Updated BaseInput dataframe input to convert to str

README.md

@@ -2,7 +2,7 @@
 [![Maintainability](https://api.codeclimate.com/v1/badges/11bf2329590e7b0164ba/maintainability)](https://codeclimate.com/github/hed-standard/hed-python/maintainability)
 [![Test Coverage](https://api.codeclimate.com/v1/badges/11bf2329590e7b0164ba/test_coverage)](https://codeclimate.com/github/hed-standard/hed-python/test_coverage)
 ![PyPI - Status](https://img.shields.io/pypi/v/hedtools)
-
+[![Documentation Status](https://readthedocs.org/projects/hed-python/badge/?version=latest)](https://hed-python.readthedocs.io/en/latest/?badge=latest)
 
 # HEDTools - Python
 HED (Hierarchical Event Descriptors) is a framework for systematically describing

docs/requirements.txt

@@ -5,6 +5,7 @@ openpyxl>=3.1.0
 pandas>=1.3.5
 portalocker>=2.7.0
 semantic_version>=2.10.0
+myst-parser>=1.0.0
 Sphinx>=5.2.2
 sphinx_rtd_theme>=1.0.0
 wordcloud==1.9.2

docs/source/conf.py

@@ -24,8 +24,8 @@
 author = 'HED Working Group'
 
 # The full version, including alpha/beta/rc tags
-version = '0.0.1'
-release = '0.0.1'
+version = '0.3.1'
+release = '0.3.1'
 
 currentdir = os.path.realpath(os.path.dirname(__file__))
 

docs/source/index.rst

@@ -1,6 +1,10 @@
 Hierarchical Event Descriptor (HED) Python Tools
 ================================================
 
+.. image:: _static/images/croppedWideLogo.png
+  :width: 220
+  :alt: HedLogo
+
 .. sidebar:: **Links**
 
    * `PDF docs <https://hed-python.readthedocs.io/_/downloads/en/latest/pdf/>`_

docs/source/introduction.rst

@@ -29,12 +29,19 @@ you can install directly from the
 `GitHub repository <https://github.com/hed-standard/hed-python>`_
 using the following command:
 
+```code
 >>> pip install git+https://github.com/hed-standard/hed-python.git
-
+```
 
 Finding help
 ============
 
+:Documentation:
+
+    See `HED resources <https://www.hed-resources.org>`_ for user documentation and tutorials.
+
+    The `HED online tools <https://hedtools.org>`_ provide an easy-to-use interface that requires no programming. 
+
 :Mailing lists and forums:
 
     * Don't hesitate to ask questions about the python hedtools on `NeuroStars

hed/models/base_input.py

@@ -70,14 +70,14 @@ def __init__(self, file, file_type=None, worksheet_name=None, has_column_names=T
         self._dataframe = None
 
         if isinstance(file, pandas.DataFrame):
-            self._dataframe = file
+            self._dataframe = file.astype(str)
             self._has_column_names = self._dataframe_has_names(self._dataframe)
         elif not file:
             raise HedFileError(HedExceptions.FILE_NOT_FOUND, "Empty file passed to BaseInput.", file)
         elif input_type in self.TEXT_EXTENSION:
             try:
                 self._dataframe = pandas.read_csv(file, delimiter='\t', header=pandas_header,
-                                                  dtype=str, keep_default_na=True, na_values=None)
+                                                  dtype=str, keep_default_na=True, na_values=["", "null"])
             except Exception as e:
                 raise HedFileError(HedExceptions.INVALID_FILE_FORMAT, str(e), self.name) from e
             # Convert nan values to a known value

hed/schema/hed_schema.py

@@ -153,6 +153,7 @@ def get_formatted_version(self):
         Returns:
             str: A json formatted string of the complete version of this schema including library name and namespace.
         """
+
         return json.dumps(self.version)
 
     def get_save_header_attributes(self, save_merged=False):

hed/tools/util/data_util.py

@@ -131,13 +131,13 @@ def get_new_dataframe(data):
         DataFrame:  A dataframe containing the contents of the tsv file or if data was
              a DataFrame to start with, a new copy of the DataFrame.
 
-    :raises HedFileError: 
+    :raises HedFileError:
         - If a filename is given and it cannot be read into a Dataframe.
 
     """
 
     if isinstance(data, str):
-        df = pd.read_csv(data, delimiter='\t', header=0, keep_default_na=False, na_values=",null")
+        df = pd.read_csv(data, delimiter='\t', header=0, keep_default_na=True, na_values=[",", "null"])
     elif isinstance(data, pd.DataFrame):
         df = data.copy()
     else:
@@ -155,7 +155,7 @@ def get_row_hash(row, key_list):
     Returns:
         str: Hash key constructed from the entries of row in the columns specified by key_list.
 
-    :raises HedFileError: 
+    :raises HedFileError:
         - If row doesn't have all of the columns in key_list HedFileError is raised.
 
     """
@@ -177,7 +177,7 @@ def get_value_dict(tsv_path, key_col='file_basename', value_col='sampling_rate')
     Returns:
         dict:  Dictionary with key_col values as the keys and the corresponding value_col values as the values.
 
-    :raises HedFileError: 
+    :raises HedFileError:
         - When tsv_path does not correspond to a file that can be read into a DataFrame.
 
     """
@@ -252,7 +252,7 @@ def reorder_columns(data, col_order, skip_missing=True):
     Returns:
         DataFrame:                  A new reordered dataframe.
 
-    :raises HedFileError:  
+    :raises HedFileError:
         - If col_order contains columns not in data and skip_missing is False.
         - If data corresponds to a filename from which a dataframe cannot be created.
 
@@ -277,7 +277,7 @@ def separate_values(values, target_values):
             list:  Target values present in values.
             list:  Target values missing from values.
 
-     Notes:  
+     Notes:
          - The function computes the set difference of target_cols and base_cols and returns a list
            of columns of target_cols that are in base_cols and a list of those missing.