Fix Sobol' typos in usage

examples/sampler/initial-sampling-method-integer.py

@@ -13,7 +13,7 @@
 (10 by default). The downside to this is that there is no guarantee that
 these samples are spread out evenly across all the dimensions.
 
-Sampling methods as Latin hypercube, Sobol, Halton and Hammersly
+Sampling methods as Latin hypercube, Sobol', Halton and Hammersly
 take advantage of the fact that we know beforehand how many random
 points we want to sample. Then these points can be "spread out" in
 such a way that each dimension is explored.
@@ -64,15 +64,15 @@ def plot_searchspace(x, title):
 x_label.append("random")
 
 #############################################################################
-# Sobol
-# -----
+# Sobol'
+# ------
 
 sobol = Sobol()
 x = sobol.generate(space.dimensions, n_samples)
-plot_searchspace(x, 'Sobol')
+plot_searchspace(x, "Sobol'")
 print("empty fields: %d" % (36 - np.size(np.unique(x, axis=0), 0)))
 pdist_data.append(pdist(x).flatten())
-x_label.append("sobol")
+x_label.append("sobol'")
 
 #############################################################################
 # Classic latin hypercube sampling

examples/sampler/initial-sampling-method.py

@@ -14,7 +14,7 @@
 (10 by default). The downside to this is that there is no guarantee that
 these samples are spread out evenly across all the dimensions.
 
-Sampling methods as Latin hypercube, Sobol, Halton and Hammersly
+Sampling methods as Latin hypercube, Sobol', Halton and Hammersly
 take advantage of the fact that we know beforehand how many random
 points we want to sample. Then these points can be "spread out" in
 such a way that each dimension is explored.
@@ -64,14 +64,14 @@ def plot_searchspace(x, title):
 x_label.append("random")
 
 #############################################################################
-# Sobol
-# -----
+# Sobol'
+# ------
 
 sobol = Sobol()
 x = sobol.generate(space.dimensions, n_samples)
-plot_searchspace(x, 'Sobol')
+plot_searchspace(x, "Sobol'")
 pdist_data.append(pdist(x).flatten())
-x_label.append("sobol")
+x_label.append("sobol'")
 
 #############################################################################
 # Classic Latin hypercube sampling

examples/sampler/sampling_comparison.py

@@ -14,7 +14,7 @@
 
 * Halton sequence,
 * Hammersly sequence,
-* Sobol sequence and
+* Sobol' sequence and
 * Latin hypercube sampling
 
 as initial points. The purely random point generation is used as
@@ -153,7 +153,7 @@ def run_measure(initial_point_generator, n_initial_points=10):
 plot = plot_convergence([("random", dummy_res),
                         ("lhs", lhs_res),
                         ("lhs_maximin", lhs2_res),
-                        ("sobol", sobol_res),
+                        ("sobol'", sobol_res),
                         ("halton", halton_res),
                         ("hammersly", hammersly_res),
                         ("grid", grid_res)],

skopt/optimizer/base.py

@@ -84,7 +84,7 @@ def base_minimize(func, dimensions, base_estimator,
         Sets a initial points generator. Can be either
 
         - `"random"` for uniform random numbers,
-        - `"sobol"` for a Sobol sequence,
+        - `"sobol"` for a Sobol' sequence,
         - `"halton"` for a Halton sequence,
         - `"hammersly"` for a Hammersly sequence,
         - `"lhs"` for a latin hypercube sequence,

skopt/optimizer/dummy.py

@@ -40,7 +40,7 @@ def dummy_minimize(func, dimensions, n_calls=100,
         Sets a initial points generator. Can be either
 
         - `"random"` for uniform random numbers,
-        - `"sobol"` for a Sobol sequence,
+        - `"sobol"` for a Sobol' sequence,
         - `"halton"` for a Halton sequence,
         - `"hammersly"` for a Hammersly sequence,
         - `"lhs"` for a latin hypercube sequence,

skopt/optimizer/forest.py

@@ -92,7 +92,7 @@ def forest_minimize(func, dimensions, base_estimator="ET", n_calls=100,
         Sets a initial points generator. Can be either
 
         - `"random"` for uniform random numbers,
-        - `"sobol"` for a Sobol sequence,
+        - `"sobol"` for a Sobol' sequence,
         - `"halton"` for a Halton sequence,
         - `"hammersly"` for a Hammersly sequence,
         - `"lhs"` for a latin hypercube sequence,

skopt/optimizer/gbrt.py

@@ -79,7 +79,7 @@ def gbrt_minimize(func, dimensions, base_estimator=None,
         Sets a initial points generator. Can be either
 
         - `"random"` for uniform random numbers,
-        - `"sobol"` for a Sobol sequence,
+        - `"sobol"` for a Sobol' sequence,
         - `"halton"` for a Halton sequence,
         - `"hammersly"` for a Hammersly sequence,
         - `"lhs"` for a latin hypercube sequence,

skopt/optimizer/gp.py

@@ -100,7 +100,7 @@ def gp_minimize(func, dimensions, base_estimator=None,
         Sets a initial points generator. Can be either
 
         - `"random"` for uniform random numbers,
-        - `"sobol"` for a Sobol sequence,
+        - `"sobol"` for a Sobol' sequence,
         - `"halton"` for a Halton sequence,
         - `"hammersly"` for a Hammersly sequence,
         - `"lhs"` for a latin hypercube sequence,

skopt/optimizer/optimizer.py

@@ -76,7 +76,7 @@ class Optimizer(object):
         Sets a initial points generator. Can be either
 
         - `"random"` for uniform random numbers,
-        - `"sobol"` for a Sobol sequence,
+        - `"sobol"` for a Sobol' sequence,
         - `"halton"` for a Halton sequence,
         - `"hammersly"` for a Hammersly sequence,
         - `"lhs"` for a latin hypercube sequence,