fix prefect code and add ds bootcamp

Rafia-Shaikh-eng · Dec 21, 2021 · 6b0f17e · 6b0f17e
1 parent b6aaedd
commit 6b0f17e
Show file tree

Hide file tree

Showing 8 changed files with 9,224 additions and 1,377 deletions.
diff --git a/.gitignore b/.gitignore
@@ -143,3 +143,4 @@ dmypy.json
 .pyre/
 .config
 
+
diff --git a/data_science_tools/prefect_example/data/processed/Mon_Dec_20_2021_20:55:20/split_data_output b/data_science_tools/prefect_example/data/processed/Mon_Dec_20_2021_20:55:20/split_data_output
diff --git a/...n_Dec_20_2021_20:55:20/get_classes_output → ...e_Dec_21_2021_16-26-44/get_classes_output b/...n_Dec_20_2021_20:55:20/get_classes_output → ...e_Dec_21_2021_16-26-44/get_classes_output
diff --git a/data_science_tools/prefect_example/data/processed/Tue_Dec_21_2021_16-26-44/split_data_output b/data_science_tools/prefect_example/data/processed/Tue_Dec_21_2021_16-26-44/split_data_output
diff --git a/data_science_tools/prefect_example/data_engineering.py b/data_science_tools/prefect_example/data_engineering.py
@@ -14,7 +14,7 @@ def load_data(path: str) -> pd.DataFrame:
     return pd.read_csv(path)
 
 
-@task(target="{date:%a_%b_%d_%Y_%H:%M:%S}/{task_name}_output", result = LocalResult(dir='data/processed'))
+@task(target="{date:%a_%b_%d_%Y_%H-%M-%S}/{task_name}_output", result = LocalResult(dir='data/processed'))
 def get_classes(data: pd.DataFrame, target_col: str) -> List[str]:
     """Task for getting the classes from the Iris data set."""
     return sorted(data[target_col].unique())
@@ -27,7 +27,7 @@ def encode_categorical_columns(data: pd.DataFrame, target_col: str) -> pd.DataFr
     return pd.get_dummies(data, columns=[target_col], prefix="", prefix_sep="")
 
 
-@task(log_stdout=True, target="{date:%a_%b_%d_%Y_%H:%M:%S}/{task_name}_output", result = LocalResult(dir='data/processed'))
+@task(log_stdout=True, target="{date:%a_%b_%d_%Y_%H-%M-%S}/{task_name}_output", result = LocalResult(dir='data/processed'))
 def split_data(data: pd.DataFrame, test_data_ratio: float, classes: list) -> Dict[str, Any]:
     """Task for splitting the classical Iris data set into training and test
     sets, each split into features and labels.