Merge pull request #174 from BIH-CEI/156-add-util-method-that-loads-data-in-whatever-format-and-provides-an-iterator-for-instances

156 add util method that loads data in whatever format and provides an iterator for instances

Author: frehburg

pyproject.toml

@@ -27,7 +27,14 @@ classifiers = [
     "Topic :: Scientific/Engineering :: Machine Learning"
 ]
 dependencies = [
-    "loguru", "phenopackets", "pandas", "openpyxl", "jupyter", "requests", "bs4",
+    "loguru",
+    "phenopackets",
+    "pandas",
+    "openpyxl",
+    "jupyter",
+    "requests",
+    "bs4",
+    "xmltodict==0.14.1",
 ]
 dynamic = ["version"]
 

src/phenopacket_mapper/__init__.py

@@ -2,8 +2,16 @@
 
 __version__ = "0.0.1"
 
-from . import cli, data_standards, pipeline, preprocessing, api_requests
+from . import data_standards, validate, preprocessing, api_requests, mapping, utils
 
-from .pipeline import PhenopacketMapper
+from .data_standards import DataModel
+from .mapping import PhenopacketMapper
 
-__all__ = ["cli", "data_standards", "pipeline", "PhenopacketMapper", "preprocessing", "api_requests"]
+__all__ = [
+    "data_standards", "DataModel",
+    "validate",
+    "preprocessing",
+    "api_requests",
+    "mapping", "PhenopacketMapper",
+    "utils",
+]

src/phenopacket_mapper/cli/__init__.py

@@ -256,6 +256,7 @@ def load_data(
         :param kwargs: Dynamically passed parameters that match {id}_column for each item
         :return: A list of `DataModelInstance` objects
         """
+        # TODO: move the dynamic params to the load method in utils.io
         column_names = dict()
         for f in self.fields:
             column_param = f"{f.id}_column"
@@ -264,7 +265,7 @@ def load_data(
             else:
                 column_names[f.id] = kwargs[column_param]
 
-        from phenopacket_mapper.pipeline import load_data_using_data_model
+        from phenopacket_mapper.utils.io import load_data_using_data_model
         return load_data_using_data_model(
             path=path,
             data_model=self,

src/phenopacket_mapper/cli/main.py

@@ -0,0 +1,19 @@
+"""This module handles the input and output of data."""
+
+from .read_json import read_json
+from .read_xml import read_xml, parse_xml
+from .data_reader import DataReader
+from .input import read_data_model, read_phenopackets, read_phenopacket_from_json, load_data_using_data_model
+from .output import write
+
+__all__ = [
+    'read_json',
+    'read_xml', 'parse_xml',
+    'DataReader',
+    'read_data_model',
+    'read_phenopackets',
+    'read_phenopacket_from_json',
+    'load_data_using_data_model',
+
+    'write',
+]