kl_divergence,
"Regression Evaluation")
def printClassEvaluation(self):
self.printer.classEvaluation(self.Y_development,
self.Y_development_predicted, self.labels)