fwature importance random forest sklearn code example
Example 1: random forrest plotting feature importance function
def plot_feature_importances(model):
n_features = data_train.shape[1]
plt.figure(figsize=(20,20))
plt.barh(range(n_features), model.feature_importances_, align='center')
plt.yticks(np.arange(n_features), data_train.columns.values)
plt.xlabel('Feature importance')
plt.ylabel('Feature')
Example 2: feature_importances_ sklearn
print(__doc__)
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_classification
from sklearn.ensemble import ExtraTreesClassifier
X, y = make_classification(n_samples=1000,
n_features=10,
n_informative=3,
n_redundant=0,
n_repeated=0,
n_classes=2,
random_state=0,
shuffle=False)
forest = ExtraTreesClassifier(n_estimators=250,
random_state=0)
forest.fit(X, y)
importances = forest.feature_importances_
std = np.std([tree.feature_importances_ for tree in forest.estimators_],
axis=0)
indices = np.argsort(importances)[::-1]
print("Feature ranking:")
for f in range(X.shape[1]):
print("%d. feature %d (%f)" % (f + 1, indices[f], importances[indices[f]]))
plt.figure()
plt.title("Feature importances")
plt.bar(range(X.shape[1]), importances[indices],
color="r", yerr=std[indices], align="center")
plt.xticks(range(X.shape[1]), indices)
plt.xlim([-1, X.shape[1]])
plt.show()