completed ticket

data/data-pipeline/data_pipeline/content/config/excel.yml

@@ -7,8 +7,7 @@ global_config:
   excel_config:
     default_column_width: 30
 sheets:
-  - main:
-    label: "Data"
+  - label: "Data"
     fields:
       - score_name: GEOID10_TRACT
         label: Census tract ID

data/data-pipeline/data_pipeline/content/schemas/csv.py

@@ -1,34 +0,0 @@
-from dataclasses import dataclass, field
-from enum import Enum
-from typing import List
-
-
-class FieldType(Enum):
-    STRING = "string"
-    INT64 = "int64"
-    BOOL = "bool"
-    FLOAT = "float"
-    PERCENTAGE = "percentage"
-    LOSS_RATE_PERCENTAGE = "loss_rate_percentage"
-
-
-@dataclass
-class CSVConfig:
-    @dataclass
-    class GlobalConfig:
-        @dataclass
-        class RoundingNum:
-            float: int
-            loss_rate_percentage: int
-
-        sort_by_label: str
-        rounding_num: RoundingNum
-
-    @dataclass
-    class Field:
-        score_name: str
-        label: str
-        format: FieldType = field(metadata={"by_value": True})
-
-    global_config: GlobalConfig
-    fields: List[Field]

data/data-pipeline/data_pipeline/content/schemas/download_schemas.py

@@ -0,0 +1,57 @@
+from dataclasses import dataclass, field
+from enum import Enum
+from typing import List
+
+
+class FieldType(Enum):
+    STRING = "string"
+    INT64 = "int64"
+    BOOL = "bool"
+    FLOAT = "float"
+    PERCENTAGE = "percentage"
+    LOSS_RATE_PERCENTAGE = "loss_rate_percentage"
+
+
+@dataclass
+class RoundingNum:
+    float: int
+    loss_rate_percentage: int
+
+
+@dataclass
+class Field:
+    score_name: str
+    label: str
+    format: FieldType = field(metadata={"by_value": True})
+
+
+@dataclass
+class CSVConfig:
+    @dataclass
+    class GlobalConfig:
+        sort_by_label: str
+        rounding_num: RoundingNum
+
+    global_config: GlobalConfig
+    fields: List[Field]
+
+
+@dataclass
+class ExcelConfig:
+    @dataclass
+    class GlobalConfig:
+        @dataclass
+        class ExcelGlobalConfig:
+            default_column_width: int
+
+        sort_by_label: str
+        rounding_num: RoundingNum
+        excel_config: ExcelGlobalConfig
+
+    @dataclass
+    class SheetItem:
+        label: str
+        fields: List[Field]
+
+    global_config: GlobalConfig
+    sheets: List[SheetItem]

data/data-pipeline/data_pipeline/etl/score/etl_score_post.py

@@ -3,6 +3,10 @@ import json
 from numpy import float64
 import numpy as np
 import pandas as pd
+from data_pipeline.content.schemas.download_schemas import (
+    CSVConfig,
+    ExcelConfig,
+)
 
 from data_pipeline.etl.base import ExtractTransformLoad
 from data_pipeline.etl.score.etl_utils import floor_series
@@ -452,7 +456,7 @@ class PostScoreETL(ExtractTransformLoad):
 
         # open excel yaml config
         excel_csv_config = load_yaml_dict_from_file(
-            self.CONTENT_CONFIG / "excel.yml"
+            self.CONTENT_CONFIG / "excel.yml", ExcelConfig
         )
 
         # Define Excel Columns Column Width
@@ -525,7 +529,7 @@ class PostScoreETL(ExtractTransformLoad):
         logger.info("Writing downloadable csv")
         # open yaml config
         downloadable_csv_config = load_yaml_dict_from_file(
-            self.CONTENT_CONFIG / "csv.yml"
+            self.CONTENT_CONFIG / "csv.yml", CSVConfig
         )
         downloadable_df = self._create_downloadable_data(
             score_df=self.output_score_county_state_merged_df,

data/data-pipeline/data_pipeline/utils.py

@@ -1,4 +1,4 @@
-from typing import List, Type
+from typing import List, Union
 import datetime
 import json
 import logging
@@ -14,7 +14,10 @@ import yaml
 from marshmallow_dataclass import class_schema
 
 from data_pipeline.config import settings
-from data_pipeline.content.schemas.csv import CSVConfig
+from data_pipeline.content.schemas.download_schemas import (
+    CSVConfig,
+    ExcelConfig,
+)
 
 
 ## zlib is not available on all systems
@@ -330,7 +333,7 @@ def zip_directory(
 
 
 def load_yaml_dict_from_file(
-    yaml_file_path: Path, yaml_schema: Type[CSVConfig]
+    yaml_file_path: Path, schema_class: Union[CSVConfig, ExcelConfig]
 ) -> dict:
     """Load a YAML file specified in path into a Python dictionary.
 
@@ -343,7 +346,10 @@ def load_yaml_dict_from_file(
     with open(yaml_file_path, encoding="UTF-8") as file:
         yaml_dict = yaml.load(file, Loader=yaml.FullLoader)
 
-    pass
+        # validate YAML
+        yaml_config_schema = class_schema(schema_class)
+        yaml_config_schema().load(yaml_dict)
+
     return yaml_dict
 
 

data/data-pipeline/poetry.lock

@@ -870,6 +870,17 @@ lint = ["pre-commit (>=1.18,<2.0)"]
 tests = ["pytest (>=5.4)", "pytest-mypy-plugins (>=1.2.0)", "typing-extensions (>=3.7.2,<3.8.0)"]
 union = ["typeguard"]
 
+[[package]]
+name = "marshmallow-enum"
+version = "1.5.1"
+description = "Enum field for Marshmallow"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+marshmallow = ">=2.0.0"
+
 [[package]]
 name = "matplotlib"
 version = "3.5.1"
@@ -1847,7 +1858,7 @@ testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.8"
-content-hash = "4278ecd8aab0cf352d62961687c33f92cda5e6d246309b046484dd797edf4986"
+content-hash = "2dda480b8f50a2414ff01d3c73663c28d64bc6df01f950367763c241a84b02f6"
 
 [metadata.files]
 appnope = [
@@ -2371,6 +2382,10 @@ marshmallow-dataclass = [
     {file = "marshmallow_dataclass-8.5.3-py3-none-any.whl", hash = "sha256:eefeff62ee975c64d293d2db9370e7e748a2ff83dcb5109416b75e087a2ac02e"},
     {file = "marshmallow_dataclass-8.5.3.tar.gz", hash = "sha256:c0c5e1ea8d0e557b6fa00343799a9a9e60757b948fb096076beb6aa76bd68d30"},
 ]
+marshmallow-enum = [
+    {file = "marshmallow-enum-1.5.1.tar.gz", hash = "sha256:38e697e11f45a8e64b4a1e664000897c659b60aa57bfa18d44e226a9920b6e58"},
+    {file = "marshmallow_enum-1.5.1-py2.py3-none-any.whl", hash = "sha256:57161ab3dbfde4f57adeb12090f39592e992b9c86d206d02f6bd03ebec60f072"},
+]
 matplotlib = [
     {file = "matplotlib-3.5.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:456cc8334f6d1124e8ff856b42d2cc1c84335375a16448189999496549f7182b"},
     {file = "matplotlib-3.5.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8a77906dc2ef9b67407cec0bdbf08e3971141e535db888974a915be5e1e3efc6"},

data/data-pipeline/pyproject.toml

@@ -25,6 +25,7 @@ ipython = "^7.31.1"
 jupyter = "^1.0.0"
 jupyter-contrib-nbextensions = "^0.5.1"
 marshmallow-dataclass = "^8.5.3"
+marshmallow-enum = "^1.5.1"
 matplotlib = "^3.4.2"
 numpy = "^1.22.1"
 pandas = "^1.2.5"