def test_feature_importances_w_subestimators():
rf = Mock()
tree_1 = Mock()
tree_1.feature_importances_ = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
tree_2 = Mock()
tree_2.feature_importances_ = np.array([0.10, 0.10, 0.8, 0.06, 0.01])
tree_3 = Mock()
tree_3.feature_importances_ = np.array([0.09, 0.01, 0.9, 0.12, 0.02])
tree_4 = Mock()
tree_4.feature_importances_ = np.array([0.12, 0.10, 0.8, 0.06, 0.01])
rf.estimators_ = [tree_1, tree_2, tree_3, tree_4]
rf.feature_importances_ = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
plot.feature_importances(rf)
def test_feature_importances_w_subestimators():
rf = Mock()
tree_1 = Mock()
tree_1.feature_importances_ = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
tree_2 = Mock()
tree_2.feature_importances_ = np.array([0.10, 0.10, 0.8, 0.06, 0.01])
tree_3 = Mock()
tree_3.feature_importances_ = np.array([0.09, 0.01, 0.9, 0.12, 0.02])
tree_4 = Mock()
tree_4.feature_importances_ = np.array([0.12, 0.10, 0.8, 0.06, 0.01])
rf.estimators_ = [tree_1, tree_2, tree_3, tree_4]
rf.feature_importances_ = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
plot.feature_importances(rf)
u'seaborn-colorblind',
u'seaborn-deep',
u'seaborn-whitegrid',
u'seaborn-bright',
u'seaborn-poster',
u'seaborn-muted',
u'seaborn-paper',
u'seaborn-white',
u'seaborn-pastel',
u'seaborn-dark',
u'seaborn-dark-palette']
'''
my_dpi = 96
plt.style.use('ggplot')
plt.rcParams["figure.figsize"] = (11.69, 8.27)
plot.feature_importances(classifier, feature_names=feature_names)
# plt.xlabel('Feature Names')
plt.ylabel('Feature Importance Score (%)')
# plt.title('Features Importance')
plt.gca().xaxis.set_minor_formatter(ticker.NullFormatter())
plt.xticks(rotation=90)
f = plt.gcf()
f.subplots_adjust(bottom=0.4)
plt.savefig("out-stats-graphs/RF_Feature_Importance1.pdf")
plt.style.use('fivethirtyeight')
plt.rcParams["figure.figsize"] = (1164 / my_dpi, 1024 / my_dpi)
plot.feature_importances(classifier, feature_names=feature_names)
plt.ylabel('Feature Importance Score (%)')
plt.xlabel('Feature Names')
plt.gca().xaxis.set_minor_formatter(ticker.NullFormatter())
def test_feature_importances_feature_names():
feature_importances = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
feature_names = ['thing_a', 'thing_b', 'thing_c', 'thing_d', 'thing_e']
plot.feature_importances(feature_importances, feature_names=feature_names)
def test_feature_importances_top3():
feature_importances = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
plot.feature_importances(feature_importances, top_n=3)
def test_feature_importances_from_array():
feature_importances = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
plot.feature_importances(feature_importances)
def test_feature_importances():
model = Mock()
model.feature_importances_ = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
plot.feature_importances(model)
def test_feature_importances(self):
with self.assertRaisesRegexp(ValueError, "needed to plot"):
plot.feature_importances(None)
def test_feature_importances_feature_names():
feature_importances = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
feature_names = ['thing_a', 'thing_b', 'thing_c', 'thing_d', 'thing_e']
plot.feature_importances(feature_importances, feature_names=feature_names)
def test_feature_importances_top3():
feature_importances = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
plot.feature_importances(feature_importances, top_n=3)
def test_feature_importances_from_array():
feature_importances = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
plot.feature_importances(feature_importances)
def test_feature_importances():
model = Mock()
model.feature_importances_ = np.array([0.12, 0.10, 0.8, 0.06, 0.03])
plot.feature_importances(model)
""" Feature importances plot """ import matplotlib.pyplot as plt from sklearn import datasets from sklearn.ensemble import RandomForestClassifier from sklearn.model_selection import train_test_split from sklearn_evaluation import plot X, y = datasets.make_classification(200, 20, n_informative=5, class_sep=0.65) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3) model = RandomForestClassifier(n_estimators=1) model.fit(X_train, y_train) # plot all features ax = plot.feature_importances(model) plt.show() # only top 5 plot.feature_importances(model, top_n=5) plt.show()
import matplotlib.pyplot as plt from sklearn import datasets from sklearn.ensemble import RandomForestClassifier from sklearn.cross_validation import train_test_split from sklearn_evaluation import plot data = datasets.make_classification(200, 10, 5, class_sep=0.65) X = data[0] y = data[1] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3) est = RandomForestClassifier() est.fit(X_train, y_train) plot.feature_importances(est, top_n=5) plt.show()
