take into account raghav comments

benchmarks/bench_isolation_forest.py

@@ -20,7 +20,6 @@
 np.random.seed(1)
 
 datasets = ['http', 'smtp', 'SA', 'SF', 'shuttle', 'forestcover']
-# datasets = ['http']
 
 for dat in datasets:
  # loading and vectorization
@@ -34,7 +33,7 @@
  dataset = fetch_mldata('shuttle')
  X = dataset.data
  y = dataset.target
- sh(X, y)
+ X, y = sh(X, y)
  # we remove data with label 4
  # normal data are then those of class 1
  s = (y != 4)
@@ -95,7 +94,7 @@
  scoring = - model.decision_function(X_test) # the lower, the more normal
 
  # Show score histograms
- f, ax = plt.subplots(3, sharex=True, sharey=True)
+ fig, ax = plt.subplots(3, sharex=True, sharey=True)
  bins = np.linspace(-0.5, 0.5, 200)
  ax[0].hist(scoring, bins, color='black')
  ax[0].set_title('decision function for %s dataset' % dat)

sklearn/ensemble/iforest.py

@@ -193,7 +193,7 @@ def fit(self, X, y=None, sample_weight=None):
  return self
 
  def predict(self, X):
- """Outlyingness of observations in X according to the fitted model.
+ """Predict if a particular sample is an outlier or not.
 
  Parameters
  ----------
@@ -206,7 +206,7 @@ def predict(self, X):
  -------
  is_inlier : array, shape = (n_samples, )
  For each observations, tells whether or not (+1 or -1) it should
- be considered as an outlier according to the fitted model.
+ be considered as an inlier according to the fitted model.
 
  """
  X = check_array(X, accept_sparse='csr')