v24.12(a)

Changes:

• New dialog tool for estimating the appropriate sample size for simple random sampling using the equation by Stehman and Foody (2019), and Cochran (1977)
• New dialog tool for estimating the appropriate sample size for systematic random sampling, considering the valid map data and map using the equation by Stehman and Foody (2019), and Cochran (1977)
• Move the grid settings into a dialog to set the number of views for the response design window
• Make the main dock widget scrollable to improve usability on small screens
• Fixed auto fill the labeling buttoms from layer function, added another way to compute the unique values if no xml color style is defined in the layer
• Don't delete the thematic map instance layer when closing the sampling design window
• Fix an issue when the thematic map has not nodata value or is not set while computing the point spacing
• Improving the process when the tests are restoring the configuration file
• Added tests for number of samples and point spacing when determining the sample size
• Fix testing, do not update progress bar if pytest is running
• Save and restore the configuration for the new dialog tool for estimating the appropriate sample size for simple and systematic random sampling
• Fix a bug in the sampling report for simple and systematic sampling without post-stratification
• Fix a bug counting the nodata value when needed in a edge case if the thematic has a very low nodata value defined, and minor improve in the counting parallel function
• Fix init and restoring the stratified sampling table when the user restore the yaml with an empty table
• Rename a variable to avoid confusing it with another variable with a similar name
• Adjusts some dialog sizes
• Fix several warning and info boxes
• Set a warning message of the Qgis version needed for the latest Acatama version
• Improving the Acatama description
• Catch any issue while converting the path
• Check the path before compute the relative path
• Update the minimum Qgis version required by the plugin, issue #22
• All commits in: https://github.com/SMByC/AcATaMa/commits

v24.10

Changes:

• Major UI refactoring, simplifying and improving usability in the main dockwidget and converting the sampling design section as a window. Many other changes.
• Many changes to adjust and fix the sampling map in stratified sampling. Print the sampling report when the sampling map and thematic map are different. Other fixes.
• Added the nodata value option for the post-stratification map in the simple and systematic sampling design
• A sampling report has been added, containing all the information about the generated samples, their distribution on thematic maps, and other relevant details. This report helps the user determine whether the generated samples meet their expectations before proceeding to the response design process.
• Enable reload sampling file button only when there is a valid sampling file selected
• Some bug fixes to support older versions of the Atacama yaml configuration
• Update and increase the svg internal size to improve the drawing resolution, other UI adjustments
• If sampling change has changed, and user reload it, report is not longer valid
• Ensure that geometry is ok when the sampling file has changed
• Improving the tooltip for the user's accuracy confidence
• Restore response design window when loading a yaml file
• AcATaMa now will save relative paths to the YAML file if the layers are in the same directory or subdirectory tree as the YAML file, making it a portable and shareable project.
• Update the band and nodata from the thematic to sampling design window
• Added more warning notes in the sampling report and adjustments in other sampling report items
• Adding a warning box about the minimum samples in strata for stratified and post-stratified sampling
• Added a new option in stratified sampling to adjust the number of samples based on minimum samples per stratum
• Check and disable the classes with zero pixels on the map in the stratified sampling table
• Adjustments for the standard error of the estimated overall accuracy and User's accuracy confidence default values based on Olofsson et al. (2014)
• Check first if the QtWebKit is available in QT5 client to avoid showing an error every time the user opening the response design window
• Clean the sampling design window before restore the plugin
• While a state of Acatama is restoring, close all the window instances of the plugin opened before restore configuration
• Added some missing connections in the sampling design window
• Convert np.NaN to np.nan for numpy > 2.0
• Replace the variable of the sampling design instance
• Move the references to another page and improving the sampling unit documentation
• Added icons and improving the information text for each sampling type
• All the warning and information messages bar in the sampling design is showing in the window and not in the generic Qgis message bar
• Added stratified method for stratified sampling report
• Use QgsUnitTypes for manage the area unit
• Some improvements for the clear and reload function
• Improve the reload and zoom buttons in the accuracy assessment window
• Fix in counting num samples
• Fixed and issue computing the analysis when pixel value to count is nodata in thematic map
• Fixbug when processing the sampling report for simple or systematic with post-stratification with the thematic map
• Fix random seed value when it is automatic
• Fixbug restoring the response design window: while saving, first check if the response_design_window is opened, if so save some of the response_design_window configuration. Bug reported by Jhonatan Arias
• Fixes several variable names in the stratified and post-stratification items
• Fix the way to compare the thematic and post-stratication map
• Fixed active/inactive boxes depending on which Acatama dialogs are open and when they are closed
• Fixes typos in post-stratification vars, functs and texts.
• Fixes long and nan nodata values, and show full value of the integer and not in scientific format
• Fixes and getting the format of the nodata values for processing
• Fix number of samples based on minimum samples per stratum when the table is filling
• Fixes typos in post stratification items for the yml Acatama status file
• Fixed a bug when a pixel is being validated outside the post-stratification map
• Fixed a division by zero bug and guaranteed a minimum zoom value of 0.1
• Fix some weird RuntimeError when rubber band has been deleted from old instances of the plugin
• Updated the documentation
• All commits in: https://github.com/SMByC/AcATaMa/commits

v24.7

Changes:

• Refactored the process to generate the sampling using QgsTask as a background process allows the QGIS instance to remain unblocked. This enables the user to terminate the sampling process at any time, which is important for some sampling scenarios that never reach the total number of samples due to some (hard) restrictions in the sampling conditions.
• Other minor improvements and bug fixes
• All commits in: https://github.com/SMByC/AcATaMa/commits

v24.6

Changes:

• Integrating the Continuous Change Detection (CCD) plugin inside the response design window in Acatama. CCD helps to analyze the trends and breakpoints of change of the samples over multi-year, using Landsat and Sentinel through Google Earth Engine.
• Save and restore the CCD configuration inside the configuration Yaml file of Acatama
• Added overall accuracy in the error matrix, adjusted some labels in results
• Added coefficient of variation and uncertainty in the Class area adjusted table in the analysis results
• Adjusting the scale/zoom factor of the views in the response design window
• Ensure if exist the instance avoiding popup error when closing the plugin
• Save and restore the auto next sample button status
• Fix saving the path for not local files
• Improving some tooltips in the response design window
• Improving some text in sampling design tab
• Show a warning dialog about the problem of editing the labeling buttons when some samples are labeled
• Fix checking the duplicate thematic class when the thematic map is not selected
• Check if the thematic map is loaded to show the auto fill button
• Check if exists a duplicate thematic class when creating the buttons for labeling
• Modify button creation ID in order to avoid empty rows or delete ones in the labeling buttons table
• Added a function to auto-fill the labeling buttons based on the current thematic map symbology
• Update the labeling status of the sampling layer for the thematic map selected
• Redistribute the samples number by area based proportion keeping the total of samples and check if new value is over the maximum value to avoid negatives in the samples
• No allow negative numbers or string in the table for fixed values by categories in stratified sampling
• Correction of column name from Standard deviation by class to User accuracy expected in the stratified random sampling table
• Improving some part of the documentation
• All commits in: https://github.com/SMByC/AcATaMa/commits

v23.4

Changelog:

• Added a new mechanism to compute in parallel the counting of the unique pixel values (thematic classes)
  required for stratified sampling design and analysis using area based proportion.
• Added the option for systematic sampling to set the initial inset from left-top corner using a random value.
• Added the external library Dask in the plugin to allow parallel computing in some processes.
• Added all the tests to verify and check the accuracy assessment results in the different sampling types.
• Fixed an issue for the standard deviation in the overall accuracy for the post-stratify estimators
• Fixed the slot event for load the file and select the layer in the ComboBox for Qgis layers
• Adjusted all the exercises with the all configurations of the plugin and added the missing ones.
• All commits in: https://github.com/SMByC/AcATaMa/commits

v22.10.23

Changelog:

• Refactoring the UI, reorganizing the tabs, set the main tab "Thematic map" in the top
  always visible. Changes in the layout for selecting the layer and its band and nodata in
  one row, reducing the space and improving the usability. UI improvements in the
  classification dialog and its view widgets.
• Overhauling all accuracy assessment results, now all results based on the type of sampling
  design into three estimators: Simple/systematic estimator, Simple/systematic post-stratified estimator
  and Stratified estimator. Now the accuracy assessment result are more precise and adjusted
  to the sampling design with more statistics data such as standard deviation for the accuracies:
  overall, user and producer.
• Improvements for counting the number of pixels for each thematic value in parallel or
  lineal processing with a process dialog
• After samples are created, the file generated is prepared and selected in respond design
  and analysis tab
• Highlight the edges of the thematic pixel respectively of the current sampling point for
  the views in the response design window
• Implemented the sampling unit using a number of pixel buffer around to current pixel for labeling,
  helping the user identify the classes around the pixel that is being labelled.
• Added a new sampling method: systematic sampling using a point spacing grid with a random offset,
  but also with the option to post-stratified the sampling and the option of neighbours aggregation.
• New dialog for easier selection the classes from categorical map to post-stratify the simple
  and systematic sampling
• Refactoring the UI, classes, functions and docs to match with the correct names of the
  accuracy assessment process described in the papers that this plugin is based on.
• Added the option to allow AcATaMa apply an automatic classification symbology to the layer
  when the layer don't have an appropriate colors/values style
• Now the yml file save all the settings and configurations made in sampling design tab
• Improved the nodata boxes and processes to handle the case of large and negative nodata values
• Check if the sampling process seems stuck due to sampling conditions and ask the user to
  continue or cancel the process
• New button for reset the categorical value table, reloading the layer style, pixel count and restoring
  default values
• Checked or activated the labeling button for the label selected for the current sample
• Adjustments and fixes in the button classification dialog
• Added a check if all button configured have a valid name in the button classification dialog
• Set by default the classification view config by 2x1 views and readjust the size of window
• Refactoring the save/restore configuration and state of Acatama in order to include more configurations
• Remember the latest save/restore configuration file
• Deleted the option to save the sampling config as .ini file, use save/restore state instead.
• Check if all button configured have a valid name and check if button name exist (not allow duplicate
  labels with the same names)
• Reviewed the user and producer accuracy value using error matrix adjusted table for stratified and
  post-stratified estimator
• Updated and adjusted the suggested filenames
• Fixes counting pixel values using parallel libraries or gdal
• Fixes some division by zero in the new way to compute the Stratified estimator
• UI adjustments
• Cleaning unused files and libs
• Minor several fixes and improvements
• Don't forget rate the plugin :)

Previous versions:

• All commits in: https://github.com/SMByC/AcATaMa/commits