From stephen_malcolm at hotmail.com  Sun Oct  4 17:14:23 2020
From: stephen_malcolm at hotmail.com (Stephen Malcolm)
Date: Sun, 4 Oct 2020 21:14:23 +0000
Subject: [scikit-learn] Rerunning Kmeans with Python
Message-ID: <VE1PR09MB30539C6C8EBD85485C2CEA018C0F0@VE1PR09MB3053.eurprd09.prod.outlook.com>

Hello all,

I've written some code to run Kmeans on a data set (please see below).
And I've plotted the results, with my two clusters/ centroids.

However, I've to re-run Kmeans several times and pull up different plots (showing the different centroid positions).
Can someone point me in the right direction how to write this extra code to perform this task?

Then I've to conclude if Kmeans is stable. I believe this is the lowest sum of squared errors?
Thanking you in advance.

#pandas used to read dataset and return the data
#numpy and matplotlib to represent and visualize the data
#sklearn to implement kmeans algorithm

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler

#import the data
data = pd.read_csv('file.csv')

#extract values
x=data['V1']
y=data['V2']

V1_V2 = np.column_stack ((V1, V2))

km_res = KMeans (n_clusters= 2).fit(V1_V2)
y_kmeans = km_res.predict(V1_V2)

plt.scatter(V1, V2, c=y_kmeans, cmap='viridis',  s = 50, alpha = 0.5)
plt.xlabel('V1')
plt.ylabel('V2')
plt.title('Visualization of raw data');

clusters = km_res.cluster_centers_
plt.scatter(clusters[:,0], clusters[:,1], c='blue', s=150)


Get Outlook for iOS<https://aka.ms/o0ukef>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/scikit-learn/attachments/20201004/07b0adab/attachment.html>

From stephen_malcolm at hotmail.com  Mon Oct  5 02:56:30 2020
From: stephen_malcolm at hotmail.com (Stephen Malcolm)
Date: Mon, 5 Oct 2020 06:56:30 +0000
Subject: [scikit-learn] Rerunning Kmeans with Python
In-Reply-To: <VE1PR09MB30539C6C8EBD85485C2CEA018C0F0@VE1PR09MB3053.eurprd09.prod.outlook.com>
References: <VE1PR09MB30539C6C8EBD85485C2CEA018C0F0@VE1PR09MB3053.eurprd09.prod.outlook.com>
Message-ID: <VE1PR09MB30539F061B04D42AD854D6E38C0C0@VE1PR09MB3053.eurprd09.prod.outlook.com>

Hello again,

I've added some extra code to plot 6 smaller graphs, which should change the initialization of the centroids.
The title of the plots should be the sum of the squared distance of each initialization (which should tell me when they converge).

The smaller graphs appear (unlabelled) however, my data is not being plotted.

Can someone tell me where I'm going wrong?

n_iter = 9
fig, ax = plt.subplots(3, 3, figsize=(16, 16))
ax = np.ravel(ax)
centers = []

for i in range(n_iter):
    # Run local implementation of kmeans

                max_iter=3,
                random_state=np.random.randint(0, 1000, size=1)

    clusters = km.clusters

    ax[i].scatter([km.labels == 0, 0], [km.labels == 0, 1],
                  c='green', label='cluster 1')
    ax[i].scatter([km.labels == 1, 0], [km.labels == 1, 1],
                  c='blue', label='cluster 2')
    ax[i].scatter(clusters[:, 0], clusters[:, 1],
                  c='r', marker='*', s=300, label='centroid')
    ax[i].set_xlim([-2, 2])
    ax[i].set_ylim([-2, 2])
    ax[i].legend(loc='lower right')
    ax[i].set_title(f'{km.error:.4f}')
    ax[i].set_aspect('equal')
plt.tight_layout();


Thanks...



________________________________
From: Stephen Malcolm <stephen_malcolm at hotmail.com>
Sent: 04 October 2020 21:14
To: scikit-learn at python.org <scikit-learn at python.org>
Subject: Rerunning Kmeans with Python

Hello all,

I've written some code to run Kmeans on a data set (please see below).
And I've plotted the results, with my two clusters/ centroids.

However, I've to re-run Kmeans several times and pull up different plots (showing the different centroid positions).
Can someone point me in the right direction how to write this extra code to perform this task?

Then I've to conclude if Kmeans is stable. I believe this is the lowest sum of squared errors?
Thanking you in advance.

#pandas used to read dataset and return the data
#numpy and matplotlib to represent and visualize the data
#sklearn to implement kmeans algorithm

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler

#import the data
data = pd.read_csv('file.csv')

#extract values
x=data['V1']
y=data['V2']

V1_V2 = np.column_stack ((V1, V2))

km_res = KMeans (n_clusters= 2).fit(V1_V2)
y_kmeans = km_res.predict(V1_V2)

plt.scatter(V1, V2, c=y_kmeans, cmap='viridis',  s = 50, alpha = 0.5)
plt.xlabel('V1')
plt.ylabel('V2')
plt.title('Visualization of raw data');

clusters = km_res.cluster_centers_
plt.scatter(clusters[:,0], clusters[:,1], c='blue', s=150)


Get Outlook for iOS<https://aka.ms/o0ukef>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/scikit-learn/attachments/20201005/49cee693/attachment-0001.html>

From olivier.grisel at ensta.org  Tue Oct 13 05:59:52 2020
From: olivier.grisel at ensta.org (Olivier Grisel)
Date: Tue, 13 Oct 2020 11:59:52 +0200
Subject: [scikit-learn] About the Boston housing prices dataset
Message-ID: <CAFvE7K7wRCebmGE=JKfiGOrWBb7QEM6o==87HuRtaC6W3_VFUw@mail.gmail.com>

Hi all,

Thanks to the sustained effort of several contributors (thanks Maria
and Lucy in particular), the Boston housing price dataset is no longer
used in the examples of scikit-learn (nor in the test suite) in the
master branch.

To give some context on why this dataset is problematic, please have a
look at this discussion and  the blog post linked in it:

https://github.com/scikit-learn/scikit-learn/issues/16155

Now that we no longer use sklearn.datasets.load_boston internally, we
have to make a decision about what to do with the loader function
itself: deprecate it? just silently hide it from our documentation
from our documentation (probably a bad idea)? keep it but educate our
users about its ethical problem?

Personally, I would be slightly in favor of the latter option and I
drafted a short paragraph here:

https://github.com/scikit-learn/scikit-learn/pull/18594#issuecomment-707601448

Please feel free to share your thoughts so that we can hopefully make
a consensual decision before the 0.24 release.

Regards,

-- 
Olivier

From jni at fastmail.com  Tue Oct 13 06:37:46 2020
From: jni at fastmail.com (Juan Nunez-Iglesias)
Date: Tue, 13 Oct 2020 21:37:46 +1100
Subject: [scikit-learn] About the Boston housing prices dataset
In-Reply-To: <CAFvE7K7wRCebmGE=JKfiGOrWBb7QEM6o==87HuRtaC6W3_VFUw@mail.gmail.com>
References: <CAFvE7K7wRCebmGE=JKfiGOrWBb7QEM6o==87HuRtaC6W3_VFUw@mail.gmail.com>
Message-ID: <A93D6DBA-5113-4DAA-AEA1-0420FD52596B@fastmail.com>

I very much like your paragraph, Olivier. I might recommend additionally raising it as a warning when calling the data creation function.

For reference, in scikit-image when we removed Lena we raised a warning and returned an alternative (the now-famous `data.astronaut()`) for two versions, before removing the image altogether.

I think that was a good approach for us, but I like your preference of using the dataset as an educational opportunity in this case. I lean in that direction also, but with the caveat that I think the message should be included in a warning, not just in the docstring.

Juan.

> On 13 Oct 2020, at 8:59 pm, Olivier Grisel <olivier.grisel at ensta.org> wrote:
> 
> Hi all,
> 
> Thanks to the sustained effort of several contributors (thanks Maria
> and Lucy in particular), the Boston housing price dataset is no longer
> used in the examples of scikit-learn (nor in the test suite) in the
> master branch.
> 
> To give some context on why this dataset is problematic, please have a
> look at this discussion and  the blog post linked in it:
> 
> https://github.com/scikit-learn/scikit-learn/issues/16155
> 
> Now that we no longer use sklearn.datasets.load_boston internally, we
> have to make a decision about what to do with the loader function
> itself: deprecate it? just silently hide it from our documentation
> from our documentation (probably a bad idea)? keep it but educate our
> users about its ethical problem?
> 
> Personally, I would be slightly in favor of the latter option and I
> drafted a short paragraph here:
> 
> https://github.com/scikit-learn/scikit-learn/pull/18594#issuecomment-707601448
> 
> Please feel free to share your thoughts so that we can hopefully make
> a consensual decision before the 0.24 release.
> 
> Regards,
> 
> -- 
> Olivier
> _______________________________________________
> scikit-learn mailing list
> scikit-learn at python.org
> https://mail.python.org/mailman/listinfo/scikit-learn


From olivier.grisel at ensta.org  Tue Oct 13 07:59:31 2020
From: olivier.grisel at ensta.org (Olivier Grisel)
Date: Tue, 13 Oct 2020 13:59:31 +0200
Subject: [scikit-learn] About the Boston housing prices dataset
In-Reply-To: <A93D6DBA-5113-4DAA-AEA1-0420FD52596B@fastmail.com>
References: <CAFvE7K7wRCebmGE=JKfiGOrWBb7QEM6o==87HuRtaC6W3_VFUw@mail.gmail.com>
 <A93D6DBA-5113-4DAA-AEA1-0420FD52596B@fastmail.com>
Message-ID: <CAFvE7K7UbU8Ux7pU2Yo1FVwyHVXiNh1ZUFutK7ANeXYnu-66Bg@mail.gmail.com>

Thanks for your input, this is also an extension I was thinking of.

From adrin.jalali at gmail.com  Tue Oct 13 10:17:16 2020
From: adrin.jalali at gmail.com (Adrin)
Date: Tue, 13 Oct 2020 16:17:16 +0200
Subject: [scikit-learn] About the Boston housing prices dataset
In-Reply-To: <CAFvE7K7UbU8Ux7pU2Yo1FVwyHVXiNh1ZUFutK7ANeXYnu-66Bg@mail.gmail.com>
References: <CAFvE7K7wRCebmGE=JKfiGOrWBb7QEM6o==87HuRtaC6W3_VFUw@mail.gmail.com>
 <A93D6DBA-5113-4DAA-AEA1-0420FD52596B@fastmail.com>
 <CAFvE7K7UbU8Ux7pU2Yo1FVwyHVXiNh1ZUFutK7ANeXYnu-66Bg@mail.gmail.com>
Message-ID: <CAEOrW4_gQ+T0J0khKinHMVCau4q90tJ2c_gP_b9HUUTSH4dJ4w@mail.gmail.com>

Isn't the Boston dataset available through openml? Maybe here:
https://www.openml.org/d/531

I'm happy to have the dataset out there on opemml, and for any material
that addresses some of the issues with it.
But for educational purposes, we don't need to have the dataset in the
package as long as users can still download it
with a oneliner using fetch_openml.

Cheers,
Adrin

On Tue, Oct 13, 2020 at 2:00 PM Olivier Grisel <olivier.grisel at ensta.org>
wrote:

> Thanks for your input, this is also an extension I was thinking of.
> _______________________________________________
> scikit-learn mailing list
> scikit-learn at python.org
> https://mail.python.org/mailman/listinfo/scikit-learn
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/scikit-learn/attachments/20201013/67afc378/attachment.html>

From olivier.grisel at ensta.org  Wed Oct 14 04:10:33 2020
From: olivier.grisel at ensta.org (Olivier Grisel)
Date: Wed, 14 Oct 2020 10:10:33 +0200
Subject: [scikit-learn] About the Boston housing prices dataset
In-Reply-To: <CAEOrW4_gQ+T0J0khKinHMVCau4q90tJ2c_gP_b9HUUTSH4dJ4w@mail.gmail.com>
References: <CAFvE7K7wRCebmGE=JKfiGOrWBb7QEM6o==87HuRtaC6W3_VFUw@mail.gmail.com>
 <A93D6DBA-5113-4DAA-AEA1-0420FD52596B@fastmail.com>
 <CAFvE7K7UbU8Ux7pU2Yo1FVwyHVXiNh1ZUFutK7ANeXYnu-66Bg@mail.gmail.com>
 <CAEOrW4_gQ+T0J0khKinHMVCau4q90tJ2c_gP_b9HUUTSH4dJ4w@mail.gmail.com>
Message-ID: <CAFvE7K6V5=aWrwQ+Ztq=dUW8iVBkrLnrVD5nUETwY86HVH3cGA@mail.gmail.com>

Le mar. 13 oct. 2020 ? 16:19, Adrin <adrin.jalali at gmail.com> a ?crit :
>
> Isn't the Boston dataset available through openml? Maybe here: https://www.openml.org/d/531
>
> I'm happy to have the dataset out there on opemml, and for any material that addresses some of the issues with it.
> But for educational purposes, we don't need to have the dataset in the package as long as users can still download it
> with a oneliner using fetch_openml.

That would be an argument in favor of deprecation warning with a
message stating the motivation for deprecation and pointing to
fetch_openml.

However it's going to break examples written in slow to update
tutorials or book once the deprecation period is over. But one could
argue that this is also the case for any other deprecation in
scikit-learn. It's just that sklearn.datasets.load_boston is used A
LOT: https://github.com/search?q=load_boston&type=code

-- 
Olivier

From adrin.jalali at gmail.com  Wed Oct 14 04:34:22 2020
From: adrin.jalali at gmail.com (Adrin)
Date: Wed, 14 Oct 2020 10:34:22 +0200
Subject: [scikit-learn] About the Boston housing prices dataset
In-Reply-To: <CAFvE7K6V5=aWrwQ+Ztq=dUW8iVBkrLnrVD5nUETwY86HVH3cGA@mail.gmail.com>
References: <CAFvE7K7wRCebmGE=JKfiGOrWBb7QEM6o==87HuRtaC6W3_VFUw@mail.gmail.com>
 <A93D6DBA-5113-4DAA-AEA1-0420FD52596B@fastmail.com>
 <CAFvE7K7UbU8Ux7pU2Yo1FVwyHVXiNh1ZUFutK7ANeXYnu-66Bg@mail.gmail.com>
 <CAEOrW4_gQ+T0J0khKinHMVCau4q90tJ2c_gP_b9HUUTSH4dJ4w@mail.gmail.com>
 <CAFvE7K6V5=aWrwQ+Ztq=dUW8iVBkrLnrVD5nUETwY86HVH3cGA@mail.gmail.com>
Message-ID: <CAEOrW48s=HXY2==LCfc5t0vAc-Rf7UnQYV9Jbo=8wJ_U+VBQ-g@mail.gmail.com>

Most of those are not talking about the ethical issues of the dataset.
Let's talk about the alternatives we have:

Keep the loader, but raise a warning:
- this will result in most people not changing their code/material, and IMO
mostly ignore the warning. Some
people may see the warning and care about it.

Deprecate, and point them to an alternative dataset, and if they really
really want the same dataset, point them
to the openml ID:
- People will have to change something, and if we give them a nice
copy/paste-able alternative which is not boston,
they'll use that instead.
- Some people will keep using boston from openml, and not care about the
ethical implications

As an addition, we can keep the load_boston in the docs only, and point
users to alternatives even after removing
the loader.

On Wed, Oct 14, 2020 at 10:11 AM Olivier Grisel <olivier.grisel at ensta.org>
wrote:

> Le mar. 13 oct. 2020 ? 16:19, Adrin <adrin.jalali at gmail.com> a ?crit :
> >
> > Isn't the Boston dataset available through openml? Maybe here:
> https://www.openml.org/d/531
> >
> > I'm happy to have the dataset out there on opemml, and for any material
> that addresses some of the issues with it.
> > But for educational purposes, we don't need to have the dataset in the
> package as long as users can still download it
> > with a oneliner using fetch_openml.
>
> That would be an argument in favor of deprecation warning with a
> message stating the motivation for deprecation and pointing to
> fetch_openml.
>
> However it's going to break examples written in slow to update
> tutorials or book once the deprecation period is over. But one could
> argue that this is also the case for any other deprecation in
> scikit-learn. It's just that sklearn.datasets.load_boston is used A
> LOT: https://github.com/search?q=load_boston&type=code
>
> --
> Olivier
> _______________________________________________
> scikit-learn mailing list
> scikit-learn at python.org
> https://mail.python.org/mailman/listinfo/scikit-learn
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/scikit-learn/attachments/20201014/372ad858/attachment.html>

From lorentzen.ch at gmail.com  Wed Oct 14 06:01:58 2020
From: lorentzen.ch at gmail.com (Christian Lorentzen)
Date: Wed, 14 Oct 2020 12:01:58 +0200
Subject: [scikit-learn] About the Boston housing prices dataset
In-Reply-To: <CAEOrW48s=HXY2==LCfc5t0vAc-Rf7UnQYV9Jbo=8wJ_U+VBQ-g@mail.gmail.com>
References: <CAFvE7K7wRCebmGE=JKfiGOrWBb7QEM6o==87HuRtaC6W3_VFUw@mail.gmail.com>
 <A93D6DBA-5113-4DAA-AEA1-0420FD52596B@fastmail.com>
 <CAFvE7K7UbU8Ux7pU2Yo1FVwyHVXiNh1ZUFutK7ANeXYnu-66Bg@mail.gmail.com>
 <CAEOrW4_gQ+T0J0khKinHMVCau4q90tJ2c_gP_b9HUUTSH4dJ4w@mail.gmail.com>
 <CAFvE7K6V5=aWrwQ+Ztq=dUW8iVBkrLnrVD5nUETwY86HVH3cGA@mail.gmail.com>
 <CAEOrW48s=HXY2==LCfc5t0vAc-Rf7UnQYV9Jbo=8wJ_U+VBQ-g@mail.gmail.com>
Message-ID: <ce72d27d-e12a-7b88-caa9-39afecc1e2b5@gmail.com>

Hi

As was recently mentioned in PR #18594, the problem with the boston 
housing dataset does not go away, just because we remove it from 
scikit-learn. On the contrary, it is a valuable dataset to show and 
teach bias and discrimination - issue #16715 is still waiting for 
someone to write an example - in particular because we have access to 
the variable "B".

Most, if not all, of the datasets in scikit-learn are available 
elsewhere, even in python. So I don't think this is a good argument 
either for removal.

As we've now removed it from tests and examples, the question for me is: 
What do we want to achieve furthermore?
Answers I can think of go down a political road...

I'm fine with Olivier's suggestion 
https://github.com/scikit-learn/scikit-learn/pull/18594#issuecomment-707626543.


All the best,
Christian


On 14.10.20 10:34, Adrin wrote:
> Most of those are not talking about the ethical issues of the dataset. 
> Let's talk about the alternatives we have:
>
> Keep the loader, but raise a warning:
> - this will result in most people not changing their code/material, 
> and IMO mostly ignore the warning. Some
> people may see the warning and care about it.
>
> Deprecate, and point them to an alternative dataset, and if they 
> really really want the same dataset, point them
> to the openml ID:
> - People will have to change something, and if we give them a nice 
> copy/paste-able alternative which is not boston,
> they'll use that instead.
> - Some people will keep using boston from openml, and not care about 
> the ethical implications
>
> As an addition, we can keep the load_boston in the docs only, and 
> point users to alternatives even after removing
> the loader.
>
> On Wed, Oct 14, 2020 at 10:11 AM Olivier Grisel 
> <olivier.grisel at ensta.org <mailto:olivier.grisel at ensta.org>> wrote:
>
>     Le mar. 13 oct. 2020 ? 16:19, Adrin <adrin.jalali at gmail.com
>     <mailto:adrin.jalali at gmail.com>> a ?crit :
>     >
>     > Isn't the Boston dataset available through openml? Maybe here:
>     https://www.openml.org/d/531
>     >
>     > I'm happy to have the dataset out there on opemml, and for any
>     material that addresses some of the issues with it.
>     > But for educational purposes, we don't need to have the dataset
>     in the package as long as users can still download it
>     > with a oneliner using fetch_openml.
>
>     That would be an argument in favor of deprecation warning with a
>     message stating the motivation for deprecation and pointing to
>     fetch_openml.
>
>     However it's going to break examples written in slow to update
>     tutorials or book once the deprecation period is over. But one could
>     argue that this is also the case for any other deprecation in
>     scikit-learn. It's just that sklearn.datasets.load_boston is used A
>     LOT: https://github.com/search?q=load_boston&type=code
>
>     -- 
>     Olivier
>     _______________________________________________
>     scikit-learn mailing list
>     scikit-learn at python.org <mailto:scikit-learn at python.org>
>     https://mail.python.org/mailman/listinfo/scikit-learn
>
>
> _______________________________________________
> scikit-learn mailing list
> scikit-learn at python.org
> https://mail.python.org/mailman/listinfo/scikit-learn
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/scikit-learn/attachments/20201014/ef665fc5/attachment-0001.html>

From marmochiaskl at gmail.com  Tue Oct 20 12:42:14 2020
From: marmochiaskl at gmail.com (Chiara Marmo)
Date: Tue, 20 Oct 2020 18:42:14 +0200
Subject: [scikit-learn] scikit-learn monthly meeting October 26th 2020
Message-ID: <CAGfF14_2ggH9hefBJLR7KD1nzW0CHTubyLC5NxZauW+NCrzzmA@mail.gmail.com>

Dear list,

The next scikit-learn monthly meeting will take place on Monday October
26th at 11AM UTC:
https://www.timeanddate.com/worldclock/meetingdetails.html?year=2020&month=10&day=26&hour=11&min=0&sec=0&p1=179&p2=240&p3=195&p4=224

While these meetings are mainly for core-devs to discuss the current
topics, we are also happy to welcome non-core devs and other project
maintainers.

Feel free to join, using the following link:

https://meet.google.com/xhq-yoga-rtf

If you plan to attend and you would like to discuss something specific
about your contribution please add your name (or github pseudo) in the "
Contributors <https://hackmd.io/47swZeY3STqn5rjtkS0mDg#Contributors>"
section, of the public pad:

https://hackmd.io/47swZeY3STqn5rjtkS0mDg

Best

Chiara
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/scikit-learn/attachments/20201020/03c47e31/attachment.html>

From myabakhova at gmail.com  Wed Oct 21 13:48:19 2020
From: myabakhova at gmail.com (Maiia Bakhova)
Date: Wed, 21 Oct 2020 10:48:19 -0700
Subject: [scikit-learn] Numeric version of Elbow method for finding an
 optimal cluster number
Message-ID: <CAC7JaAoY0Ub8zKUa0A_w0aUJCV5vG4M4FBtTNH1N-EXP-4se0w@mail.gmail.com>

Hello,
Sorry, this is not about scikit-learn. It is my method which I once offered
here, and was told that
it is too easy to code. Since then I have been talking to other people and
learn that linguists
do not understand enough math to work it out, and even people who are good
at math would prefer
a ready script. I wrote one and would like to share.
I did a numeric implementation of the Elbow method for calculating the
optimal cluster number. I will appecuat it greatly if you show my work here
and people would give me feedback on it.
https://github.com/Mathemilda/Numeric_ElbowMethod_For_K-means
Best,
Mya
-- 
Maiia Bakhova
Mathematician in Data Science
http://myabakhova.blogspot.com
https://www.linkedin.com/in/myabakhova
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/scikit-learn/attachments/20201021/98b526fd/attachment.html>

From julio at esbet.es  Wed Oct 21 13:53:08 2020
From: julio at esbet.es (Julio Antonio Soto)
Date: Wed, 21 Oct 2020 19:53:08 +0200
Subject: [scikit-learn] Numeric version of Elbow method for finding an
 optimal cluster number
In-Reply-To: <CAC7JaAoY0Ub8zKUa0A_w0aUJCV5vG4M4FBtTNH1N-EXP-4se0w@mail.gmail.com>
References: <CAC7JaAoY0Ub8zKUa0A_w0aUJCV5vG4M4FBtTNH1N-EXP-4se0w@mail.gmail.com>
Message-ID: <7A9722F4-43EB-40C2-8CFC-E7236F6ECBE3@esbet.es>

Hi Mya,

To me, it looks very similar to the kneed library: https://github.com/arvkevi/kneed

Best regards


> El 21 oct 2020, a las 19:48, Maiia Bakhova <myabakhova at gmail.com> escribi?:
> 
> ?
> Hello,
> Sorry, this is not about scikit-learn. It is my method which I once offered here, and was told that 
> it is too easy to code. Since then I have been talking to other people and learn that linguists 
> do not understand enough math to work it out, and even people who are good at math would prefer 
> a ready script. I wrote one and would like to share.
> I did a numeric implementation of the Elbow method for calculating the optimal cluster number. I will appecuat it greatly if you show my work here and people would give me feedback on it.
> https://github.com/Mathemilda/Numeric_ElbowMethod_For_K-means
> Best, 
> Mya
> -- 
> Maiia Bakhova
> Mathematician in Data Science 
> http://myabakhova.blogspot.com
> https://www.linkedin.com/in/myabakhova
> 
> _______________________________________________
> scikit-learn mailing list
> scikit-learn at python.org
> https://mail.python.org/mailman/listinfo/scikit-learn
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/scikit-learn/attachments/20201021/fa35d8ac/attachment.html>

From myabakhova at gmail.com  Thu Oct 22 13:59:44 2020
From: myabakhova at gmail.com (Maiia Bakhova)
Date: Thu, 22 Oct 2020 10:59:44 -0700
Subject: [scikit-learn] scikit-learn Digest, Vol 55, Issue 5
In-Reply-To: <mailman.34.1603382403.27186.scikit-learn@python.org>
References: <mailman.34.1603382403.27186.scikit-learn@python.org>
Message-ID: <CAC7JaApU4Z-gZpYm-t8ffdNMv2B1R1_Kh7SFpOgRSB5Xb7=qww@mail.gmail.com>

Hello Julio,
Thanks for your feedback!
The Elbow method may produce plots with concavity changing from one point
to a next. It means that some points
must be removed from consideration, and my method takes care of this.
In addition the math is adapted for clustering procedure and much simpler.
This helps with efficiency and maintenance.
Best regards,
Mya

On Thu, Oct 22, 2020 at 9:04 AM <scikit-learn-request at python.org> wrote:

> Send scikit-learn mailing list submissions to
>         scikit-learn at python.org
>
> To subscribe or unsubscribe via the World Wide Web, visit
>         https://mail.python.org/mailman/listinfo/scikit-learn
> or, via email, send a message with subject or body 'help' to
>         scikit-learn-request at python.org
>
> You can reach the person managing the list at
>         scikit-learn-owner at python.org
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of scikit-learn digest..."
>
>
> Today's Topics:
>
>    1. Numeric version of Elbow method for finding an optimal
>       cluster number (Maiia Bakhova)
>    2. Re: Numeric version of Elbow method for finding an optimal
>       cluster number (Julio Antonio Soto)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Wed, 21 Oct 2020 10:48:19 -0700
> From: Maiia Bakhova <myabakhova at gmail.com>
> To: scikit-learn at python.org
> Subject: [scikit-learn] Numeric version of Elbow method for finding an
>         optimal cluster number
> Message-ID:
>         <
> CAC7JaAoY0Ub8zKUa0A_w0aUJCV5vG4M4FBtTNH1N-EXP-4se0w at mail.gmail.com>
> Content-Type: text/plain; charset="utf-8"
>
> Hello,
> Sorry, this is not about scikit-learn. It is my method which I once offered
> here, and was told that
> it is too easy to code. Since then I have been talking to other people and
> learn that linguists
> do not understand enough math to work it out, and even people who are good
> at math would prefer
> a ready script. I wrote one and would like to share.
> I did a numeric implementation of the Elbow method for calculating the
> optimal cluster number. I will appecuat it greatly if you show my work here
> and people would give me feedback on it.
> https://github.com/Mathemilda/Numeric_ElbowMethod_For_K-means
> Best,
> Mya
> --
> Maiia Bakhova
> Mathematician in Data Science
> http://myabakhova.blogspot.com
> https://www.linkedin.com/in/myabakhova
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <
> https://mail.python.org/pipermail/scikit-learn/attachments/20201021/98b526fd/attachment-0001.html
> >
>
> ------------------------------
>
> Message: 2
> Date: Wed, 21 Oct 2020 19:53:08 +0200
> From: Julio Antonio Soto <julio at esbet.es>
> To: Scikit-learn mailing list <scikit-learn at python.org>
> Subject: Re: [scikit-learn] Numeric version of Elbow method for
>         finding an optimal cluster number
> Message-ID: <7A9722F4-43EB-40C2-8CFC-E7236F6ECBE3 at esbet.es>
> Content-Type: text/plain; charset="utf-8"
>
> Hi Mya,
>
> To me, it looks very similar to the kneed library:
> https://github.com/arvkevi/kneed
>
> Best regards
>
>
> > El 21 oct 2020, a las 19:48, Maiia Bakhova <myabakhova at gmail.com>
> escribi?:
> >
> > ?
> > Hello,
> > Sorry, this is not about scikit-learn. It is my method which I once
> offered here, and was told that
> > it is too easy to code. Since then I have been talking to other people
> and learn that linguists
> > do not understand enough math to work it out, and even people who are
> good at math would prefer
> > a ready script. I wrote one and would like to share.
> > I did a numeric implementation of the Elbow method for calculating the
> optimal cluster number. I will appecuat it greatly if you show my work here
> and people would give me feedback on it.
> > https://github.com/Mathemilda/Numeric_ElbowMethod_For_K-means
> > Best,
> > Mya
> > --
> > Maiia Bakhova
> > Mathematician in Data Science
> > http://myabakhova.blogspot.com
> > https://www.linkedin.com/in/myabakhova
> >
> > _______________________________________________
> > scikit-learn mailing list
> > scikit-learn at python.org
> > https://mail.python.org/mailman/listinfo/scikit-learn
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <
> https://mail.python.org/pipermail/scikit-learn/attachments/20201021/fa35d8ac/attachment-0001.html
> >
>
> ------------------------------
>
> Subject: Digest Footer
>
> _______________________________________________
> scikit-learn mailing list
> scikit-learn at python.org
> https://mail.python.org/mailman/listinfo/scikit-learn
>
>
> ------------------------------
>
> End of scikit-learn Digest, Vol 55, Issue 5
> *******************************************
>


-- 
Maiia Bakhova
Mathematician in Data Science
http://myabakhova.blogspot.com
https://www.linkedin.com/in/myabakhova
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/scikit-learn/attachments/20201022/1192154d/attachment.html>

From marmochiaskl at gmail.com  Fri Oct 23 05:00:11 2020
From: marmochiaskl at gmail.com (Chiara Marmo)
Date: Fri, 23 Oct 2020 11:00:11 +0200
Subject: [scikit-learn] scikit-learn monthly meeting October 26th 2020
In-Reply-To: <CAGfF14_2ggH9hefBJLR7KD1nzW0CHTubyLC5NxZauW+NCrzzmA@mail.gmail.com>
References: <CAGfF14_2ggH9hefBJLR7KD1nzW0CHTubyLC5NxZauW+NCrzzmA@mail.gmail.com>
Message-ID: <CAGfF14-FYV29+1SDUntB6K=OocHgyNpKY=4UH0HVc5wcS_cYKA@mail.gmail.com>

Dear all,

this a reminder for the Monday core-dev meeting: please note that the
meeting will take place at 7AM for our colleagues in New York, it will be
nice not to wait the European Monday morning to fill the agenda... :)

Thanks for your collaboration.

Chiara

On Tue, Oct 20, 2020 at 6:42 PM Chiara Marmo <marmochiaskl at gmail.com> wrote:

> Dear list,
>
> The next scikit-learn monthly meeting will take place on Monday October
> 26th at 11AM UTC:
> https://www.timeanddate.com/worldclock/meetingdetails.html?year=2020&month=10&day=26&hour=11&min=0&sec=0&p1=179&p2=240&p3=195&p4=224
>
> While these meetings are mainly for core-devs to discuss the current
> topics, we are also happy to welcome non-core devs and other project
> maintainers.
>
> Feel free to join, using the following link:
>
> https://meet.google.com/xhq-yoga-rtf
>
> If you plan to attend and you would like to discuss something specific
> about your contribution please add your name (or github pseudo) in the "
> Contributors <https://hackmd.io/47swZeY3STqn5rjtkS0mDg#Contributors>"
> section, of the public pad:
>
> https://hackmd.io/47swZeY3STqn5rjtkS0mDg
>
> Best
>
> Chiara
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/scikit-learn/attachments/20201023/308862bb/attachment.html>

From helmrp at yahoo.com  Sat Oct 31 12:51:29 2020
From: helmrp at yahoo.com (The Helmbolds)
Date: Sat, 31 Oct 2020 16:51:29 +0000 (UTC)
Subject: [scikit-learn] Question RE: skLearn Logistic Regression
References: <1071563725.605939.1604163089727.ref@mail.yahoo.com>
Message-ID: <1071563725.605939.1604163089727@mail.yahoo.com>

I have a case with binary results and 1-D features, like:
? ? X = np.array(-3,-2,-1,0,1,2,3,)
and
? ? y = np.array(0, 0, 0, 1, 1, 1, 1)
only longer arrays (about 180 entries in each array) of this general type.?

So this should be the "simplest" case.
Altho I've tried several variations of the Logistic input formats, in
?? LogisticRegression.fit(X, y)
they keep being rejected with the most common error message being
?? Missing argument y
I assure you I do indeed have an array "y" that is passed to "fit"
So----What do I have to do to get Logistic Regression to accept 1-D features?

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/scikit-learn/attachments/20201031/ab13aef7/attachment.html>

From seralouk at hotmail.com  Sat Oct 31 13:21:08 2020
From: seralouk at hotmail.com (serafim loukas)
Date: Sat, 31 Oct 2020 17:21:08 +0000
Subject: [scikit-learn] Question RE: skLearn Logistic Regression
In-Reply-To: <1071563725.605939.1604163089727@mail.yahoo.com>
References: <1071563725.605939.1604163089727.ref@mail.yahoo.com>
 <1071563725.605939.1604163089727@mail.yahoo.com>
Message-ID: <0E057EC7-9B81-470D-8FB4-E723362D2728@hotmail.com>

These are not numpy arrays.

Try:

X = np.array([-3,-2,-1,0,1,2,3]).reshape(-1,1)

And

y = np.array([0, 0, 0, 1, 1, 1, 1]).reshape(-1,1)

Makis


On 31 Oct 2020, at 17:51, The Helmbolds via scikit-learn <scikit-learn at python.org<mailto:scikit-learn at python.org>> wrote:

I have a case with binary results and 1-D features, like:

    X = np.array(-3,-2,-1,0,1,2,3,)

and

    y = np.array(0, 0, 0, 1, 1, 1, 1)

only longer arrays (about 180 entries in each array) of this general type.

So this should be the "simplest" case.

Altho I've tried several variations of the Logistic input formats, in

   LogisticRegression.fit(X, y)

they keep being rejected with the most common error message being

   Missing argument y

I assure you I do indeed have an array "y" that is passed to "fit"

So----What do I have to do to get Logistic Regression to accept 1-D features?


_______________________________________________
scikit-learn mailing list
scikit-learn at python.org<mailto:scikit-learn at python.org>
https://mail.python.org/mailman/listinfo/scikit-learn

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/scikit-learn/attachments/20201031/501a5459/attachment.html>