Bilstm Keras multilabel classification : predict the same value for each token - python-3.x

I have made a bi lstm and I would like to be able to predict new values with it, i.e. I would like to have the corresponding labels in output. However, I notice that I always get the same value. Do you know why? Did I make a mistake in my settings? You can see in the first picture my bi-lstm and in the second picture the predictions. Tanhk you!!!

Related

Scoring Model giving reversed results using logistic regression

I am trying to implement a scoring model following the link https://rstudio-pubs-static.s3.amazonaws.com/376828_032c59adbc984b0ab892ce0026370352.html#1_introduction.
Post the entire implementation though, When I create pivot with my generated scores and the original labels, the average scores for "good' labels is significantly lower than the ones for " high" labels.
Hence, my problem can be oversimplified to why would logistic regression give reversed probabilities for 0-1 target variable( In my model I am using 0 for bad and 1 for good).
Any suggestions and solutions would be welcome.

Interpreting array of coefficients for multiple regression

I created a multiple regression model with sklearn and used .coef_ to get the coefficients. It returned an array of coefficients but I am not sure what each one represents. Could someone help me understand? Many thanks

Why does k=1 in KNN give the best accuracy?

I am using Weka IBk for text classificaiton. Each document basically is a short sentence. The training dataset contains 15,000 documents. While testing, I can see that k=1 gives the best accuracy? How can this be explained?
If you are querying your learner with the same dataset you have trained on with k=1, the output values should be perfect barring you have data with the same parameters that have different outcome values. Do some reading on overfitting as it applies to KNN learners.
In the case where you are querying with the same dataset as you trained with, the query will come in for each learner with some given parameter values. Because that point exists in the learner from the dataset you trained with, the learner will match that training point as closest to the parameter values and therefore output whatever Y value existed for that training point, which in this case is the same as the point you queried with.
The possibilities are:
The data training with data tests are the same data
Data tests have high similarity with the training data
The boundaries between classes are very clear
The optimal value for K is depends on the data. In general, the value of k may reduce the effect of noise on the classification, but makes the boundaries between each classification becomes more blurred.
If your result variable contains values of 0 or 1 - then make sure you are using as.factor, otherwise it might be interpreting the data as continuous.
Accuracy is generally calculated for the points that are not in training dataset that is unseen data points because if you calculate the accuracy for unseen values (values not in training dataset), you can claim that my model's accuracy is the accuracy that is been calculated for the unseen values.
If you calculate accuracy for training dataset, KNN with k=1, you get 100% as the values are already seen by the model and a rough decision boundary is formed for k=1. When you calculate the accuracy for the unseen data it performs really bad that is the training error would be very low but the actual error would be very high. So it would be better if you choose an optimal k. To choose an optimal k you should be plotting a graph between error and k value for the unseen data that is the test data, now you should choose the value of the where the error is lowest.
To answer your question now,
1) you might have taken the entire dataset as train data set and would have chosen a subpart of the dataset as the test dataset.
(or)
2) you might have taken accuracy for the training dataset.
If these two are not the cases than please check the accuracy values for higher k, you will get even better accuracy for k>1 for the unseen data or the test data.

Azure Machine Learning - Empty score results

I've trained a model, the test results on test-set are okay.
Now I have saved the model as 'Trained model' and made a new experiment into a new dataset, for making predictions where I don't have the actual value's.
Normally, the trained model gives me a scored label result per instance.
But now, the scored label results are empty. Also when I convert the score results to CSV the scored labels column is empty.
Even stranger, when I take a look at the Statistics of the score Visualize tab, I DO see the statistics of the scored values. But no actual scored values...
Is this a bug? Or am I forgetting something important? Whats going on ;) ?
If your test dataset is missing the dependent values, your predictive experiment may fail for some models. The solution is to pad your csv file with zero values instead of blank values.
I had this same issue and it was frustrating but I think I finally understand why this is happening.
When I was training my experiment, part of the cleaning process was populating missing values or trimming existing data with R.
The problem is if one of those features is optional. For instance if you have a column that is not filled in, the scoring model will fail in the web service.
To see if this problem affects you, go to your Predictive Experiment and visualize the Score Model results. If you see empty Predicted Label & Predicted Score values, you can easily see which data points are missing.

Excel - Iteration based on changing cell value, pasting result

So I have set up a linear model in excel of passenger numbers and population. There are two decay parameters which change the forecasts of passenger numbers - for the different types of transport.
Manually I can change the decay factors 0.1-1.0 for every combination, to see how the fit of the model changes. I would like to find the combination of parameters that creates the best model fit at a 0.01 accuracy. Any ideas how?
Essentially the passenger forecasts change when setting parameters which in turn changes the model fit. I need an easy way to see how model fit changes with changing the parameters! Thanks.

Resources