diff --git a/.gitignore b/.gitignore
index b1eb3a2..43a6eb6 100644
--- a/.gitignore
+++ b/.gitignore
@@ -113,3 +113,6 @@ models/*
 
 # Dotenv file with name and email
 .name_and_email
+
+# Linting cache
+.ruff_cache
diff --git a/Dockerfile b/Dockerfile
index 293ec80..59f72b6 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -12,4 +12,4 @@ RUN poetry env use python3.11
 RUN poetry install --no-interaction --no-cache --without dev
 
 # Run the script
-CMD poetry run python src/scripts/your_script.py
+CMD poetry run python src/scripts/build_tts_dataset.py
diff --git a/README.md b/README.md
index cde3e30..3795160 100644
--- a/README.md
+++ b/README.md
@@ -7,109 +7,37 @@ ______________________________________________________________________
 [![Documentation](https://img.shields.io/badge/docs-passing-green)](https://alexandrainst.github.io/tts_text/tts_text.html)
 [![License](https://img.shields.io/github/license/alexandrainst/tts_text)](https://github.com/alexandrainst/tts_text/blob/main/LICENSE)
 [![LastCommit](https://img.shields.io/github/last-commit/alexandrainst/tts_text)](https://github.com/alexandrainst/tts_text/commits/main)
-[![Code Coverage](https://img.shields.io/badge/Coverage-100%25-brightgreen.svg)](https://github.com/alexandrainst/tts_text/tree/main/tests)
+[![Code Coverage](https://img.shields.io/badge/Coverage-47%25-orange.svg)](https://github.com/alexandrainst/tts_text/tree/main/tests)
 [![Contributor Covenant](https://img.shields.io/badge/Contributor%20Covenant-2.0-4baaaa.svg)](https://github.com/alexandrainst/tts_text/blob/main/CODE_OF_CONDUCT.md)
 
 
 Developers:
 
 - Anders Jess Pedersen (anders.j.pedersen@alexandra.dk)
+- Dan Saattrup Nielsen (dan.nielsen@alexandra.dk)
 
 
-## Setup
+## Quick Start
 
-### Installation
+The quickest way to build the dataset is using Docker. With Docker installed, simply
+write `make docker` and the final dataset will be built in the `data/processed`
+directory, with the individual datasets in `data/raw`.
 
-1. Run `make install`, which installs Poetry (if it isn't already installed), sets up a virtual environment and all Python dependencies therein.
-2. Run `source .venv/bin/activate` to activate the virtual environment.
-
-### Adding and Removing Packages
-
-To install new PyPI packages, run:
-
-```
-poetry add <package-name>
-```
-
-To remove them again, run:
-```
-poetry remove <package-name>
-```
-
-To show all installed packages, run:
-```
-poetry show
-```
 
+## Development Setup
 
-## A Word on Modules and Scripts
-In the `src` directory there are two subdirectories, `tts_text`
-and `scripts`. This is a brief explanation of the differences between the two.
+To install the project for further development, run the following steps:
 
-### Modules
-All Python files in the `tts_text` directory are _modules_
-internal to the project package. Examples here could be a general data loading script,
-a definition of a model, or a training function. Think of modules as all the building
-blocks of a project.
-
-When a module is importing functions/classes from other modules we use the _relative
-import_ notation - here's an example:
-
-```
-from .other_module import some_function
-```
-
-### Scripts
-Python files in the `scripts` folder are scripts, which are short code snippets that
-are _external_ to the project package, and which is meant to actually run the code. As
-such, _only_ scripts will be called from the terminal. An analogy here is that the
-internal `numpy` code are all modules, but the Python code you write where you import
-some `numpy` functions and actually run them, that a script.
+1. Run `make install`, which installs Poetry (if it isn't already installed), sets up a
+   virtual environment and all Python dependencies therein.
+2. Run `source .venv/bin/activate` to activate the virtual environment.
 
-When importing module functions/classes when you're in a script, you do it like you
-would normally import from any other package:
+With the project installed, you can build the dataset by running:
 
 ```
-from tts_text import some_function
+python src/scripts/build_tts_dataset.py
 ```
 
-Note that this is also how we import functions/classes in tests, since each test Python
-file is also a Python script, rather than a module.
-
-
-## Features
-
-### Docker Setup
-
-A Dockerfile is included in the new repositories, which by default runs
-`src/scripts/your_script.py`. You can build the Docker image and run the Docker
-container by running `make docker`.
-
-### Automatic Documentation
-
-Run `make docs` to create the documentation in the `docs` folder, which is based on
-your docstrings in your code. You can view this by running `make view-docs`.
-
-### Automatic Test Coverage Calculation
-
-Run `make test` to test your code, which also updates the "coverage badge" in the
-README, showing you how much of your code base that is currently being tested.
-
-### Continuous Integration
-
-Github CI pipelines are included in the repo, running all the tests in the `tests`
-directory, as well as building online documentation, if Github Pages has been enabled
-for the repository (can be enabled on Github in the repository settings).
-
-### Code Spaces
-
-Code Spaces is a new feature on Github, that allows you to develop on a project
-completely in the cloud, without having to do any local setup at all. This repo comes
-included with a configuration file for running code spaces on Github. When hosted on
-`alexandrainst/tts_text` then simply press the `<> Code` button
-and add a code space to get started, which will open a VSCode window directly in your
-browser.
-
 
 ## Project structure
 ```
@@ -150,16 +78,22 @@ browser.
 │   └── .gitkeep
 ├── notebooks
 │   └── .gitkeep
+├── poetry.lock
 ├── poetry.toml
 ├── pyproject.toml
 ├── src
 │   ├── scripts
-│   │   ├── fix_dot_env_file.py
-│   │   └── your_script.py
+│   │   ├── build_tts_dataset.py
+│   │   └── fix_dot_env_file.py
 │   └── tts_text
 │       ├── __init__.py
-│       └── your_module.py
+│       ├── __pycache__
+│       ├── bus_stops_and_stations.py
+│       ├── dates.py
+│       ├── times.py
+│       └── utils.py
 └── tests
     ├── __init__.py
+    ├── __pycache__
     └── test_dummy.py
 ```
diff --git a/config/config.yaml b/config/config.yaml
index 73551cf..a0d1ecb 100644
--- a/config/config.yaml
+++ b/config/config.yaml
@@ -8,3 +8,8 @@ dirs:
   processed: processed
   final: final
   models: models
+
+sampling_probabilities:
+  dates: 0.25
+  times: 0.25
+  bus_stops_and_stations: 0.5
diff --git a/makefile b/makefile
index f98baf1..ab11f92 100644
--- a/makefile
+++ b/makefile
@@ -152,7 +152,7 @@ test:  ## Run tests
 
 docker:  ## Build Docker image and run container
 	@docker build -t tts_text .
-	@docker run -it --rm tts_text
+	@docker run -it --rm -v ./data:/project/data tts_text
 
 tree:  ## Print directory tree
 	@tree -a --gitignore -I .git .
diff --git a/poetry.lock b/poetry.lock
index b205b88..f899c23 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -212,6 +212,102 @@ MarkupSafe = ">=2.0"
 [package.extras]
 i18n = ["Babel (>=2.7)"]
 
+[[package]]
+name = "lxml"
+version = "4.9.3"
+description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
+files = [
+    {file = "lxml-4.9.3-cp27-cp27m-macosx_11_0_x86_64.whl", hash = "sha256:b0a545b46b526d418eb91754565ba5b63b1c0b12f9bd2f808c852d9b4b2f9b5c"},
+    {file = "lxml-4.9.3-cp27-cp27m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:075b731ddd9e7f68ad24c635374211376aa05a281673ede86cbe1d1b3455279d"},
+    {file = "lxml-4.9.3-cp27-cp27m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:1e224d5755dba2f4a9498e150c43792392ac9b5380aa1b845f98a1618c94eeef"},
+    {file = "lxml-4.9.3-cp27-cp27mu-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c0781a98ff5e6586926293e59480b64ddd46282953203c76ae15dbbbf302e8bb"},
+    {file = "lxml-4.9.3-cp27-cp27mu-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:cef2502e7e8a96fe5ad686d60b49e1ab03e438bd9123987994528febd569868e"},
+    {file = "lxml-4.9.3-cp310-cp310-macosx_11_0_x86_64.whl", hash = "sha256:b86164d2cff4d3aaa1f04a14685cbc072efd0b4f99ca5708b2ad1b9b5988a991"},
+    {file = "lxml-4.9.3-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:42871176e7896d5d45138f6d28751053c711ed4d48d8e30b498da155af39aebd"},
+    {file = "lxml-4.9.3-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:411007c0d88188d9f621b11d252cce90c4a2d1a49db6c068e3c16422f306eab8"},
+    {file = "lxml-4.9.3-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:cd47b4a0d41d2afa3e58e5bf1f62069255aa2fd6ff5ee41604418ca925911d76"},
+    {file = "lxml-4.9.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0e2cb47860da1f7e9a5256254b74ae331687b9672dfa780eed355c4c9c3dbd23"},
+    {file = "lxml-4.9.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:1247694b26342a7bf47c02e513d32225ededd18045264d40758abeb3c838a51f"},
+    {file = "lxml-4.9.3-cp310-cp310-win32.whl", hash = "sha256:cdb650fc86227eba20de1a29d4b2c1bfe139dc75a0669270033cb2ea3d391b85"},
+    {file = "lxml-4.9.3-cp310-cp310-win_amd64.whl", hash = "sha256:97047f0d25cd4bcae81f9ec9dc290ca3e15927c192df17331b53bebe0e3ff96d"},
+    {file = "lxml-4.9.3-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:1f447ea5429b54f9582d4b955f5f1985f278ce5cf169f72eea8afd9502973dd5"},
+    {file = "lxml-4.9.3-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:57d6ba0ca2b0c462f339640d22882acc711de224d769edf29962b09f77129cbf"},
+    {file = "lxml-4.9.3-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:71c52db65e4b56b8ddc5bb89fb2e66c558ed9d1a74a45ceb7dcb20c191c3df2f"},
+    {file = "lxml-4.9.3-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:d73d8ecf8ecf10a3bd007f2192725a34bd62898e8da27eb9d32a58084f93962b"},
+    {file = "lxml-4.9.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0a3d3487f07c1d7f150894c238299934a2a074ef590b583103a45002035be120"},
+    {file = "lxml-4.9.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:9e28c51fa0ce5674be9f560c6761c1b441631901993f76700b1b30ca6c8378d6"},
+    {file = "lxml-4.9.3-cp311-cp311-win32.whl", hash = "sha256:0bfd0767c5c1de2551a120673b72e5d4b628737cb05414f03c3277bf9bed3305"},
+    {file = "lxml-4.9.3-cp311-cp311-win_amd64.whl", hash = "sha256:25f32acefac14ef7bd53e4218fe93b804ef6f6b92ffdb4322bb6d49d94cad2bc"},
+    {file = "lxml-4.9.3-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:d3ff32724f98fbbbfa9f49d82852b159e9784d6094983d9a8b7f2ddaebb063d4"},
+    {file = "lxml-4.9.3-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:48d6ed886b343d11493129e019da91d4039826794a3e3027321c56d9e71505be"},
+    {file = "lxml-4.9.3-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:9a92d3faef50658dd2c5470af249985782bf754c4e18e15afb67d3ab06233f13"},
+    {file = "lxml-4.9.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:b4e4bc18382088514ebde9328da057775055940a1f2e18f6ad2d78aa0f3ec5b9"},
+    {file = "lxml-4.9.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:fc9b106a1bf918db68619fdcd6d5ad4f972fdd19c01d19bdb6bf63f3589a9ec5"},
+    {file = "lxml-4.9.3-cp312-cp312-win_amd64.whl", hash = "sha256:d37017287a7adb6ab77e1c5bee9bcf9660f90ff445042b790402a654d2ad81d8"},
+    {file = "lxml-4.9.3-cp35-cp35m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:56dc1f1ebccc656d1b3ed288f11e27172a01503fc016bcabdcbc0978b19352b7"},
+    {file = "lxml-4.9.3-cp35-cp35m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:578695735c5a3f51569810dfebd05dd6f888147a34f0f98d4bb27e92b76e05c2"},
+    {file = "lxml-4.9.3-cp35-cp35m-win32.whl", hash = "sha256:704f61ba8c1283c71b16135caf697557f5ecf3e74d9e453233e4771d68a1f42d"},
+    {file = "lxml-4.9.3-cp35-cp35m-win_amd64.whl", hash = "sha256:c41bfca0bd3532d53d16fd34d20806d5c2b1ace22a2f2e4c0008570bf2c58833"},
+    {file = "lxml-4.9.3-cp36-cp36m-macosx_11_0_x86_64.whl", hash = "sha256:64f479d719dc9f4c813ad9bb6b28f8390360660b73b2e4beb4cb0ae7104f1c12"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:dd708cf4ee4408cf46a48b108fb9427bfa00b9b85812a9262b5c668af2533ea5"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c31c7462abdf8f2ac0577d9f05279727e698f97ecbb02f17939ea99ae8daa98"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:4930be26af26ac545c3dffb662521d4e6268352866956672231887d18f0eaab2"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:4aec80cde9197340bc353d2768e2a75f5f60bacda2bab72ab1dc499589b3878c"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:14e019fd83b831b2e61baed40cab76222139926b1fb5ed0e79225bc0cae14584"},
+    {file = "lxml-4.9.3-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:0c0850c8b02c298d3c7006b23e98249515ac57430e16a166873fc47a5d549287"},
+    {file = "lxml-4.9.3-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:aca086dc5f9ef98c512bac8efea4483eb84abbf926eaeedf7b91479feb092458"},
+    {file = "lxml-4.9.3-cp36-cp36m-win32.whl", hash = "sha256:50baa9c1c47efcaef189f31e3d00d697c6d4afda5c3cde0302d063492ff9b477"},
+    {file = "lxml-4.9.3-cp36-cp36m-win_amd64.whl", hash = "sha256:bef4e656f7d98aaa3486d2627e7d2df1157d7e88e7efd43a65aa5dd4714916cf"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:46f409a2d60f634fe550f7133ed30ad5321ae2e6630f13657fb9479506b00601"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:4c28a9144688aef80d6ea666c809b4b0e50010a2aca784c97f5e6bf143d9f129"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:53ace1c1fd5a74ef662f844a0413446c0629d151055340e9893da958a374f70d"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:17a753023436a18e27dd7769e798ce302963c236bc4114ceee5b25c18c52c693"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:7d298a1bd60c067ea75d9f684f5f3992c9d6766fadbc0bcedd39750bf344c2f4"},
+    {file = "lxml-4.9.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:081d32421db5df44c41b7f08a334a090a545c54ba977e47fd7cc2deece78809a"},
+    {file = "lxml-4.9.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:23eed6d7b1a3336ad92d8e39d4bfe09073c31bfe502f20ca5116b2a334f8ec02"},
+    {file = "lxml-4.9.3-cp37-cp37m-win32.whl", hash = "sha256:1509dd12b773c02acd154582088820893109f6ca27ef7291b003d0e81666109f"},
+    {file = "lxml-4.9.3-cp37-cp37m-win_amd64.whl", hash = "sha256:120fa9349a24c7043854c53cae8cec227e1f79195a7493e09e0c12e29f918e52"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:4d2d1edbca80b510443f51afd8496be95529db04a509bc8faee49c7b0fb6d2cc"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:8d7e43bd40f65f7d97ad8ef5c9b1778943d02f04febef12def25f7583d19baac"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:6fc3c450eaa0b56f815c7b62f2b7fba7266c4779adcf1cece9e6deb1de7305ce"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:65299ea57d82fb91c7f019300d24050c4ddeb7c5a190e076b5f48a2b43d19c42"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:eadfbbbfb41b44034a4c757fd5d70baccd43296fb894dba0295606a7cf3124aa"},
+    {file = "lxml-4.9.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:3e9bdd30efde2b9ccfa9cb5768ba04fe71b018a25ea093379c857c9dad262c40"},
+    {file = "lxml-4.9.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:fcdd00edfd0a3001e0181eab3e63bd5c74ad3e67152c84f93f13769a40e073a7"},
+    {file = "lxml-4.9.3-cp38-cp38-win32.whl", hash = "sha256:57aba1bbdf450b726d58b2aea5fe47c7875f5afb2c4a23784ed78f19a0462574"},
+    {file = "lxml-4.9.3-cp38-cp38-win_amd64.whl", hash = "sha256:92af161ecbdb2883c4593d5ed4815ea71b31fafd7fd05789b23100d081ecac96"},
+    {file = "lxml-4.9.3-cp39-cp39-macosx_11_0_x86_64.whl", hash = "sha256:9bb6ad405121241e99a86efff22d3ef469024ce22875a7ae045896ad23ba2340"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:8ed74706b26ad100433da4b9d807eae371efaa266ffc3e9191ea436087a9d6a7"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:303bf1edce6ced16bf67a18a1cf8339d0db79577eec5d9a6d4a80f0fb10aa2da"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:5515edd2a6d1a5a70bfcdee23b42ec33425e405c5b351478ab7dc9347228f96e"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:690dafd0b187ed38583a648076865d8c229661ed20e48f2335d68e2cf7dc829d"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:b6420a005548ad52154c8ceab4a1290ff78d757f9e5cbc68f8c77089acd3c432"},
+    {file = "lxml-4.9.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:bb3bb49c7a6ad9d981d734ef7c7193bc349ac338776a0360cc671eaee89bcf69"},
+    {file = "lxml-4.9.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d27be7405547d1f958b60837dc4c1007da90b8b23f54ba1f8b728c78fdb19d50"},
+    {file = "lxml-4.9.3-cp39-cp39-win32.whl", hash = "sha256:8df133a2ea5e74eef5e8fc6f19b9e085f758768a16e9877a60aec455ed2609b2"},
+    {file = "lxml-4.9.3-cp39-cp39-win_amd64.whl", hash = "sha256:4dd9a263e845a72eacb60d12401e37c616438ea2e5442885f65082c276dfb2b2"},
+    {file = "lxml-4.9.3-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:6689a3d7fd13dc687e9102a27e98ef33730ac4fe37795d5036d18b4d527abd35"},
+    {file = "lxml-4.9.3-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:f6bdac493b949141b733c5345b6ba8f87a226029cbabc7e9e121a413e49441e0"},
+    {file = "lxml-4.9.3-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:c2006f5c8d28dee289f7020f721354362fa304acbaaf9745751ac4006650254b"},
+    {file = "lxml-4.9.3-pp38-pypy38_pp73-macosx_11_0_x86_64.whl", hash = "sha256:5c245b783db29c4e4fbbbfc9c5a78be496c9fea25517f90606aa1f6b2b3d5f7b"},
+    {file = "lxml-4.9.3-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:4fb960a632a49f2f089d522f70496640fdf1218f1243889da3822e0a9f5f3ba7"},
+    {file = "lxml-4.9.3-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:9719fe17307a9e814580af1f5c6e05ca593b12fb7e44fe62450a5384dbf61b4b"},
+    {file = "lxml-4.9.3-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:3331bece23c9ee066e0fb3f96c61322b9e0f54d775fccefff4c38ca488de283a"},
+    {file = "lxml-4.9.3-pp39-pypy39_pp73-macosx_11_0_x86_64.whl", hash = "sha256:ed667f49b11360951e201453fc3967344d0d0263aa415e1619e85ae7fd17b4e0"},
+    {file = "lxml-4.9.3-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:8b77946fd508cbf0fccd8e400a7f71d4ac0e1595812e66025bac475a8e811694"},
+    {file = "lxml-4.9.3-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:fe4bda6bd4340caa6e5cf95e73f8fea5c4bfc55763dd42f1b50a94c1b4a2fbd4"},
+    {file = "lxml-4.9.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:f3df3db1d336b9356dd3112eae5f5c2b8b377f3bc826848567f10bfddfee77e9"},
+    {file = "lxml-4.9.3.tar.gz", hash = "sha256:48628bd53a426c9eb9bc066a923acaa0878d1e86129fd5359aee99285f4eed9c"},
+]
+
+[package.extras]
+cssselect = ["cssselect (>=0.7)"]
+html5 = ["html5lib"]
+htmlsoup = ["BeautifulSoup4"]
+source = ["Cython (>=0.29.35)"]
+
 [[package]]
 name = "markupsafe"
 version = "2.1.3"
@@ -239,16 +335,6 @@ files = [
     {file = "MarkupSafe-2.1.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5bbe06f8eeafd38e5d0a4894ffec89378b6c6a625ff57e3028921f8ff59318ac"},
     {file = "MarkupSafe-2.1.3-cp311-cp311-win32.whl", hash = "sha256:dd15ff04ffd7e05ffcb7fe79f1b98041b8ea30ae9234aed2a9168b5797c3effb"},
     {file = "MarkupSafe-2.1.3-cp311-cp311-win_amd64.whl", hash = "sha256:134da1eca9ec0ae528110ccc9e48041e0828d79f24121a1a146161103c76e686"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:f698de3fd0c4e6972b92290a45bd9b1536bffe8c6759c62471efaa8acb4c37bc"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:aa57bd9cf8ae831a362185ee444e15a93ecb2e344c8e52e4d721ea3ab6ef1823"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffcc3f7c66b5f5b7931a5aa68fc9cecc51e685ef90282f4a82f0f5e9b704ad11"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47d4f1c5f80fc62fdd7777d0d40a2e9dda0a05883ab11374334f6c4de38adffd"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1f67c7038d560d92149c060157d623c542173016c4babc0c1913cca0564b9939"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:9aad3c1755095ce347e26488214ef77e0485a3c34a50c5a5e2471dff60b9dd9c"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:14ff806850827afd6b07a5f32bd917fb7f45b046ba40c57abdb636674a8b559c"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8f9293864fe09b8149f0cc42ce56e3f0e54de883a9de90cd427f191c346eb2e1"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-win32.whl", hash = "sha256:715d3562f79d540f251b99ebd6d8baa547118974341db04f5ad06d5ea3eb8007"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-win_amd64.whl", hash = "sha256:1b8dd8c3fd14349433c79fa8abeb573a55fc0fdd769133baac1f5e07abf54aeb"},
     {file = "MarkupSafe-2.1.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8e254ae696c88d98da6555f5ace2279cf7cd5b3f52be2b5cf97feafe883b58d2"},
     {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb0932dc158471523c9637e807d9bfb93e06a95cbf010f1a38b98623b929ef2b"},
     {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9402b03f1a1b4dc4c19845e5c749e3ab82d5078d16a2a4c2cd2df62d57bb0707"},
@@ -295,6 +381,47 @@ files = [
 [package.dependencies]
 setuptools = "*"
 
+[[package]]
+name = "numpy"
+version = "1.26.1"
+description = "Fundamental package for array computing in Python"
+optional = false
+python-versions = "<3.13,>=3.9"
+files = [
+    {file = "numpy-1.26.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:82e871307a6331b5f09efda3c22e03c095d957f04bf6bc1804f30048d0e5e7af"},
+    {file = "numpy-1.26.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:cdd9ec98f0063d93baeb01aad472a1a0840dee302842a2746a7a8e92968f9575"},
+    {file = "numpy-1.26.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d78f269e0c4fd365fc2992c00353e4530d274ba68f15e968d8bc3c69ce5f5244"},
+    {file = "numpy-1.26.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8ab9163ca8aeb7fd32fe93866490654d2f7dda4e61bc6297bf72ce07fdc02f67"},
+    {file = "numpy-1.26.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:78ca54b2f9daffa5f323f34cdf21e1d9779a54073f0018a3094ab907938331a2"},
+    {file = "numpy-1.26.1-cp310-cp310-win32.whl", hash = "sha256:d1cfc92db6af1fd37a7bb58e55c8383b4aa1ba23d012bdbba26b4bcca45ac297"},
+    {file = "numpy-1.26.1-cp310-cp310-win_amd64.whl", hash = "sha256:d2984cb6caaf05294b8466966627e80bf6c7afd273279077679cb010acb0e5ab"},
+    {file = "numpy-1.26.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cd7837b2b734ca72959a1caf3309457a318c934abef7a43a14bb984e574bbb9a"},
+    {file = "numpy-1.26.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1c59c046c31a43310ad0199d6299e59f57a289e22f0f36951ced1c9eac3665b9"},
+    {file = "numpy-1.26.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d58e8c51a7cf43090d124d5073bc29ab2755822181fcad978b12e144e5e5a4b3"},
+    {file = "numpy-1.26.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6081aed64714a18c72b168a9276095ef9155dd7888b9e74b5987808f0dd0a974"},
+    {file = "numpy-1.26.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:97e5d6a9f0702c2863aaabf19f0d1b6c2628fbe476438ce0b5ce06e83085064c"},
+    {file = "numpy-1.26.1-cp311-cp311-win32.whl", hash = "sha256:b9d45d1dbb9de84894cc50efece5b09939752a2d75aab3a8b0cef6f3a35ecd6b"},
+    {file = "numpy-1.26.1-cp311-cp311-win_amd64.whl", hash = "sha256:3649d566e2fc067597125428db15d60eb42a4e0897fc48d28cb75dc2e0454e53"},
+    {file = "numpy-1.26.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:1d1bd82d539607951cac963388534da3b7ea0e18b149a53cf883d8f699178c0f"},
+    {file = "numpy-1.26.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:afd5ced4e5a96dac6725daeb5242a35494243f2239244fad10a90ce58b071d24"},
+    {file = "numpy-1.26.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a03fb25610ef560a6201ff06df4f8105292ba56e7cdd196ea350d123fc32e24e"},
+    {file = "numpy-1.26.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dcfaf015b79d1f9f9c9fd0731a907407dc3e45769262d657d754c3a028586124"},
+    {file = "numpy-1.26.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e509cbc488c735b43b5ffea175235cec24bbc57b227ef1acc691725beb230d1c"},
+    {file = "numpy-1.26.1-cp312-cp312-win32.whl", hash = "sha256:af22f3d8e228d84d1c0c44c1fbdeb80f97a15a0abe4f080960393a00db733b66"},
+    {file = "numpy-1.26.1-cp312-cp312-win_amd64.whl", hash = "sha256:9f42284ebf91bdf32fafac29d29d4c07e5e9d1af862ea73686581773ef9e73a7"},
+    {file = "numpy-1.26.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bb894accfd16b867d8643fc2ba6c8617c78ba2828051e9a69511644ce86ce83e"},
+    {file = "numpy-1.26.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e44ccb93f30c75dfc0c3aa3ce38f33486a75ec9abadabd4e59f114994a9c4617"},
+    {file = "numpy-1.26.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9696aa2e35cc41e398a6d42d147cf326f8f9d81befcb399bc1ed7ffea339b64e"},
+    {file = "numpy-1.26.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a5b411040beead47a228bde3b2241100454a6abde9df139ed087bd73fc0a4908"},
+    {file = "numpy-1.26.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:1e11668d6f756ca5ef534b5be8653d16c5352cbb210a5c2a79ff288e937010d5"},
+    {file = "numpy-1.26.1-cp39-cp39-win32.whl", hash = "sha256:d1d2c6b7dd618c41e202c59c1413ef9b2c8e8a15f5039e344af64195459e3104"},
+    {file = "numpy-1.26.1-cp39-cp39-win_amd64.whl", hash = "sha256:59227c981d43425ca5e5c01094d59eb14e8772ce6975d4b2fc1e106a833d5ae2"},
+    {file = "numpy-1.26.1-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:06934e1a22c54636a059215d6da99e23286424f316fddd979f5071093b648668"},
+    {file = "numpy-1.26.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:76ff661a867d9272cd2a99eed002470f46dbe0943a5ffd140f49be84f68ffc42"},
+    {file = "numpy-1.26.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:6965888d65d2848e8768824ca8288db0a81263c1efccec881cb35a0d805fcd2f"},
+    {file = "numpy-1.26.1.tar.gz", hash = "sha256:c8c6c72d4a9f831f328efb1312642a1cafafaa88981d9ab76368d50d07d93cbe"},
+]
+
 [[package]]
 name = "omegaconf"
 version = "2.3.0"
@@ -321,6 +448,73 @@ files = [
     {file = "packaging-23.2.tar.gz", hash = "sha256:048fb0e9405036518eaaf48a55953c750c11e1a1b68e0dd1a9d62ed0c092cfc5"},
 ]
 
+[[package]]
+name = "pandas"
+version = "2.1.1"
+description = "Powerful data structures for data analysis, time series, and statistics"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "pandas-2.1.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:58d997dbee0d4b64f3cb881a24f918b5f25dd64ddf31f467bb9b67ae4c63a1e4"},
+    {file = "pandas-2.1.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:02304e11582c5d090e5a52aec726f31fe3f42895d6bfc1f28738f9b64b6f0614"},
+    {file = "pandas-2.1.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffa8f0966de2c22de408d0e322db2faed6f6e74265aa0856f3824813cf124363"},
+    {file = "pandas-2.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c1f84c144dee086fe4f04a472b5cd51e680f061adf75c1ae4fc3a9275560f8f4"},
+    {file = "pandas-2.1.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:75ce97667d06d69396d72be074f0556698c7f662029322027c226fd7a26965cb"},
+    {file = "pandas-2.1.1-cp310-cp310-win_amd64.whl", hash = "sha256:4c3f32fd7c4dccd035f71734df39231ac1a6ff95e8bdab8d891167197b7018d2"},
+    {file = "pandas-2.1.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9e2959720b70e106bb1d8b6eadd8ecd7c8e99ccdbe03ee03260877184bb2877d"},
+    {file = "pandas-2.1.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:25e8474a8eb258e391e30c288eecec565bfed3e026f312b0cbd709a63906b6f8"},
+    {file = "pandas-2.1.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b8bd1685556f3374520466998929bade3076aeae77c3e67ada5ed2b90b4de7f0"},
+    {file = "pandas-2.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dc3657869c7902810f32bd072f0740487f9e030c1a3ab03e0af093db35a9d14e"},
+    {file = "pandas-2.1.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:05674536bd477af36aa2effd4ec8f71b92234ce0cc174de34fd21e2ee99adbc2"},
+    {file = "pandas-2.1.1-cp311-cp311-win_amd64.whl", hash = "sha256:b407381258a667df49d58a1b637be33e514b07f9285feb27769cedb3ab3d0b3a"},
+    {file = "pandas-2.1.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:c747793c4e9dcece7bb20156179529898abf505fe32cb40c4052107a3c620b49"},
+    {file = "pandas-2.1.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3bcad1e6fb34b727b016775bea407311f7721db87e5b409e6542f4546a4951ea"},
+    {file = "pandas-2.1.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f5ec7740f9ccb90aec64edd71434711f58ee0ea7f5ed4ac48be11cfa9abf7317"},
+    {file = "pandas-2.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:29deb61de5a8a93bdd033df328441a79fcf8dd3c12d5ed0b41a395eef9cd76f0"},
+    {file = "pandas-2.1.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4f99bebf19b7e03cf80a4e770a3e65eee9dd4e2679039f542d7c1ace7b7b1daa"},
+    {file = "pandas-2.1.1-cp312-cp312-win_amd64.whl", hash = "sha256:84e7e910096416adec68075dc87b986ff202920fb8704e6d9c8c9897fe7332d6"},
+    {file = "pandas-2.1.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:366da7b0e540d1b908886d4feb3d951f2f1e572e655c1160f5fde28ad4abb750"},
+    {file = "pandas-2.1.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9e50e72b667415a816ac27dfcfe686dc5a0b02202e06196b943d54c4f9c7693e"},
+    {file = "pandas-2.1.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cc1ab6a25da197f03ebe6d8fa17273126120874386b4ac11c1d687df288542dd"},
+    {file = "pandas-2.1.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a0dbfea0dd3901ad4ce2306575c54348d98499c95be01b8d885a2737fe4d7a98"},
+    {file = "pandas-2.1.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:0489b0e6aa3d907e909aef92975edae89b1ee1654db5eafb9be633b0124abe97"},
+    {file = "pandas-2.1.1-cp39-cp39-win_amd64.whl", hash = "sha256:4cdb0fab0400c2cb46dafcf1a0fe084c8bb2480a1fa8d81e19d15e12e6d4ded2"},
+    {file = "pandas-2.1.1.tar.gz", hash = "sha256:fecb198dc389429be557cde50a2d46da8434a17fe37d7d41ff102e3987fd947b"},
+]
+
+[package.dependencies]
+numpy = [
+    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
+    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
+]
+python-dateutil = ">=2.8.2"
+pytz = ">=2020.1"
+tzdata = ">=2022.1"
+
+[package.extras]
+all = ["PyQt5 (>=5.15.6)", "SQLAlchemy (>=1.4.36)", "beautifulsoup4 (>=4.11.1)", "bottleneck (>=1.3.4)", "dataframe-api-compat (>=0.1.7)", "fastparquet (>=0.8.1)", "fsspec (>=2022.05.0)", "gcsfs (>=2022.05.0)", "html5lib (>=1.1)", "hypothesis (>=6.46.1)", "jinja2 (>=3.1.2)", "lxml (>=4.8.0)", "matplotlib (>=3.6.1)", "numba (>=0.55.2)", "numexpr (>=2.8.0)", "odfpy (>=1.4.1)", "openpyxl (>=3.0.10)", "pandas-gbq (>=0.17.5)", "psycopg2 (>=2.9.3)", "pyarrow (>=7.0.0)", "pymysql (>=1.0.2)", "pyreadstat (>=1.1.5)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)", "pyxlsb (>=1.0.9)", "qtpy (>=2.2.0)", "s3fs (>=2022.05.0)", "scipy (>=1.8.1)", "tables (>=3.7.0)", "tabulate (>=0.8.10)", "xarray (>=2022.03.0)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.3)", "zstandard (>=0.17.0)"]
+aws = ["s3fs (>=2022.05.0)"]
+clipboard = ["PyQt5 (>=5.15.6)", "qtpy (>=2.2.0)"]
+compression = ["zstandard (>=0.17.0)"]
+computation = ["scipy (>=1.8.1)", "xarray (>=2022.03.0)"]
+consortium-standard = ["dataframe-api-compat (>=0.1.7)"]
+excel = ["odfpy (>=1.4.1)", "openpyxl (>=3.0.10)", "pyxlsb (>=1.0.9)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.3)"]
+feather = ["pyarrow (>=7.0.0)"]
+fss = ["fsspec (>=2022.05.0)"]
+gcp = ["gcsfs (>=2022.05.0)", "pandas-gbq (>=0.17.5)"]
+hdf5 = ["tables (>=3.7.0)"]
+html = ["beautifulsoup4 (>=4.11.1)", "html5lib (>=1.1)", "lxml (>=4.8.0)"]
+mysql = ["SQLAlchemy (>=1.4.36)", "pymysql (>=1.0.2)"]
+output-formatting = ["jinja2 (>=3.1.2)", "tabulate (>=0.8.10)"]
+parquet = ["pyarrow (>=7.0.0)"]
+performance = ["bottleneck (>=1.3.4)", "numba (>=0.55.2)", "numexpr (>=2.8.0)"]
+plot = ["matplotlib (>=3.6.1)"]
+postgresql = ["SQLAlchemy (>=1.4.36)", "psycopg2 (>=2.9.3)"]
+spss = ["pyreadstat (>=1.1.5)"]
+sql-other = ["SQLAlchemy (>=1.4.36)"]
+test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)"]
+xml = ["lxml (>=4.8.0)"]
+
 [[package]]
 name = "pdoc"
 version = "14.1.0"
@@ -460,6 +654,31 @@ psutil = ["psutil (>=3.0)"]
 setproctitle = ["setproctitle"]
 testing = ["filelock"]
 
+[[package]]
+name = "python-dateutil"
+version = "2.8.2"
+description = "Extensions to the standard Python datetime module"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
+files = [
+    {file = "python-dateutil-2.8.2.tar.gz", hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86"},
+    {file = "python_dateutil-2.8.2-py2.py3-none-any.whl", hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9"},
+]
+
+[package.dependencies]
+six = ">=1.5"
+
+[[package]]
+name = "pytz"
+version = "2023.3.post1"
+description = "World timezone definitions, modern and historical"
+optional = false
+python-versions = "*"
+files = [
+    {file = "pytz-2023.3.post1-py2.py3-none-any.whl", hash = "sha256:ce42d816b81b68506614c11e8937d3aa9e41007ceb50bfdcb0749b921bf646c7"},
+    {file = "pytz-2023.3.post1.tar.gz", hash = "sha256:7b4fddbeb94a1eba4b557da24f19fdf9db575192544270a9101d8509f9f43d7b"},
+]
+
 [[package]]
 name = "pyyaml"
 version = "6.0.1"
@@ -472,7 +691,6 @@ files = [
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
-    {file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
     {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
     {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
     {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
@@ -480,15 +698,8 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
-    {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
     {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
-    {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
-    {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
-    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
-    {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
-    {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
-    {file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
     {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
     {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
     {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
@@ -505,7 +716,6 @@ files = [
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
-    {file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
     {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
     {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
     {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
@@ -513,7 +723,6 @@ files = [
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
-    {file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
     {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
     {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
     {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
@@ -550,6 +759,17 @@ docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments
 testing = ["build[virtualenv]", "filelock (>=3.4.0)", "flake8-2020", "ini2toml[lite] (>=0.9)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pip (>=19.1)", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy (>=0.9.1)", "pytest-perf", "pytest-ruff", "pytest-timeout", "pytest-xdist", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
 testing-integration = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "packaging (>=23.1)", "pytest", "pytest-enabler", "pytest-xdist", "tomli", "virtualenv (>=13.0.0)", "wheel"]
 
+[[package]]
+name = "six"
+version = "1.16.0"
+description = "Python 2 and 3 compatibility utilities"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
+files = [
+    {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
+    {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
+]
+
 [[package]]
 name = "toml"
 version = "0.10.2"
@@ -561,6 +781,17 @@ files = [
     {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
 ]
 
+[[package]]
+name = "tzdata"
+version = "2023.3"
+description = "Provider of IANA time zone data"
+optional = false
+python-versions = ">=2"
+files = [
+    {file = "tzdata-2023.3-py2.py3-none-any.whl", hash = "sha256:7e65763eef3120314099b6939b5546db7adce1e7d6f2e179e3df563c70511eda"},
+    {file = "tzdata-2023.3.tar.gz", hash = "sha256:11ef1e08e54acb0d4f95bdb1be05da659673de4acbd21bf9c69e94cc5e907a3a"},
+]
+
 [[package]]
 name = "virtualenv"
 version = "20.24.6"
@@ -584,4 +815,4 @@ test = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "coverage-enable-subprocess
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.11,<3.13"
-content-hash = "a20684012fd755c517c0928a6d5f204587c0dba67f64680a5f72e3e71352cc57"
+content-hash = "f9932f087b8f6044380421db8941ce8bce765407af2a31f2f3f57f3769ea74ac"
diff --git a/pyproject.toml b/pyproject.toml
index 641ffd9..38d0011 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,6 +4,7 @@ version = "0.0.0"
 description = "Code for collection/generation of text for tts data collection"
 authors = [
     "Anders Jess Pedersen <anders.j.pedersen@alexandra.dk>",
+    "Dan Saattrup Nielsen <dan.nielsen@alexandra.dk>",
 ]
 readme = "README.md"
 license = "MIT"
@@ -11,6 +12,8 @@ license = "MIT"
 [tool.poetry.dependencies]
 python = ">=3.11,<3.13"
 hydra-core = "^1.3.2"
+lxml = "^4.9.3"
+pandas = "^2.1.1"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^7.4.2"
diff --git a/src/scripts/build_tts_dataset.py b/src/scripts/build_tts_dataset.py
new file mode 100644
index 0000000..69fed69
--- /dev/null
+++ b/src/scripts/build_tts_dataset.py
@@ -0,0 +1,50 @@
+"""Build the Danish text-to-speech dataset."""
+
+from tts_text.dates import build_date_dataset
+from tts_text.times import build_time_dataset
+from tts_text.bus_stops_and_stations import build_bus_stop_and_station_dataset
+from tts_text.utils import interleave_datasets
+import hydra
+from omegaconf import DictConfig
+from pathlib import Path
+import logging
+
+
+logger = logging.getLogger(__name__)
+
+
+@hydra.main(config_path="../../config", config_name="config", version_base=None)
+def main(config: DictConfig) -> None:
+    """Build the Danish text-to-speech dataset.
+
+    Args:
+        config: The Hydra configuration.
+    """
+    # Get the individual datasets
+    raw_dir = Path(config.dirs.data) / config.dirs.raw
+    date_dataset = build_date_dataset(output_dir=raw_dir)
+    time_dataset = build_time_dataset(output_dir=raw_dir)
+    bus_stops_and_stations = build_bus_stop_and_station_dataset(output_dir=raw_dir)
+
+    # Combine the datasets
+    sampling_probabilities = config.sampling_probabilities
+    dataset_itr = interleave_datasets(
+        datasets=[date_dataset, time_dataset, bus_stops_and_stations],
+        sampling_probabilities=[
+            sampling_probabilities.dates,
+            sampling_probabilities.times,
+            sampling_probabilities.bus_stops_and_stations,
+        ],
+    )
+
+    # Save the dataset
+    dataset_path = Path(config.dirs.data) / config.dirs.processed / "dataset.txt"
+    dataset_path.unlink(missing_ok=True)
+    with dataset_path.open("a") as f:
+        for sample in dataset_itr:
+            f.write(sample + "\n")
+    logger.info(f"Saved dataset to {dataset_path}.")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/src/scripts/your_script.py b/src/scripts/your_script.py
deleted file mode 100644
index 827add9..0000000
--- a/src/scripts/your_script.py
+++ /dev/null
@@ -1,24 +0,0 @@
-"""Main script for your project.
-
-Usage:
-    python src/scripts/your_script.py <config_key>=<config_value> ...
-"""
-
-import hydra
-from omegaconf import DictConfig
-
-from tts_text.your_module import example_function
-
-
-@hydra.main(config_path="../../config", config_name="config", version_base=None)
-def main(config: DictConfig) -> None:
-    """Main function for your project.
-
-    Args:
-        config: The Hydra config for your project.
-    """
-    example_function(config=config)
-
-
-if __name__ == "__main__":
-    main()
diff --git a/src/tts_text/bus_stops_and_stations.py b/src/tts_text/bus_stops_and_stations.py
new file mode 100644
index 0000000..c679835
--- /dev/null
+++ b/src/tts_text/bus_stops_and_stations.py
@@ -0,0 +1,34 @@
+"""Building a list of Danish bus stops and stations."""
+
+from pathlib import Path
+import pandas as pd
+import re
+
+
+def build_bus_stop_and_station_dataset(output_dir: Path | str) -> list[str]:
+    """Builds a list of all bus stops and stations in Denmark.
+
+    Args:
+        output_dir: The directory to save the dataset to.
+
+    Returns:
+        A list of all bus stops and stations in Denmark.
+    """
+    # Extract the table with all bus stops and stations from the website
+    table = pd.read_html("https://danskejernbaner.dk/vis.stations.oversigt.php")[0]
+
+    # Extract the list of bus stops and stations from the table, and clean them up
+    dataset = table["Stationens navn"].tolist()
+    dataset = list(
+        {
+            re.sub(r"\(.+\)|\[.+\]", "", bus_stop_or_station).strip()
+            for bus_stop_or_station in dataset
+        }
+    )
+
+    # Save the dataset
+    dataset_path = Path(output_dir) / "bus_stops_and_stations.txt"
+    with dataset_path.open("w") as f:
+        f.write("\n".join(dataset))
+
+    return dataset
diff --git a/src/tts_text/dates.py b/src/tts_text/dates.py
new file mode 100644
index 0000000..452d741
--- /dev/null
+++ b/src/tts_text/dates.py
@@ -0,0 +1,47 @@
+"""Building a list of Danish dates."""
+
+from pathlib import Path
+import random
+
+
+DAYS = [f"{numeral}." for numeral in range(1, 32)]
+MONTHS = [
+    "Januar",
+    "Februar",
+    "Marts",
+    "April",
+    "Maj",
+    "Juni",
+    "Juli",
+    "August",
+    "September",
+    "Oktober",
+    "November",
+    "December",
+]
+YEARS = [year for year in range(1970, 2030)]
+
+
+def build_date_dataset(output_dir: Path | str) -> list[str]:
+    """Build the date dataset.
+
+    Args:
+        output_dir: The directory to save the dataset to.
+
+    Returns:
+        A list of strings representing dates in Danish.
+    """
+    # Build the dataset
+    dataset: list[str] = list()
+    dataset.extend(
+        [f"{day} {month} {year}" for day in DAYS for month in MONTHS for year in YEARS]
+    )
+    dataset.extend([f"{day} {month}" for day in DAYS for month in MONTHS])
+    random.shuffle(dataset)
+
+    # Save the dataset
+    dataset_path = Path(output_dir) / "dates.txt"
+    with dataset_path.open("w") as f:
+        f.write("\n".join(dataset))
+
+    return dataset
diff --git a/src/tts_text/times.py b/src/tts_text/times.py
new file mode 100644
index 0000000..69127f6
--- /dev/null
+++ b/src/tts_text/times.py
@@ -0,0 +1,62 @@
+"""Building a list of Danish times."""
+
+from pathlib import Path
+import random
+
+
+MINUTES = list(range(0, 60))
+HOURS = list(range(0, 24))
+HOUR_PREFIXES = [
+    "Fem i",
+    "Fem over",
+    "Ti i",
+    "Ti over",
+    "Kvart i",
+    "Kvart over",
+    "Tyve i",
+    "Tyve over",
+    "Halv",
+]
+HOUR_STRINGS = [
+    "et",
+    "to",
+    "tre",
+    "fire",
+    "fem",
+    "seks",
+    "syv",
+    "otte",
+    "ni",
+    "ti",
+    "elleve",
+    "tolv",
+]
+
+
+def build_time_dataset(output_dir: Path | str) -> list[str]:
+    """Build the time dataset.
+
+    Args:
+        output_dir: The directory to save the dataset to.
+
+    Returns:
+        A list of strings representing times in Danish.
+    """
+    # Build the dataset
+    dataset: list[str] = list()
+    dataset.extend([f"{hour:02}:{minute:02}" for hour in HOURS for minute in MINUTES])
+    dataset.extend(
+        [
+            f"{hour_prefix} {hour_str}"
+            for hour_str in HOUR_STRINGS
+            for hour_prefix in HOUR_PREFIXES
+        ]
+    )
+    random.shuffle(dataset)
+
+    # Save the dataset
+    dataset_path = Path(output_dir) / "times.txt"
+    with dataset_path.open("w") as f:
+        f.write("\n".join(dataset))
+
+    return dataset
diff --git a/src/tts_text/utils.py b/src/tts_text/utils.py
new file mode 100644
index 0000000..5949a93
--- /dev/null
+++ b/src/tts_text/utils.py
@@ -0,0 +1,36 @@
+"""Utility functions used by the other modules."""
+
+from typing import Generator
+import numpy as np
+import random
+
+
+def interleave_datasets(
+    datasets: list[list[str]], sampling_probabilities: list[float]
+) -> Generator[str, None, None]:
+    """Interleave multiple datasets according to the given sampling probabilities.
+
+    Args:
+        datasets: The datasets to interleave.
+        sampling_probabilities: The sampling probabilities for each dataset.
+
+    Yields:
+        The interleaved dataset.
+    """
+    while True:
+        # Sample a dataset
+        dataset_idx = np.random.choice(len(datasets), p=sampling_probabilities)
+        dataset = datasets[dataset_idx]
+
+        # If the dataset is empty then stop
+        if len(dataset) == 0:
+            return
+
+        # Sample a sample from the dataset
+        sample_idx = random.randrange(len(dataset))
+        sample = dataset[sample_idx]
+
+        # Remove the sample from the dataset
+        dataset.pop(sample_idx)
+
+        yield sample
diff --git a/src/tts_text/your_module.py b/src/tts_text/your_module.py
deleted file mode 100644
index 33a99eb..0000000
--- a/src/tts_text/your_module.py
+++ /dev/null
@@ -1,17 +0,0 @@
-"""An example module for your project."""
-
-from omegaconf import DictConfig
-import logging
-
-
-logger = logging.getLogger(__name__)
-
-
-def example_function(config: DictConfig) -> None:
-    """An example function for your project.
-
-    Args:
-        config: The Hydra config for your project.
-    """
-    logger.info("Hello World!")
-    logger.info(f"Your config is: {config}")