This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# in <root>/src/<project>/pipeline_registry.py | |
def register_pipelines() -> Dict[str, Pipeline]: | |
data_engineering_pipeline = de.create_pipeline() | |
xgb_pipe = ds.create_xgb_pipeline() | |
rr_pipe = ds.create_rr_pipeline() | |
logres_pipe = ds.create_logres_pipeline() | |
rr_ho_pipe = ds.create_rr_ho_pipeline() | |
return { |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# in <root>/src/<project>/pipelines/data_science/pipeline.py | |
from kedro.pipeline import node, pipeline | |
from .nodes import split_data, fit_xgboost | |
def create_plot_roc_node(): | |
return node( | |
func=plot_roc, | |
inputs=["clf", "X_test", "y_test"], | |
outputs="roc_graph", |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# in <root>/src/<project>/pipelines/data_science/nodes.py | |
def rr_objective(X_train: pd.DataFrame, y_train: pd.Series, | |
X_test: pd.DataFrame, y_test: pd.Series, | |
trial: optuna.trial): | |
max_depth = trial.suggest_int("max_depth", 8, 64, log=True) | |
min_samples_split = trial.suggest_int("min_samples_split", 50, 1000, ) | |
ccp_alpha = trial.suggest_float("ccp_alpha", 0.001, 0.03, log=True) | |
rr_clf = RandomForestClassifier(max_depth=max_depth, | |
min_samples_split=min_samples_split, |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# in <root>/conf/base/catalog.yaml | |
insurance: | |
type: pandas.CSVDataSet | |
filepath: data/01_raw/train.csv | |
layer: raw | |
model_input_table: | |
type: pandas.ParquetDataSet | |
filepath: data/03_primary/model_input_table.pq |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# (1) virtual environment | |
conda activate kedro-env | |
pip install kedro kedro-mlflow optuna kedro-viz | |
# (2) new project with starter | |
# put anything, for me, I wrote 'tutorial' | |
kedro new --starter=pandas-iris | |
cd tutorial | |
# (3) fire up git. The starter already has a gitignore file and |
NewerOlder