def fit(self, X, y):
X_train, X_test, y_train, y_test = T_T_S(
X, y, test_size=self.test_size, random_state=self.random_state)
dim = X_train.shape[1]
self.indices_ = tuple(range(dim))
self.subsets_ = [self.indices_]
score = self._calc_score(X_train, y_train, X_test, y_test,
self.indices_)
self.scores_ = [score]
while dim > self.k_features:
scores = []
subsets = []
for p in combinations(self.indices_, r=dim - 1):
score = self._calc_score(X_train, y_train, X_test, y_test, p)
scores.append(score)
subsets.append(p)
# print(p, score)
# p = score =
# (0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11) 0.8863636363636364
# (0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12) 0.9090909090909091
# (0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 12) 0.9318181818181818
best = np.argmax(scores)
self.indices_ = subsets[best] # finds and saves the best features
self.subsets_.append(self.indices_)
dim -= 1
self.scores_.append(scores[best])
#print('Number of dimensions and indices ', dim, self.indices_)
self.k_score_ = self.scores_[-1]
return self
'Class label', 'Alcohol', 'Malic Acid', 'Ash', 'Alcalinity of ash',
'Magnesium', 'Total phenols', 'Flavanoids', 'Nonflavanoids phenols',
'Proanthocyanins', 'Color Intensity', 'Hue',
'OD280/OD315 of diluted wines', 'Proline'
]
print('Wine data')
print()
print(df_wine.head())
print()
print(df_wine.tail())
print()
X, y = df_wine.iloc[:, 1:].values, df_wine.iloc[:, 0].values
X_train, X_test, y_train, y_test =\
T_T_S(X,y,test_size = .3, random_state = 0, stratify = y)
# stratify ensures same class proportions of training and test data sets
print('Training Data Size = ', len(X_train))
print('Test Data Size = ', len(X_test))
print()
pause()
feat_labels = df_wine.columns[1:]
forest = RFC(n_estimators=500, random_state=1)
forest.fit(X_train, y_train)
tic_fwd = time()
sfs_forward = SequentialFeatureSelector(forest,
n_features_to_select=5,
direction='forward').fit(