-
Notifications
You must be signed in to change notification settings - Fork 53
Expand file tree
/
Copy pathplot_ML_flow_chart.py
More file actions
134 lines (100 loc) · 4.78 KB
/
Copy pathplot_ML_flow_chart.py
File metadata and controls
134 lines (100 loc) · 4.78 KB
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
"""
Tutorial Diagrams
-----------------
This script plots the flow-charts used in the scikit-learn tutorials.
"""
import numpy as np
import pylab as pl
from matplotlib.patches import Circle, Rectangle, Polygon, Arrow, FancyArrow
def create_base(box_bg = '#CCCCCC',
arrow1 = '#88CCFF',
arrow2 = '#88FF88',
supervised=True):
fig = pl.figure(figsize=(9, 6), facecolor='w')
ax = pl.axes((0, 0, 1, 1),
xticks=[], yticks=[], frameon=False)
ax.set_xlim(0, 9)
ax.set_ylim(0, 6)
patches = [Rectangle((0.3, 3.6), 1.5, 1.8, zorder=1, fc=box_bg),
Rectangle((0.5, 3.8), 1.5, 1.8, zorder=2, fc=box_bg),
Rectangle((0.7, 4.0), 1.5, 1.8, zorder=3, fc=box_bg),
Rectangle((2.9, 3.6), 0.2, 1.8, fc=box_bg),
Rectangle((3.1, 3.8), 0.2, 1.8, fc=box_bg),
Rectangle((3.3, 4.0), 0.2, 1.8, fc=box_bg),
Rectangle((0.3, 0.2), 1.5, 1.8, fc=box_bg),
Rectangle((2.9, 0.2), 0.2, 1.8, fc=box_bg),
Circle((5.5, 3.5), 1.0, fc=box_bg),
Polygon([[5.5, 1.7],
[6.1, 1.1],
[5.5, 0.5],
[4.9, 1.1]], fc=box_bg),
FancyArrow(2.3, 4.6, 0.35, 0, fc=arrow1,
width=0.25, head_width=0.5, head_length=0.2),
FancyArrow(3.75, 4.2, 0.5, -0.2, fc=arrow1,
width=0.25, head_width=0.5, head_length=0.2),
FancyArrow(5.5, 2.4, 0, -0.4, fc=arrow1,
width=0.25, head_width=0.5, head_length=0.2),
FancyArrow(2.0, 1.1, 0.5, 0, fc=arrow2,
width=0.25, head_width=0.5, head_length=0.2),
FancyArrow(3.3, 1.1, 1.3, 0, fc=arrow2,
width=0.25, head_width=0.5, head_length=0.2),
FancyArrow(6.2, 1.1, 0.8, 0, fc=arrow2,
width=0.25, head_width=0.5, head_length=0.2)]
if supervised:
patches += [Rectangle((0.3, 2.4), 1.5, 0.5, zorder=1, fc=box_bg),
Rectangle((0.5, 2.6), 1.5, 0.5, zorder=2, fc=box_bg),
Rectangle((0.7, 2.8), 1.5, 0.5, zorder=3, fc=box_bg),
FancyArrow(2.3, 2.9, 2.0, 0, fc=arrow1,
width=0.25, head_width=0.5, head_length=0.2),
Rectangle((7.3, 0.85), 1.5, 0.5, fc=box_bg)]
else:
patches += [Rectangle((7.3, 0.2), 1.5, 1.8, fc=box_bg)]
for p in patches:
ax.add_patch(p)
pl.text(1.45, 4.9, "Training\nText,\nDocuments,\nImages,\netc.",
ha='center', va='center', fontsize=14)
pl.text(3.6, 4.9, "Feature\nVectors",
ha='left', va='center', fontsize=14)
pl.text(5.5, 3.5, "Machine\nLearning\nAlgorithm",
ha='center', va='center', fontsize=14)
pl.text(1.05, 1.1, "New Text,\nDocument,\nImage,\netc.",
ha='center', va='center', fontsize=14)
pl.text(3.3, 1.7, "Feature\nVector",
ha='left', va='center', fontsize=14)
pl.text(5.5, 1.1, "Predictive\nModel",
ha='center', va='center', fontsize=12)
if supervised:
pl.text(1.45, 3.05, "Labels",
ha='center', va='center', fontsize=14)
pl.text(8.05, 1.1, "Expected\nLabel",
ha='center', va='center', fontsize=14)
pl.text(8.8, 5.8, "Supervised Learning Model",
ha='right', va='top', fontsize=18)
else:
pl.text(8.05, 1.1,
"Likelihood\nor Cluster ID\nor Better\nRepresentation",
ha='center', va='center', fontsize=12)
pl.text(8.8, 5.8, "Unsupervised Learning Model",
ha='right', va='top', fontsize=18)
def plot_supervised(annotate=False):
create_base(supervised=True)
if annotate:
fontdict = dict(color='r', weight='bold', size=14)
pl.text(1.9, 4.55, 'X = vec.fit_transform(input)',
fontdict=fontdict,
rotation=20, ha='left', va='bottom')
pl.text(3.7, 3.2, 'clf.fit(X, y)',
fontdict=fontdict,
rotation=20, ha='left', va='bottom')
pl.text(1.7, 1.5, 'X_new = vec.transform(input)',
fontdict=fontdict,
rotation=20, ha='left', va='bottom')
pl.text(6.1, 1.5, 'y_new = clf.predict(X_new)',
fontdict=fontdict,
rotation=20, ha='left', va='bottom')
def plot_unsupervised():
create_base(supervised=False)
plot_supervised(False)
plot_supervised(True)
plot_unsupervised()
pl.show()