seasonal | Robustly estimate trend and periodicity in a timeseries

I'm going through the documentation of the sktime package. One thing I just cannot find is the feature importance (that we'd get with sklearn models) or model summary (like the one we can obtain from statsmodels). Is it something that is just not implemented yet?

It seems that this functionality is implemented for models like AutoETS or AutoARIMA.

Can someone help me understand why my understanding of an elasticsearch analyser is wrong?

I have an index containing various fields, one in particular is:

I have counts of hourly salmon passage past an observation tower over the course of a season and found the proportion of the total seasonal passage for each hour.

I want to find the span of hours that account for at least 80% of daily passage. In other words, I need to find the shortest combination of continuous counts which sum to greater than or equal to 0.80.

For example, if I have:

I'm trying to draw a seasonal plots for dataframe df, which contains time series data for 2 variables (value1 and value2):

This is a continuation question from this answer: https://stackoverflow.com/a/45254762/5893585

I am using the do function in dplyr within the prophet package. When attempting this I want to make a future dataframe with weekends excluded. Below is my current code:

Current dataframe:

I want to return a dataframe from this function, which can be used elsewhere (for plotly graph to be exact).

My idea is to use the dataframe I can create with points_sum(), save it as the team name, and then use that dataframe in my px.line(dataframe = team_name).

In essence, I want to use the men_points_df variable after I created it.

I have the below code that works the way as intended (3 functions total). I am looking for help in how to write better code. I'm thinking there has to be a more efficient or cleaner way to write this code. In particular, the way I wrote the date code I am confused how it is working, just know that it is. Please and thank you for any help I can get on this!

The idea was developing a function that could determine what a delay of revenue timing could look like, given the seasonality of the business. The function pulls in a months value (original end date - new end date). Then the function will begin to sum the percentages based on the month following the current end month and until the difference in the dates is reached. Then this percentage value is taken to get us the impact in delayed timing.

IE supposed to start January 2021, but had to move until May 2021. This causes a delay of 4 months. Starting from February, sum the percentages for the following 4 months.

Google Sheet: Google Sheets Example

The online documentation indicates that the algorithm under the hood is the same to estimate the (s)Arima models. During some tests, with a Kaggle dataset, I had different models: ARIMA function show me a sArima, auto.arima only Arima model.

I have 634 *.npy files, each contain a 2D numpy array of shape (8194, 76). I want to use STL decomposition on each column five time with different frequencies. so what I'm trying to do is: