multilabel-classification

来源： https://stackoverflow.com/questions/53037451/keras-custom-metrics-for-multi-label-classfication

问题 I have a multilabel classification problem, which I am trying to solve with CNNs in Pytorch. I have 80,000 training examples and 7900 classes; every example can belong to multiple classes at the same time, mean number of classes per example is 130. The problem is that my dataset is very imbalance. For some classes, I have only ~900 examples, which is around 1%. For “overrepresented” classes I have ~12000 examples (15%). When I train the model I use BCEWithLogitsLoss from pytorch with a

问题 In the spacy's text classification train_textcat example, there are two labels specified Positive and Negative . Hence the cats score is represented as cats = [{"POSITIVE": bool(y), "NEGATIVE": not bool(y)} for y in labels] I am working with Multilabel classfication which means i have more than two labels to tag in one text. I have added my labels as textcat.add_label("CONSTRUCTION") and to specify cats score I have used cats = [{"POSITIVE": bool(y), "NEGATIVE": not bool(y)} for y in labels]

问题 I have a pandas data frame that contains information about messages sent by user. For my model, I'm interested in predicting missing recipients of a message i,e given recipients A,B,C of a message I want to predict who else should have been part of the recipients. I'm doing multi-label classification using OneVsRestClassifier and LinearSVC. For features, I want to use the recipients of the message. subject and body. Since recipients is a list of users, I want to transform that column using

问题 I have a pandas data frame that contains information about messages sent by user. For my model, I'm interested in predicting missing recipients of a message i,e given recipients A,B,C of a message I want to predict who else should have been part of the recipients. I'm doing multi-label classification using OneVsRestClassifier and LinearSVC. For features, I want to use the recipients of the message. subject and body. Since recipients is a list of users, I want to transform that column using

问题 I have to predict the type of program a student is in based on other attributes. prog is a categorical variable indicating what type of program a student is in: “General” (1), “Academic” (2), or “Vocational” (3) Ses is a categorical variable indicating someone’s socioeconomic class: “Low” (1), “Middle” (2), and “High” (3) read , write , math , science is their scores on different tests honors Whether they have enrolled or not csv file in image format; import pandas as pd; import numpy as np;

问题 I am using multilabel.randomForestSRC learner from mlr package for a multi-label classification problem I would like to return the variables importances The getFeatureImportance function return this issue : code: getFeatureImportance(mod) Error: Error in checkLearner(object$learner, props = "featimp") : Learner 'multilabel.randomForestSRC' must support properties 'featimp', but does not support featimp' 回答1: You can use extract the variable importance using randomForestSRC::vimp , using the

问题 I am using multilabel.randomForestSRC learner from mlr package for a multi-label classification problem I would like to return the variables importances The getFeatureImportance function return this issue : code: getFeatureImportance(mod) Error: Error in checkLearner(object$learner, props = "featimp") : Learner 'multilabel.randomForestSRC' must support properties 'featimp', but does not support featimp' 回答1: You can use extract the variable importance using randomForestSRC::vimp , using the

问题 I am trying to understand how to make a confusion matrix and ROC curve for my multilabel classification problem. I am building a neural network. Here are my classes: mlb = MultiLabelBinarizer() ohe = mlb.fit_transform(as_list) # loop over each of the possible class labels and show them for (i, label) in enumerate(mlb.classes_): print("{}. {}".format(i + 1, label)) [INFO] class labels: 1. class1 2. class2 3. class3 4. class4 5. class5 6. class6 My labels are transformed: ohe array([[0, 1, 0, 0

问题 I am working on a multilabel classification problem with KERAS. When i execute the code like this i get the following error: ValueError: Error when checking target: expected activation_19 to have 2 dimensions, but got array with shape (32, 6, 6) This is because of my lists full of "0" and "1" in the labels dictionary, which dont fit to keras.utils.to_categorical in return statement, as i learned recently. softmax cant handle more than one "1" as well. I guess I first need a Label_Encoder and