All Questions

Filter by
Sorted by
Tagged with
0
votes
0answers
10 views

Is automated load testing best practise for MlOps

I have an an ml ops pipeline setup to automatically update a machine learning model in production. The general pipeline steps are: Run unit tests Preprocess training data Train model Evaluate model ...
0
votes
0answers
9 views

How to add custom embeddings for bert

Pretrained Bert input has token embeddings, segment embeddings, position embeddings. But I would like to add some custom embeddings along with them and feed them to pretrained bert. How can I ...
1
vote
0answers
10 views

Create A count Features right

I have a table like that: PC USER Period A U1 2020/01 A U2 2020/02 A U3 2020/03 A U4 2020/04 B U1 2020/01 B U2 2020/02 B U2 2020/03 for every row show the max connection: PC USER Period Max ...
0
votes
0answers
18 views

Dual Optimization SVM in Python using Numpy

I need to implement the dual function of SVMs optimization problem with numpy in Python and I am pretty stuck since I am not a Python or a numpy pro at all. Dual function evaluation What I want to ...
0
votes
0answers
30 views

What if training loss is negative

I have designed a custom loss function where I have to maximize the KL divergence. So I took KL(P||Q) and negated it and now my loss function is -KL(P||Q) and this loss function leads to negative ...
0
votes
0answers
11 views

Why feature engineering and filling NaN's reduce score?

I used CatBoost for InClass Kaggle competition. I have tried various strategies to filling NaN values. Convert float binary variables to categorical. Add new categorical features (from age, for ...
0
votes
0answers
19 views

Feature importance in binary classification

I am wondering if there is a way to check the feature importance for each class in a binary classification task separately. Or any way to check the correlation between features and both target classes ...
0
votes
1answer
17 views

Not in index Error

xtrain is a numpy array ...
1
vote
1answer
30 views

Select one best model according to accuracy, precision, recall, f1 score and roc score

I have two classifiers that classify the same dataset with these results: ...
1
vote
0answers
12 views

Appropriate objective for a data science project

I've done a couple of DA projects found on the internet and I want to start one myself. I'm interested in baseball data and I think I can exploit a lot of that data but also want to delimit the topic. ...
0
votes
0answers
10 views

How can I master the Maths behind Machine Learning / Deep Learning?

Hello Stack Community ! I am a Computer Engineer , who is interested in understanding and properly interpreting the mathematics behind the ML and DL algorithms I have worked with some classification ...
0
votes
0answers
8 views

Is there an easy way to find the number of subscribers of a channel using python?

I will get a list of discord channels and I want to get the number of subscribers. For example, givens this : https://discord.com/invite/NqfVS7M How do I get the number of subscribers?
1
vote
1answer
20 views

How to split unbalanced data for supervised learning?

Suppose I have data I want to use for supervised learning, but there is a pretty bad target/class/labels imbalance. Should I: Limit the size of the training set to make sure there is a flat target/...
1
vote
1answer
12 views

What topic does a "selection" algorithm fall under?

I am looking to develop a simple algorithm that is given a set of 10 vectors for a year from which to predict the "winner". This will be a supervised task where the algorithm will be trained ...
1
vote
0answers
41 views

Predicting single floats based on set of 2 feature arrays each of 100 values

I am trying to predict audio to video desynchronization based on set of two arrays of lenght 100 which consist of coresponding audio and video samples. The problem is that my labels are single floats (...
0
votes
0answers
13 views

How can I combine the information from these two dataframes?

If one of my dataframes gives me some info about items: ...
0
votes
1answer
18 views

How to properly perform sentiment analysis?

How to properly perform sentiment analysis for text with 300-600 words? If I use TextBlob and clean my data and remove stopwords(extended words and comma backslash..etc) do I need to tokenize the ...
0
votes
1answer
14 views

What is the difference between rule based & feature based methods in sentiment analysis?

if I use TextBlob in Python to get data label 0/1 of texts (postive/negative) and then use logistic regression for training and prediction, is this feature method or rule based method?
1
vote
0answers
8 views

Is there a reason not to wirk with AMP (automatic mixed precision)?

According to: Introducing native PyTorch automatic mixed precision for faster training on NVIDIA GPUs It's better to use AMP (with 16 Floating Point) due to: Shorter training time. Lower memory ...
1
vote
0answers
15 views

Late entry in Survival Analysis

I would like to ask how to deal with new entries of individuals in Survival Analysis. I have a study about the time to event of several individuals who suffer from a disease. The study starts on a ...
0
votes
0answers
15 views

How to perform entity level train-val-test split for NER task?

A normal and stratified split option is provided by sklearn method that can be used for ML problems like multi-class classification. This is relatively easier to do as (1) one sample has one class, ...
0
votes
2answers
44 views

Call function from one class in the same class

I have 2 classes model and impute. I am defining a function mode_impute inside ...
4
votes
2answers
186 views

How to determine if my data split is appropriate for my data size?

I currently have a model that has a pretty large dataset (50ishMB) and was performing pretty well with a 80:20 split. However, when I tried changing it up to a 50:50 split, the model performed 28% ...
0
votes
0answers
13 views

Can PCA help to reduce false positives in image-based classification?

I'm working on a 2-class problem where cancer cells need to be accurately identified from a mixed population containing cancer cells + white blood cells (WBCs). The model I have been using - SVM with ...
0
votes
0answers
17 views

Reinforcement learning policy gradient derivation

I was reading a document about Reinforcement Learning policy gradient http://web.stanford.edu/class/cs234/CS234Win2019/slides/lnotes8.pdf when I encountered this expression $ \nabla_{\theta} \mathbb{...
1
vote
1answer
27 views

Is it normal for exhaustive feature selector to run for three days?

I'm trying to optimize my features in a dataset to get a better predictive model. I used Exhaustive feature selector from mlxtend. This checks all possible combinations of features. I have a dataset ...
1
vote
1answer
25 views

Help starting ML project in pythin(novice)

I am starting a machine learning project (for fun!), but I am not sure where to start from... I am fairly new to ML so any hints are appreciated. I have a relatively large data-set where each input is ...
1
vote
1answer
23 views

Exact Predictions for Regression problems in Machine Learning

I am working on shipment days delivery problem , where i want to predict shipment days (continuous variable target) I have tries both Neural Network and Random Forest regressors ,i got very low error ...
1
vote
1answer
11 views

Is there a way to train Doc2Vec on a corpus of docs and be able to take a novel doc and see how similar it is to the trained corpus?

I have a project idea, where I train a bunch of documents on Doc2Vec and then take a novel, input doc, and ideally be able to be told how similar it is to the docs supplied for training as a whole or ...
1
vote
1answer
15 views

Using precision as a metric - how to gauge if more TP's

So precision is calculated as tp/(tp+fp) But this doesn't seem to be a good way to assess a model as both of the below would give a result of 1? Binary Classification ...
4
votes
1answer
35 views

XGBoost non-linear regression

Is it possible to use XGBoost regressor to do non-linear regressions? I know of the objectives linear and logistic. The ...
0
votes
1answer
10 views

Anomaly Detection Techniques

Often the hardest part of solving an Anomaly Detection problem can be finding the right technique for the job. Different Anomaly techniques are better suited for different types of data and different ...
0
votes
0answers
15 views

Balanced target variable in KNN classification

In many places, I have seen it only mentioned that predict the label of the query point as the label with more than half of the labels of it's K nearest neighbours. However, I don't see it mentioned ...
0
votes
0answers
9 views

Best method for address book ranking

I would like to be able to ingest an address book and determine from the contacts who someone’s closest family and friends are likely to be. Any advice on an approach appreciated. I am planning to ...
0
votes
0answers
23 views

showing this error ValueError: shapes (1,400) and (10000,10) not aligned: 400 (dim 1) != 10000 (dim 0)

I am trying to run a network and get this error .I am a noob,can someone help me. ...
0
votes
0answers
11 views

Additional Sklearn Acceleration Packages

As a data scientist, I am always looking for ways to improve my workflows. I am familiar with Intel's sklearn acceleration module, Intelex. While this has sped up my algorithms between 3-70x based on ...
0
votes
0answers
7 views

Potential models/methods to predict walking times in postal center

I have a dataset containing the walking times it takes to walk from one postal bin to another postal bin in a mail distribution center. The features I have, include the total mail workers on the floor ...
0
votes
0answers
12 views

Deep Neural Network (ANN)

How do I improve the accuracy of an ANN model ? It is currently giving me an accuracy of 93%. ...
0
votes
0answers
14 views

Custom layers in Keras -- custom weights

I am trying to understand how to build custom layers in Keras and I went through a couple examples: here and here. The syntax is, of course, similar, but in non of the cases it is addressed why ...
0
votes
1answer
17 views

Is there an official procedure to compute mIoU?

Although it sounds silly, I'm not finding an official source to compute mIoU. I'm realizing a semantic segmentation task, and I want to compute the mIoU over a dataset. My doubt is, should I compute ...
2
votes
2answers
88 views

Dataset and why use evaluate()?

I am starting in Machine Learning, and I have doubts about some concepts. I've read we need to split our dataset into training, validation and test sets. I'll ask four questions related to them. 1 - ...
2
votes
1answer
26 views

Optimizing MAE degrades MAE metrics

I have run a lighgbm regression model by optimizing on RMSE and measuring the performance on RMSE: ...
1
vote
1answer
19 views

Reasons for a model predicting probability of being class 1 at x value

All, This is a general question. I have a binary classification which predicts if someone is rich or not. I had a question from someone asking that if the probability someone is rich is 0.6 and ...
1
vote
0answers
15 views

FactoMineR: detecting dimensions with noises

I have some categorical datasets and was considering to do MCA using FactoMineR. Is there a way to detect dimensions with noises in FactoMineR? Considering to do a cluster analysis afterwards so it ...
0
votes
0answers
21 views

Error:DQN expects a model that has one dimension for each action, in this case (1, 2, 1, 0)

I am building an RL agent for which the model is defined: ...
1
vote
0answers
8 views

Scaling the output of a segmentation model (UNet)

So, I have to solve an instance segmentation problem and I am thinking of implementing a UNet model based on Ronneberger et. al. 2015 paper. The problem I have is that the output size has to be ...
1
vote
0answers
6 views

Layout/Drawing in Workflows or a node for a Sub-Workflow

I am creating Orange Workflows for a few days, therefore I am pretty new. I want to spread my workflows with colleagues such that they can also use them and further develop them. I am facing now the ...
1
vote
0answers
5 views

quereies related to autoencoder

i want to design an deep auto encoder after following keras tutorial. Input is a simple 2-dimensional image consists of 512 rows and 50 columns matrix My trial code is ...

15 30 50 per page