Chapter 7 – Ensemble Learning and Random Forests
This notebook contains all the sample code and solutions to the exercises in chapter 7.
First, let's make sure this notebook works well in both python 2 and 3, import a few common modules, ensure MatplotLib plots figures inline and prepare a function to save the figures:
In [1]:
# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals
# Common imports
import numpy as np
import os
# to make this notebook's output stable across runs
np.random.seed(42)
# To plot pretty figures
%matplotlib inline
import matplotlib as mpl
import matplotlib.pyplot as plt
mpl.rc('axes', labelsize=14)
mpl.rc('xtick', labelsize=12)
mpl.rc('ytick', labelsize=12)
# Where to save the figures
PROJECT_ROOT_DIR = "."
CHAPTER_ID = "ensembles"
def image_path(fig_id):
return os.path.join(PROJECT_ROOT_DIR, "images", CHAPTER_ID, fig_id)
def save_fig(fig_id, tight_layout=True):
print("Saving figure", fig_id)
if tight_layout:
plt.tight_layout()
plt.savefig(image_path(fig_id) + ".png", format='png', dpi=300)
In [2]:
heads_proba = 0.51
coin_tosses = (np.random.rand(10000, 10) < heads_proba).astype(np.int32)
cumulative_heads_ratio = np.cumsum(coin_tosses, axis=0) / np.arange(1, 10001).reshape(-1, 1)
In [3]:
plt.figure(figsize=(8,3.5))
plt.plot(cumulative_heads_ratio)
plt.plot([0, 10000], [0.51, 0.51], "k--", linewidth=2, label="51%")
plt.plot([0, 10000], [0.5, 0.5], "k-", label="50%")
plt.xlabel("Number of coin tosses")
plt.ylabel("Heads ratio")
plt.legend(loc="lower right")
plt.axis([0, 10000, 0.42, 0.58])
save_fig("law_of_large_numbers_plot")
plt.show()
In [4]:
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_moons
X, y = make_moons(n_samples=500, noise=0.30, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
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.
In [5]:
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import VotingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
log_clf = LogisticRegression(solver="liblinear", random_state=42)
rnd_clf = RandomForestClassifier(n_estimators=10, random_state=42)
svm_clf = SVC(gamma="auto", random_state=42)
voting_clf = VotingClassifier(
estimators=[('lr', log_clf), ('rf', rnd_clf), ('svc', svm_clf)],
voting='hard')
In [6]:
voting_clf.fit(X_train, y_train)
Out[6]:
In [7]:
from sklearn.metrics import accuracy_score
for clf in (log_clf, rnd_clf, svm_clf, voting_clf):
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print(clf.__class__.__name__, accuracy_score(y_test, y_pred))
In [8]:
log_clf = LogisticRegression(solver="liblinear", random_state=42)
rnd_clf = RandomForestClassifier(n_estimators=10, random_state=42)
svm_clf = SVC(gamma="auto", probability=True, random_state=42)
voting_clf = VotingClassifier(
estimators=[('lr', log_clf), ('rf', rnd_clf), ('svc', svm_clf)],
voting='soft')
voting_clf.fit(X_train, y_train)
Out[8]:
In [9]:
from sklearn.metrics import accuracy_score
for clf in (log_clf, rnd_clf, svm_clf, voting_clf):
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print(clf.__class__.__name__, accuracy_score(y_test, y_pred))
In [10]:
from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier
bag_clf = BaggingClassifier(
DecisionTreeClassifier(random_state=42), n_estimators=500,
max_samples=100, bootstrap=True, n_jobs=-1, random_state=42)
bag_clf.fit(X_train, y_train)
y_pred = bag_clf.predict(X_test)
In [11]:
from sklearn.metrics import accuracy_score
print(accuracy_score(y_test, y_pred))
In [12]:
tree_clf = DecisionTreeClassifier(random_state=42)
tree_clf.fit(X_train, y_train)
y_pred_tree = tree_clf.predict(X_test)
print(accuracy_score(y_test, y_pred_tree))
In [13]:
from matplotlib.colors import ListedColormap
def plot_decision_boundary(clf, X, y, axes=[-1.5, 2.5, -1, 1.5], alpha=0.5, contour=True):
x1s = np.linspace(axes[0], axes[1], 100)
x2s = np.linspace(axes[2], axes[3], 100)
x1, x2 = np.meshgrid(x1s, x2s)
X_new = np.c_[x1.ravel(), x2.ravel()]
y_pred = clf.predict(X_new).reshape(x1.shape)
custom_cmap = ListedColormap(['#fafab0','#9898ff','#a0faa0'])
plt.contourf(x1, x2, y_pred, alpha=0.3, cmap=custom_cmap)
if contour:
custom_cmap2 = ListedColormap(['#7d7d58','#4c4c7f','#507d50'])
plt.contour(x1, x2, y_pred, cmap=custom_cmap2, alpha=0.8)
plt.plot(X[:, 0][y==0], X[:, 1][y==0], "yo", alpha=alpha)
plt.plot(X[:, 0][y==1], X[:, 1][y==1], "bs", alpha=alpha)
plt.axis(axes)
plt.xlabel(r"$x_1$", fontsize=18)
plt.ylabel(r"$x_2$", fontsize=18, rotation=0)
In [14]:
plt.figure(figsize=(11,4))
plt.subplot(121)
plot_decision_boundary(tree_clf, X, y)
plt.title("Decision Tree", fontsize=14)
plt.subplot(122)
plot_decision_boundary(bag_clf, X, y)
plt.title("Decision Trees with Bagging", fontsize=14)
save_fig("decision_tree_without_and_with_bagging_plot")
plt.show()
In [15]:
bag_clf = BaggingClassifier(
DecisionTreeClassifier(splitter="random", max_leaf_nodes=16, random_state=42),
n_estimators=500, max_samples=1.0, bootstrap=True, n_jobs=-1, random_state=42)
In [16]:
bag_clf.fit(X_train, y_train)
y_pred = bag_clf.predict(X_test)
In [17]:
from sklearn.ensemble import RandomForestClassifier
rnd_clf = RandomForestClassifier(n_estimators=500, max_leaf_nodes=16, n_jobs=-1, random_state=42)
rnd_clf.fit(X_train, y_train)
y_pred_rf = rnd_clf.predict(X_test)
In [18]:
np.sum(y_pred == y_pred_rf) / len(y_pred) # almost identical predictions
Out[18]:
In [19]:
from sklearn.datasets import load_iris
iris = load_iris()
rnd_clf = RandomForestClassifier(n_estimators=500, n_jobs=-1, random_state=42)
rnd_clf.fit(iris["data"], iris["target"])
for name, score in zip(iris["feature_names"], rnd_clf.feature_importances_):
print(name, score)
In [20]:
rnd_clf.feature_importances_
Out[20]:
In [21]:
plt.figure(figsize=(6, 4))
for i in range(15):
tree_clf = DecisionTreeClassifier(max_leaf_nodes=16, random_state=42 + i)
indices_with_replacement = np.random.randint(0, len(X_train), len(X_train))
tree_clf.fit(X[indices_with_replacement], y[indices_with_replacement])
plot_decision_boundary(tree_clf, X, y, axes=[-1.5, 2.5, -1, 1.5], alpha=0.02, contour=False)
plt.show()
In [22]:
bag_clf = BaggingClassifier(
DecisionTreeClassifier(random_state=42), n_estimators=500,
bootstrap=True, n_jobs=-1, oob_score=True, random_state=40)
bag_clf.fit(X_train, y_train)
bag_clf.oob_score_
Out[22]:
In [23]:
bag_clf.oob_decision_function_
Out[23]:
In [24]:
from sklearn.metrics import accuracy_score
y_pred = bag_clf.predict(X_test)
accuracy_score(y_test, y_pred)
Out[24]:
In [25]:
try:
from sklearn.datasets import fetch_openml
mnist = fetch_openml('mnist_784', version=1)
mnist.target = mnist.target.astype(np.int64)
except ImportError:
from sklearn.datasets import fetch_mldata
mnist = fetch_mldata('MNIST original')
In [26]:
rnd_clf = RandomForestClassifier(n_estimators=10, random_state=42)
rnd_clf.fit(mnist["data"], mnist["target"])
Out[26]:
In [27]:
def plot_digit(data):
image = data.reshape(28, 28)
plt.imshow(image, cmap = mpl.cm.hot,
interpolation="nearest")
plt.axis("off")
In [28]:
plot_digit(rnd_clf.feature_importances_)
cbar = plt.colorbar(ticks=[rnd_clf.feature_importances_.min(), rnd_clf.feature_importances_.max()])
cbar.ax.set_yticklabels(['Not important', 'Very important'])
save_fig("mnist_feature_importance_plot")
plt.show()
In [29]:
from sklearn.ensemble import AdaBoostClassifier
ada_clf = AdaBoostClassifier(
DecisionTreeClassifier(max_depth=1), n_estimators=200,
algorithm="SAMME.R", learning_rate=0.5, random_state=42)
ada_clf.fit(X_train, y_train)
Out[29]:
In [30]:
plot_decision_boundary(ada_clf, X, y)
In [31]:
m = len(X_train)
plt.figure(figsize=(11, 4))
for subplot, learning_rate in ((121, 1), (122, 0.5)):
sample_weights = np.ones(m)
plt.subplot(subplot)
for i in range(5):
svm_clf = SVC(kernel="rbf", C=0.05, gamma="auto", random_state=42)
svm_clf.fit(X_train, y_train, sample_weight=sample_weights)
y_pred = svm_clf.predict(X_train)
sample_weights[y_pred != y_train] *= (1 + learning_rate)
plot_decision_boundary(svm_clf, X, y, alpha=0.2)
plt.title("learning_rate = {}".format(learning_rate), fontsize=16)
if subplot == 121:
plt.text(-0.7, -0.65, "1", fontsize=14)
plt.text(-0.6, -0.10, "2", fontsize=14)
plt.text(-0.5, 0.10, "3", fontsize=14)
plt.text(-0.4, 0.55, "4", fontsize=14)
plt.text(-0.3, 0.90, "5", fontsize=14)
save_fig("boosting_plot")
plt.show()
In [32]:
list(m for m in dir(ada_clf) if not m.startswith("_") and m.endswith("_"))
Out[32]:
In [33]:
np.random.seed(42)
X = np.random.rand(100, 1) - 0.5
y = 3*X[:, 0]**2 + 0.05 * np.random.randn(100)
In [34]:
from sklearn.tree import DecisionTreeRegressor
tree_reg1 = DecisionTreeRegressor(max_depth=2, random_state=42)
tree_reg1.fit(X, y)
Out[34]:
In [35]:
y2 = y - tree_reg1.predict(X)
tree_reg2 = DecisionTreeRegressor(max_depth=2, random_state=42)
tree_reg2.fit(X, y2)
Out[35]:
In [36]:
y3 = y2 - tree_reg2.predict(X)
tree_reg3 = DecisionTreeRegressor(max_depth=2, random_state=42)
tree_reg3.fit(X, y3)
Out[36]:
In [37]:
X_new = np.array([[0.8]])
In [38]:
y_pred = sum(tree.predict(X_new) for tree in (tree_reg1, tree_reg2, tree_reg3))
In [39]:
y_pred
Out[39]:
In [40]:
def plot_predictions(regressors, X, y, axes, label=None, style="r-", data_style="b.", data_label=None):
x1 = np.linspace(axes[0], axes[1], 500)
y_pred = sum(regressor.predict(x1.reshape(-1, 1)) for regressor in regressors)
plt.plot(X[:, 0], y, data_style, label=data_label)
plt.plot(x1, y_pred, style, linewidth=2, label=label)
if label or data_label:
plt.legend(loc="upper center", fontsize=16)
plt.axis(axes)
plt.figure(figsize=(11,11))
plt.subplot(321)
plot_predictions([tree_reg1], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label="$h_1(x_1)$", style="g-", data_label="Training set")
plt.ylabel("$y$", fontsize=16, rotation=0)
plt.title("Residuals and tree predictions", fontsize=16)
plt.subplot(322)
plot_predictions([tree_reg1], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label="$h(x_1) = h_1(x_1)$", data_label="Training set")
plt.ylabel("$y$", fontsize=16, rotation=0)
plt.title("Ensemble predictions", fontsize=16)
plt.subplot(323)
plot_predictions([tree_reg2], X, y2, axes=[-0.5, 0.5, -0.5, 0.5], label="$h_2(x_1)$", style="g-", data_style="k+", data_label="Residuals")
plt.ylabel("$y - h_1(x_1)$", fontsize=16)
plt.subplot(324)
plot_predictions([tree_reg1, tree_reg2], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label="$h(x_1) = h_1(x_1) + h_2(x_1)$")
plt.ylabel("$y$", fontsize=16, rotation=0)
plt.subplot(325)
plot_predictions([tree_reg3], X, y3, axes=[-0.5, 0.5, -0.5, 0.5], label="$h_3(x_1)$", style="g-", data_style="k+")
plt.ylabel("$y - h_1(x_1) - h_2(x_1)$", fontsize=16)
plt.xlabel("$x_1$", fontsize=16)
plt.subplot(326)
plot_predictions([tree_reg1, tree_reg2, tree_reg3], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label="$h(x_1) = h_1(x_1) + h_2(x_1) + h_3(x_1)$")
plt.xlabel("$x_1$", fontsize=16)
plt.ylabel("$y$", fontsize=16, rotation=0)
save_fig("gradient_boosting_plot")
plt.show()
In [41]:
from sklearn.ensemble import GradientBoostingRegressor
gbrt = GradientBoostingRegressor(max_depth=2, n_estimators=3, learning_rate=1.0, random_state=42)
gbrt.fit(X, y)
Out[41]:
In [42]:
gbrt_slow = GradientBoostingRegressor(max_depth=2, n_estimators=200, learning_rate=0.1, random_state=42)
gbrt_slow.fit(X, y)
Out[42]:
In [43]:
plt.figure(figsize=(11,4))
plt.subplot(121)
plot_predictions([gbrt], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label="Ensemble predictions")
plt.title("learning_rate={}, n_estimators={}".format(gbrt.learning_rate, gbrt.n_estimators), fontsize=14)
plt.subplot(122)
plot_predictions([gbrt_slow], X, y, axes=[-0.5, 0.5, -0.1, 0.8])
plt.title("learning_rate={}, n_estimators={}".format(gbrt_slow.learning_rate, gbrt_slow.n_estimators), fontsize=14)
save_fig("gbrt_learning_rate_plot")
plt.show()
In [44]:
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
X_train, X_val, y_train, y_val = train_test_split(X, y, random_state=49)
gbrt = GradientBoostingRegressor(max_depth=2, n_estimators=120, random_state=42)
gbrt.fit(X_train, y_train)
errors = [mean_squared_error(y_val, y_pred)
for y_pred in gbrt.staged_predict(X_val)]
bst_n_estimators = np.argmin(errors) + 1
gbrt_best = GradientBoostingRegressor(max_depth=2,n_estimators=bst_n_estimators, random_state=42)
gbrt_best.fit(X_train, y_train)
Out[44]:
In [45]:
min_error = np.min(errors)
In [46]:
plt.figure(figsize=(11, 4))
plt.subplot(121)
plt.plot(errors, "b.-")
plt.plot([bst_n_estimators, bst_n_estimators], [0, min_error], "k--")
plt.plot([0, 120], [min_error, min_error], "k--")
plt.plot(bst_n_estimators, min_error, "ko")
plt.text(bst_n_estimators, min_error*1.2, "Minimum", ha="center", fontsize=14)
plt.axis([0, 120, 0, 0.01])
plt.xlabel("Number of trees")
plt.title("Validation error", fontsize=14)
plt.subplot(122)
plot_predictions([gbrt_best], X, y, axes=[-0.5, 0.5, -0.1, 0.8])
plt.title("Best model (%d trees)" % bst_n_estimators, fontsize=14)
save_fig("early_stopping_gbrt_plot")
plt.show()
In [47]:
gbrt = GradientBoostingRegressor(max_depth=2, warm_start=True, random_state=42)
min_val_error = float("inf")
error_going_up = 0
for n_estimators in range(1, 120):
gbrt.n_estimators = n_estimators
gbrt.fit(X_train, y_train)
y_pred = gbrt.predict(X_val)
val_error = mean_squared_error(y_val, y_pred)
if val_error < min_val_error:
min_val_error = val_error
error_going_up = 0
else:
error_going_up += 1
if error_going_up == 5:
break # early stopping
In [48]:
print(gbrt.n_estimators)
In [49]:
print("Minimum validation MSE:", min_val_error)
In [50]:
try:
import xgboost
except ImportError as ex:
print("Error: the xgboost library is not installed.")
xgboost = None
In [51]:
if xgboost is not None: # not shown in the book
xgb_reg = xgboost.XGBRegressor(random_state=42)
xgb_reg.fit(X_train, y_train)
y_pred = xgb_reg.predict(X_val)
val_error = mean_squared_error(y_val, y_pred)
print("Validation MSE:", val_error)
In [52]:
if xgboost is not None: # not shown in the book
xgb_reg.fit(X_train, y_train,
eval_set=[(X_val, y_val)], early_stopping_rounds=2)
y_pred = xgb_reg.predict(X_val)
val_error = mean_squared_error(y_val, y_pred)
print("Validation MSE:", val_error)
In [53]:
%timeit xgboost.XGBRegressor().fit(X_train, y_train) if xgboost is not None else None
In [54]:
%timeit GradientBoostingRegressor().fit(X_train, y_train)
See Appendix A.
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).
The MNIST dataset was loaded earlier.
In [55]:
from sklearn.model_selection import train_test_split
In [56]:
X_train_val, X_test, y_train_val, y_test = train_test_split(
mnist.data, mnist.target, test_size=10000, random_state=42)
X_train, X_val, y_train, y_val = train_test_split(
X_train_val, y_train_val, test_size=10000, random_state=42)
Exercise: Then train various classifiers, such as a Random Forest classifier, an Extra-Trees classifier, and an SVM.
In [57]:
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
from sklearn.svm import LinearSVC
from sklearn.neural_network import MLPClassifier
In [58]:
random_forest_clf = RandomForestClassifier(n_estimators=10, random_state=42)
extra_trees_clf = ExtraTreesClassifier(n_estimators=10, random_state=42)
svm_clf = LinearSVC(random_state=42)
mlp_clf = MLPClassifier(random_state=42)
In [59]:
estimators = [random_forest_clf, extra_trees_clf, svm_clf, mlp_clf]
for estimator in estimators:
print("Training the", estimator)
estimator.fit(X_train, y_train)
In [60]:
[estimator.score(X_val, y_val) for estimator in estimators]
Out[60]:
The linear SVM is far outperformed by the other classifiers. However, let's keep it for now since it may improve the voting classifier's performance.
Exercise: Next, try to combine them into an ensemble that outperforms them all on the validation set, using a soft or hard voting classifier.
In [61]:
from sklearn.ensemble import VotingClassifier
In [62]:
named_estimators = [
("random_forest_clf", random_forest_clf),
("extra_trees_clf", extra_trees_clf),
("svm_clf", svm_clf),
("mlp_clf", mlp_clf),
]
In [63]:
voting_clf = VotingClassifier(named_estimators)
In [64]:
voting_clf.fit(X_train, y_train)
Out[64]:
In [65]:
voting_clf.score(X_val, y_val)
Out[65]:
In [66]:
[estimator.score(X_val, y_val) for estimator in voting_clf.estimators_]
Out[66]:
Let's remove the SVM to see if performance improves. It is possible to remove an estimator by setting it to None using set_params() like this:
In [67]:
voting_clf.set_params(svm_clf=None)
Out[67]:
This updated the list of estimators:
In [68]:
voting_clf.estimators
Out[68]:
However, it did not update the list of trained estimators:
In [69]:
voting_clf.estimators_
Out[69]:
So we can either fit the VotingClassifier again, or just remove the SVM from the list of trained estimators:
In [70]:
del voting_clf.estimators_[2]
Now let's evaluate the VotingClassifier again:
In [71]:
voting_clf.score(X_val, y_val)
Out[71]:
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":
In [72]:
voting_clf.voting = "soft"
In [73]:
voting_clf.score(X_val, y_val)
Out[73]:
That's a significant improvement, and it's much better than each of the individual classifiers.
Once you have found one, try it on the test set. How much better does it perform compared to the individual classifiers?
In [74]:
voting_clf.score(X_test, y_test)
Out[74]:
In [75]:
[estimator.score(X_test, y_test) for estimator in voting_clf.estimators_]
Out[75]:
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!
Exercise: Run the individual classifiers from the previous exercise to make predictions on the validation set, and create a new training set with the resulting predictions: each training instance is a vector containing the set of predictions from all your classifiers for an image, and the target is the image's class. Train a classifier on this new training set.
In [76]:
X_val_predictions = np.empty((len(X_val), len(estimators)), dtype=np.float32)
for index, estimator in enumerate(estimators):
X_val_predictions[:, index] = estimator.predict(X_val)
In [77]:
X_val_predictions
Out[77]:
In [78]:
rnd_forest_blender = RandomForestClassifier(n_estimators=200, oob_score=True, random_state=42)
rnd_forest_blender.fit(X_val_predictions, y_val)
Out[78]:
In [79]:
rnd_forest_blender.oob_score_
Out[79]:
You could fine-tune this blender or try other types of blenders (e.g., an MLPClassifier), then select the best one using cross-validation, as always.
Exercise: Congratulations, you have just trained a blender, and together with the classifiers they form a stacking ensemble! Now let's evaluate the ensemble on the test set. For each image in the test set, make predictions with all your classifiers, then feed the predictions to the blender to get the ensemble's predictions. How does it compare to the voting classifier you trained earlier?
In [80]:
X_test_predictions = np.empty((len(X_test), len(estimators)), dtype=np.float32)
for index, estimator in enumerate(estimators):
X_test_predictions[:, index] = estimator.predict(X_test)
In [81]:
y_pred = rnd_forest_blender.predict(X_test_predictions)
In [82]:
from sklearn.metrics import accuracy_score
In [83]:
accuracy_score(y_test, y_pred)
Out[83]:
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.