forked from Starignus/AppliedML_Python_Coursera
-
Notifications
You must be signed in to change notification settings - Fork 0
/
adspy_shared_utilities.py
292 lines (232 loc) · 11.2 KB
/
adspy_shared_utilities.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
# version 1.0
import numpy
import pandas as pd
import seaborn as sn
import matplotlib.pyplot as plt
import matplotlib.cm as cm
from matplotlib.colors import ListedColormap, BoundaryNorm
from sklearn import neighbors
import matplotlib.patches as mpatches
import graphviz
from sklearn.tree import export_graphviz
import matplotlib.patches as mpatches
# Meshgrid expanation https://stackoverflow.com/questions/36013063/what-is-purpose-of-meshgrid-in-python
def load_crime_dataset():
# Communities and Crime dataset for regression
# https://archive.ics.uci.edu/ml/datasets/Communities+and+Crime+Unnormalized
crime = pd.read_table('CommViolPredUnnormalizedData.txt', sep=',', na_values='?')
crime.head()
# remove features with poor coverage or lower relevance, and keep ViolentCrimesPerPop target column
columns_to_keep = [5, 6] + list(range(11,26)) + list(range(32, 103)) + [145]
crime = crime.ix[:,columns_to_keep].dropna()
crime.head()
X_crime = crime.ix[:,range(0,88)]
y_crime = crime['ViolentCrimesPerPop']
return (X_crime, y_crime)
def plot_decision_tree(clf, feature_names, class_names):
# This function requires the pydotplus module and assumes it's been installed.
# In some cases (typically under Windows) even after running conda install, there is a problem where the
# pydotplus module is not found when running from within the notebook environment. The following code
# may help to guarantee the module is installed in the current notebook environment directory.
#
# import sys; sys.executable
# !{sys.executable} -m pip install pydotplus
export_graphviz(clf, out_file="readonly/adspy_temp.dot", feature_names=feature_names, class_names=class_names, filled = True, impurity = False)
with open("readonly/adspy_temp.dot") as f:
dot_graph = f.read()
# Alternate method using pydotplus, if installed.
# graph = pydotplus.graphviz.graph_from_dot_data(dot_graph)
# return graph.create_png()
return graphviz.Source(dot_graph)
def plot_feature_importances(clf, feature_names):
c_features = len(feature_names)
plt.barh(range(c_features), clf.feature_importances_)
plt.xlabel("Feature importance")
plt.ylabel("Feature name")
plt.yticks(numpy.arange(c_features), feature_names)
def plot_labelled_scatter(X, y, class_labels):
num_labels = len(class_labels)
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
marker_array = ['o', '^', '*']
color_array = ['#FFFF00', '#00AAFF', '#000000', '#FF00AA']
cmap_bold = ListedColormap(color_array)
bnorm = BoundaryNorm(numpy.arange(0, num_labels + 1, 1), ncolors=num_labels)
plt.figure()
plt.scatter(X[:, 0], X[:, 1], s=65, c=y, cmap=cmap_bold, norm = bnorm, alpha = 0.40, edgecolor='black', lw = 1)
plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
h = []
for c in range(0, num_labels):
h.append(mpatches.Patch(color=color_array[c], label=class_labels[c]))
plt.legend(handles=h)
plt.show()
def plot_class_regions_for_classifier_subplot(clf, X, y, X_test, y_test, title, subplot, target_names = None, plot_decision_regions = True):
numClasses = numpy.amax(y) + 1
color_list_light = ['#FFFFAA', '#EFEFEF', '#AAFFAA', '#AAAAFF']
color_list_bold = ['#EEEE00', '#000000', '#00CC00', '#0000CC']
cmap_light = ListedColormap(color_list_light[0:numClasses])
cmap_bold = ListedColormap(color_list_bold[0:numClasses])
h = 0.03
k = 0.5
x_plot_adjust = 0.1
y_plot_adjust = 0.1
plot_symbol_size = 50
x_min = X[:, 0].min()
x_max = X[:, 0].max()
y_min = X[:, 1].min()
y_max = X[:, 1].max()
x2, y2 = numpy.meshgrid(numpy.arange(x_min - k, x_max + k, h), numpy.arange(y_min - k, y_max + k, h))
# numpy.c_ Translates slice objects to concatenation along the second axis
# e.g. np.c_[np.array([[1,2,3]]), 0, 0, np.array([[4,5,6]])]
# ravel() Returns a contiguous flattened array.
# x = np.array([[1, 2, 3], [4, 5, 6]])
# np.ravel(x) = [1 2 3 4 5 6]
P = clf.predict(numpy.c_[x2.ravel(), y2.ravel()])
P = P.reshape(x2.shape)
if plot_decision_regions:
subplot.contourf(x2, y2, P, cmap=cmap_light, alpha = 0.8)
subplot.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold, s=plot_symbol_size, edgecolor = 'black')
subplot.set_xlim(x_min - x_plot_adjust, x_max + x_plot_adjust)
subplot.set_ylim(y_min - y_plot_adjust, y_max + y_plot_adjust)
if (X_test is not None):
subplot.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cmap_bold, s=plot_symbol_size, marker='^', edgecolor = 'black')
train_score = clf.score(X, y)
test_score = clf.score(X_test, y_test)
title = title + "\nTrain score = {:.2f}, Test score = {:.2f}".format(train_score, test_score)
subplot.set_title(title)
if (target_names is not None):
legend_handles = []
for i in range(0, len(target_names)):
patch = mpatches.Patch(color=color_list_bold[i], label=target_names[i])
legend_handles.append(patch)
subplot.legend(loc=0, handles=legend_handles)
def plot_class_regions_for_classifier(clf, X, y, X_test=None, y_test=None, title=None, target_names = None, plot_decision_regions = True):
numClasses = numpy.amax(y) + 1
color_list_light = ['#FFFFAA', '#EFEFEF', '#AAFFAA', '#AAAAFF']
color_list_bold = ['#EEEE00', '#000000', '#00CC00', '#0000CC']
cmap_light = ListedColormap(color_list_light[0:numClasses])
cmap_bold = ListedColormap(color_list_bold[0:numClasses])
h = 0.03
k = 0.5
x_plot_adjust = 0.1
y_plot_adjust = 0.1
plot_symbol_size = 50
x_min = X[:, 0].min()
x_max = X[:, 0].max()
y_min = X[:, 1].min()
y_max = X[:, 1].max()
x2, y2 = numpy.meshgrid(numpy.arange(x_min-k, x_max+k, h), numpy.arange(y_min-k, y_max+k, h))
# numpy.c_ Translates slice objects to concatenation along the second axis
# e.g. np.c_[np.array([[1,2,3]]), 0, 0, np.array([[4,5,6]])]
# ravel() Returns a contiguous flattened array.
# x = np.array([[1, 2, 3], [4, 5, 6]])
# np.ravel(x) = [1 2 3 4 5 6]
P = clf.predict(numpy.c_[x2.ravel(), y2.ravel()])
P = P.reshape(x2.shape)
plt.figure()
if plot_decision_regions:
plt.contourf(x2, y2, P, cmap=cmap_light, alpha = 0.8)
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold, s=plot_symbol_size, edgecolor = 'black')
plt.xlim(x_min - x_plot_adjust, x_max + x_plot_adjust)
plt.ylim(y_min - y_plot_adjust, y_max + y_plot_adjust)
if (X_test is not None):
plt.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cmap_bold, s=plot_symbol_size, marker='^', edgecolor = 'black')
train_score = clf.score(X, y)
test_score = clf.score(X_test, y_test)
title = title + "\nTrain score = {:.2f}, Test score = {:.2f}".format(train_score, test_score)
if (target_names is not None):
legend_handles = []
for i in range(0, len(target_names)):
patch = mpatches.Patch(color=color_list_bold[i], label=target_names[i])
legend_handles.append(patch)
plt.legend(loc=0, handles=legend_handles)
if (title is not None):
plt.title(title)
plt.show()
def plot_fruit_knn(X, y, n_neighbors, weights):
if isinstance(X, (pd.DataFrame,)):
X_mat = X[['height', 'width']].as_matrix()
y_mat = y.as_matrix()
elif isinstance(X, (np.ndarray,)):
# When X was scaled is already a matrix
X_mat = X_mat[:, :2]
y_mat = y.as_matrix()
print(X_mat)
# Create color maps
cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF','#AFAFAF'])
cmap_bold = ListedColormap(['#FF0000', '#00FF00', '#0000FF','#AFAFAF'])
clf = neighbors.KNeighborsClassifier(n_neighbors, weights=weights)
clf.fit(X_mat, y_mat)
# Plot the decision boundary by assigning a color in the color map
# to each mesh point.
mesh_step_size = .01 # step size in the mesh
plot_symbol_size = 50
x_min, x_max = X_mat[:, 0].min() - 1, X_mat[:, 0].max() + 1
y_min, y_max = X_mat[:, 1].min() - 1, X_mat[:, 1].max() + 1
xx, yy = numpy.meshgrid(numpy.arange(x_min, x_max, mesh_step_size),
numpy.arange(y_min, y_max, mesh_step_size))
# numpy.c_ Translates slice objects to concatenation along the second axis
# e.g. np.c_[np.array([[1,2,3]]), 0, 0, np.array([[4,5,6]])]
# ravel() Returns a contiguous flattened array.
# x = np.array([[1, 2, 3], [4, 5, 6]])
# np.ravel(x) = [1 2 3 4 5 6]
Z = clf.predict(numpy.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure()
plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
# Plot training points
plt.scatter(X_mat[:, 0], X_mat[:, 1], s=plot_symbol_size, c=y, cmap=cmap_bold, edgecolor = 'black')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
patch0 = mpatches.Patch(color='#FF0000', label='apple')
patch1 = mpatches.Patch(color='#00FF00', label='mandarin')
patch2 = mpatches.Patch(color='#0000FF', label='orange')
patch3 = mpatches.Patch(color='#AFAFAF', label='lemon')
plt.legend(handles=[patch0, patch1, patch2, patch3])
plt.xlabel('height (cm)')
plt.ylabel('width (cm)')
plt.show()
def plot_two_class_knn(X, y, n_neighbors, weights, X_test, y_test):
X_mat = X
y_mat = y
# Create color maps
cmap_light = ListedColormap(['#FFFFAA', '#AAFFAA', '#AAAAFF','#EFEFEF'])
cmap_bold = ListedColormap(['#FFFF00', '#00FF00', '#0000FF','#000000'])
clf = neighbors.KNeighborsClassifier(n_neighbors, weights=weights)
clf.fit(X_mat, y_mat)
# Plot the decision boundary by assigning a color in the color map
# to each mesh point.
mesh_step_size = .01 # step size in the mesh
plot_symbol_size = 50
x_min, x_max = X_mat[:, 0].min() - 1, X_mat[:, 0].max() + 1
y_min, y_max = X_mat[:, 1].min() - 1, X_mat[:, 1].max() + 1
xx, yy = numpy.meshgrid(numpy.arange(x_min, x_max, mesh_step_size),
numpy.arange(y_min, y_max, mesh_step_size))
# numpy.c_ Translates slice objects to concatenation along the second axis
# e.g. np.c_[np.array([[1,2,3]]), 0, 0, np.array([[4,5,6]])]
# ravel() Returns a contiguous flattened array.
# x = np.array([[1, 2, 3], [4, 5, 6]])
# np.ravel(x) = [1 2 3 4 5 6]
Z = clf.predict(numpy.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure()
plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
# Plot training points
plt.scatter(X_mat[:, 0], X_mat[:, 1], s=plot_symbol_size, c=y, cmap=cmap_bold, edgecolor = 'black')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
title = "Neighbors = {}".format(n_neighbors)
if (X_test is not None):
train_score = clf.score(X_mat, y_mat)
test_score = clf.score(X_test, y_test)
title = title + "\nTrain score = {:.2f}, Test score = {:.2f}".format(train_score, test_score)
patch0 = mpatches.Patch(color='#FFFF00', label='class 0')
patch1 = mpatches.Patch(color='#000000', label='class 1')
plt.legend(handles=[patch0, patch1])
plt.xlabel('Feature 0')
plt.ylabel('Feature 1')
plt.title(title)
plt.show()