-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
4 changed files
with
159 additions
and
0 deletions.
There are no files selected for viewing
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,118 @@ | ||
| columns: | ||
| - Elevation: int | ||
| - Aspect: int | ||
| - Slope: int | ||
| - Horizontal_Distance_To_Hydrology: int | ||
| - Vertical_Distance_To_Hydrology: int | ||
| - Horizontal_Distance_To_Roadways: int | ||
| - Horizontal_Distance_To_Fire_Points: int | ||
| - Hillshade_9am: int | ||
| - Hillshade_Noon: int | ||
| - Hillshade_3pm: int | ||
| - Wilderness_Area1: int | ||
| - Wilderness_Area2: int | ||
| - Wilderness_Area3: int | ||
| - Wilderness_Area4: int | ||
| - Soil_Type1: int | ||
| - Soil_Type2: int | ||
| - Soil_Type3: int | ||
| - Soil_Type4: int | ||
| - Soil_Type5: int | ||
| - Soil_Type6: int | ||
| - Soil_Type8: int | ||
| - Soil_Type9: int | ||
| - Soil_Type10: int | ||
| - Soil_Type11: int | ||
| - Soil_Type12: int | ||
| - Soil_Type13: int | ||
| - Soil_Type14: int | ||
| - Soil_Type15: int | ||
| - Soil_Type16: int | ||
| - Soil_Type17: int | ||
| - Soil_Type18: int | ||
| - Soil_Type19: int | ||
| - Soil_Type20: int | ||
| - Soil_Type21: int | ||
| - Soil_Type22: int | ||
| - Soil_Type23: int | ||
| - Soil_Type24: int | ||
| - Soil_Type25: int | ||
| - Soil_Type26: int | ||
| - Soil_Type27: int | ||
| - Soil_Type28: int | ||
| - Soil_Type29: int | ||
| - Soil_Type30: int | ||
| - Soil_Type31: int | ||
| - Soil_Type32: int | ||
| - Soil_Type33: int | ||
| - Soil_Type34: int | ||
| - Soil_Type35: int | ||
| - Soil_Type36: int | ||
| - Soil_Type37: int | ||
| - Soil_Type38: int | ||
| - Soil_Type39: int | ||
| - Soil_Type40: int | ||
| - CoverType: category | ||
|
|
||
|
|
||
| numerical_columns: | ||
| - Elevation | ||
| - Aspect | ||
| - Slope | ||
| - Horizontal_Distance_To_Hydrology | ||
| - Vertical_Distance_To_Hydrology | ||
| - Horizontal_Distance_To_Roadways | ||
| - Horizontal_Distance_To_Fire_Points | ||
| - Hillshade_9am | ||
| - Hillshade_Noon | ||
| - Hillshade_3pm | ||
| - Wilderness_Area1 | ||
| - Wilderness_Area2 | ||
| - Wilderness_Area3 | ||
| - Wilderness_Area4 | ||
| - Soil_Type1 | ||
| - Soil_Type2 | ||
| - Soil_Type3 | ||
| - Soil_Type4 | ||
| - Soil_Type5 | ||
| - Soil_Type6 | ||
| - Soil_Type9 | ||
| - Soil_Type10 | ||
| - Soil_Type11 | ||
| - Soil_Type12 | ||
| - Soil_Type13 | ||
| - Soil_Type14 | ||
| - Soil_Type16 | ||
| - Soil_Type17 | ||
| - Soil_Type18 | ||
| - Soil_Type19 | ||
| - Soil_Type20 | ||
| - Soil_Type21 | ||
| - Soil_Type22 | ||
| - Soil_Type23 | ||
| - Soil_Type24 | ||
| - Soil_Type25 | ||
| - Soil_Type26 | ||
| - Soil_Type27 | ||
| - Soil_Type28 | ||
| - Soil_Type29 | ||
| - Soil_Type30 | ||
| - Soil_Type31 | ||
| - Soil_Type32 | ||
| - Soil_Type33 | ||
| - Soil_Type34 | ||
| - Soil_Type35 | ||
| - Soil_Type37 | ||
| - Soil_Type38 | ||
| - Soil_Type39 | ||
| - Soil_Type40 | ||
|
|
||
| categorical_columns: | ||
| - Cover_Type | ||
|
|
||
| drop_columns: | ||
| - Soil_Type7 | ||
| - Soil_Type8 | ||
| - Soil_Type15 | ||
| - Soil_Type36 | ||
|
|
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,19 @@ | ||
| import os | ||
| from from_root import from_root | ||
| from pathlib import Path | ||
|
|
||
| ## file names | ||
|
|
||
| FILE_NAME: str = "covertype.csv" | ||
| TRAIN_FILE_NAME: str = "train.csv" | ||
| TEST_FILE_NAME: str = "test.csv" | ||
| SCHEMA_FILE_PATH: Path = os.path.join("config", "schema.yaml") | ||
|
|
||
|
|
||
| ARTIFACT_DIR = os.path.join(from_root(), "artifacts") | ||
|
|
||
| ## Data Ingestion | ||
|
|
||
| DATA_INGESTION_DIR: str = "DataIngestion" | ||
| DATA_INGESTION_FEATURE_STORE: str = "feature_store" | ||
| DATA_INGESTION_TRAIN_TEST_SPLIT: float = 0.2 |
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,7 @@ | ||
| from dataclasses import dataclass | ||
|
|
||
|
|
||
| @dataclass | ||
| class DataIngestionArtifact: | ||
| trained_file_path:str | ||
| test_file_path:str |
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,15 @@ | ||
| from dataclasses import dataclass | ||
| from from_root import from_root | ||
| import os | ||
| from pathlib import Path | ||
| from forestCover.constants import (ARTIFACT_DIR, DATA_INGESTION_DIR, DATA_INGESTION_FEATURE_STORE, TRAIN_FILE_NAME, | ||
| TEST_FILE_NAME, DATA_INGESTION_TRAIN_TEST_SPLIT) | ||
|
|
||
|
|
||
| @dataclass | ||
| class DataIngestionConfig: | ||
| data_ingestion_dir: Path = os.path.join(ARTIFACT_DIR, DATA_INGESTION_DIR) | ||
| feature_store_path: Path = os.path.join(data_ingestion_dir, DATA_INGESTION_FEATURE_STORE) | ||
| train_file_path: Path = os.path.join(data_ingestion_dir, TRAIN_FILE_NAME) | ||
| test_file_path: Path = os.path.join(data_ingestion_dir, TEST_FILE_NAME) | ||
| train_test_ratio: float = DATA_INGESTION_TRAIN_TEST_SPLIT |