jakew/data-science-research
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add Kaggle feature engineering course

Browse source
This commit is contained in:
Jake Walker 2024-02-23 11:00:34 +00:00
parent f1b466a4a6
commit 48cc096617
16 changed files with 1328 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
kaggle_feature_engineering/.gitattributes vendored Normal file
View file

@ -0,0 +1 @@
data/* filter=lfs diff=lfs merge=lfs -text

BIN
kaggle_feature_engineering/data/abalone.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:b21020af9e01fc7e003fb30056c4ba7837eb151b432865766ec2d2a194c47c4b
3 size 216903

BIN
kaggle_feature_engineering/data/accidents.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:afbf3b0b9714fde81531add594ceaaeee94b78e84d5b094cc68cdd655a4c219a
3 size 21358170

BIN
kaggle_feature_engineering/data/airbnb.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:e420db40ff10fcb40efc1b5b1648ee0b18a48f4e4537155cecc59fe95d18783a
3 size 7077973

BIN
kaggle_feature_engineering/data/ames.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:433d33973067190aab972cff60ec77478427a300bfdd57747406b85624edd9b6
3 size 1465815

BIN
kaggle_feature_engineering/data/autos.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:421edd11257cbe2f69ec1e40e7c1ff84c1ebc5b436162f76edc20acad92028f7
3 size 21637

BIN
kaggle_feature_engineering/data/bike-sharing.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:e03de4ee4ef4dc376ac6e04bf829673c6269e8eba5c60fa121640fa2f829504f
3 size 1156736

BIN
kaggle_feature_engineering/data/caravan.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:5d5bdca1be0b9a6c012b93a8c8104761201bd70f7e08764fa67f2cfb26243723
3 size 1011973

BIN
kaggle_feature_engineering/data/concrete.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:901749b7e40a90657777fb0a88489638f2d9f80546e72b28cf720a2fdd778a76
3 size 48486

BIN
kaggle_feature_engineering/data/customer.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:055ef09502c9f2a95cd94868ccb8795e6dbad24ee95d8afdb38dae25d7a05214
3 size 1644739

BIN
kaggle_feature_engineering/data/housing.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:0e4a0bc8b337d88c95259a8ec05a58c662f26f87487f9cbf2448fe93207bcb5c
3 size 1959699

BIN
kaggle_feature_engineering/data/movielens1m.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:89b0a6acdbffa9c3601cc233c09e119e40b5fe7b26679cf6b24ad88a4845c50b
3 size 76245897

BIN
kaggle_feature_engineering/data/spotify.csv (Stored with Git LFS) Normal file
View file

Binary file not shown.
1 version https://git-lfs.github.com/spec/v1
2 oid sha256:9902920cfe4940f0914ebb6716801a42f7f19ac88fbd6693eaae7e2822b16845
3 size 7971379

1
kaggle_feature_engineering/mutual_information.ipynb Normal file
View file

File diff suppressed because one or more lines are too long

1268
kaggle_feature_engineering/poetry.lock generated Normal file
View file

File diff suppressed because it is too large Load diff

22
kaggle_feature_engineering/pyproject.toml Normal file
View file

@ -0,0 +1,22 @@
[tool.poetry]
name = "kaggle-feature-engineering"
version = "0.1.0"
description = ""
authors = ["Jake Walker <hi@jakew.me>"]
license = "UNLICENSED"
readme = "README.md"
[tool.poetry.dependencies]
python = "^3.11"
pandas = "^2.2.0"
scikit-learn = "^1.4.0"
numpy = "^1.26.3"
ipykernel = "^6.29.0"
[tool.poetry.group.optional.dependencies]
kaggle = "^1.6.4"
flake8 = "^7.0.0"
[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"