ENH Match the book exactly

Including import order and comments

Author: luispedro

ch02/figure1.py

@@ -5,9 +5,12 @@
 #
 # It is made available under the MIT License
 
-from sklearn.datasets import load_iris
 from matplotlib import pyplot as plt
 
+# We load the data with load_iris from sklearn
+from sklearn.datasets import load_iris
+
+# load_iris returns an object with several fields
 data = load_iris()
 features = data.data
 feature_names = data.feature_names

ch02/figure2.py

@@ -10,14 +10,18 @@
 from matplotlib import pyplot as plt
 from sklearn.datasets import load_iris
 data = load_iris()
-features = data['data']
-feature_names = data['feature_names']
-species = data['target_names'][data['target']]
+features = data.data
+feature_names = data.feature_names
+target = data.target
+target_names = data.target_names
 
-is_setosa = (species == 'setosa')
+# We use NumPy fancy indexing to get an array of strings:
+labels = target_names[target]
+
+is_setosa = (labels == 'setosa')
 features = features[~is_setosa]
-species = species[~is_setosa]
-is_virginica = (species == 'virginica')
+labels = labels[~is_setosa]
+is_virginica = (labels == 'virginica')
 
 # Hand fixed threshold:
 t = 1.75

ch02/simple_threshold.py

@@ -12,9 +12,12 @@
 target = data['target']
 target_names = data['target_names']
 labels = target_names[target]
-
 plength = features[:, 2]
+
+# To use numpy operations to get setosa features,
+# we build a boolean array
 is_setosa = (labels == 'setosa')
+
 max_setosa = plength[is_setosa].max()
 min_non_setosa = plength[~is_setosa].min()