Start to implement prediction

poetry.lock

@@ -821,6 +821,71 @@ files = [
     {file = "nodeenv-1.9.1.tar.gz", hash = "sha256:6ec12890a2dab7946721edbfbcd91f3319c6ccc9aec47be7c7e6b7011ee6645f"},
 ]
 
+[[package]]
+name = "numpy"
+version = "2.2.3"
+description = "Fundamental package for array computing in Python"
+optional = false
+python-versions = ">=3.10"
+groups = ["main"]
+files = [
+    {file = "numpy-2.2.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:cbc6472e01952d3d1b2772b720428f8b90e2deea8344e854df22b0618e9cce71"},
+    {file = "numpy-2.2.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:cdfe0c22692a30cd830c0755746473ae66c4a8f2e7bd508b35fb3b6a0813d787"},
+    {file = "numpy-2.2.3-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:e37242f5324ffd9f7ba5acf96d774f9276aa62a966c0bad8dae692deebec7716"},
+    {file = "numpy-2.2.3-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:95172a21038c9b423e68be78fd0be6e1b97674cde269b76fe269a5dfa6fadf0b"},
+    {file = "numpy-2.2.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d5b47c440210c5d1d67e1cf434124e0b5c395eee1f5806fdd89b553ed1acd0a3"},
+    {file = "numpy-2.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0391ea3622f5c51a2e29708877d56e3d276827ac5447d7f45e9bc4ade8923c52"},
+    {file = "numpy-2.2.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:f6b3dfc7661f8842babd8ea07e9897fe3d9b69a1d7e5fbb743e4160f9387833b"},
+    {file = "numpy-2.2.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:1ad78ce7f18ce4e7df1b2ea4019b5817a2f6a8a16e34ff2775f646adce0a5027"},
+    {file = "numpy-2.2.3-cp310-cp310-win32.whl", hash = "sha256:5ebeb7ef54a7be11044c33a17b2624abe4307a75893c001a4800857956b41094"},
+    {file = "numpy-2.2.3-cp310-cp310-win_amd64.whl", hash = "sha256:596140185c7fa113563c67c2e894eabe0daea18cf8e33851738c19f70ce86aeb"},
+    {file = "numpy-2.2.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:16372619ee728ed67a2a606a614f56d3eabc5b86f8b615c79d01957062826ca8"},
+    {file = "numpy-2.2.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:5521a06a3148686d9269c53b09f7d399a5725c47bbb5b35747e1cb76326b714b"},
+    {file = "numpy-2.2.3-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:7c8dde0ca2f77828815fd1aedfdf52e59071a5bae30dac3b4da2a335c672149a"},
+    {file = "numpy-2.2.3-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:77974aba6c1bc26e3c205c2214f0d5b4305bdc719268b93e768ddb17e3fdd636"},
+    {file = "numpy-2.2.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d42f9c36d06440e34226e8bd65ff065ca0963aeecada587b937011efa02cdc9d"},
+    {file = "numpy-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f2712c5179f40af9ddc8f6727f2bd910ea0eb50206daea75f58ddd9fa3f715bb"},
+    {file = "numpy-2.2.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c8b0451d2ec95010d1db8ca733afc41f659f425b7f608af569711097fd6014e2"},
+    {file = "numpy-2.2.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:d9b4a8148c57ecac25a16b0e11798cbe88edf5237b0df99973687dd866f05e1b"},
+    {file = "numpy-2.2.3-cp311-cp311-win32.whl", hash = "sha256:1f45315b2dc58d8a3e7754fe4e38b6fce132dab284a92851e41b2b344f6441c5"},
+    {file = "numpy-2.2.3-cp311-cp311-win_amd64.whl", hash = "sha256:9f48ba6f6c13e5e49f3d3efb1b51c8193215c42ac82610a04624906a9270be6f"},
+    {file = "numpy-2.2.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:12c045f43b1d2915eca6b880a7f4a256f59d62df4f044788c8ba67709412128d"},
+    {file = "numpy-2.2.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:87eed225fd415bbae787f93a457af7f5990b92a334e346f72070bf569b9c9c95"},
+    {file = "numpy-2.2.3-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:712a64103d97c404e87d4d7c47fb0c7ff9acccc625ca2002848e0d53288b90ea"},
+    {file = "numpy-2.2.3-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:a5ae282abe60a2db0fd407072aff4599c279bcd6e9a2475500fc35b00a57c532"},
+    {file = "numpy-2.2.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5266de33d4c3420973cf9ae3b98b54a2a6d53a559310e3236c4b2b06b9c07d4e"},
+    {file = "numpy-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3b787adbf04b0db1967798dba8da1af07e387908ed1553a0d6e74c084d1ceafe"},
+    {file = "numpy-2.2.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:34c1b7e83f94f3b564b35f480f5652a47007dd91f7c839f404d03279cc8dd021"},
+    {file = "numpy-2.2.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:4d8335b5f1b6e2bce120d55fb17064b0262ff29b459e8493d1785c18ae2553b8"},
+    {file = "numpy-2.2.3-cp312-cp312-win32.whl", hash = "sha256:4d9828d25fb246bedd31e04c9e75714a4087211ac348cb39c8c5f99dbb6683fe"},
+    {file = "numpy-2.2.3-cp312-cp312-win_amd64.whl", hash = "sha256:83807d445817326b4bcdaaaf8e8e9f1753da04341eceec705c001ff342002e5d"},
+    {file = "numpy-2.2.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:7bfdb06b395385ea9b91bf55c1adf1b297c9fdb531552845ff1d3ea6e40d5aba"},
+    {file = "numpy-2.2.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:23c9f4edbf4c065fddb10a4f6e8b6a244342d95966a48820c614891e5059bb50"},
+    {file = "numpy-2.2.3-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:a0c03b6be48aaf92525cccf393265e02773be8fd9551a2f9adbe7db1fa2b60f1"},
+    {file = "numpy-2.2.3-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:2376e317111daa0a6739e50f7ee2a6353f768489102308b0d98fcf4a04f7f3b5"},
+    {file = "numpy-2.2.3-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8fb62fe3d206d72fe1cfe31c4a1106ad2b136fcc1606093aeab314f02930fdf2"},
+    {file = "numpy-2.2.3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:52659ad2534427dffcc36aac76bebdd02b67e3b7a619ac67543bc9bfe6b7cdb1"},
+    {file = "numpy-2.2.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:1b416af7d0ed3271cad0f0a0d0bee0911ed7eba23e66f8424d9f3dfcdcae1304"},
+    {file = "numpy-2.2.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:1402da8e0f435991983d0a9708b779f95a8c98c6b18a171b9f1be09005e64d9d"},
+    {file = "numpy-2.2.3-cp313-cp313-win32.whl", hash = "sha256:136553f123ee2951bfcfbc264acd34a2fc2f29d7cdf610ce7daf672b6fbaa693"},
+    {file = "numpy-2.2.3-cp313-cp313-win_amd64.whl", hash = "sha256:5b732c8beef1d7bc2d9e476dbba20aaff6167bf205ad9aa8d30913859e82884b"},
+    {file = "numpy-2.2.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:435e7a933b9fda8126130b046975a968cc2d833b505475e588339e09f7672890"},
+    {file = "numpy-2.2.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:7678556eeb0152cbd1522b684dcd215250885993dd00adb93679ec3c0e6e091c"},
+    {file = "numpy-2.2.3-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:2e8da03bd561504d9b20e7a12340870dfc206c64ea59b4cfee9fceb95070ee94"},
+    {file = "numpy-2.2.3-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:c9aa4496fd0e17e3843399f533d62857cef5900facf93e735ef65aa4bbc90ef0"},
+    {file = "numpy-2.2.3-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f4ca91d61a4bf61b0f2228f24bbfa6a9facd5f8af03759fe2a655c50ae2c6610"},
+    {file = "numpy-2.2.3-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:deaa09cd492e24fd9b15296844c0ad1b3c976da7907e1c1ed3a0ad21dded6f76"},
+    {file = "numpy-2.2.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:246535e2f7496b7ac85deffe932896a3577be7af8fb7eebe7146444680297e9a"},
+    {file = "numpy-2.2.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:daf43a3d1ea699402c5a850e5313680ac355b4adc9770cd5cfc2940e7861f1bf"},
+    {file = "numpy-2.2.3-cp313-cp313t-win32.whl", hash = "sha256:cf802eef1f0134afb81fef94020351be4fe1d6681aadf9c5e862af6602af64ef"},
+    {file = "numpy-2.2.3-cp313-cp313t-win_amd64.whl", hash = "sha256:aee2512827ceb6d7f517c8b85aa5d3923afe8fc7a57d028cffcd522f1c6fd082"},
+    {file = "numpy-2.2.3-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:3c2ec8a0f51d60f1e9c0c5ab116b7fc104b165ada3f6c58abf881cb2eb16044d"},
+    {file = "numpy-2.2.3-pp310-pypy310_pp73-macosx_14_0_x86_64.whl", hash = "sha256:ed2cf9ed4e8ebc3b754d398cba12f24359f018b416c380f577bbae112ca52fc9"},
+    {file = "numpy-2.2.3-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:39261798d208c3095ae4f7bc8eaeb3481ea8c6e03dc48028057d3cbdbdb8937e"},
+    {file = "numpy-2.2.3-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:783145835458e60fa97afac25d511d00a1eca94d4a8f3ace9fe2043003c678e4"},
+    {file = "numpy-2.2.3.tar.gz", hash = "sha256:dbdc15f0c81611925f382dfa97b3bd0bc2c1ce19d4fe50482cb0ddc12ba30020"},
+]
+
 [[package]]
 name = "packaging"
 version = "24.2"
@@ -1614,4 +1679,4 @@ watchdog = ["watchdog (>=2.3)"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.12,<4.0"
-content-hash = "b628f92560d4625be8cc0fedb426c0771b1c9a9c389f74fb9929bfaef0501d0b"
+content-hash = "b32ba1ec8fded698aa3d69272d543bf383c844a57fc307558ebd1de6a11c7120"

pyproject.toml

@@ -16,7 +16,8 @@ dependencies = [
     "fava (>=1.30.1,<2.0.0)",
     "pydantic (>=2.10.6,<3.0.0)",
     "beancount (>=3.1.0,<4.0.0)",
-    "rich (>=13.9.4,<14.0.0)"
+    "rich (>=13.9.4,<14.0.0)",
+    "numpy (>=2.2.3,<3.0.0)"
 ]
 
 [tool.poetry.group.dev.dependencies]

src/toldg/__main__.py

@@ -1,8 +1,10 @@
 import logging
+import sys
 
 from rich.logging import RichHandler
 
 from toldg.process import process_csv_files, process_ldg_files
+from toldg.train import train
 from toldg.utils import load_config, remove_if_exists, write_meta
 
 
@@ -18,10 +20,13 @@ def init_logging():
 def main():
     init_logging()
     config = load_config()
-    remove_if_exists(config.output_file)
+    if len(sys.argv) > 2 and sys.argv[2] == "train":
-    write_meta(config)
+        train(config)
-    process_ldg_files(config)
+    else:
-    process_csv_files(config)
+        remove_if_exists(config.output_file)
+        write_meta(config)
+        process_ldg_files(config)
+        process_csv_files(config)
 
 
 if __name__ == "__main__":

src/toldg/process.py

@@ -82,7 +82,7 @@ def apply_mappings(transactions: List[Transaction], mappings: Dict[str, Mapping]
         assert mapping.count == 0, f"{mapping} was not used as often as expected!"
 
 
-def process_csv_files(config: Config):
+def process_csv_files(config: Config) -> List[Transaction]:
     csv_files = toldg.utils.get_csv_files(config.input_directory)
     transactions = []
     for csv_file in csv_files:
@@ -95,3 +95,4 @@ def process_csv_files(config: Config):
     toldg.predict.add_account2(transactions, config.categories)
     toldg.utils.write_mappings(transactions, config.mappings_file)
     toldg.write.render_to_file(transactions, config)
+    return transactions

src/toldg/train.py

@@ -0,0 +1,9 @@
+from toldg.models import Config, CsvConfig, Mapping, Transaction
+from toldg.process import process_csv_files
+
+
+def train(config: Config):
+    print("[train] start")
+    transactions = process_csv_files(config)
+    for t in transactions:
+        pass