I am trying to extracted feature importance from a model built in python using tf.estimator.BoostedTreeRegressor.
It looks like a standard way to achieve it is by iterating over all trees in the forest and from the importance of each tree's coefficients to calculate some statistics.
Example in sklearn, xgboost. I have not found how to address this issue in tensorflow.
This is not possible at the moment using TensorFlow's Premade BoostedTreeRegressor or Classifier Estimators.
Related
I'm attempting to train an xgboost classification model using BQML. But I'd like to give one feature a higher weight. I couldn't find any documentation about assigning feature weights. There is CLASS_WEIGHTS to assign weights to class labels but that is not what I want. BQML documentation.
I feel like this feature is not available yet and I have to create handmade models using sklearn.
I am new to machine learning models and data science libraries. I wanted to use the Hidden Markov model for statistical data prediction on the fly which read the data from kafka and builds the model which is used to predict the data during the run-time and do the same for continous stream always.
Currently i can see only Tensorflow hidden markov model implementation in tensorflow python (tensorflow_probability distribution). Is their any other library available which can help me acheive the above scenario
Suggestions can involve the libraries of JAVA and python
Please feel free to add any resource links that can help me to understand the usage of tensorflow for hidden markov model
this might be a nice place to start: https://hmmlearn.readthedocs.io/en/latest/tutorial.html
Other alternatives, I found, are
Java:
Mallet library and it's extention GRMM in particular.
Python:
Pommegranate with it's HMM support.
Having said that, TensorFlow is much better known active and supported library, in my impression. I'd try that first.
I'm searching a library that would support Hierarchical HMMs (HHMM). That would probably require some tweaking into one of the listed ones.
I have a regression model based on various independent features which eventually predict a value with a custom loss function. Somewhat similar to the link below.
https://www.evergreeninnovations.co/blog-quantile-loss-function-for-machine-learning/
The current model is built using Tensorflow library but now I want to use MXNet becuase of the speed and other advantages it provides. How to write a similar logic in MXNet with a custom loss function?
Simple regression with L2 loss is featured in 2 famous tutorials - you can just pick any of those and customize the loss:
In the D2L.ai book (used at many universities):
https://d2l.ai/chapter_linear-networks/linear-regression-gluon.html
In The Straight Dope (guide to the python API of MXNet,
gluon). A lot of that guide went into D2L.ai:
https://gluon.mxnet.io/chapter02_supervised-learning/linear-regression-gluon.html
If we use beam search in seq2seq model it will give more proper results. There are several tensorflow implementations.
But with the softmax function in each cell you can't use beam search in the training process. So is there any other modified optimization function when using beam search?
As Oliver mentioned in order to use beam search in the training procedure we have to use beam search optimization which is clearly mentioned in the paper Sequence-to-Sequence Learning as Beam-Search Optimization.
We can't use beam search in the training procedure with the current loss function. Because current loss function is a log loss which is taken on each time step. It's a greedy way. It also clearly mentioned in the this paper Sequence to Sequence Learning
with Neural Networks.
In the section 3.2 it has mentioned the above case neatly.
"where
S
is the training set. Once training is complete, we produce tr
anslations by finding the most
likely translation according to the LSTM:"
So the original seq2seq architecture use beam search only in the testing time. If we want to use this beam search in the training time we have to use another loss and optimization method as in the paper.
Sequence-to-Sequence Learning as Beam-Search Optimization is a paper that describes the steps neccesary to use beam search in the training process.
https://arxiv.org/abs/1606.02960
The following issue contains a script that can perform the beam search however it does not contain any of the training logic
https://github.com/tensorflow/tensorflow/issues/654
What I understand is, if loss is calculated at individual word level, there is no sense of sequence. A bad sequence(with mostly random words) can have loss similar to a better sequence(with mostly connected words) as loss can be spread in different ways over the vocabulary.
No, we do not need to use a beam search in the training stage. When training modern-day seq-to-seq models like Transformers we use teacher enforcing training mechanism, where we feed right-shifted target sequence to the decoder side. Again beam-search can improve generalizability, but it is not practical to use in the training stage. But there are alternatives like the use of loss function label-smoothed-cross-entropy.
This is a newbie question for the tensorflow experts:
I reading lot of data from power transformer connected to an array of solar panels using arduinos, my question is can I use tensorflow to predict the power generation in future.
I am completely new to tensorflow, if can point me to something similar I can start with that or any github repo which is doing similar predictive modeling.
Edit: Kyle pointed me to the MNIST data, which I believe is a Image Dataset. Again, not sure if tensorflow is the right computation library for this problem or does it only work on Image datasets?
thanks, Rajesh
Surely you can use tensorflow to solve your problem.
TensorFlow™ is an open source software library for numerical
computation using data flow graphs.
So it works not only on Image dataset but also others. Don't worry about this.
And about prediction, first you need to train a model(such as linear regression) on you dataset, then predict. The tutorial code can be found in tensorflow homepage .
Get your hand dirty, you will find it works on your dataset.
Good luck.
You can absolutely use TensorFlow to predict time series. There are plenty of examples out there, like this one. And this is a really interesting one on using RNN to predict basketball trajectories.
In general, TF is a very flexible platform for solving problems with machine learning. You can create any kind of network you can think of in it, and train that network to act as a model for your process. Depending on what kind of costs you define and how you train it, you can build a network to classify data into categories, predict a time series forward a number of steps, and other cool stuff.
There is, sadly, no short answer for how to do this, but that's just because the possibilities are endless! Have fun!