def feature_selection(self, X, y, state='train'):
if state == 'train':
print('Feature_selection starts!')
fb = FeatureBand(r0=self.fb_r0,
n0=self.fb_n0,
clf=load_clf('logistic'),
max_iter=self.fb_max_iter,
k=self.fb_k,
population_size=self.fb_population_size,
local_search=True)
times, iter_best, global_best = fb.fit(X,
y,
metrics=self.fb_metric)
for key in self.train_data:
self.train_data[key] = fb.transform(self.train_data[key])
self.fb_operator = fb
if self.headers is not None:
self.selected_headers = self.headers[fb.featrue_selected]
return 0
DATASET = "rna" # ["madelon", "basehock", "usps", "coil20"]
FINAL_CLASSIFIER = "logistic" # ["knn", "logistic", "linear_svm"]
k = 300
n_splits = 5
r0 = 50
max_iter = 200
population_size = 10
n0 = 500
#x, y = load_dataset(DATASET)
x = np.array(pd.read_csv('./medicaldata/tpotfssRNASeq/Xtrain.csv'))
y = np.array(pd.read_csv('./medicaldata/tpotfssRNASeq/ytrain.csv',
header=None))
print(x.shape, y.shape)
clf = load_clf(FINAL_CLASSIFIER)
skf = StratifiedKFold(n_splits=n_splits, random_state=42)
fold_index = 0
perfs = []
for train_index, test_index in skf.split(x, y):
print("fold:", fold_index + 1)
if fold_index != 0:
continue
#x_train, x_test = x[train_index], x[test_index]
#y_train, y_test = y[train_index], y[test_index]
x_train, y_train = x, y
fb = FeatureBand(r0=r0,
n0=n0,
clf=clf,
max_iter=max_iter,
from featureband.CCM.core import ccm
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import accuracy_score
DATASET = "usps" # ["madelon", "basehock", "usps", "coil20"]
FINAL_CLASSIFIER = "knn" # ["knn", "logistic", "linear_svm"]
n_splits = 5
x, y = load_dataset(DATASET)
n_samples = np.random.choice(x.shape[0], 3000, replace=False)
x = x[n_samples, :]
y = y[n_samples]
print(x.shape, y.shape)
knn = load_clf("knn")
logistic = load_clf("logistic")
knn_perfs = np.zeros(10)
logistic_perfs = np.zeros(10)
skf = StratifiedKFold(n_splits=n_splits, random_state=42)
fold_index = 0
fout = open("usps_data.txt", 'w')
for train_index, test_index in skf.split(x, y):
print("fold:", fold_index + 1)
x_train, x_test = x[train_index], x[test_index]
y_train, y_test = y[train_index], y[test_index]
for i, k in enumerate(np.arange(10, 101, 10)):
rank = ccm.ccm(x_train,