def main(project_name, ind=None):
training = pd.read_csv(os.path.normpath(
os.path.realpath(
r"dataset\{0}\classes\training.csv".format(project_name))),
sep=';')
testing = pd.read_csv(os.path.normpath(
os.path.realpath(
r"dataset\{0}\classes\testing.csv".format(project_name))),
sep=';')
training_y = training['Bugged'].apply(lambda x: 1 if x else 0)
training_X = training.drop('Bugged', axis=1)
testing_y = testing['Bugged'].apply(lambda x: 1 if x else 0)
testing_X = testing.drop('Bugged', axis=1)
clf = HungaBungaClassifier(brain=True,
ind=ind,
scoring=metrics.make_scorer(pr_auc_score,
needs_proba=True))
clf.fit(training_X, training_y)
model = clf.model
print(
json.dumps({
'model':
model.__class__.__name__,
'score':
'%0.3f' % eval(model, model.classes_, testing_X, testing_y)
}))
from sklearn import datasets iris = datasets.load_iris() x, y = iris.data, iris.target from hunga_bunga import HungaBungaClassifier, HungaBungaRegressor clf = HungaBungaClassifier() clf.fit(x, y) clf.predict(x)
a[c] = str(f) c = c+1 #print(a) X = data[a] # Features y = data['0'] # Target variable # Split dataset into training set and test set X_c, X_r, y_c, y_r = train_test_split(X, y, test_size=0.25, random_state=1) # 75% training and 25% test # iris = datasets.load_iris() # X_c, y_c = iris.data, iris.target # X_r, y_r = gen_reg_data(10, 3, 100, 3, sum, 0.3) # ---------- Classification ---------- clf = HungaBungaClassifier() clf.fit(X_c, y_c) print(clf.predict(X_c)) # ---------- Regression ---------- # mdl = HungaBungaRegressor() # mdl.fit(X_r, y_r) # print(mdl.predict(X_c))
fn_d = 'Enterobase.xlsx'
WS = pd.read_excel(fn_d)
sb = WS['strain_barcode']
st = WS['source_type']
y_ = []
for i in range(len(g_id)):
g_id[i] = g_id[i].strip('>')
y_.append(st[g_id[i] == sb].ravel()[0])
y = np.array(y_)
y[y == 'Human'] = 0
y[y == 'Avian'] = 1
y = y.astype('int')
## Filter Features
clf = ExtraTreesClassifier(n_estimators=50)
clf = clf.fit(X, y)
clf.feature_importances_
selectmodel = SelectFromModel(clf, prefit=True)
X_new = selectmodel.transform(X)
## Hunga Bunga
clf = HungaBungaClassifier()
clf.fit(X_new, y)