from app.dame_utils import DameUtils
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('ml',
choices=[
'nltk', 'svc', 'sgd', 'gaussianNB', 'multinomialNB',
'bernoulliNB', 'forest', 'tree', 'mlp'
])
parser.add_argument('--noshow', dest='noshow', action='store_true')
parser.add_argument('--verbose', default=False, action="store_true")
args = parser.parse_args()
ds = DameSexmachine()
X = np.array(ds.features_list(path="files/names/allnoundefined.csv"))
y = ds.gender_list(path="files/names/allnoundefined.csv")
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
if (args.verbose):
print(X)
print(y)
if (args.ml == "svc"):
svc = SVC(random_state=42)
svc.fit(X_train, y_train)
svc_disp = plot_roc_curve(svc, X_test, y_test)
elif (args.ml == "forest"):
rfc = RandomForestClassifier(n_estimators=10, random_state=42)
rfc.fit(X_train, y_train)
def test_sexmachine_features_list_all(self):
s = DameSexmachine()
fl = s.features_list(path="files/names/all.csv")
self.assertTrue(len(fl) > 1000)
def test_sexmachine_features_list_all_method_returns_correct_result(self):
s = DameSexmachine()
fl = s.features_list(path="files/names/all.csv")
self.assertTrue(len(fl) > 1000)
def test_sexmachine_features_list(self):
s = DameSexmachine()
fl = s.features_list()
self.assertTrue(len(fl) > 20)
def test_sexmachine_features_list_method_returns_correct_result(self):
s = DameSexmachine()
fl = s.features_list()
self.assertTrue(len(fl) > 20)
