1,055 questions
Advice
0
votes
0
replies
32
views
Why use loss threshold for anomaly detection using AutoEncoders?
Recently I have been practicing with AutoEncoders and trying to use them for anomaly detection. I have been told that using a threshold on the loss to classify anomalies (calibrated with roc-curve) is ...
- 1
0
votes
1
answer
126
views
Extracting the values from ROC curve
I could create a ROC curve for my Statistical analysis
library(pROC)
plot(roc(aSAH$outcome, aSAH$s100b,
levels=c("Good", "Poor")))
However I would like plot the same using ...
- 3,928
0
votes
1
answer
78
views
Keras AUC metric breaking on a multi-class problem
I'm attempting to train a multi-class image classification model based on standardised 128x128 images. When I use "accuracy" alone as a metric, I have no issues. When I introduce AUC, I can'...
- 1,019
1
vote
1
answer
105
views
Print AUC in my multiple ROC Curves from ggroc [closed]
this is my 3 ROC Curves !
rocs <- list()
rocs[["modele1"]] <- roc(data3$USI3, predict(modele1))
rocs[["modele2"]] <- roc(data3$USI3, predict(modele2))
rocs[["modele3&...
- 120
0
votes
0
answers
42
views
ROC and continuous values
So I used GradientBoostingRegressor to predict a target from a number of variables. The target is whole numbers from 0 to 27. The GradientBoostingRegressor returns y_pred_gb = reg.predict(input_test), ...
- 33
0
votes
1
answer
47
views
How to make a multifactor model in pROC?
I have a data table with a response 'y' and some predictors, 'X1' and 'X2' among them. I can create two one-factor models with pROC:
roc1 <- roc(data$y, data$X1)
roc2 <- roc(data$y, data$X2)
...
- 597
0
votes
0
answers
56
views
AUC-ROC Comparison and Intepretation if FPR < 1
I am comparing two unsupervised models that predict a binary class, each with a different threshold parameter (p for model A and g for model B, ranging from 0 to 1).
You can see that Model B has no ...
0
votes
2
answers
187
views
ROC curve *without* a model estimator?
I have created an AI Tool which extracts content from an image and then reviews that content for completeness and accuracy. I am trying to evaluate the performance of this tool and am gathering ...
- 883
0
votes
0
answers
54
views
TypeError: Singleton array array(1) cannot be considered a valid collection
I have a dataset where my target variable is a number between 1 and 8.
Now I am going to implement Cubic SVM.
import numpy as np
import pandas as pd
from sklearn.model_selection import ...
-1
votes
1
answer
1k
views
Logistic Regression Model - Prediction and ROC AUC
I am building a Logistic Regression using statsmodels (statsmodels.api) and would like to understand how to get predictions for the test dataset. This is what I have so far:
x_train_data, x_test_data, ...
- 385
0
votes
1
answer
59
views
Different values between auc obtained from cross_validate and RocCurveDisplay
I tried two ways to calculate AUC score after training a Random Forest classifier. The first one is obtaining the metric from the cross_validate function:
numeric_transformer = make_pipeline(
...
0
votes
1
answer
198
views
Switching binary classification python scikit-learn model to multi-class classification model
I'm currently having trouble switching the following code to fit a multiclass variable (3 levels).
# data import
from ucimlrepo import fetch_ucirepo
import numpy as np
import pandas as pd
import ...
2
votes
1
answer
111
views
How can I add cut-off points to ROC curve plot in R?
Is there a simple way to do this? I am trying to make an ROC curve in R that displays marked point corresponding to criterion/cut-off values. This is the code I have in RStudio (below):
library(pROC)
...
- 23
5
votes
1
answer
157
views
Different ROC optimal cutoff obtained from different functions with same methods
I just tried to calculate optimal cutoff from a ROC curve. However, when I tried several functions from different packages, they returned different results. Which one is corrent one if I want to use ...
- 55
0
votes
1
answer
611
views
How to plot multiple ROC curves in one plot in R from three machine learning algorithms ran in tidymodels?
I ran three machine learning algorithms (logistic regression, xg-boost, random forest) on my data named 'muvr_model_1' using tidymodels package in R using following codes;
library(dplyr)
library(...
- 69