Fix issues in 05.11

notebooks/05.11-K-Means.md

@@ -310,7 +310,7 @@ Let's see how it does:
 from sklearn.manifold import TSNE
 
 # Project the data: this step will take several seconds
-tsne = TSNE(n_components=2, init='pca', random_state=0)
+tsne = TSNE(n_components=2, init='random', random_state=0)
 digits_proj = tsne.fit_transform(digits.data)
 
 # Compute the clusters
@@ -327,7 +327,7 @@ for i in range(10):
 accuracy_score(digits.target, labels)
 ```
 
-That's nearly 94% classification accuracy *without using the labels*.
+That's nearly 92% classification accuracy *without using the labels*.
 This is the power of unsupervised learning when used carefully: it can extract information from the dataset that it might be difficult to do by hand or by eye.
 
 
@@ -393,6 +393,8 @@ Now let's reduce these 16 million colors to just 16 colors, using a *k*-means cl
 Because we are dealing with a very large dataset, we will use the mini batch *k*-means, which operates on subsets of the data to compute the result much more quickly than the standard *k*-means algorithm:
 
 ```python
+import warnings; warnings.simplefilter('ignore')  # Fix NumPy issues.
+
 from sklearn.cluster import MiniBatchKMeans
 kmeans = MiniBatchKMeans(16)
 kmeans.fit(data)