importances = forest.feature_importances_
indices = np.argsort(importances)[::-1]
# np.argsort(importances)
# np.argsort(importances)[::-1]
for f in range(X_train.shape[1]):
print("%2d) % - *s %f" %
(f + 1, 30, feat_labels[f], importances[indices[f]]))
plt.title("Feature Importances")
plt.bar(range(X_train.shape[1]),
importances[indices],
color="lightblue",
align="center")
plt.xticks(range(X_train.shape[1]), feat_labels, rotation=90)
plt.xlim([-1, X_train.shape[1]])
plt.tight_layout()
plt.show()
from sklearn.feature_selection import SelectFromModel
X_selected = forest.SelectFromModel(X_train, threshold=0.15)
X_selected = SelectFromModel(forest, threshold=0.15)
sfm.fit(X, y)
n_features = sfm.transform(X).shape[1]
X_selected = forest.transform(X_train, threshold=0.15)
X_selected.shape
