Merge pull request #23 from dsih-artpark/v3

V3 merge - merging PR and will create tag as well.

.gitignore

@@ -142,4 +142,7 @@ dmypy.json
 .DS_Store
 
 # All Data Files
-*.csv
+*.csv
+data/**
+testing.py
+_src/**

README.MD

@@ -1,4 +1,4 @@
-# README.MD - epipipeline v2.0.11
+# README.MD - epipipeline v3.0.0
 
 This repository contains code that can be used to standardise linelists and summaries.
 
@@ -9,6 +9,6 @@ The standards currently used are:
 1. Linelists: [YAML](https://raw.githubusercontent.com/dsih-artpark/data_documentation/production/documentation/EP/EP0005DS0014-KA_Dengue_LL/datadictionary.yaml), [MD](https://raw.githubusercontent.com/dsih-artpark/data_documentation/production/documentation/EP/EP0005DS0014-KA_Dengue_LL/datadictionary.MD)
 2. Daily Summaries: [YAML](https://raw.githubusercontent.com/dsih-artpark/data_documentation/production/documentation/EP/EP0006DS0015-KA_Dengue_Daily_SUM/datadictionary.yaml), [MD](https://raw.githubusercontent.com/dsih-artpark/data_documentation/production/documentation/EP/EP0006DS0015-KA_Dengue_Daily_SUM/datadictionary.md)
 
-This package's latest stable release, v2.0.11, supports Karnataka data. The package is still in a limited beta, and documentation and feature addition is underway.
+This package's latest stable release, v3, supports Karnataka data. The package is still in a limited beta, and documentation and feature addition is underway.
 
 To install the package, copy the following snippet:

pyproject.toml

@@ -1,22 +1,29 @@
 [tool.poetry]
 name = "epipipeline"
-version = "2.0.11"
+version = "3.0.0"
 description = ""
 authors = ["Sai Sneha <[email protected]>"]
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = "^3.11"
+python = "^3.9.0"
 pandas = "^2.2.0"
 boto3 = "^1.34.40"
 requests = "^2.31.0"
 fuzzywuzzy = "^0.18.0"
 openpyxl = "^3.1.2"
 python-levenshtein = "^0.25.0"
 pyyaml = "^6.0.1"
+ipython = "^8.0.0"
 dataio = {git = "[email protected]:dsih-artpark/dataio.git"}
 
 
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "I", "FLY", "RUF", "B", "ICN"]
+
+[tool.ruff]
+line-length = 140

src/epipipeline/__init__.py

@@ -1,2 +1,21 @@
 from importlib.metadata import version
+
+import pandas as pd
+
+from epipipeline.logging_config import setup_logging
+
 __version__ = version(__name__)
+setup_logging()
+
+
+def get_regionIDs(*, regionIDs_path="data/GS0015DS0034-LGD_Region_IDs_and_Names/regionids.csv"):
+
+    regionIDs_df = pd.read_csv(regionIDs_path)
+
+    regionIDs_dict = {}
+    for _, row in regionIDs_df.iterrows():
+        regionIDs_dict[row["regionID"]] = {"regionName": row["regionName"],
+                                           "parentID": row["parentID"]
+                                           }
+    return regionIDs_df, regionIDs_dict
+

src/epipipeline/logging_config.py

@@ -0,0 +1,66 @@
+# epipipeline/logging_config.py
+import logging
+import logging.config
+
+def setup_logging(default_level='WARNING'):
+    """
+    Set up logging configuration.
+
+    Args:
+        default_level (str): The default logging level ('DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL').
+    """
+    default_level = default_level.upper()
+    if default_level not in ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']:
+        raise ValueError(f"Invalid logging level: {default_level}")
+
+    logging_config = {
+        'version': 1,
+        'disable_existing_loggers': False,
+        'formatters': {
+            'standard': {
+                'format': '%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+            },
+        },
+        'handlers': {
+            'console': {
+                'class': 'logging.StreamHandler',
+                'formatter': 'standard',
+            },
+            'file': {
+                'class': 'logging.FileHandler',
+                'formatter': 'standard',
+                'filename': 'epipipeline.log',
+            },
+        },
+        'loggers': {
+            '': {
+                'handlers': ['console', 'file'],
+                'level': default_level,
+                'propagate': True,
+            },
+            'epipipeline': {
+                'handlers': ['console', 'file'],
+                'level': default_level,
+                'propagate': False,
+            },
+        }
+    }
+
+    logging.config.dictConfig(logging_config)
+
+def set_logging_level(level):
+    """
+    Set the logging level for the 'epipipeline' logger and all its handlers.
+
+    Args:
+        level (str): The logging level to set ('DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL').
+    """
+    level = level.upper()
+    if level not in ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']:
+        raise ValueError(f"Invalid logging level: {level}")
+
+    logger = logging.getLogger('epipipeline')
+    logger.setLevel(level)
+
+    for handler in logger.handlers:
+        handler.setLevel(level)