why is my Whatsapp Chat Analyser ML Model showing an error? - machine-learning

Image 1
Image 2
I'm building a WhatsApp chat analyzer ML Model in jupyter notebook and I got some errors.
In the second image in the 3rd line, those rows are not placed in proper columns. two rows are combined in one row. Please help me out with this problem.
I tried changing the format but it didn't match and didn't work

Related

Google Sheets: adding different weights to some elements for a graph

I am new to Google Sheets/Excel and I need help solving a problem:
I have a single column with a different element in each cell and need to create a graph to show how many of each are showing.
The problem is that I need to make some elements weigh 2 while others 0.5 before making the graph.
Thank you for answering!
I tried looking for some coding to add weight (I just started today using Google sheets), I tried using AVERAGE.WEIGHTED() but with no result. I did not manage to find anything else.

Connect Google Sheet into Photoshop

I am hardly finding a way to connect or live-import data from Google Sheet in Photoshop.
There are several way to edit or replace some text layers, or even upload the PSD file into online real time editors, or using Adobe API, but is not exactly what I am looking for or at least I am struggling with.
This is the scenario:
here my Photoshop Artboard
and here my Google Sheet
what I want to do is to connect each layer from artboards' Photoshop with a defined cell/position in Google Sheet in order to get a live update when sorting or updating those cells. The cells and columns could be more than 10.000 in what I want to do.
And perhaps.. the struggling things is that I want to keep this flow in the Adobe/Photoshop application.
Do you have anything that I need to check or have knowledge to clearify this situation?
Many thanks!
Yes, in principle...
Yes, it's possible to load in a .CSV into photoshop and modify layer data, such as text.
Doing it live? This post has more info.
"connect each layer from artboards' Photoshop with a defined
cell/position"
Have you created a Photoshop document with 10,000 layers? You haven't really explained what you will be doing with the Google Sheet, so I can't help you further.
Try a prototype with smaller data sizes first - see if you can get that to work.

Error - WebApp Implementation with Principal Component Analysis(PCA) - Azure ML Studio

After applying Principal Component Analysis PCA to my data set in order to achieve better model accuracy. The 13 features dimensions, I am reducing it to 10 features using PCA. Everything is fine till here.
After implementing the model in WebApp, it is building & seems fine in the studio.
In the testing phase of model prediction, Instead of displaying 10 features as an input, the UI system is showing the original features which is 13 & the output is showing 10 featuenter image description hereres which does not have any feature names for the newly generated features which are 10. And also prediction is not working at all after executing it.\
Attached are the screenshots, Please refer.
Could you please also show your diagram of the experiment? This kind of issue happens when you are not setting the input of the model correctly according to your requirement. Please double check how you define your experiment.
One thing I want to highlight is, in the portal/ quick test page, all the input data will be the same as your original import data according to the document.
https://learn.microsoft.com/en-us/azure/machine-learning/classic/tutorial-part3-credit-risk-deploy#deploy-as-a-new-web-service

In this website, how do I input Jupyter notebook cells, code, and outputs in the formatting box?

I want to post blocks of code coming from the jupyter notebook and want to keep their format, color, ins, outs, and answers just like it shows in the image link below.
(I had to post a link since StackOverflow won't allow me to post a picture
just yet.)
I tried to do it manually just as regular code, but it is time-consuming typing and formatting all the cells, also it won't show the different colors in my lines of code in the preview.
Furthermore, I tried the formatting links given on this site, but didn't see anything related to building jupyter notebook sample code
Similar to the answer given to this question:
sample answer to a question

Wit.ai recognizes numbers as location

We are facing the issue that wit.ai recognizes almost every number as a location. Sometimes even as a DateTime, but almost never as a number. We tried to teach it that 1 is a number, 2 is a number, etc., but it doesn't seem to pick that up, see the screenshot below:
Are we doing something wrong?
I tried a new bot app and just added one sentence with wit/number entity in the sample database and It works okay for me as you can see:
Maybe your problem is with other samples which make the tagging problem confusing for the algorithm behind wit.ai (probably a CRF or RNN based model). I suggest you to add many more samples with wit/number entity in them and check if it works.

Resources