anomaly-detection | simple demonstration of sub-sequence sampling | Machine Learning library

Per your comment, you have a namespace collision between a var cov_matrix and a function cov_matrix()

Change that line to e.g.

The answer to this question is that the environment had a library versions such as numpy that were too new for pycaret to work with, for example, pycaret need numpy (1.19.5 and will not work with newer).

My solution was to create a new environment in anaconda, which used pip install pycaret[full], and added nothing else to the environment. It worked after this.

1. If you have both the actual counts and the forecast in the table then 'render timechart shows both. Note that you need to specify to max_t+horizon in make-series.

I'm afraid all information on PowerBI says this is not possible. The API only supports PDF, PPTX and PNG options, and as such the integration with Power Automate doesn't do any better.

The StackOverflow question you link has some information on retrieving the Dataset but that's before the anomaly detection has processed the data.

I'm afraid your best bet is to, indeed, use the Azure service. I'd suggest ditching PowerBI and going to an ETL tool like DataFactory or even into the AzureML propositions Microsoft offers. You'll be more flexible than in PowerBI as well since you'll have the full power of Python/R notebooks at your disposal.

Sorry I can't give you a better answer.

It could be that the decay_rate argument in tf.keras.optimizers.schedules.ExponentialDecay is decaying your learning rate quicker than you think it is, effectively making your learning rate zero.

Use class_mode="input" at the flow_from_directory so returned Y will be same as X

https://github.com/tensorflow/tensorflow/blob/v2.4.1/tensorflow/python/keras/preprocessing/image.py#L867-L958

class_mode: One of "categorical", "binary", "sparse", "input", or None. Default: "categorical". Determines the type of label arrays that are returned: - "categorical" will be 2D one-hot encoded labels, - "binary" will be 1D binary labels, "sparse" will be 1D integer labels, - "input" will be images identical to input images (mainly used to work with autoencoders). - If None, no labels are returned (the generator will only yield batches of image data, which is useful to use with model.predict()). Please note that in case of class_mode None, the data still needs to reside in a subdirectory of directory for it to work correctly.

Code should end up like:

you can find the number of neighbors of the constructed knn model by printing it. By default, n_neighbors=5, radius=1.0.
I run the knn demo code locally, with:

The time_decompose() function requires data in the form of:

A tibble or tbl_time object

(from ?time_decompose)

Perhaps zem is a data.frame? You can include as_tibble() in the pipe to make sure it is a tibble ahead of time.

In addition, it expects to work on time based data:

It is designed to work with time-based data, and as such must have a column that contains date or datetime information.

I added to your test data a column with dates. Here is a working example:

There is no official or correct way of designing the architecture of an LSTM based autoencoder... The only specifics the name provides is that the model should be an Autoencoder and that it should use an LSTM layer somewhere.

The implementations you found are each different and unique on their own even though they could be used for the same task.

Let's describe them:

• TF implementation:

  • It assumes the input has only one channel, meaning that each element in the sequence is just a number and that this is already preprocessed.
  • The default behaviour of the LSTM layer in Keras/TF is to output only the last output of the LSTM, you could set it to output all the output steps with the return_sequences parameter.
  • In this case the input data has been shrank to (batch_size, LSTM_units)
  • Consider that the last output of an LSTM is of course a function of the previous outputs (specifically if it is a stateful LSTM)
  • It applies a Dense(1) in the last layer in order to get the same shape as the input.

• PyTorch 1:

  • They apply an embedding to the input before it is fed to the LSTM.
  • This is standard practice and it helps for example to transform each input element to a vector form (see word2vec for example where in a text sequence, each word that isn't a vector is mapped into a vector space). It is only a preprocessing step so that the data has a more meaningful form.
  • This does not defeat the idea of the LSTM autoencoder, because the embedding is applied independently to each element of the input sequence, so it is not encoded when it enters the LSTM layer.

• PyTorch 2:

  • In this case the input shape is not (seq_len, 1) as in the first TF example, so the decoder doesn't need a dense after. The author used a number of units in the LSTM layer equal to the input shape.

In the end you choose the architecture of your model depending on the data you want to train on, specifically: the nature (text, audio, images), the input shape, the amount of data you have and so on...