Questions tagged [distribution]
The distribution tag has no usage guidance.
169 questions
0
votes
1
answer
25
views
Correct way to compare results of binary classifiers with different sensitivities
I am comparing 5 third party classification models on a subset of results (specifically, false positives I am examining to find a common cause). The five models all output values between 0 and 1 but ...
- 101
-1
votes
1
answer
30
views
Is variance proportional to the maximum distance between samples of a distribution?
I have two sets of data: one is set1=[2,2,2,4.5] and set2=[2,1.5,2,4.5,2.5]. If I plot their distributions, set1 is:
set2 is:
I would say that set2 is a wider distribution and so I would expect a ...
0
votes
0
answers
28
views
Finding proper expressions for DistributionLambda parameters in TensorFlow Probability
In TensorFlow Probability, when we build a model with DistributionLambda layer, we must pass the expressions for distribution parameters. Most often, these expressions transform the output of previos ...
- 13
0
votes
0
answers
17
views
Linear discriminant analysis and PDF
I'm going through LDA material. I'm not 100% sure how to interprete the PDF of two samples in the context of LDA.
Suppose this situation:
For one thing, why is the shape of the pink PDF on the right ...
0
votes
0
answers
37
views
How to approach Machine Learning with Circular distribution (Classification problem)
I have 41 continuous columns and all are distributed roundly to each pair:
I used:
SMOTE for resampling data ( my dataset is imbalanced)
Test dataset: last month in the data dataset. Train dataset: ...
0
votes
0
answers
18
views
Angular Distribution Function for Clustered Data Points
I was tasked recently with analyzing a cluster of individual points (each point representing a particulate), and I was advised that it would be good to apply an angular distribution function (ADF) on ...
0
votes
1
answer
241
views
Using Maximum Mean Discrepancy (MMD) to Compare Kernel Density Estimates (KDEs)
I'm interested in comparing two Kernel Density Estimates (KDEs) and I've come across the Maximum Mean Discrepancy (MMD) metric ...
- 103
0
votes
1
answer
94
views
Is Maximum Mean Discrepancy (MMD) suitable for comparing distributions with different sample sizes?
I'm working on a project where I need to compare the similarity of two probability distributions using MMD. However, the two datasets have different sample sizes. I've read that MMD can be affected by ...
- 103
0
votes
0
answers
15
views
Two overlap gaussian mixtures come from one or two generations of data?
Reviewing for a ML exam, my teacher asked last year a philosophical question about gaussians and generations of data which I couldn’t find no good answer.
Imagine that an oracle can say with 100% ...
0
votes
1
answer
72
views
Binary Classification Dataset Distribution
I have a question regarding the distribution of my dataset. I have a binary classification task which I need to label. I now want to know how I should distribute the labels for optimal training / ...
- 1
1
vote
2
answers
64
views
Is there a measure to compare features on the basis of normality
I have a dataset of cars and it has many features including 'acceleration’, ‘horsepower’, and ‘mpg'.
I am supposed to check which of these features is the most similar to a normal distribution, so I ...
- 11
0
votes
0
answers
34
views
What can I do when validation data and test data has different distribution in imbalance classification?
I am building classification model for bio (scRNA) data. Datasets in this field, for example, dataset A has 1, 2 classes, dataset B has 2, 3 classes kind of that. So I integrated datasets for training ...
0
votes
1
answer
545
views
What is a good metric for comparing a single value to a distribution?
I'd like to compare single values from one distribution to another distribution, effectively transforming the second distribution in such way, that its values reflect both datasets simultaneously, i.e....
- 1
0
votes
1
answer
69
views
For standard deviation's formula, why does division by sample size come before square rooting?
Why is this used to calculate a sample's standard deviation:
$s=\sqrt{\frac{1}{N-1}\sum_{i=1}^N(x_i-\bar{x})^2}$
and not something like:
$s=\frac{1}{N-1}\sqrt{\sum_{i=1}^N(x_i-\bar{x})^2}$
I ...
0
votes
0
answers
109
views
Distribution check - different results using plt.hist and seaborn.displot
I have an apparently very simple task: checking the distribution of values contained in an array data. Only thing is, I get two completely different results by ...
- 101
1
vote
0
answers
70
views
Understanding Syntactic divergence
I am trying to read a paper https://arxiv.org/abs/2004.14444 Section 6.1 of the paper describes Syntactic divergence. I have confusion regarding the distribution graphs and split of the dataset.
If a ...
- 11
5
votes
1
answer
3k
views
What is the difference between Covariate Shift, Label Shift, Concept Shift, Concept Drift, and Prior Probability Shift?
As a beginner in MLOps, I was overwhelmed by some confusing definitions.
As far as I understand, when we have a classifier or regressor with y = f(X) function:
<...
1
vote
0
answers
38
views
Strange behaviour around zero for predicted distributions from a deep learning regression model
Can somebody help make sense of these very odd distributions that I obtained from my trained deep learning regression model?
The model was trained with either MAE or MSE loss, which is what the ...
0
votes
1
answer
120
views
What is the next after finding best distribution for my data?
I found the distribution of my data with "distfit" library for python. But what now? The best distribution that describes my data is "weibull" distribution. But I don't know what ...
- 53
0
votes
0
answers
55
views
Multiclass classification (gradient boosted trees) predictions distribution using softmax()
Let's consider a multiclass problem where the target is composed by 20% class 'A', 50% of class 'B' and 30% of class 'C'.
The model is trained and then the class predictions are obtained via the ...
- 133
0
votes
1
answer
244
views
Compute the pdf from pandas kde
I have data (features/targets in machine learning terminology), e.g. X1(t), X2(t), ... XN(t) and dependent variable y(t). I can use pandas to plot the kde's of the independent variables (X1(t),...).
I ...
- 121
0
votes
1
answer
123
views
How can I obtain the mean of a Poisson distribution given the first improbable point of the distribution?
I generated a Poisson distribution with mean equal to 3 and 10000 samples by using np.random.poisson(3,10000). The plot is the following:
from this plot I see that ...
0
votes
0
answers
29
views
Task Distribution
I would like to distribute tasks (going to companies and signing a deal) to sales representatives based on some condition like company location (is it near the representative's place) or profit of the ...
- 1
1
vote
1
answer
50
views
name of log(n+1) plot
I am trying to plot a distribution of positive integers which contains a lot of variance. I opted to use the log of the y-values but that causes issues due to the inclusion of zeros. I though of ...
- 113
0
votes
2
answers
3k
views
How to plot categorical variables with a pie chart
I am concerned with a single column (fruit) from my df:
...
- 33
1
vote
0
answers
14
views
How can PCA be distributed among workers?
I want to distribute the work from PCA among a set of workers.
So let samples $x_1,... , x_d\in \mathbb{R}^n$ be samples. Then to find a dimension reduction subspace we need
covariance matrix $cov(\...
- 111
2
votes
1
answer
73
views
How to measure statistical similarity or discrepancy between a dataset and a distribution?
Is any way to measure statistical similarity or discrepancy between a dataset and a distribution? I have do some research, but find most of method are intended to describe discrepancy between data and ...
- 21
0
votes
1
answer
27
views
Is it possible to find an internal event in a Classification between two classes?
I am very new to the machine learning area. So my question might be trivial
I have two classes $U, V$ of binary vectors. In the training phase,
I use $u_1,\ldots, u_{1000}$ from $U$ class and $v_1, \...
- 1
0
votes
0
answers
97
views
Function for KDE-style distribution generation for sampling
I have some points in pytorch and I would like to sample from a distribution that resembles these points. I noticed that the seaborn kde plots seem to draw out/define a distribution graphically and I ...
- 45
1
vote
1
answer
28
views
What thought processes do people use for generating priors on a variable's probability distribution?
Example
Consider a block of text with a variety of sentence types within it, of which there are 7. Within a text these sentences will be more or less likely to appear, dependent on where in the text ...
- 133
1
vote
1
answer
106
views
Handling gaps in regression model
I'm facing a regression problem where I'm supposed to predict the delay of some trains. There's some peculiar particularity, however: a train is not considered delayed until it has more than 10 mins ...
- 65
0
votes
2
answers
3k
views
Comparing distributions Python
I have a larger dataset (random variable) 'x' containing values approximating a Gaussian distribution. From 'x', a much smaller random variable 'y' is sampled without replacement. I want to compare ...
- 121
1
vote
0
answers
20
views
Probability notation q(y) and q(Y) and its implication to vector functions
The function in question is (from Appendix B, Proof of proposition 2.1 from Posterior Regularization for Structured Latent Variable Models):
$$q(\textbf{Z}) = \frac{p_{\theta}(\textbf{Z}|\textbf{X})...
- 131
2
votes
2
answers
2k
views
Does t-test require Standard Deviation of sample for calculation
Might be a novice question, but the main difference between a t-test and z-test, I was able to understand, is that the z-test calculation requires the SD value of the population where as in a t-test, ...
- 193
-1
votes
1
answer
60
views
Normalizing Distributions for features in predicting
Should features used for predictions be normalized if they are highly skewed. Or should I only normalize target feature that is supposed to be predicted?
- 33
0
votes
0
answers
25
views
How to do ? serious skewed right transformations normally distribution
My target is doing two-way Anova. But Here is some problem.
This is my data like
I try log(X). Looks like a normal distribution. But try Kolmogorov-Smirnov prove is not.
Can anyone recommend another ...
- 1
4
votes
2
answers
846
views
Analysis of probability distribution of each features and Machine Learning
While I know that probability distributions are for hypothesis testing, confidence level constructions, etc. They definitely have many roles in statistical analysis.
However, it is not obvious to me ...
- 411
1
vote
0
answers
29
views
Is there a way to create a continuous distribution graph from discrete percentiles?
I have an underlying distribution that I know is 1-tailed (Packet Response time), but the service that runs the benchmark is opaque to me. It only returns a percentile table up to some number of nines ...
- 11
0
votes
1
answer
410
views
Distribution of text data
How can I identify whether the training data and test data came from same distribution or not?
I tried with TFIDF and cosine similarity
...
- 249
2
votes
0
answers
20
views
Measuring the distance between data points based on mutual linkages
How to measure the distance between two data points (or: nodes?) based on their mutual share of linkages?
I don't know the technical term for that, so here is a fictitious example from scientific ...
- 123
1
vote
1
answer
226
views
How to find the distribution of a single variable based on population distribution
I am trying to find the age distribution of the subset of married people of a population. However, I realise that just visualising the married count by age (Figure 1) is highly dependent on the ...
- 31
1
vote
2
answers
661
views
Distribution Shift vs Transfer Learning
Transfer learning (TL) is a research problem in machine learning (ML) that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem [1]
...
- 6,370
1
vote
0
answers
3k
views
How to generate a positive skewed array?
As the title suggests, I would like to specify the task that I really need help with:
Given three possible distributions of an array:
I know that given a skewed dataset (the left and the right), then ...
- 11
0
votes
0
answers
175
views
A feature is still right-skewed after log scaling. How should it be normalized for machine learning?
I've attached two images below of a heavily right-skewed feature - call it x. I log scaled x, but it is still right-skewed and ...
- 821
1
vote
1
answer
47
views
Check if distribution per week is the same
I have sales by customer (b2b) and by date. I want to check if the distribution per day inside weeks remains the same from week to week.
Initial dataset
Customer
Date
Sales
Alpha
2019-02-23
527
...
- 111
1
vote
0
answers
25
views
Criteria for assessing difficulty of a question
I have a list of questions and how many times they have been answered correctly and incorrectly. Based on this, I applied the formula:
...
- 11
1
vote
0
answers
31
views
Testing a Binary Classifier
I have been training a binary multilayer perceptron on a database made out of roughly 3600 0 values, and 4 1 values. Afterwards, I'm testing the MLP on a test set made out of 7 0 values and 7 1 ...
1
vote
0
answers
75
views
Estimating the (normal?) distribution of the grayscale values of a region in camera footage
The problem:
Given a small ($25\times25$) region on a $1080$p image extracted from camera footage of a railway system, I am trying to detect whether there is a train present or not. I proceed to take ...
- 111
0
votes
1
answer
101
views
Non IID variables and SVM Classifier
I am training an SVM model to predict the trend of stock prices (one-day ahead predictions. Classification task). It Had completely slipped from my mind that SVMs assume IID data until I had a ...
- 101
1
vote
2
answers
3k
views
Data Analytics how to read ECDF graph
Hi there, My question is about how to read ECDF graphs. I am still quite unsure what the jumps / zig-zags in the graph mean and what is happening when there is a horizontal line and so on. I would be ...
- 111