From b54ee1b60839b0c70a67c7491b38c6021b1b60d0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aur=C3=A9lien=20Geron?= <ageron@users.noreply.github.com>
Date: Fri, 21 Dec 2018 10:18:31 +0800
Subject: [PATCH] Update notebooks 1 to 8 to latest library versions (in
 particular Scikit-Learn 0.20)

---
 01_the_machine_learning_landscape.ipynb       |   6 +-
 02_end_to_end_machine_learning_project.ipynb  |  59 +-
 03_classification.ipynb                       | 437 +++++++-------
 04_training_linear_models.ipynb               |  15 +-
 05_support_vector_machines.ipynb              |  83 ++-
 06_decision_trees.ipynb                       |   4 +-
 07_ensemble_learning_and_random_forests.ipynb | 141 +++--
 08_dimensionality_reduction.ipynb             | 535 +++++++++---------
 8 files changed, 694 insertions(+), 586 deletions(-)

diff --git a/01_the_machine_learning_landscape.ipynb b/01_the_machine_learning_landscape.ipynb
index 8b99fce..1ca8b0b 100644
--- a/01_the_machine_learning_landscape.ipynb
+++ b/01_the_machine_learning_landscape.ipynb
@@ -64,7 +64,7 @@
     "\n",
     "# Ignore useless warnings (see SciPy issue #5998)\n",
     "import warnings\n",
-    "warnings.filterwarnings(action=\"ignore\", module=\"scipy\", message=\"^internal gelsd\")"
+    "warnings.filterwarnings(action=\"ignore\", message=\"^internal gelsd\")"
    ]
   },
   {
@@ -407,7 +407,7 @@
    "source": [
     "cyprus_gdp_per_capita = gdp_per_capita.loc[\"Cyprus\"][\"GDP per capita\"]\n",
     "print(cyprus_gdp_per_capita)\n",
-    "cyprus_predicted_life_satisfaction = lin1.predict(cyprus_gdp_per_capita)[0][0]\n",
+    "cyprus_predicted_life_satisfaction = lin1.predict([[cyprus_gdp_per_capita]])[0][0]\n",
     "cyprus_predicted_life_satisfaction"
    ]
   },
@@ -719,7 +719,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.3"
+   "version": "3.6.6"
   },
   "nav_menu": {},
   "toc": {
diff --git a/02_end_to_end_machine_learning_project.ipynb b/02_end_to_end_machine_learning_project.ipynb
index 7e5480f..52ac5cb 100644
--- a/02_end_to_end_machine_learning_project.ipynb
+++ b/02_end_to_end_machine_learning_project.ipynb
@@ -661,15 +661,25 @@
     "sample_incomplete_rows"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Warning**: Since Scikit-Learn 0.20, the `sklearn.preprocessing.Imputer` class was replaced by the `sklearn.impute.SimpleImputer` class."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 49,
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sklearn.preprocessing import Imputer\n",
+    "try:\n",
+    "    from sklearn.impute import SimpleImputer # Scikit-Learn 0.20+\n",
+    "except ImportError:\n",
+    "    from sklearn.preprocessing import Imputer as SimpleImputer\n",
     "\n",
-    "imputer = Imputer(strategy=\"median\")"
+    "imputer = SimpleImputer(strategy=\"median\")"
    ]
   },
   {
@@ -798,7 +808,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "**Warning**: earlier versions of the book used the `LabelEncoder` class or Pandas' `Series.factorize()` method to encode string categorical attributes as integers. However, the `OrdinalEncoder` class that is planned to be introduced in Scikit-Learn 0.20 (see [PR #10521](https://github.com/scikit-learn/scikit-learn/issues/10521)) is preferable since it is designed for input features (`X` instead of labels `y`) and it plays well with pipelines (introduced later in this notebook). For now, we will import it from `future_encoders.py`, but once it is available you can import it directly from `sklearn.preprocessing`."
+    "**Warning**: earlier versions of the book used the `LabelEncoder` class or Pandas' `Series.factorize()` method to encode string categorical attributes as integers. However, the `OrdinalEncoder` class that was introduced in Scikit-Learn 0.20 (see [PR #10521](https://github.com/scikit-learn/scikit-learn/issues/10521)) is preferable since it is designed for input features (`X` instead of labels `y`) and it plays well with pipelines (introduced later in this notebook). If you are using an older version of Scikit-Learn (<0.20), then you can import it from `future_encoders.py` instead."
    ]
   },
   {
@@ -807,7 +817,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from future_encoders import OrdinalEncoder"
+    "try:\n",
+    "    from sklearn.preprocessing import OrdinalEncoder\n",
+    "except ImportError:\n",
+    "    from future_encoders import OrdinalEncoder # Scikit-Learn < 0.20"
    ]
   },
   {
@@ -834,7 +847,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "**Warning**: earlier versions of the book used the `LabelBinarizer` or `CategoricalEncoder` classes to convert each categorical value to a one-hot vector. It is now preferable to use the `OneHotEncoder` class. Right now it can only handle integer categorical inputs, but in Scikit-Learn 0.20 it will also handle string categorical inputs (see [PR #10521](https://github.com/scikit-learn/scikit-learn/issues/10521)). So for now we import it from `future_encoders.py`, but when Scikit-Learn 0.20 is released, you can import it from `sklearn.preprocessing` instead:"
+    "**Warning**: earlier versions of the book used the `LabelBinarizer` or `CategoricalEncoder` classes to convert each categorical value to a one-hot vector. It is now preferable to use the `OneHotEncoder` class. Since Scikit-Learn 0.20 it can handle string categorical inputs (see [PR #10521](https://github.com/scikit-learn/scikit-learn/issues/10521)), not just integer categorical inputs. If you are using an older version of Scikit-Learn, you can import the new version from `future_encoders.py`:"
    ]
   },
   {
@@ -843,7 +856,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from future_encoders import OneHotEncoder\n",
+    "try:\n",
+    "    from sklearn.preprocessing import OrdinalEncoder # just to raise an ImportError if Scikit-Learn < 0.20\n",
+    "    from sklearn.preprocessing import OneHotEncoder\n",
+    "except ImportError:\n",
+    "    from future_encoders import OneHotEncoder # Scikit-Learn < 0.20\n",
     "\n",
     "cat_encoder = OneHotEncoder()\n",
     "housing_cat_1hot = cat_encoder.fit_transform(housing_cat)\n",
@@ -959,7 +976,7 @@
     "from sklearn.preprocessing import StandardScaler\n",
     "\n",
     "num_pipeline = Pipeline([\n",
-    "        ('imputer', Imputer(strategy=\"median\")),\n",
+    "        ('imputer', SimpleImputer(strategy=\"median\")),\n",
     "        ('attribs_adder', CombinedAttributesAdder()),\n",
     "        ('std_scaler', StandardScaler()),\n",
     "    ])\n",
@@ -980,7 +997,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "**Warning**: earlier versions of the book applied different transformations to different columns using a solution based on a `DataFrameSelector` transformer and a `FeatureUnion` (see below). It is now preferable to use the `ColumnTransformer` class that will be introduced in Scikit-Learn 0.20. For now we import it from `future_encoders.py`, but when Scikit-Learn 0.20 is released, you can import it from `sklearn.compose` instead:"
+    "**Warning**: earlier versions of the book applied different transformations to different columns using a solution based on a `DataFrameSelector` transformer and a `FeatureUnion` (see below). It is now preferable to use the `ColumnTransformer` class that was introduced in Scikit-Learn 0.20. If you are using an older version of Scikit-Learn, you can import it from `future_encoders.py`:"
    ]
   },
   {
@@ -989,7 +1006,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from future_encoders import ColumnTransformer"
+    "try:\n",
+    "    from sklearn.compose import ColumnTransformer\n",
+    "except ImportError:\n",
+    "    from future_encoders import ColumnTransformer # Scikit-Learn < 0.20"
    ]
   },
   {
@@ -1070,7 +1090,7 @@
     "\n",
     "old_num_pipeline = Pipeline([\n",
     "        ('selector', OldDataFrameSelector(num_attribs)),\n",
-    "        ('imputer', Imputer(strategy=\"median\")),\n",
+    "        ('imputer', SimpleImputer(strategy=\"median\")),\n",
     "        ('attribs_adder', CombinedAttributesAdder()),\n",
     "        ('std_scaler', StandardScaler()),\n",
     "    ])\n",
@@ -1275,6 +1295,13 @@
     "display_scores(lin_rmse_scores)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Note**: we specify `n_estimators=10` to avoid a warning about the fact that the default value is going to change to 100 in Scikit-Learn 0.22."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 91,
@@ -1283,7 +1310,7 @@
    "source": [
     "from sklearn.ensemble import RandomForestRegressor\n",
     "\n",
-    "forest_reg = RandomForestRegressor(random_state=42)\n",
+    "forest_reg = RandomForestRegressor(n_estimators=10, random_state=42)\n",
     "forest_reg.fit(housing_prepared, housing_labels)"
    ]
   },
@@ -2114,10 +2141,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "param_grid = [\n",
-    "        {'preparation__num__imputer__strategy': ['mean', 'median', 'most_frequent'],\n",
-    "         'feature_selection__k': list(range(1, len(feature_importances) + 1))}\n",
-    "]\n",
+    "param_grid = [{\n",
+    "    'preparation__num__imputer__strategy': ['mean', 'median', 'most_frequent'],\n",
+    "    'feature_selection__k': list(range(1, len(feature_importances) + 1))\n",
+    "}]\n",
     "\n",
     "grid_search_prep = GridSearchCV(prepare_select_and_predict_pipeline, param_grid, cv=5,\n",
     "                                scoring='neg_mean_squared_error', verbose=2, n_jobs=4)\n",
@@ -2164,7 +2191,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.6.6"
   },
   "nav_menu": {
    "height": "279px",
diff --git a/03_classification.ipynb b/03_classification.ipynb
index 9812293..c25e2ef 100644
--- a/03_classification.ipynb
+++ b/03_classification.ipynb
@@ -66,15 +66,26 @@
     "# MNIST"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Warning**: `fetch_mldata()` is deprecated since Scikit-Learn 0.20. You should use `fetch_openml()` instead. However, it returns the unsorted MNIST dataset, whereas `fetch_mldata()` returned the dataset sorted by target (the training set and the test test were sorted separately). In general, this is fine, but if you want to get the exact same results as before, you need to sort the dataset using the following function:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sklearn.datasets import fetch_mldata\n",
-    "mnist = fetch_mldata('MNIST original')\n",
-    "mnist"
+    "def sort_by_target(mnist):\n",
+    "    reorder_train = np.array(sorted([(target, i) for i, target in enumerate(mnist.target[:60000])]))[:, 1]\n",
+    "    reorder_test = np.array(sorted([(target, i) for i, target in enumerate(mnist.target[60000:])]))[:, 1]\n",
+    "    mnist.data[:60000] = mnist.data[reorder_train]\n",
+    "    mnist.target[:60000] = mnist.target[reorder_train]\n",
+    "    mnist.data[60000:] = mnist.data[reorder_test + 60000]\n",
+    "    mnist.target[60000:] = mnist.target[reorder_test + 60000]"
    ]
   },
   {
@@ -82,6 +93,32 @@
    "execution_count": 3,
    "metadata": {},
    "outputs": [],
+   "source": [
+    "try:\n",
+    "    from sklearn.datasets import fetch_openml\n",
+    "    mnist = fetch_openml('mnist_784', version=1, cache=True)\n",
+    "    mnist.target = mnist.target.astype(np.int8) # fetch_openml() returns targets as strings\n",
+    "    sort_by_target(mnist) # fetch_openml() returns an unsorted dataset\n",
+    "except ImportError:\n",
+    "    from sklearn.datasets import fetch_mldata\n",
+    "    mnist = fetch_mldata('MNIST original')\n",
+    "mnist[\"data\"], mnist[\"target\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mnist.data.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "X, y = mnist[\"data\"], mnist[\"target\"]\n",
     "X.shape"
@@ -89,7 +126,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -98,7 +135,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -107,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -127,7 +164,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -140,7 +177,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -163,7 +200,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -176,7 +213,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -185,7 +222,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -194,7 +231,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -213,7 +250,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -221,21 +258,28 @@
     "y_test_5 = (y_test == 5)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Note**: a few hyperparameters will have a different default value in future versions of Scikit-Learn, so a warning is issued if you do not set them explicitly. This is why we set `max_iter=5` and `tol=-np.infty`, to get the same results as in the book, while avoiding the warnings."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn.linear_model import SGDClassifier\n",
     "\n",
-    "sgd_clf = SGDClassifier(max_iter=5, random_state=42)\n",
+    "sgd_clf = SGDClassifier(max_iter=5, tol=-np.infty, random_state=42)\n",
     "sgd_clf.fit(X_train, y_train_5)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -244,7 +288,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -254,7 +298,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -278,7 +322,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -292,7 +336,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -302,7 +346,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -313,7 +357,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -324,7 +368,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -333,7 +377,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -342,7 +386,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -353,7 +397,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -362,7 +406,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -371,7 +415,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -380,7 +424,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -390,7 +434,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -399,7 +443,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -409,7 +453,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -419,7 +463,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -428,7 +472,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 35,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -439,7 +483,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -456,7 +500,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -465,7 +509,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -476,7 +520,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -487,7 +531,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -507,7 +551,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -516,7 +560,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 42,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -525,7 +569,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -534,7 +578,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 44,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -543,7 +587,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 45,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -568,7 +612,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 46,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -579,7 +623,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 47,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -598,7 +642,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 48,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -607,21 +651,28 @@
     "roc_auc_score(y_train_5, y_scores)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Note**: we set `n_estimators=10` to avoid a warning about the fact that its default value will be set to 100 in Scikit-Learn 0.22."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 49,
    "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn.ensemble import RandomForestClassifier\n",
-    "forest_clf = RandomForestClassifier(random_state=42)\n",
+    "forest_clf = RandomForestClassifier(n_estimators=10, random_state=42)\n",
     "y_probas_forest = cross_val_predict(forest_clf, X_train, y_train_5, cv=3,\n",
     "                                    method=\"predict_proba\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 50,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -631,7 +682,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 51,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -645,7 +696,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 52,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -654,7 +705,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 53,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -664,7 +715,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 54,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -680,7 +731,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 55,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -690,7 +741,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 56,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -700,7 +751,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 57,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -709,7 +760,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 58,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -718,7 +769,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 59,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -727,19 +778,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 60,
    "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn.multiclass import OneVsOneClassifier\n",
-    "ovo_clf = OneVsOneClassifier(SGDClassifier(max_iter=5, random_state=42))\n",
+    "ovo_clf = OneVsOneClassifier(SGDClassifier(max_iter=5, tol=-np.infty, random_state=42))\n",
     "ovo_clf.fit(X_train, y_train)\n",
     "ovo_clf.predict([some_digit])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 61,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -748,7 +799,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": 62,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -758,7 +809,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 61,
+   "execution_count": 63,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -767,7 +818,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 62,
+   "execution_count": 64,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -776,7 +827,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 63,
+   "execution_count": 65,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -788,7 +839,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 64,
+   "execution_count": 66,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -799,7 +850,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 65,
+   "execution_count": 67,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -813,7 +864,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 66,
+   "execution_count": 68,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -824,7 +875,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 67,
+   "execution_count": 69,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -834,7 +885,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 70,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -846,7 +897,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 71,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -874,7 +925,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 72,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -890,7 +941,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 73,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -906,7 +957,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": 74,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -923,7 +974,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 75,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -937,7 +988,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 74,
+   "execution_count": 76,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -950,7 +1001,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": 77,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -976,7 +1027,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 76,
+   "execution_count": 78,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -988,7 +1039,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 77,
+   "execution_count": 79,
    "metadata": {
     "scrolled": true
    },
@@ -1007,7 +1058,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 78,
+   "execution_count": 80,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1018,7 +1069,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 79,
+   "execution_count": 81,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1027,7 +1078,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
+   "execution_count": 82,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1037,7 +1088,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 83,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1050,7 +1101,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
+   "execution_count": 84,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1068,7 +1119,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 83,
+   "execution_count": 85,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1077,10 +1128,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 84,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 86,
+   "metadata": {},
    "outputs": [],
    "source": [
     "y_knn_expanded_pred = knn_clf.predict(X_test)"
@@ -1088,7 +1137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 85,
+   "execution_count": 87,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1097,7 +1146,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 86,
+   "execution_count": 88,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1107,7 +1156,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 87,
+   "execution_count": 89,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1130,9 +1179,16 @@
     "## 1. An MNIST Classifier With Over 97% Accuracy"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Warning**: the next cell may take hours to run, depending on your hardware."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 88,
+   "execution_count": 90,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1147,7 +1203,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 89,
+   "execution_count": 91,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1156,7 +1212,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 90,
+   "execution_count": 92,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1165,7 +1221,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 91,
+   "execution_count": 93,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1184,10 +1240,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 92,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 94,
+   "metadata": {},
    "outputs": [],
    "source": [
     "from scipy.ndimage.interpolation import shift"
@@ -1195,10 +1249,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 93,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 95,
+   "metadata": {},
    "outputs": [],
    "source": [
     "def shift_image(image, dx, dy):\n",
@@ -1209,7 +1261,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 94,
+   "execution_count": 96,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1232,10 +1284,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 95,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 97,
+   "metadata": {},
    "outputs": [],
    "source": [
     "X_train_augmented = [image for image in X_train]\n",
@@ -1252,10 +1302,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 96,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 98,
+   "metadata": {},
    "outputs": [],
    "source": [
     "shuffle_idx = np.random.permutation(len(X_train_augmented))\n",
@@ -1265,10 +1313,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 97,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 99,
+   "metadata": {},
    "outputs": [],
    "source": [
     "knn_clf = KNeighborsClassifier(**grid_search.best_params_)"
@@ -1276,7 +1322,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 98,
+   "execution_count": 100,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1285,7 +1331,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 99,
+   "execution_count": 101,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1330,7 +1376,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 100,
+   "execution_count": 102,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1341,7 +1387,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 101,
+   "execution_count": 103,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1354,7 +1400,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 102,
+   "execution_count": 104,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1378,7 +1424,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 103,
+   "execution_count": 105,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1410,7 +1456,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 104,
+   "execution_count": 106,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1440,7 +1486,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 105,
+   "execution_count": 107,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1465,7 +1511,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 106,
+   "execution_count": 108,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1481,7 +1527,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 107,
+   "execution_count": 109,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1490,7 +1536,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 108,
+   "execution_count": 110,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1499,7 +1545,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 109,
+   "execution_count": 111,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1522,7 +1568,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 110,
+   "execution_count": 112,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1543,29 +1589,32 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Let's build the pipeline for the numerical attributes:"
+    "Let's build the pipeline for the numerical attributes:\n",
+    "\n",
+    "**Warning**: Since Scikit-Learn 0.20, the `sklearn.preprocessing.Imputer` class was replaced by the `sklearn.impute.SimpleImputer` class."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 111,
+   "execution_count": 113,
    "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn.pipeline import Pipeline\n",
-    "from sklearn.preprocessing import Imputer\n",
-    "\n",
-    "imputer = Imputer(strategy=\"median\")\n",
+    "try:\n",
+    "    from sklearn.impute import SimpleImputer # Scikit-Learn 0.20+\n",
+    "except ImportError:\n",
+    "    from sklearn.preprocessing import Imputer as SimpleImputer\n",
     "\n",
     "num_pipeline = Pipeline([\n",
     "        (\"select_numeric\", DataFrameSelector([\"Age\", \"SibSp\", \"Parch\", \"Fare\"])),\n",
-    "        (\"imputer\", Imputer(strategy=\"median\")),\n",
+    "        (\"imputer\", SimpleImputer(strategy=\"median\")),\n",
     "    ])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 112,
+   "execution_count": 114,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1576,12 +1625,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We will also need an imputer for the string categorical columns (the regular `Imputer` does not work on those):"
+    "We will also need an imputer for the string categorical columns (the regular `SimpleImputer` does not work on those):"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 113,
+   "execution_count": 115,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1599,16 +1648,20 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We can convert each categorical value to a one-hot vector using a `OneHotEncoder`. Right now this class can only handle integer categorical inputs, but in Scikit-Learn 0.20 it will also handle string categorical inputs (see [PR #10521](https://github.com/scikit-learn/scikit-learn/issues/10521)). So for now we import it from `future_encoders.py`, but when Scikit-Learn 0.20 is released, you can import it from `sklearn.preprocessing` instead:"
+    "**Warning**: earlier versions of the book used the `LabelBinarizer` or `CategoricalEncoder` classes to convert each categorical value to a one-hot vector. It is now preferable to use the `OneHotEncoder` class. Since Scikit-Learn 0.20 it can handle string categorical inputs (see [PR #10521](https://github.com/scikit-learn/scikit-learn/issues/10521)), not just integer categorical inputs. If you are using an older version of Scikit-Learn, you can import the new version from `future_encoders.py`:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 114,
+   "execution_count": 116,
    "metadata": {},
    "outputs": [],
    "source": [
-    "from future_encoders import OneHotEncoder"
+    "try:\n",
+    "    from sklearn.preprocessing import OrdinalEncoder # just to raise an ImportError if Scikit-Learn < 0.20\n",
+    "    from sklearn.preprocessing import OneHotEncoder\n",
+    "except ImportError:\n",
+    "    from future_encoders import OneHotEncoder # Scikit-Learn < 0.20"
    ]
   },
   {
@@ -1620,7 +1673,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 115,
+   "execution_count": 117,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1633,7 +1686,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 116,
+   "execution_count": 118,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1649,7 +1702,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 117,
+   "execution_count": 119,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1669,7 +1722,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 118,
+   "execution_count": 120,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1686,7 +1739,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 119,
+   "execution_count": 121,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1702,13 +1755,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 120,
+   "execution_count": 122,
    "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn.svm import SVC\n",
     "\n",
-    "svm_clf = SVC()\n",
+    "svm_clf = SVC(gamma=\"auto\")\n",
     "svm_clf.fit(X_train, y_train)"
    ]
   },
@@ -1721,7 +1774,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 121,
+   "execution_count": 123,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1738,7 +1791,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 122,
+   "execution_count": 124,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1764,13 +1817,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 123,
+   "execution_count": 125,
    "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn.ensemble import RandomForestClassifier\n",
     "\n",
-    "forest_clf = RandomForestClassifier(random_state=42)\n",
+    "forest_clf = RandomForestClassifier(n_estimators=100, random_state=42)\n",
     "forest_scores = cross_val_score(forest_clf, X_train, y_train, cv=10)\n",
     "forest_scores.mean()"
    ]
@@ -1791,7 +1844,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 124,
+   "execution_count": 126,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1817,7 +1870,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 125,
+   "execution_count": 127,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1827,7 +1880,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 126,
+   "execution_count": 128,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1851,7 +1904,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 127,
+   "execution_count": 129,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1878,7 +1931,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 128,
+   "execution_count": 130,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1894,7 +1947,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 129,
+   "execution_count": 131,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1906,7 +1959,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 130,
+   "execution_count": 132,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1915,7 +1968,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 131,
+   "execution_count": 133,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1931,7 +1984,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 132,
+   "execution_count": 134,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1946,7 +1999,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 133,
+   "execution_count": 135,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1963,7 +2016,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 134,
+   "execution_count": 136,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1972,7 +2025,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 135,
+   "execution_count": 137,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1988,7 +2041,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 136,
+   "execution_count": 138,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2007,7 +2060,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 137,
+   "execution_count": 139,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2023,7 +2076,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 138,
+   "execution_count": 140,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2032,7 +2085,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 139,
+   "execution_count": 141,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2055,7 +2108,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 140,
+   "execution_count": 142,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2072,7 +2125,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 141,
+   "execution_count": 143,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2088,7 +2141,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 142,
+   "execution_count": 144,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2110,7 +2163,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 143,
+   "execution_count": 145,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2134,7 +2187,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 144,
+   "execution_count": 146,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2153,7 +2206,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 145,
+   "execution_count": 147,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2169,7 +2222,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 146,
+   "execution_count": 148,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2193,7 +2246,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 147,
+   "execution_count": 149,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2211,7 +2264,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 148,
+   "execution_count": 150,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2237,7 +2290,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 149,
+   "execution_count": 151,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2260,7 +2313,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 150,
+   "execution_count": 152,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2312,7 +2365,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 151,
+   "execution_count": 153,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2337,7 +2390,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 152,
+   "execution_count": 154,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2369,7 +2422,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 153,
+   "execution_count": 155,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2380,7 +2433,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 154,
+   "execution_count": 156,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2396,7 +2449,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 155,
+   "execution_count": 157,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2412,7 +2465,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 156,
+   "execution_count": 158,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2428,14 +2481,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 157,
+   "execution_count": 159,
    "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn.linear_model import LogisticRegression\n",
     "from sklearn.model_selection import cross_val_score\n",
     "\n",
-    "log_clf = LogisticRegression(random_state=42)\n",
+    "log_clf = LogisticRegression(solver=\"liblinear\", random_state=42)\n",
     "score = cross_val_score(log_clf, X_train_transformed, y_train, cv=3, verbose=3)\n",
     "score.mean()"
    ]
@@ -2451,7 +2504,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 158,
+   "execution_count": 160,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2459,7 +2512,7 @@
     "\n",
     "X_test_transformed = preprocess_pipeline.transform(X_test)\n",
     "\n",
-    "log_clf = LogisticRegression(random_state=42)\n",
+    "log_clf = LogisticRegression(solver=\"liblinear\", random_state=42)\n",
     "log_clf.fit(X_train_transformed, y_train)\n",
     "\n",
     "y_pred = log_clf.predict(X_test_transformed)\n",
@@ -2492,7 +2545,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.6"
   },
   "nav_menu": {},
   "toc": {
diff --git a/04_training_linear_models.ipynb b/04_training_linear_models.ipynb
index 1845e8e..1326008 100644
--- a/04_training_linear_models.ipynb
+++ b/04_training_linear_models.ipynb
@@ -65,7 +65,7 @@
     "\n",
     "# Ignore useless warnings (see SciPy issue #5998)\n",
     "import warnings\n",
-    "warnings.filterwarnings(action=\"ignore\", module=\"scipy\", message=\"^internal gelsd\")"
+    "warnings.filterwarnings(action=\"ignore\", message=\"^internal gelsd\")"
    ]
   },
   {
@@ -384,7 +384,7 @@
    "outputs": [],
    "source": [
     "from sklearn.linear_model import SGDRegressor\n",
-    "sgd_reg = SGDRegressor(max_iter=50, penalty=None, eta0=0.1, random_state=42)\n",
+    "sgd_reg = SGDRegressor(max_iter=50, tol=-np.infty, penalty=None, eta0=0.1, random_state=42)\n",
     "sgd_reg.fit(X, y.ravel())"
    ]
   },
@@ -727,7 +727,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sgd_reg = SGDRegressor(max_iter=5, penalty=\"l2\", random_state=42)\n",
+    "sgd_reg = SGDRegressor(max_iter=50, tol=-np.infty, penalty=\"l2\", random_state=42)\n",
     "sgd_reg.fit(X, y.ravel())\n",
     "sgd_reg.predict([[1.5]])"
    ]
@@ -810,6 +810,7 @@
     "X_val_poly_scaled = poly_scaler.transform(X_val)\n",
     "\n",
     "sgd_reg = SGDRegressor(max_iter=1,\n",
+    "                       tol=-np.infty,\n",
     "                       penalty=None,\n",
     "                       eta0=0.0005,\n",
     "                       warm_start=True,\n",
@@ -854,7 +855,7 @@
    "outputs": [],
    "source": [
     "from sklearn.base import clone\n",
-    "sgd_reg = SGDRegressor(max_iter=1, warm_start=True, penalty=None,\n",
+    "sgd_reg = SGDRegressor(max_iter=1, tol=-np.infty, warm_start=True, penalty=None,\n",
     "                       learning_rate=\"constant\", eta0=0.0005, random_state=42)\n",
     "\n",
     "minimum_val_error = float(\"inf\")\n",
@@ -1043,7 +1044,7 @@
    "outputs": [],
    "source": [
     "from sklearn.linear_model import LogisticRegression\n",
-    "log_reg = LogisticRegression(random_state=42)\n",
+    "log_reg = LogisticRegression(solver=\"liblinear\", random_state=42)\n",
     "log_reg.fit(X, y)"
    ]
   },
@@ -1123,7 +1124,7 @@
     "X = iris[\"data\"][:, (2, 3)]  # petal length, petal width\n",
     "y = (iris[\"target\"] == 2).astype(np.int)\n",
     "\n",
-    "log_reg = LogisticRegression(C=10**10, random_state=42)\n",
+    "log_reg = LogisticRegression(solver=\"liblinear\", C=10**10, random_state=42)\n",
     "log_reg.fit(X, y)\n",
     "\n",
     "x0, x1 = np.meshgrid(\n",
@@ -1742,7 +1743,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.4"
+   "version": "3.6.6"
   },
   "nav_menu": {},
   "toc": {
diff --git a/05_support_vector_machines.ipynb b/05_support_vector_machines.ipynb
index ef7c39f..40ac5a0 100644
--- a/05_support_vector_machines.ipynb
+++ b/05_support_vector_machines.ipynb
@@ -774,6 +774,13 @@
     "y = (0.2 + 0.1 * X + 0.5 * X**2 + np.random.randn(m, 1)/10).ravel()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Warning**: the default value of `gamma` will change from `'auto'` to `'scale'` in version 0.22 to better account for unscaled features. To preserve the same results as in the book, we explicitly set it to `'auto'`, but you should probably just use the default in your own code."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 27,
@@ -782,7 +789,7 @@
    "source": [
     "from sklearn.svm import SVR\n",
     "\n",
-    "svm_poly_reg = SVR(kernel=\"poly\", degree=2, C=100, epsilon=0.1)\n",
+    "svm_poly_reg = SVR(kernel=\"poly\", degree=2, C=100, epsilon=0.1, gamma=\"auto\")\n",
     "svm_poly_reg.fit(X, y)"
    ]
   },
@@ -794,8 +801,8 @@
    "source": [
     "from sklearn.svm import SVR\n",
     "\n",
-    "svm_poly_reg1 = SVR(kernel=\"poly\", degree=2, C=100, epsilon=0.1)\n",
-    "svm_poly_reg2 = SVR(kernel=\"poly\", degree=2, C=0.01, epsilon=0.1)\n",
+    "svm_poly_reg1 = SVR(kernel=\"poly\", degree=2, C=100, epsilon=0.1, gamma=\"auto\")\n",
+    "svm_poly_reg2 = SVR(kernel=\"poly\", degree=2, C=0.01, epsilon=0.1, gamma=\"auto\")\n",
     "svm_poly_reg1.fit(X, y)\n",
     "svm_poly_reg2.fit(X, y)"
    ]
@@ -876,7 +883,7 @@
     "ax1 = fig.add_subplot(111, projection='3d')\n",
     "plot_3D_decision_function(ax1, w=svm_clf2.coef_[0], b=svm_clf2.intercept_[0])\n",
     "\n",
-    "save_fig(\"iris_3D_plot\")\n",
+    "#save_fig(\"iris_3D_plot\")\n",
     "plt.show()"
    ]
   },
@@ -1165,7 +1172,7 @@
    "source": [
     "from sklearn.linear_model import SGDClassifier\n",
     "\n",
-    "sgd_clf = SGDClassifier(loss=\"hinge\", alpha = 0.017, max_iter = 50, random_state=42)\n",
+    "sgd_clf = SGDClassifier(loss=\"hinge\", alpha = 0.017, max_iter = 50, tol=-np.infty, random_state=42)\n",
     "sgd_clf.fit(X, y.ravel())\n",
     "\n",
     "m = len(X)\n",
@@ -1265,7 +1272,7 @@
     "lin_clf = LinearSVC(loss=\"hinge\", C=C, random_state=42)\n",
     "svm_clf = SVC(kernel=\"linear\", C=C)\n",
     "sgd_clf = SGDClassifier(loss=\"hinge\", learning_rate=\"constant\", eta0=0.001, alpha=alpha,\n",
-    "                        max_iter=100000, random_state=42)\n",
+    "                        max_iter=100000, tol=-np.infty, random_state=42)\n",
     "\n",
     "scaler = StandardScaler()\n",
     "X_scaled = scaler.fit_transform(X)\n",
@@ -1354,9 +1361,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sklearn.datasets import fetch_mldata\n",
+    "try:\n",
+    "    from sklearn.datasets import fetch_openml\n",
+    "    mnist = fetch_openml('mnist_784', version=1, cache=True)\n",
+    "except ImportError:\n",
+    "    from sklearn.datasets import fetch_mldata\n",
+    "    mnist = fetch_mldata('MNIST original')\n",
     "\n",
-    "mnist = fetch_mldata(\"MNIST original\")\n",
     "X = mnist[\"data\"]\n",
     "y = mnist[\"target\"]\n",
     "\n",
@@ -1425,7 +1436,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Wow, 82% accuracy on MNIST is a really bad performance. This linear model is certainly too simple for MNIST, but perhaps we just needed to scale the data first:"
+    "Wow, 86% accuracy on MNIST is a really bad performance. This linear model is certainly too simple for MNIST, but perhaps we just needed to scale the data first:"
    ]
   },
   {
@@ -1474,7 +1485,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "svm_clf = SVC(decision_function_shape=\"ovr\")\n",
+    "svm_clf = SVC(decision_function_shape=\"ovr\", gamma=\"auto\")\n",
     "svm_clf.fit(X_train_scaled[:10000], y_train[:10000])"
    ]
   },
@@ -1505,7 +1516,7 @@
     "from scipy.stats import reciprocal, uniform\n",
     "\n",
     "param_distributions = {\"gamma\": reciprocal(0.001, 0.1), \"C\": uniform(1, 10)}\n",
-    "rnd_search_cv = RandomizedSearchCV(svm_clf, param_distributions, n_iter=10, verbose=2)\n",
+    "rnd_search_cv = RandomizedSearchCV(svm_clf, param_distributions, n_iter=10, verbose=2, cv=3)\n",
     "rnd_search_cv.fit(X_train_scaled[:1000], y_train[:1000])"
    ]
   },
@@ -1536,7 +1547,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 60,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1545,7 +1556,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": 61,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1562,7 +1573,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 61,
+   "execution_count": 62,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1600,7 +1611,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 62,
+   "execution_count": 63,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1620,7 +1631,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 63,
+   "execution_count": 64,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1638,7 +1649,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 64,
+   "execution_count": 65,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1658,7 +1669,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 65,
+   "execution_count": 66,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1677,7 +1688,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 66,
+   "execution_count": 67,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1697,7 +1708,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 67,
+   "execution_count": 68,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1713,7 +1724,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 69,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1722,13 +1733,13 @@
     "from scipy.stats import reciprocal, uniform\n",
     "\n",
     "param_distributions = {\"gamma\": reciprocal(0.001, 0.1), \"C\": uniform(1, 10)}\n",
-    "rnd_search_cv = RandomizedSearchCV(SVR(), param_distributions, n_iter=10, verbose=2, random_state=42)\n",
+    "rnd_search_cv = RandomizedSearchCV(SVR(), param_distributions, n_iter=10, verbose=2, cv=3, random_state=42)\n",
     "rnd_search_cv.fit(X_train_scaled, y_train)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 70,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1744,7 +1755,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 71,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1762,7 +1773,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 72,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1771,6 +1782,26 @@
     "np.sqrt(mse)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cmap = matplotlib.cm.get_cmap(\"jet\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.datasets import fetch_openml\n",
+    "mnist = fetch_openml(\"mnist_784\", version=1)\n",
+    "print(mnist.data.shape)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -1795,7 +1826,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.6"
   },
   "nav_menu": {},
   "toc": {
diff --git a/06_decision_trees.ipynb b/06_decision_trees.ipynb
index ba8bd50..908abf7 100644
--- a/06_decision_trees.ipynb
+++ b/06_decision_trees.ipynb
@@ -531,7 +531,7 @@
     "from sklearn.model_selection import GridSearchCV\n",
     "\n",
     "params = {'max_leaf_nodes': list(range(2, 100)), 'min_samples_split': [2, 3, 4]}\n",
-    "grid_search_cv = GridSearchCV(DecisionTreeClassifier(random_state=42), params, n_jobs=-1, verbose=1)\n",
+    "grid_search_cv = GridSearchCV(DecisionTreeClassifier(random_state=42), params, n_jobs=-1, verbose=1, cv=3)\n",
     "\n",
     "grid_search_cv.fit(X_train, y_train)"
    ]
@@ -710,7 +710,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.6"
   },
   "nav_menu": {
    "height": "309px",
diff --git a/07_ensemble_learning_and_random_forests.ipynb b/07_ensemble_learning_and_random_forests.ipynb
index eed1f84..a7697cf 100644
--- a/07_ensemble_learning_and_random_forests.ipynb
+++ b/07_ensemble_learning_and_random_forests.ipynb
@@ -115,6 +115,13 @@
     "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Warning**: In Scikit-Learn 0.20, some hyperparameters (`solver`, `n_estimators`, `gamma`, etc.) start issuing warnings about the fact that their default value will change in Scikit-Learn 0.22. To avoid these warnings and ensure that this notebooks keeps producing the same outputs as in the book, I set the hyperparameters to their old default value.  In your own code, you can simply rely on the latest default values instead."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 5,
@@ -126,9 +133,9 @@
     "from sklearn.linear_model import LogisticRegression\n",
     "from sklearn.svm import SVC\n",
     "\n",
-    "log_clf = LogisticRegression(random_state=42)\n",
-    "rnd_clf = RandomForestClassifier(random_state=42)\n",
-    "svm_clf = SVC(random_state=42)\n",
+    "log_clf = LogisticRegression(solver=\"liblinear\", random_state=42)\n",
+    "rnd_clf = RandomForestClassifier(n_estimators=10, random_state=42)\n",
+    "svm_clf = SVC(gamma=\"auto\", random_state=42)\n",
     "\n",
     "voting_clf = VotingClassifier(\n",
     "    estimators=[('lr', log_clf), ('rf', rnd_clf), ('svc', svm_clf)],\n",
@@ -164,9 +171,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "log_clf = LogisticRegression(random_state=42)\n",
-    "rnd_clf = RandomForestClassifier(random_state=42)\n",
-    "svm_clf = SVC(probability=True, random_state=42)\n",
+    "log_clf = LogisticRegression(solver=\"liblinear\", random_state=42)\n",
+    "rnd_clf = RandomForestClassifier(n_estimators=10, random_state=42)\n",
+    "svm_clf = SVC(gamma=\"auto\", probability=True, random_state=42)\n",
     "\n",
     "voting_clf = VotingClassifier(\n",
     "    estimators=[('lr', log_clf), ('rf', rnd_clf), ('svc', svm_clf)],\n",
@@ -420,8 +427,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sklearn.datasets import fetch_mldata\n",
-    "mnist = fetch_mldata('MNIST original')"
+    "try:\n",
+    "    from sklearn.datasets import fetch_openml\n",
+    "    mnist = fetch_openml('mnist_784', version=1)\n",
+    "    mnist.target = mnist.target.astype(np.int64)\n",
+    "except ImportError:\n",
+    "    from sklearn.datasets import fetch_mldata\n",
+    "    mnist = fetch_mldata('MNIST original')"
    ]
   },
   {
@@ -430,7 +442,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "rnd_clf = RandomForestClassifier(random_state=42)\n",
+    "rnd_clf = RandomForestClassifier(n_estimators=10, random_state=42)\n",
     "rnd_clf.fit(mnist[\"data\"], mnist[\"target\"])"
    ]
   },
@@ -505,7 +517,7 @@
     "    sample_weights = np.ones(m)\n",
     "    plt.subplot(subplot)\n",
     "    for i in range(5):\n",
-    "        svm_clf = SVC(kernel=\"rbf\", C=0.05, random_state=42)\n",
+    "        svm_clf = SVC(kernel=\"rbf\", C=0.05, gamma=\"auto\", random_state=42)\n",
     "        svm_clf.fit(X_train, y_train, sample_weight=sample_weights)\n",
     "        y_pred = svm_clf.predict(X_train)\n",
     "        sample_weights[y_pred != y_train] *= (1 + learning_rate)\n",
@@ -911,36 +923,25 @@
     "Exercise: _Load the MNIST data and split it into a training set, a validation set, and a test set (e.g., use 50,000 instances for training, 10,000 for validation, and 10,000 for testing)._"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The MNIST dataset was loaded earlier."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 55,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from sklearn.datasets import fetch_mldata"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "mnist = fetch_mldata('MNIST original')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 57,
-   "metadata": {},
-   "outputs": [],
    "source": [
     "from sklearn.model_selection import train_test_split"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 56,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -959,7 +960,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 57,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -970,19 +971,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": 58,
    "metadata": {},
    "outputs": [],
    "source": [
-    "random_forest_clf = RandomForestClassifier(random_state=42)\n",
-    "extra_trees_clf = ExtraTreesClassifier(random_state=42)\n",
+    "random_forest_clf = RandomForestClassifier(n_estimators=10, random_state=42)\n",
+    "extra_trees_clf = ExtraTreesClassifier(n_estimators=10, random_state=42)\n",
     "svm_clf = LinearSVC(random_state=42)\n",
     "mlp_clf = MLPClassifier(random_state=42)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 61,
+   "execution_count": 59,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -994,7 +995,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 62,
+   "execution_count": 60,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1017,7 +1018,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 63,
+   "execution_count": 61,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1026,7 +1027,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 64,
+   "execution_count": 62,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1040,7 +1041,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 65,
+   "execution_count": 63,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1049,7 +1050,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 66,
+   "execution_count": 64,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1058,7 +1059,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 67,
+   "execution_count": 65,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1067,7 +1068,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 66,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1083,7 +1084,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 67,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1099,16 +1100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "voting_clf.estimators"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 68,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1124,7 +1116,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": 69,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1140,7 +1132,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 70,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1156,7 +1148,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 74,
+   "execution_count": 71,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1167,12 +1159,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Much better! The SVM was hurting performance. Now let's try using a soft voting classifier. We do not actually need to retrain the classifier, we can just set `voting` to `\"soft\"`:"
+    "A bit better! The SVM was hurting performance. Now let's try using a soft voting classifier. We do not actually need to retrain the classifier, we can just set `voting` to `\"soft\"`:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": 72,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1181,7 +1173,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 76,
+   "execution_count": 73,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1204,7 +1196,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 77,
+   "execution_count": 74,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1213,7 +1205,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 78,
+   "execution_count": 75,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1224,7 +1216,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The voting classifier reduced the error rate from about 4.9% for our best model (the `MLPClassifier`) to just 3.5%. That's about 28% less errors, not bad!"
+    "The voting classifier reduced the error rate from about 4.0% for our best model (the `MLPClassifier`) to just 3.1%. That's about 22.5% less errors, not bad!"
    ]
   },
   {
@@ -1243,7 +1235,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 79,
+   "execution_count": 76,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1255,7 +1247,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
+   "execution_count": 77,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1264,7 +1256,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 78,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1274,7 +1266,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
+   "execution_count": 79,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1297,7 +1289,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 83,
+   "execution_count": 80,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1309,7 +1301,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 84,
+   "execution_count": 81,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1318,7 +1310,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 85,
+   "execution_count": 82,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1327,7 +1319,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 86,
+   "execution_count": 83,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1338,15 +1330,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This stacking ensemble does not perform as well as the soft voting classifier we trained earlier, but it still beats all the individual classifiers."
+    "This stacking ensemble does not perform as well as the soft voting classifier we trained earlier, it's just as good as the best individual classifier."
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -1365,7 +1350,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.6"
   },
   "nav_menu": {
    "height": "252px",
diff --git a/08_dimensionality_reduction.ipynb b/08_dimensionality_reduction.ipynb
index e5ef84c..bd18d4b 100644
--- a/08_dimensionality_reduction.ipynb
+++ b/08_dimensionality_reduction.ipynb
@@ -60,7 +60,7 @@
     "\n",
     "# Ignore useless warnings (see SciPy issue #5998)\n",
     "import warnings\n",
-    "warnings.filterwarnings(action=\"ignore\", module=\"scipy\", message=\"^internal gelsd\")"
+    "warnings.filterwarnings(action=\"ignore\", message=\"^internal gelsd\")"
    ]
   },
   {
@@ -504,6 +504,10 @@
     "ax.set_ylim(axes[2:4])\n",
     "ax.set_zlim(axes[4:6])\n",
     "\n",
+    "# Workaround for https://github.com/matplotlib/matplotlib/issues/12239\n",
+    "for spine in ax.spines.values():\n",
+    "    spine.set_visible(False)\n",
+    "\n",
     "save_fig(\"dataset_3d_plot\")\n",
     "plt.show()"
    ]
@@ -567,6 +571,10 @@
     "ax.set_ylim(axes[2:4])\n",
     "ax.set_zlim(axes[4:6])\n",
     "\n",
+    "# Workaround for https://github.com/matplotlib/matplotlib/issues/12239\n",
+    "for spine in ax.spines.values():\n",
+    "    spine.set_visible(False)\n",
+    "\n",
     "save_fig(\"swiss_roll_plot\")\n",
     "plt.show()"
    ]
@@ -627,6 +635,10 @@
     "ax.set_ylim(axes[2:4])\n",
     "ax.set_zlim(axes[4:6])\n",
     "\n",
+    "# Workaround for https://github.com/matplotlib/matplotlib/issues/12239\n",
+    "for spine in ax.spines.values():\n",
+    "    spine.set_visible(False)\n",
+    "\n",
     "save_fig(\"manifold_decision_boundary_plot1\")\n",
     "plt.show()\n",
     "\n",
@@ -659,6 +671,10 @@
     "ax.set_ylim(axes[2:4])\n",
     "ax.set_zlim(axes[4:6])\n",
     "\n",
+    "# Workaround for https://github.com/matplotlib/matplotlib/issues/12239\n",
+    "for spine in ax.spines.values():\n",
+    "    spine.set_visible(False)\n",
+    "\n",
     "save_fig(\"manifold_decision_boundary_plot3\")\n",
     "plt.show()\n",
     "\n",
@@ -764,8 +780,13 @@
    "outputs": [],
    "source": [
     "from six.moves import urllib\n",
-    "from sklearn.datasets import fetch_mldata\n",
-    "mnist = fetch_mldata('MNIST original')"
+    "try:\n",
+    "    from sklearn.datasets import fetch_openml\n",
+    "    mnist = fetch_openml('mnist_784', version=1)\n",
+    "    mnist.target = mnist.target.astype(np.int64)\n",
+    "except ImportError:\n",
+    "    from sklearn.datasets import fetch_mldata\n",
+    "    mnist = fetch_mldata('MNIST original')"
    ]
   },
   {
@@ -1244,6 +1265,10 @@
     "ax.set_yticklabels([])\n",
     "ax.set_zticklabels([])\n",
     "\n",
+    "# Workaround for https://github.com/matplotlib/matplotlib/issues/12239\n",
+    "for spine in ax.spines.values():\n",
+    "    spine.set_visible(False)\n",
+    "\n",
     "save_fig(\"preimage_plot\", tight_layout=False)\n",
     "plt.show()"
    ]
@@ -1276,7 +1301,7 @@
     "\n",
     "clf = Pipeline([\n",
     "        (\"kpca\", KernelPCA(n_components=2)),\n",
-    "        (\"log_reg\", LogisticRegression())\n",
+    "        (\"log_reg\", LogisticRegression(solver=\"liblinear\"))\n",
     "    ])\n",
     "\n",
     "param_grid = [{\n",
@@ -1474,7 +1499,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 73,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1483,7 +1508,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 74,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1495,24 +1520,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 75,
    "metadata": {},
    "outputs": [],
    "source": [
     "plt.figure(figsize=(9, 3.5))\n",
     "\n",
     "plt.subplot(121)\n",
-    "plt.plot(X[y==0, 0], X[y==0, 1], \"yo\", label=\"Iris-Setosa\")\n",
-    "plt.plot(X[y==1, 0], X[y==1, 1], \"bs\", label=\"Iris-Versicolor\")\n",
-    "plt.plot(X[y==2, 0], X[y==2, 1], \"g^\", label=\"Iris-Virginica\")\n",
+    "plt.plot(X[y==0, 2], X[y==0, 3], \"yo\", label=\"Iris-Setosa\")\n",
+    "plt.plot(X[y==1, 2], X[y==1, 3], \"bs\", label=\"Iris-Versicolor\")\n",
+    "plt.plot(X[y==2, 2], X[y==2, 3], \"g^\", label=\"Iris-Virginica\")\n",
     "plt.xlabel(\"Petal length\", fontsize=14)\n",
     "plt.ylabel(\"Petal width\", fontsize=14)\n",
     "plt.legend(fontsize=12)\n",
     "\n",
     "plt.subplot(122)\n",
-    "plt.scatter(X[:, 0], X[:, 1], c=\"k\", marker=\".\")\n",
+    "plt.scatter(X[:, 2], X[:, 3], c=\"k\", marker=\".\")\n",
     "plt.xlabel(\"Petal length\", fontsize=14)\n",
-    "plt.tick_params(labelleft='off')\n",
+    "plt.tick_params(labelleft=False)\n",
     "\n",
     "save_fig(\"classification_vs_clustering_diagram\")\n",
     "plt.show()"
@@ -1522,12 +1547,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "A Gaussian mixture model (explained below) can actually separate these clusters pretty well."
+    "A Gaussian mixture model (explained below) can actually separate these clusters pretty well (using all 4 features: petal length & width, and sepal length & width)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 76,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1536,7 +1561,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 77,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1547,22 +1572,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 78,
    "metadata": {},
    "outputs": [],
    "source": [
-    "plt.plot(X[y_pred==0, 0], X[y_pred==0, 1], \"yo\", label=\"Cluster 1\")\n",
-    "plt.plot(X[y_pred==1, 0], X[y_pred==1, 1], \"bs\", label=\"Cluster 2\")\n",
-    "plt.plot(X[y_pred==2, 0], X[y_pred==2, 1], \"g^\", label=\"Cluster 3\")\n",
+    "plt.plot(X[y_pred==0, 2], X[y_pred==0, 3], \"yo\", label=\"Cluster 1\")\n",
+    "plt.plot(X[y_pred==1, 2], X[y_pred==1, 3], \"bs\", label=\"Cluster 2\")\n",
+    "plt.plot(X[y_pred==2, 2], X[y_pred==2, 3], \"g^\", label=\"Cluster 3\")\n",
     "plt.xlabel(\"Petal length\", fontsize=14)\n",
     "plt.ylabel(\"Petal width\", fontsize=14)\n",
-    "plt.legend(loc=\"upper right\", fontsize=12)\n",
+    "plt.legend(loc=\"upper left\", fontsize=12)\n",
     "plt.show()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 79,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1571,7 +1596,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 80,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1594,7 +1619,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 81,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1603,7 +1628,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 82,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1618,7 +1643,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 83,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1635,7 +1660,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 84,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1647,7 +1672,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 85,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1673,7 +1698,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 86,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1682,7 +1707,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 87,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1700,7 +1725,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 88,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1709,7 +1734,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 89,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1725,7 +1750,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 90,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1741,7 +1766,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 91,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1757,7 +1782,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 92,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1781,7 +1806,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 93,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1818,16 +1843,16 @@
     "    if show_xlabels:\n",
     "        plt.xlabel(\"$x_1$\", fontsize=14)\n",
     "    else:\n",
-    "        plt.tick_params(labelbottom='off')\n",
+    "        plt.tick_params(labelbottom=False)\n",
     "    if show_ylabels:\n",
     "        plt.ylabel(\"$x_2$\", fontsize=14, rotation=0)\n",
     "    else:\n",
-    "        plt.tick_params(labelleft='off')"
+    "        plt.tick_params(labelleft=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 94,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1860,7 +1885,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 95,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1876,7 +1901,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 96,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1917,7 +1942,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 97,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1941,7 +1966,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 98,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1951,7 +1976,7 @@
     "plot_data(X)\n",
     "plot_centroids(kmeans_iter1.cluster_centers_, circle_color='r', cross_color='w')\n",
     "plt.ylabel(\"$x_2$\", fontsize=14, rotation=0)\n",
-    "plt.tick_params(labelbottom='off')\n",
+    "plt.tick_params(labelbottom=False)\n",
     "plt.title(\"Update the centroids (initially randomly)\", fontsize=14)\n",
     "\n",
     "plt.subplot(322)\n",
@@ -1994,7 +2019,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 99,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2017,7 +2042,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 100,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2049,7 +2074,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 101,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2065,7 +2090,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 102,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2082,7 +2107,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 103,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2105,7 +2130,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 104,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2114,7 +2139,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 105,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2137,7 +2162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 106,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2155,7 +2180,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 107,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2197,7 +2222,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 108,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2206,7 +2231,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 109,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2239,7 +2264,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 110,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2248,7 +2273,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 111,
    "metadata": {
     "scrolled": true
    },
@@ -2273,7 +2298,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 112,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2282,7 +2307,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 113,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2292,7 +2317,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 114,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2308,7 +2333,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 115,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2319,7 +2344,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 116,
    "metadata": {
     "scrolled": false
    },
@@ -2338,7 +2363,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 117,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2355,7 +2380,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 118,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2364,7 +2389,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 119,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2396,7 +2421,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 120,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2412,7 +2437,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 121,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2421,7 +2446,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 122,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2437,7 +2462,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 123,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2446,7 +2471,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
+   "execution_count": 124,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2464,7 +2489,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 103,
+   "execution_count": 125,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2508,7 +2533,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 127,
+   "execution_count": 126,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2529,7 +2554,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 128,
+   "execution_count": 127,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2538,7 +2563,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 129,
+   "execution_count": 128,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2554,7 +2579,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 130,
+   "execution_count": 129,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2565,7 +2590,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 131,
+   "execution_count": 130,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2594,7 +2619,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 132,
+   "execution_count": 131,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2618,7 +2643,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 133,
+   "execution_count": 132,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2627,7 +2652,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 134,
+   "execution_count": 133,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2636,7 +2661,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 135,
+   "execution_count": 134,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2646,7 +2671,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 136,
+   "execution_count": 135,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2675,7 +2700,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 137,
+   "execution_count": 136,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2712,7 +2737,7 @@
     "        plt.gca().set_xticks([-0.1, 0, 0.2, 0.4, 0.6, 0.8, 1])\n",
     "        plt.xlabel(\"Silhouette Coefficient\")\n",
     "    else:\n",
-    "        plt.tick_params(labelbottom='off')\n",
+    "        plt.tick_params(labelbottom=False)\n",
     "\n",
     "    plt.axvline(x=silhouette_scores[k - 2], color=\"red\", linestyle=\"--\")\n",
     "    plt.title(\"$k={}$\".format(k), fontsize=16)\n",
@@ -2730,7 +2755,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 118,
+   "execution_count": 137,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2744,7 +2769,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 119,
+   "execution_count": 138,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2753,7 +2778,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 140,
+   "execution_count": 139,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2765,7 +2790,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 141,
+   "execution_count": 140,
    "metadata": {
     "scrolled": false
    },
@@ -2794,7 +2819,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 142,
+   "execution_count": 141,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2805,7 +2830,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 143,
+   "execution_count": 142,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2817,7 +2842,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 144,
+   "execution_count": 143,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2831,7 +2856,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 145,
+   "execution_count": 144,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2869,7 +2894,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 146,
+   "execution_count": 145,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2878,7 +2903,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 147,
+   "execution_count": 146,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2894,7 +2919,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 148,
+   "execution_count": 147,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2903,7 +2928,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 149,
+   "execution_count": 148,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2919,7 +2944,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 150,
+   "execution_count": 149,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2928,17 +2953,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 151,
+   "execution_count": 150,
    "metadata": {},
    "outputs": [],
    "source": [
-    "log_reg = LogisticRegression(random_state=42)\n",
+    "log_reg = LogisticRegression(multi_class=\"ovr\", solver=\"liblinear\", random_state=42)\n",
     "log_reg.fit(X_train, y_train)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 152,
+   "execution_count": 151,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2954,7 +2979,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 153,
+   "execution_count": 152,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2963,20 +2988,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 154,
+   "execution_count": 153,
    "metadata": {},
    "outputs": [],
    "source": [
     "pipeline = Pipeline([\n",
     "    (\"kmeans\", KMeans(n_clusters=50, random_state=42)),\n",
-    "    (\"log_reg\", LogisticRegression(random_state=42)),\n",
+    "    (\"log_reg\", LogisticRegression(multi_class=\"ovr\", solver=\"liblinear\", random_state=42)),\n",
     "])\n",
     "pipeline.fit(X_train, y_train)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 155,
+   "execution_count": 154,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2985,7 +3010,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 156,
+   "execution_count": 155,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3001,7 +3026,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 157,
+   "execution_count": 156,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3010,7 +3035,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 158,
+   "execution_count": 157,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3021,7 +3046,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 159,
+   "execution_count": 158,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3030,7 +3055,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 160,
+   "execution_count": 159,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3067,7 +3092,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 161,
+   "execution_count": 160,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3076,11 +3101,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 162,
+   "execution_count": 161,
    "metadata": {},
    "outputs": [],
    "source": [
-    "log_reg = LogisticRegression(random_state=42)\n",
+    "log_reg = LogisticRegression(multi_class=\"ovr\", solver=\"liblinear\", random_state=42)\n",
     "log_reg.fit(X_train[:n_labeled], y_train[:n_labeled])\n",
     "log_reg.score(X_test, y_test)"
    ]
@@ -3094,7 +3119,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 163,
+   "execution_count": 162,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3103,7 +3128,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 164,
+   "execution_count": 163,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3122,7 +3147,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 165,
+   "execution_count": 164,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3138,7 +3163,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 166,
+   "execution_count": 165,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3159,11 +3184,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 167,
+   "execution_count": 166,
    "metadata": {},
    "outputs": [],
    "source": [
-    "log_reg = LogisticRegression(random_state=42)\n",
+    "log_reg = LogisticRegression(multi_class=\"ovr\", solver=\"liblinear\", random_state=42)\n",
     "log_reg.fit(X_representative_digits, y_representative_digits)\n",
     "log_reg.score(X_test, y_test)"
    ]
@@ -3184,7 +3209,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 168,
+   "execution_count": 167,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3195,17 +3220,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 169,
+   "execution_count": 168,
    "metadata": {},
    "outputs": [],
    "source": [
-    "log_reg = LogisticRegression(random_state=42)\n",
+    "log_reg = LogisticRegression(multi_class=\"ovr\", solver=\"liblinear\", random_state=42)\n",
     "log_reg.fit(X_train, y_train_propagated)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 170,
+   "execution_count": 169,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3221,7 +3246,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 171,
+   "execution_count": 170,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3238,7 +3263,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 172,
+   "execution_count": 171,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3249,17 +3274,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 173,
+   "execution_count": 172,
    "metadata": {},
    "outputs": [],
    "source": [
-    "log_reg = LogisticRegression(random_state=42)\n",
+    "log_reg = LogisticRegression(multi_class=\"ovr\", solver=\"liblinear\", random_state=42)\n",
     "log_reg.fit(X_train_partially_propagated, y_train_partially_propagated)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 174,
+   "execution_count": 173,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3282,7 +3307,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 175,
+   "execution_count": 174,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3307,7 +3332,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 106,
+   "execution_count": 175,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3316,7 +3341,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 107,
+   "execution_count": 176,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3325,7 +3350,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 108,
+   "execution_count": 177,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3334,7 +3359,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 112,
+   "execution_count": 178,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3344,7 +3369,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 113,
+   "execution_count": 179,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3353,7 +3378,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 114,
+   "execution_count": 180,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3362,7 +3387,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 115,
+   "execution_count": 181,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3371,7 +3396,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 182,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3380,7 +3405,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 183,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3389,7 +3414,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 184,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3399,7 +3424,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 185,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3422,17 +3447,17 @@
     "    if show_xlabels:\n",
     "        plt.xlabel(\"$x_1$\", fontsize=14)\n",
     "    else:\n",
-    "        plt.tick_params(labelbottom='off')\n",
+    "        plt.tick_params(labelbottom=False)\n",
     "    if show_ylabels:\n",
     "        plt.ylabel(\"$x_2$\", fontsize=14, rotation=0)\n",
     "    else:\n",
-    "        plt.tick_params(labelleft='off')\n",
+    "        plt.tick_params(labelleft=False)\n",
     "    plt.title(\"eps={:.2f}, min_samples={}\".format(dbscan.eps, dbscan.min_samples), fontsize=14)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 186,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3450,7 +3475,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 188,
+   "execution_count": 187,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3459,7 +3484,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 189,
+   "execution_count": 188,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3468,7 +3493,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 190,
+   "execution_count": 189,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3478,7 +3503,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 191,
+   "execution_count": 190,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3488,7 +3513,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 192,
+   "execution_count": 191,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3497,7 +3522,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 193,
+   "execution_count": 192,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3510,7 +3535,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 194,
+   "execution_count": 193,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3536,7 +3561,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 195,
+   "execution_count": 194,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3545,7 +3570,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 196,
+   "execution_count": 195,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3555,7 +3580,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 197,
+   "execution_count": 196,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3565,7 +3590,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 198,
+   "execution_count": 197,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3574,7 +3599,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 199,
+   "execution_count": 198,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3586,17 +3611,17 @@
     "    if show_xlabels:\n",
     "        plt.xlabel(\"$x_1$\", fontsize=14)\n",
     "    else:\n",
-    "        plt.tick_params(labelbottom='off')\n",
+    "        plt.tick_params(labelbottom=False)\n",
     "    if show_ylabels:\n",
     "        plt.ylabel(\"$x_2$\", fontsize=14, rotation=0)\n",
     "    else:\n",
-    "        plt.tick_params(labelleft='off')\n",
+    "        plt.tick_params(labelleft=False)\n",
     "    plt.title(\"RBF gamma={}\".format(sc.gamma), fontsize=14)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 200,
+   "execution_count": 199,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3620,7 +3645,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 201,
+   "execution_count": 200,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3629,7 +3654,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 202,
+   "execution_count": 201,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3639,7 +3664,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 203,
+   "execution_count": 202,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3648,7 +3673,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 204,
+   "execution_count": 203,
    "metadata": {
     "scrolled": true
    },
@@ -3666,7 +3691,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 204,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3687,7 +3712,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 205,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3696,7 +3721,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 206,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3713,7 +3738,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 207,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3722,7 +3747,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 208,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3731,7 +3756,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 209,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3747,7 +3772,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 210,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3763,7 +3788,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 211,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3779,7 +3804,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 212,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3788,7 +3813,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 213,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3804,7 +3829,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 214,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3814,7 +3839,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 215,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3837,7 +3862,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 216,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3853,7 +3878,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 217,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3876,7 +3901,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 178,
+   "execution_count": 218,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3910,12 +3935,12 @@
     "    if show_ylabels:\n",
     "        plt.ylabel(\"$x_2$\", fontsize=14, rotation=0)\n",
     "    else:\n",
-    "        plt.tick_params(labelleft='off')"
+    "        plt.tick_params(labelleft=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 155,
+   "execution_count": 219,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3940,7 +3965,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 221,
+   "execution_count": 220,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3956,7 +3981,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 222,
+   "execution_count": 221,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3974,7 +3999,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 223,
+   "execution_count": 222,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3986,7 +4011,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 224,
+   "execution_count": 223,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4011,7 +4036,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 94,
+   "execution_count": 224,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4022,7 +4047,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 100,
+   "execution_count": 225,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4030,7 +4055,7 @@
     "\n",
     "plot_gaussian_mixture(gm, X)\n",
     "plt.scatter(anomalies[:, 0], anomalies[:, 1], color='r', marker='*')\n",
-    "plt.ylim(ymax=5.1)\n",
+    "plt.ylim(top=5.1)\n",
     "\n",
     "save_fig(\"mixture_anomaly_detection_diagram\")\n",
     "plt.show()"
@@ -4062,7 +4087,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 227,
+   "execution_count": 226,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4071,7 +4096,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 228,
+   "execution_count": 227,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4087,7 +4112,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 229,
+   "execution_count": 228,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4104,7 +4129,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 230,
+   "execution_count": 229,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4113,7 +4138,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 231,
+   "execution_count": 230,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4136,7 +4161,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 232,
+   "execution_count": 231,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4146,7 +4171,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 233,
+   "execution_count": 232,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4156,7 +4181,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 234,
+   "execution_count": 233,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4187,7 +4212,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 235,
+   "execution_count": 234,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4206,7 +4231,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 236,
+   "execution_count": 235,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4215,7 +4240,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 237,
+   "execution_count": 236,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4238,7 +4263,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 157,
+   "execution_count": 237,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4247,7 +4272,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 158,
+   "execution_count": 238,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4264,7 +4289,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 159,
+   "execution_count": 239,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4273,7 +4298,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 160,
+   "execution_count": 240,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4284,7 +4309,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 161,
+   "execution_count": 241,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4299,7 +4324,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 162,
+   "execution_count": 242,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4308,7 +4333,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 163,
+   "execution_count": 243,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4317,7 +4342,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 179,
+   "execution_count": 244,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4344,7 +4369,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 167,
+   "execution_count": 245,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4353,7 +4378,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 168,
+   "execution_count": 246,
    "metadata": {
     "scrolled": true
    },
@@ -4365,7 +4390,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 169,
+   "execution_count": 247,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4525,18 +4550,15 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 251,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "from sklearn.datasets import fetch_mldata\n",
-    "mnist = fetch_mldata('MNIST original')"
+    "The MNIST dataset was loaded earlier."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 252,
+   "execution_count": 251,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4556,18 +4578,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 253,
+   "execution_count": 252,
    "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn.ensemble import RandomForestClassifier\n",
     "\n",
-    "rnd_clf = RandomForestClassifier(random_state=42)"
+    "rnd_clf = RandomForestClassifier(n_estimators=10, random_state=42)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 254,
+   "execution_count": 253,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4580,7 +4602,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 255,
+   "execution_count": 254,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4589,7 +4611,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 256,
+   "execution_count": 255,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4608,7 +4630,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 257,
+   "execution_count": 256,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4627,11 +4649,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 258,
+   "execution_count": 257,
    "metadata": {},
    "outputs": [],
    "source": [
-    "rnd_clf2 = RandomForestClassifier(random_state=42)\n",
+    "rnd_clf2 = RandomForestClassifier(n_estimators=10, random_state=42)\n",
     "t0 = time.time()\n",
     "rnd_clf2.fit(X_train_reduced, y_train)\n",
     "t1 = time.time()"
@@ -4639,7 +4661,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 259,
+   "execution_count": 258,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4662,7 +4684,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 260,
+   "execution_count": 259,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4683,7 +4705,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 261,
+   "execution_count": 260,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4697,7 +4719,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 262,
+   "execution_count": 261,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4706,7 +4728,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 263,
+   "execution_count": 262,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4723,7 +4745,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 264,
+   "execution_count": 263,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4735,7 +4757,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 265,
+   "execution_count": 264,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4746,12 +4768,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Nice! Reducing dimensionality led to a 4× speedup. :)  Let's the model's accuracy:"
+    "Nice! Reducing dimensionality led to a 4× speedup. :)  Let's check the model's accuracy:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 266,
+   "execution_count": 265,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4791,18 +4813,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Let's start by loading the MNIST dataset (again):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 267,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from sklearn.datasets import fetch_mldata\n",
-    "\n",
-    "mnist = fetch_mldata('MNIST original')"
+    "The MNIST dataset was loaded above."
    ]
   },
   {
@@ -4814,7 +4825,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 268,
+   "execution_count": 266,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4836,7 +4847,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 269,
+   "execution_count": 267,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4855,7 +4866,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 270,
+   "execution_count": 268,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4882,14 +4893,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 271,
+   "execution_count": 269,
    "metadata": {},
    "outputs": [],
    "source": [
     "plt.figure(figsize=(9,9))\n",
     "cmap = matplotlib.cm.get_cmap(\"jet\")\n",
     "for digit in (2, 3, 5):\n",
-    "    plt.scatter(X_reduced[y == digit, 0], X_reduced[y == digit, 1], c=cmap(digit / 9))\n",
+    "    plt.scatter(X_reduced[y == digit, 0], X_reduced[y == digit, 1], c=[cmap(digit / 9)])\n",
     "plt.axis('off')\n",
     "plt.show()"
    ]
@@ -4903,7 +4914,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 272,
+   "execution_count": 270,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4917,13 +4928,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 273,
+   "execution_count": 271,
    "metadata": {},
    "outputs": [],
    "source": [
     "plt.figure(figsize=(9,9))\n",
     "for digit in (2, 3, 5):\n",
-    "    plt.scatter(X_subset_reduced[y_subset == digit, 0], X_subset_reduced[y_subset == digit, 1], c=cmap(digit / 9))\n",
+    "    plt.scatter(X_subset_reduced[y_subset == digit, 0], X_subset_reduced[y_subset == digit, 1], c=[cmap(digit / 9)])\n",
     "plt.axis('off')\n",
     "plt.show()"
    ]
@@ -4953,7 +4964,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 274,
+   "execution_count": 272,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4972,7 +4983,7 @@
     "    cmap = matplotlib.cm.get_cmap(\"jet\")\n",
     "    digits = np.unique(y)\n",
     "    for digit in digits:\n",
-    "        plt.scatter(X_normalized[y == digit, 0], X_normalized[y == digit, 1], c=cmap(digit / 9))\n",
+    "        plt.scatter(X_normalized[y == digit, 0], X_normalized[y == digit, 1], c=[cmap(digit / 9)])\n",
     "    plt.axis(\"off\")\n",
     "    ax = plt.gcf().gca()  # get current axes in current figure\n",
     "    for index, image_coord in enumerate(X_normalized):\n",
@@ -4997,7 +5008,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 275,
+   "execution_count": 273,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5013,7 +5024,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 276,
+   "execution_count": 274,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5022,7 +5033,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 277,
+   "execution_count": 275,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5045,7 +5056,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 278,
+   "execution_count": 276,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5069,7 +5080,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 279,
+   "execution_count": 277,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5092,7 +5103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 280,
+   "execution_count": 278,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5126,7 +5137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 281,
+   "execution_count": 279,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5150,7 +5161,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 282,
+   "execution_count": 280,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5184,7 +5195,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 283,
+   "execution_count": 281,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5214,7 +5225,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 284,
+   "execution_count": 282,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5237,7 +5248,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 285,
+   "execution_count": 283,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -5284,7 +5295,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.6.6"
   }
  },
  "nbformat": 4,