Experimenting with climatological min max norm anomaly maps to select the highest variation regions for training of the emulator

Full scale code with 9var 9sampl after testing the lightweight code 1var1samp for correction of RMSE, length of Forecast series plot and Heatmap scales of RMSE that are now up to 20%

LSTM module successfully run for INTPP and NO3. Test run completed. Next are  adding CORR_FORECAST and Heatmap for RMSE and CORR_FORECAST and GEO information for plots

Added geolocation info dictionary for index values and heat map. A bug seems to persist in ARIMA. Test now with 9VAR and 4Geoloc.

Test run for 2 variables and 2 geo-locations completed successfull. Now the code implemented until the Extractor step. Cross-correlation added. Now the test run will be for all variables and geo-locations. For 2 var and 2 geo, the runtime was 9 minutes in total. After this test-run, then implement LSTM and ARIMA model, and at the end the sampling code snippets from the SAMPMARINEX project

Running the code with TimeseriesExtractor tests. Getattr() works the best. Issue with the k_factor extraction

Successfull testing the cross correlation. The scipy.stats.personr is used for correlation calculation. Next is to test for all variables and 4 distinct areas

Debug the ARIMA loop with wrong break point of while condition and pqd loop and some minor LSTM plot output. Now with full scale test of 9var and 10 geo-locations

Switching off some printing output and testing if the loop is redundanct for plot_with_markers() function

Because of recurrent kernel dead issue, reducing the number of var and areas to get the procedure done...