From 315223d19909ff78e50c028ac3da745070d6662d Mon Sep 17 00:00:00 2001 From: s464962 Date: Tue, 28 May 2024 23:09:18 +0200 Subject: [PATCH] IUM_10 --- .dvc/.gitignore | 3 +++ .dvc/config | 4 ++++ .dvcignore | 3 +++ data/car_prices.csv.dvc | 5 +++++ dvc.yaml | 27 +++++++++++++++++++++++++++ 5 files changed, 42 insertions(+) create mode 100644 .dvc/.gitignore create mode 100644 .dvc/config create mode 100644 .dvcignore create mode 100644 data/car_prices.csv.dvc create mode 100644 dvc.yaml diff --git a/.dvc/.gitignore b/.dvc/.gitignore new file mode 100644 index 0000000..69f937a --- /dev/null +++ b/.dvc/.gitignore @@ -0,0 +1,3 @@ +/config.local +/tmp +/cache diff --git a/.dvc/config b/.dvc/config new file mode 100644 index 0000000..3a7ae37 --- /dev/null +++ b/.dvc/config @@ -0,0 +1,4 @@ +[core] + remote = ium_ssh_remote +['remote "ium_ssh_remote"'] + url = ssh://ium-sftp@tzietkiewicz.vm.wmi.amu.edu.pl \ No newline at end of file diff --git a/.dvcignore b/.dvcignore new file mode 100644 index 0000000..2ccdbc9 --- /dev/null +++ b/.dvcignore @@ -0,0 +1,3 @@ +# Add patterns of files dvc should ignore, which could improve +# the performance. Learn more at +# https://dvc.org/doc/user-guide/dvcignore diff --git a/data/car_prices.csv.dvc b/data/car_prices.csv.dvc new file mode 100644 index 0000000..b2da8f4 --- /dev/null +++ b/data/car_prices.csv.dvc @@ -0,0 +1,5 @@ +outs: +- md5: e600483fd4125216e9bfdc962f26565f + size: 88047552 + hash: md5 + path: car_prices.csv diff --git a/dvc.yaml b/dvc.yaml new file mode 100644 index 0000000..654b69d --- /dev/null +++ b/dvc.yaml @@ -0,0 +1,27 @@ +stages: + download: + cmd: bash create-dataset.sh 10000 + deps: + - create-dataset.sh + outs: + - data/car_prices.csv + - data/car_prices_test.csv + - data/car_prices_dev.csv + - data/car_prices_train.csv + + train: + cmd: python model.py + deps: + - model.py + - data/car_prices_train.csv + outs: + - car_prices_predict_model.h5 + + predict: + cmd: python predict.py + deps: + - predict.py + - data/car_prices_test.csv + - car_prices_predict_model.h5 + outs: + - predicted_selling_prices.csv