minor plotting fixes, fixes for scikit-learn master

Author: amueller

mglearn/datasets.py

@@ -38,7 +38,7 @@ def load_citibike():
     data_mine['one'] = 1
     data_mine['starttime'] = pd.to_datetime(data_mine.starttime)
     data_starttime = data_mine.set_index("starttime")
-    data_resampled = data_starttime.resample("3h", how="sum").fillna(0)
+    data_resampled = data_starttime.resample("3h").sum().fillna(0)
     return data_resampled.one
 
 

mglearn/plot_cross_validation.py

@@ -17,7 +17,7 @@ def plot_label_kfold():
     n_iter = 3
     n_samples_per_fold = 1
 
-    cv = LabelKFold(n_folds=3)
+    cv = LabelKFold(n_splits=3)
     mask = np.zeros((n_iter, n_samples))
     for i, (train, test) in enumerate(cv.split(range(12), labels=labels)):
         mask[i, train] = 1
@@ -45,8 +45,8 @@ def plot_label_kfold():
     axes.set_xlabel("Data points")
     axes.set_xticks(np.arange(n_samples) + .5)
     axes.set_xticklabels(np.arange(1, n_samples + 1))
-    axes.set_yticks(np.arange(n_iter) + .3)
-    axes.set_yticklabels(["Split %d" % x for x in range(1, n_iter + 1)] + ["labels"]);
+    axes.set_yticks(np.arange(n_iter + 1) + .3)
+    axes.set_yticklabels(["Split %d" % x for x in range(1, n_iter + 1)] + ["Group"]);
     plt.legend([boxes[0], boxes[1]], ["Training set", "Test set"], loc=(1, .3));
     plt.tight_layout()
 
@@ -55,7 +55,7 @@ def plot_label_kfold():
 def plot_shuffle_split():
     from sklearn.model_selection import ShuffleSplit
     plt.figure(figsize=(10, 2))
-    plt.title("ShuffleSplit with 10 points, train_size=5, test_size=2, n_iter=4")
+    plt.title("ShuffleSplit with 10 points, train_size=5, test_size=2, n_splits=4")
 
     axes = plt.gca()
     axes.set_frame_on(False)
@@ -65,7 +65,7 @@ def plot_shuffle_split():
     n_iter = 4
     n_samples_per_fold = 1
 
-    ss = ShuffleSplit(n_iter=4, train_size=5, test_size=2, random_state=43)
+    ss = ShuffleSplit(n_splits=4, train_size=5, test_size=2, random_state=43)
     mask = np.zeros((n_iter, n_samples))
     for i, (train, test) in enumerate(ss.split(range(10))):
         mask[i, train] = 1

mglearn/plot_helpers.py

@@ -4,6 +4,7 @@
 from matplotlib.colors import ListedColormap, colorConverter, LinearSegmentedColormap
 
 
+cm_cycle = ListedColormap(['#0000aa', '#ff2020', '#50ff50', 'c', '#fff000'])
 cm3 = ListedColormap(['#0000aa', '#ff2020', '#50ff50'])
 cm2 = ListedColormap(['#0000aa', '#ff2020'])
 

mglearn/plot_interactive_tree.py

@@ -39,17 +39,24 @@ def tree_image(tree, fout=None):
 
 
 def plot_tree_progressive():
-    fig, axes = plt.subplots(4, 2, figsize=(15, 25), subplot_kw={'xticks': (), 'yticks': ()})
     X, y = make_moons(n_samples=100, noise=0.25, random_state=3)
+    plt.figure()
+    ax = plt.gca()
+    discrete_scatter(X[:, 0], X[:, 1], y, ax=ax)
+    ax.set_xticks(())
+    ax.set_yticks(())
+
+    axes = []
+    for i in range(3):
+        fig, ax = plt.subplots(1, 2, figsize=(12, 4),
+                               subplot_kw={'xticks': (), 'yticks': ()})
+        axes.append(ax)
+    axes = np.array(axes)
 
     for i, max_depth in enumerate([1, 2, 9]):
-        tree = plot_tree(X, y, max_depth=max_depth, ax=axes[i + 1, 0])
-        axes[i + 1, 1].imshow(tree_image(tree))
-        axes[i + 1, 1].set_axis_off()
-    axes[0, 1].set_visible(False)
-    for ax in axes[:, 0]:
-        discrete_scatter(X[:, 0], X[:, 1], y, ax=ax)
-        ax.legend(loc="best")
+        tree = plot_tree(X, y, max_depth=max_depth, ax=axes[i, 0])
+        axes[i, 1].imshow(tree_image(tree))
+        axes[i, 1].set_axis_off()
 
 
 def plot_tree_partition(X, y, tree, ax=None):

mglearn/plot_metrics.py

@@ -6,14 +6,14 @@
 
 
 def plot_confusion_matrix_illustration():
+    plt.figure(figsize=(8, 8))
     confusion = np.array([[401, 2], [8, 39]])
-    plt.title("confusion_matrix")
-    plt.text(0.45, .6, confusion[0, 0], size=70, horizontalalignment='right')
-    plt.text(0.45, .1, confusion[1, 0], size=70, horizontalalignment='right')
-    plt.text(.95, .6, confusion[0, 1], size=70, horizontalalignment='right')
-    plt.text(.95, 0.1, confusion[1, 1], size=70, horizontalalignment='right')
-    plt.xticks([.25, .75], ["predicted 'not 9'", "predicted '9'"], size=20)
-    plt.yticks([.25, .75], ["true '9'", "true 'not 9'"], size=20)
+    plt.text(0.40, .7, confusion[0, 0], size=70, horizontalalignment='right')
+    plt.text(0.40, .2, confusion[1, 0], size=70, horizontalalignment='right')
+    plt.text(.90, .7, confusion[0, 1], size=70, horizontalalignment='right')
+    plt.text(.90, 0.2, confusion[1, 1], size=70, horizontalalignment='right')
+    plt.xticks([.25, .75], ["predicted 'not nine'", "predicted 'nine'"], size=20)
+    plt.yticks([.25, .75], ["true 'nine'", "true 'not nine'"], size=20)
     plt.plot([.5, .5], [0, 1], '--', c='k')
     plt.plot([0, 1], [.5, .5], '--', c='k')
 
@@ -22,7 +22,6 @@ def plot_confusion_matrix_illustration():
 
 
 def plot_binary_confusion_matrix():
-    plt.title("binary_confusion_matrix_tp_fp")
     plt.text(0.45, .6, "TN", size=100, horizontalalignment='right')
     plt.text(0.45, .1, "FN", size=100, horizontalalignment='right')
     plt.text(.95, .6, "FP", size=100, horizontalalignment='right')

mglearn/plot_tree_nonmonotonous.py

@@ -12,6 +12,7 @@ def plot_tree_not_monotone():
     y = y % 2
     plt.figure()
     discrete_scatter(X[:, 0], X[:, 1], y)
+    plt.legend(["Class 0", "Class 1"], loc="best")
 
     # learn a decision tree model
     tree = DecisionTreeClassifier(random_state=0).fit(X, y)

preamble.py

@@ -1,12 +1,27 @@
-from IPython.display import set_matplotlib_formats
+from IPython.display import set_matplotlib_formats, display
+import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
 import mglearn
+from cycler import cycler
 
+#set_matplotlib_formats('png', 'svg')
 set_matplotlib_formats('pdf', 'png')
 plt.rcParams['savefig.dpi'] = 300
+plt.rcParams['image.cmap'] = "viridis"
 plt.rcParams['image.interpolation'] = "none"
 plt.rcParams['savefig.bbox'] = "tight"
-np.set_printoptions(precision=3)
+plt.rcParams['lines.linewidth'] = 2
+plt.rcParams['legend.numpoints'] = 1
+plt.rc('axes', prop_cycle=(cycler('color', mglearn.plot_helpers.cm_cycle.colors) +
+                           cycler('linestyle', ['-', '--', ':',
+                                                '-.', '--'])
+                           )
+       )
+
+np.set_printoptions(precision=3, suppress=True)
+
+pd.set_option("display.max_columns", 8)
+pd.set_option('precision', 2)
 
 np, mglearn