File dependencies

[rpantera]

Jupyter Notebook
Untitled3
Last Checkpoint: 04/16/2018
(autosaved)
Current Kernel Logo
Logout
Python 3 Trusted
File
Edit
View
Insert
Cell
Kernel
Widgets
Help
Run
In [1]:

1
%matplotlib tk
2
import matplotlib.pyplot as plt
3
from sklearn import datasets
4
from neupy import algorithms, utils
5
​
6
from helpers import plot_2d_grid
7
​
8
​
9
plt.style.use('ggplot')
10
utils.reproducible()
11
​
12
​
13
if name == 'main':
14
GRID_WIDTH = 20
15
GRID_HEIGHT = 1
16
​
17
data, targets = datasets.make_moons(n_samples=400, noise=0.1)
18
data = data[targets == 1]
19
​
20
sofm = algorithms.SOFM(
21
n_inputs=2,
22
features_grid=(GRID_HEIGHT, GRID_WIDTH),
23
​
24
verbose=True,
25
shuffle_data=True,
26
​
27
# The winning neuron will be selected based on the
28
# Euclidean distance. For this task it's important
29
# that distance is Euclidean. Other distances will
30
# not give us the same results.
31
distance='euclid',
32
​
33
learning_radius=2,
34
# Reduce learning radius by 1 after every 20 epochs.
35
# Learning radius will be equal to 2 during first
36
# 20 epochs and on the 21st epoch it will be equal to 1.
37
reduce_radius_after=20,
38
​
39
# 2 Means that neighbour neurons will have high learning
40
# rates during the first iterations
41
std=2,
42
# Defines a rate at which parameter std will be reduced.
43
# Reduction is monotonic and reduces after each epoch.
44
# In 50 epochs std = 2 / 2 = 1 and after 100 epochs
45
# std = 2 / 3 and so on.
46
reduce_std_after=50,
47
​
48
# Step (or learning rate)
49
step=0.3,
50
# Defines a rate at which parameter step will reduced.
51
# Reduction is monotonic and reduces after each epoch.
52
# In 50 epochs step = 0.3 / 2 = 0.15 and after 100 epochs
53
# std = 0.3 / 3 = 0.1 and so on.
54
reduce_step_after=50,
55
)
56
sofm.train(data, epochs=20)
57
​
58
red, blue = ('#E24A33', '#348ABD')
59
​
60
plt.scatter(*data.T, color=blue)
61
plt.scatter(*sofm.weight, color=red)
62
​
63
weights = sofm.weight.reshape((2, GRID_HEIGHT, GRID_WIDTH))
64
plot_2d_grid(weights, color=red)
65
​
66
plt.show()
67
​

ModuleNotFoundError Traceback (most recent call last)
in
4 from neupy import algorithms, utils
5
----> 6 from helpers import plot_2d_grid
7
8

ModuleNotFoundError: No module named 'helpers'

I did not move any files from where the examples were installed. I did not find a "helpers" file related to neupy on my disk. I read all the fixes for that type of problem. After 4 hours I could not make this file work.

[rpantera]

This will not work in a Jupiter notebook. Just got it to work in MAC OSX terminal

[rpantera]

Is there any way to make this Neupy work with Jupiter notebooks or spyder in Anaconda?

[rpantera]

Jupyter. Autocorrect keeps on fixing it.

[itdxer]

You can find this function here: https://github.com/itdxer/neupy/blob/master/examples/competitive/utils.py

[itdxer]

It should have been utils instead of helpers. I've fixes 3 examples that still used old helpers module

[rpantera]

Thank you By the way, are you available for consultation. If so would there be a charge for your services? R. Pantera

…

On May 20, 2019, at 12:17 AM, Yurii Shevchuk ***@***.***> wrote: You can find this function here: https://github.com/itdxer/neupy/blob/master/examples/competitive/utils.py <https://github.com/itdxer/neupy/blob/master/examples/competitive/utils.py> — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#244?email_source=notifications&email_token=AAYECHZSBDQNXJSQ2O43Z53PWJF63A5CNFSM4HN6OM42YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODVX42MA#issuecomment-493866288>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AAYECH26YORP2FZHLKHFDKLPWJF63ANCNFSM4HN6OM4Q>.

[itdxer]

No, I'm not. Sorry, I don't have a lot of free time