DOC: update examples, use matplotlib.pyplot instead of pylab

Author: glouppe

examples/ensemble/plot_adaboost_hastie_10_2.py

@@ -26,11 +26,12 @@
 # License: BSD 3 clause
 
 import numpy as np
+import matplotlib.pyplot as plt
+
 from sklearn import datasets
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.metrics import zero_one_loss
 from sklearn.ensemble import AdaBoostClassifier
-import pylab as pl
 
 
 n_estimators = 400
@@ -64,7 +65,7 @@
     algorithm="SAMME.R")
 ada_real.fit(X_train, y_train)
 
-fig = pl.figure()
+fig = plt.figure()
 ax = fig.add_subplot(111)
 
 ax.plot([1, n_estimators], [dt_stump_err] * 2, 'k-',
@@ -108,4 +109,4 @@
 leg = ax.legend(loc='upper right', fancybox=True)
 leg.get_frame().set_alpha(0.7)
 
-pl.show()
+plt.show()

examples/ensemble/plot_adaboost_multiclass.py

@@ -31,7 +31,7 @@
 
 from sklearn.externals.six.moves import zip
 
-import pylab as pl
+import matplotlib.pyplot as plt
 
 from sklearn.datasets import make_gaussian_quantiles
 from sklearn.ensemble import AdaBoostClassifier
@@ -74,36 +74,36 @@
 
 n_trees = xrange(1, len(bdt_discrete) + 1)
 
-pl.figure(figsize=(15, 5))
+plt.figure(figsize=(15, 5))
 
-pl.subplot(131)
-pl.plot(n_trees, discrete_test_errors, c='black', label='SAMME')
-pl.plot(n_trees, real_test_errors, c='black',
+plt.subplot(131)
+plt.plot(n_trees, discrete_test_errors, c='black', label='SAMME')
+plt.plot(n_trees, real_test_errors, c='black',
         linestyle='dashed', label='SAMME.R')
-pl.legend()
-pl.ylim(0.18, 0.62)
-pl.ylabel('Test Error')
-pl.xlabel('Number of Trees')
-
-pl.subplot(132)
-pl.plot(n_trees, bdt_discrete.estimator_errors_, "b", label='SAMME', alpha=.5)
-pl.plot(n_trees, bdt_real.estimator_errors_, "r", label='SAMME.R', alpha=.5)
-pl.legend()
-pl.ylabel('Error')
-pl.xlabel('Number of Trees')
-pl.ylim((.2,
+plt.legend()
+plt.ylim(0.18, 0.62)
+plt.ylabel('Test Error')
+plt.xlabel('Number of Trees')
+
+plt.subplot(132)
+plt.plot(n_trees, bdt_discrete.estimator_errors_, "b", label='SAMME', alpha=.5)
+plt.plot(n_trees, bdt_real.estimator_errors_, "r", label='SAMME.R', alpha=.5)
+plt.legend()
+plt.ylabel('Error')
+plt.xlabel('Number of Trees')
+plt.ylim((.2,
         max(bdt_real.estimator_errors_.max(),
             bdt_discrete.estimator_errors_.max()) * 1.2))
-pl.xlim((-20, len(bdt_discrete) + 20))
+plt.xlim((-20, len(bdt_discrete) + 20))
 
-pl.subplot(133)
-pl.plot(n_trees, bdt_discrete.estimator_weights_, "b", label='SAMME')
-pl.legend()
-pl.ylabel('Weight')
-pl.xlabel('Number of Trees')
-pl.ylim((0, bdt_discrete.estimator_weights_.max() * 1.2))
-pl.xlim((-20, len(bdt_discrete) + 20))
+plt.subplot(133)
+plt.plot(n_trees, bdt_discrete.estimator_weights_, "b", label='SAMME')
+plt.legend()
+plt.ylabel('Weight')
+plt.xlabel('Number of Trees')
+plt.ylim((0, bdt_discrete.estimator_weights_.max() * 1.2))
+plt.xlim((-20, len(bdt_discrete) + 20))
 
 # prevent overlapping y-axis labels
-pl.subplots_adjust(wspace=0.25)
-pl.show()
+plt.subplots_adjust(wspace=0.25)
+plt.show()

examples/ensemble/plot_adaboost_regression.py

@@ -15,6 +15,7 @@
 print(__doc__)
 
 import numpy as np
+import matplotlib.pyplot as plt
 
 # Create a the dataset
 rng = np.random.RandomState(1)
@@ -38,14 +39,12 @@
 y_2 = clf_2.predict(X)
 
 # Plot the results
-import pylab as pl
-
-pl.figure()
-pl.scatter(X, y, c="k", label="training samples")
-pl.plot(X, y_1, c="g", label="n_estimators=1", linewidth=2)
-pl.plot(X, y_2, c="r", label="n_estimators=300", linewidth=2)
-pl.xlabel("data")
-pl.ylabel("target")
-pl.title("Boosted Decision Tree Regression")
-pl.legend()
-pl.show()
+plt.figure()
+plt.scatter(X, y, c="k", label="training samples")
+plt.plot(X, y_1, c="g", label="n_estimators=1", linewidth=2)
+plt.plot(X, y_2, c="r", label="n_estimators=300", linewidth=2)
+plt.xlabel("data")
+plt.ylabel("target")
+plt.title("Boosted Decision Tree Regression")
+plt.legend()
+plt.show()

examples/ensemble/plot_adaboost_twoclass.py

@@ -18,8 +18,8 @@
 """
 print(__doc__)
 
-import pylab as pl
 import numpy as np
+import matplotlib.pyplot as plt
 
 from sklearn.ensemble import AdaBoostClassifier
 from sklearn.tree import DecisionTreeClassifier
@@ -47,47 +47,47 @@
 plot_step = 0.02
 class_names = "AB"
 
-pl.figure(figsize=(10, 5))
+plt.figure(figsize=(10, 5))
 
 # Plot the decision boundaries
-pl.subplot(121)
+plt.subplot(121)
 x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
 y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
 xx, yy = np.meshgrid(np.arange(x_min, x_max, plot_step),
                      np.arange(y_min, y_max, plot_step))
 
 Z = bdt.predict(np.c_[xx.ravel(), yy.ravel()])
 Z = Z.reshape(xx.shape)
-cs = pl.contourf(xx, yy, Z, cmap=pl.cm.Paired)
-pl.axis("tight")
+cs = plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)
+plt.axis("tight")
 
 # Plot the training points
 for i, n, c in zip(range(2), class_names, plot_colors):
     idx = np.where(y == i)
-    pl.scatter(X[idx, 0], X[idx, 1],
-               c=c, cmap=pl.cm.Paired,
+    plt.scatter(X[idx, 0], X[idx, 1],
+               c=c, cmap=plt.cm.Paired,
                label="Class %s" % n)
-pl.xlim(x_min, x_max)
-pl.ylim(y_min, y_max)
-pl.legend(loc='upper right')
-pl.xlabel("Decision Boundary")
+plt.xlim(x_min, x_max)
+plt.ylim(y_min, y_max)
+plt.legend(loc='upper right')
+plt.xlabel("Decision Boundary")
 
 # Plot the two-class decision scores
 twoclass_output = bdt.decision_function(X)
 plot_range = (twoclass_output.min(), twoclass_output.max())
-pl.subplot(122)
+plt.subplot(122)
 for i, n, c in zip(range(2), class_names, plot_colors):
-    pl.hist(twoclass_output[y == i],
+    plt.hist(twoclass_output[y == i],
             bins=10,
             range=plot_range,
             facecolor=c,
             label='Class %s' % n,
             alpha=.5)
-x1, x2, y1, y2 = pl.axis()
-pl.axis((x1, x2, y1, y2 * 1.2))
-pl.legend(loc='upper right')
-pl.ylabel('Samples')
-pl.xlabel('Decision Scores')
+x1, x2, y1, y2 = plt.axis()
+plt.axis((x1, x2, y1, y2 * 1.2))
+plt.legend(loc='upper right')
+plt.ylabel('Samples')
+plt.xlabel('Decision Scores')
 
-pl.subplots_adjust(wspace=0.25)
-pl.show()
+plt.subplots_adjust(wspace=0.25)
+plt.show()

examples/ensemble/plot_bias_variance.py

@@ -67,7 +67,7 @@
 # License: BSD 3 clause
 
 import numpy as np
-from matplotlib import pyplot as plt
+import matplotlib.pyplot as plt
 
 from sklearn.ensemble import BaggingRegressor
 from sklearn.tree import DecisionTreeRegressor

examples/ensemble/plot_forest_importances.py

@@ -13,7 +13,7 @@
 print(__doc__)
 
 import numpy as np
-import pylab as pl
+import matplotlib.pyplot as plt
 
 from sklearn.datasets import make_classification
 from sklearn.ensemble import ExtraTreesClassifier
@@ -45,10 +45,10 @@
     print("%d. feature %d (%f)" % (f + 1, indices[f], importances[indices[f]]))
 
 # Plot the feature importances of the forest
-pl.figure()
-pl.title("Feature importances")
-pl.bar(range(10), importances[indices],
+plt.figure()
+plt.title("Feature importances")
+plt.bar(range(10), importances[indices],
        color="r", yerr=std[indices], align="center")
-pl.xticks(range(10), indices)
-pl.xlim([-1, 10])
-pl.show()
+plt.xticks(range(10), indices)
+plt.xlim([-1, 10])
+plt.show()

examples/ensemble/plot_forest_importances_faces.py

@@ -13,7 +13,7 @@
 print(__doc__)
 
 from time import time
-import pylab as pl
+import matplotlib.pyplot as plt
 
 from sklearn.datasets import fetch_olivetti_faces
 from sklearn.ensemble import ExtraTreesClassifier
@@ -44,6 +44,6 @@
 importances = importances.reshape(data.images[0].shape)
 
 # Plot pixel importances
-pl.matshow(importances, cmap=pl.cm.hot)
-pl.title("Pixel importances with forests of trees")
-pl.show()
+plt.matshow(importances, cmap=plt.cm.hot)
+plt.title("Pixel importances with forests of trees")
+plt.show()

examples/ensemble/plot_forest_iris.py

@@ -41,7 +41,7 @@
 print(__doc__)
 
 import numpy as np
-import pylab as pl
+import matplotlib.pyplot as plt
 
 from sklearn import clone
 from sklearn.datasets import load_iris
@@ -54,7 +54,7 @@
 n_classes = 3
 n_estimators = 30
 plot_colors = "ryb"
-cmap = pl.cm.RdYlBu
+cmap = plt.cm.RdYlBu
 plot_step = 0.02  # fine step width for decision surface contours
 plot_step_coarser = 0.5  # step widths for coarse classifier guesses
 RANDOM_SEED = 13  # fix the seed on each iteration
@@ -101,10 +101,10 @@
             model_details += " with {} estimators".format(len(model.estimators_))
         print( model_details + " with features", pair, "has a score of", scores )
 
-        pl.subplot(3, 4, plot_idx)
+        plt.subplot(3, 4, plot_idx)
         if plot_idx <= len(models):
             # Add a title at the top of each column
-            pl.title(model_title)
+            plt.title(model_title)
 
         # Now plot the decision boundary using a fine mesh as input to a
         # filled contour plot
@@ -118,7 +118,7 @@
         if isinstance(model, DecisionTreeClassifier):
             Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
             Z = Z.reshape(xx.shape)
-            cs = pl.contourf(xx, yy, Z, cmap=cmap)
+            cs = plt.contourf(xx, yy, Z, cmap=cmap)
         else:
             # Choose alpha blend level with respect to the number of estimators
             # that are in use (noting that AdaBoost can use fewer estimators
@@ -127,26 +127,26 @@
             for tree in model.estimators_:
                 Z = tree.predict(np.c_[xx.ravel(), yy.ravel()])
                 Z = Z.reshape(xx.shape)
-                cs = pl.contourf(xx, yy, Z, alpha=estimator_alpha, cmap=cmap)
+                cs = plt.contourf(xx, yy, Z, alpha=estimator_alpha, cmap=cmap)
 
         # Build a coarser grid to plot a set of ensemble classifications
         # to show how these are different to what we see in the decision
         # surfaces. These points are regularly space and do not have a black outline
         xx_coarser, yy_coarser = np.meshgrid(np.arange(x_min, x_max, plot_step_coarser),
                                              np.arange(y_min, y_max, plot_step_coarser))
         Z_points_coarser = model.predict(np.c_[xx_coarser.ravel(), yy_coarser.ravel()]).reshape(xx_coarser.shape)
-        cs_points = pl.scatter(xx_coarser, yy_coarser, s=15, c=Z_points_coarser, cmap=cmap, edgecolors="none")
+        cs_points = plt.scatter(xx_coarser, yy_coarser, s=15, c=Z_points_coarser, cmap=cmap, edgecolors="none")
 
         # Plot the training points, these are clustered together and have a
         # black outline
         for i, c in zip(xrange(n_classes), plot_colors):
             idx = np.where(y == i)
-            pl.scatter(X[idx, 0], X[idx, 1], c=c, label=iris.target_names[i],
+            plt.scatter(X[idx, 0], X[idx, 1], c=c, label=iris.target_names[i],
                        cmap=cmap)
 
         plot_idx += 1  # move on to the next plot in sequence
 
-pl.suptitle("Classifiers on feature subsets of the Iris dataset")
-pl.axis("tight")
+plt.suptitle("Classifiers on feature subsets of the Iris dataset")
+plt.axis("tight")
 
-pl.show()
+plt.show()

examples/ensemble/plot_gradient_boosting_oob.py

@@ -30,7 +30,7 @@
 # License: BSD 3 clause
 
 import numpy as np
-from matplotlib import pyplot as plt
+import matplotlib.pyplot as plt
 
 from sklearn import ensemble
 from sklearn.cross_validation import KFold

examples/ensemble/plot_gradient_boosting_quantile.py

@@ -8,9 +8,9 @@
 """
 
 import numpy as np
-import pylab as pl
-from sklearn.ensemble import GradientBoostingRegressor
+import matplotlib.pyplot as plt
 
+from sklearn.ensemble import GradientBoostingRegressor
 
 np.random.seed(1)
 
@@ -63,17 +63,17 @@ def f(x):
 
 # Plot the function, the prediction and the 95% confidence interval based on
 # the MSE
-fig = pl.figure()
-pl.plot(xx, f(xx), 'g:', label=u'$f(x) = x\,\sin(x)$')
-pl.plot(X, y, 'b.', markersize=10, label=u'Observations')
-pl.plot(xx, y_pred, 'r-', label=u'Prediction')
-pl.plot(xx, y_upper, 'k-')
-pl.plot(xx, y_lower, 'k-')
-pl.fill(np.concatenate([xx, xx[::-1]]),
+fig = plt.figure()
+plt.plot(xx, f(xx), 'g:', label=u'$f(x) = x\,\sin(x)$')
+plt.plot(X, y, 'b.', markersize=10, label=u'Observations')
+plt.plot(xx, y_pred, 'r-', label=u'Prediction')
+plt.plot(xx, y_upper, 'k-')
+plt.plot(xx, y_lower, 'k-')
+plt.fill(np.concatenate([xx, xx[::-1]]),
         np.concatenate([y_upper, y_lower[::-1]]),
         alpha=.5, fc='b', ec='None', label='95% prediction interval')
-pl.xlabel('$x$')
-pl.ylabel('$f(x)$')
-pl.ylim(-10, 20)
-pl.legend(loc='upper left')
-pl.show()
+plt.xlabel('$x$')
+plt.ylabel('$f(x)$')
+plt.ylim(-10, 20)
+plt.legend(loc='upper left')
+plt.show()