diff --git a/sklearn/decomposition/fastica_.py b/sklearn/decomposition/fastica_.py
index dd04e8e93a1c6..d841926cdfc87 100644
--- a/sklearn/decomposition/fastica_.py
+++ b/sklearn/decomposition/fastica_.py
@@ -436,11 +436,18 @@ def my_g(x):
     mixing_ : array, shape (n_features, n_components)
         The mixing matrix.
 
+    mean_ : array, shape(n_features)
+        The mean over features. Only set if `self.whiten` is True.
+
     n_iter_ : int
         If the algorithm is "deflation", n_iter is the
         maximum number of iterations run across all components. Else
         they are just the number of iterations taken to converge.
 
+    whitening_ : array, shape (n_components, n_features)
+        Only set if whiten is 'True'. This is the pre-whitening matrix
+        that projects data onto the first `n_components` principal components.
+
     Examples
     --------
     >>> from sklearn.datasets import load_digits
diff --git a/sklearn/decomposition/nmf.py b/sklearn/decomposition/nmf.py
index ae624e2a1b4ab..f64bc34b7fad7 100644
--- a/sklearn/decomposition/nmf.py
+++ b/sklearn/decomposition/nmf.py
@@ -1192,6 +1192,11 @@ class NMF(BaseEstimator, TransformerMixin):
     components_ : array, [n_components, n_features]
         Factorization matrix, sometimes called 'dictionary'.
 
+    n_components_ : integer
+        The number of components. It is same as the `n_components` parameter
+        if it was given. Otherwise, it will be same as the number of
+        features.
+
     reconstruction_err_ : number
         Frobenius norm of the matrix difference, or beta-divergence, between
         the training data ``X`` and the reconstructed data ``WH`` from
diff --git a/sklearn/decomposition/pca.py b/sklearn/decomposition/pca.py
index ccde667d0d20d..f8c28e1373b6e 100644
--- a/sklearn/decomposition/pca.py
+++ b/sklearn/decomposition/pca.py
@@ -237,6 +237,12 @@ class PCA(_BasePCA):
         n_components, or the lesser value of n_features and n_samples
         if n_components is None.
 
+    n_features_ : int
+        Number of features in the training data.
+
+    n_samples_ : int
+        Number of samples in the training data.
+
     noise_variance_ : float
         The estimated noise covariance following the Probabilistic PCA model
         from Tipping and Bishop 1999. See "Pattern Recognition and
diff --git a/sklearn/random_projection.py b/sklearn/random_projection.py
index f4fa2c608b842..8297a42ab17f8 100644
--- a/sklearn/random_projection.py
+++ b/sklearn/random_projection.py
@@ -453,7 +453,7 @@ class GaussianRandomProjection(BaseRandomProjection):
 
     Attributes
     ----------
-    n_component_ : int
+    n_components_ : int
         Concrete number of components computed when n_components="auto".
 
     components_ : numpy array of shape [n_components, n_features]
@@ -573,7 +573,7 @@ class SparseRandomProjection(BaseRandomProjection):
 
     Attributes
     ----------
-    n_component_ : int
+    n_components_ : int
         Concrete number of components computed when n_components="auto".
 
     components_ : CSR matrix with shape [n_components, n_features]