From 7b99dd547dde5ad81e62d5e529ffc9d0131588c4 Mon Sep 17 00:00:00 2001 From: Gianatmaja Date: Fri, 17 Nov 2023 15:16:23 +0800 Subject: [PATCH] Updated README.md --- README.md | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 62873d5..b2c513c 100644 --- a/README.md +++ b/README.md @@ -85,9 +85,14 @@ To use WhizML in your data science project, perform the following steps: curl -LJO https://https://github.com/Gianatmaja/WhizML/archive/vX.Y.Z.zip ``` -2. Place your raw data file in the `data/raw/` directory, and fill-in the `config.yml` file. +2. To install the requirements, run the following command: -3. Run the `eda` pipeline to determine the required data-preprocessing. +```bash +pip install -r requirements.txt +``` +3. Place your raw data file in the `data/raw/` directory, and fill-in the `config.yml` file. + +4. Run the `eda` pipeline to determine the required data-preprocessing. ```YAML task: @@ -99,11 +104,11 @@ task: data_drift_analysis: ``` -4. Develop the requried data-preprocessing steps to obtain the train and test set data. +5. Develop the requried data-preprocessing steps to obtain the train and test set data. -5. Run the `model_experimentation` pipeline and determine the best model. +6. Run the `model_experimentation` pipeline and determine the best model. -6. Paste the run url (from Wandb) of the best model to the `config.yml` file. +7. Paste the run url (from Wandb) of the best model to the `config.yml` file. ```YAML task: @@ -113,7 +118,7 @@ wandb: best_model_url: ``` -7. Run the rest of the pipelines as needed. +8. Run the rest of the pipelines as needed. ```bash python main.py