Continue to work on docs

docs/source/conf.py

@@ -44,6 +44,7 @@
     "sphinx.ext.doctest",
     "sphinx.ext.autodoc",
     "sphinx.ext.autosummary",
+    "myst_parser",
 ]
 
 autosummary_generate = True
@@ -62,10 +63,10 @@
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'classic'
+html_theme = "classic"
 
-#'sphinx_rtd_theme' (you need to 
-#"alabaster"
+#'sphinx_rtd_theme' (you need to
+# "alabaster"
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,

docs/source/index.rst

@@ -6,11 +6,21 @@
 Welcome to pydit's documentation!
 =================================
 
+.. include:: readme_link.rst
+
+Detailed documentation
+======================
+
 .. autosummary::
    :toctree: _autosummary
    :recursive:
 
-   pydit
+   pydit.functions
+   pydit.logger
+   pydit.filemanager
+   pydit.utils
+
+
 
 Indices and tables
 ==================

docs/source/readme_link.rst

@@ -0,0 +1,2 @@
+.. include:: ../../README.md
+   :parser: myst_parser.sphinx_

pydit/functions/add_counts.py

@@ -1,4 +1,4 @@
-""" Add a count column that will bring the count of that key in the referenced table"""
+""" Adds the count of that key from another dataframe, similar to COUNTIF() in Excel"""
 
 import logging
 import pandas as pd
@@ -9,13 +9,15 @@
 def add_counts_between_related_df(
     df1, df2, left_on="", right_on="", on="", inplace=False
 ):
-    """Add a count column to bring the count of that key in those tables
+    """Add a count column to bring the count of that key in another dataframe
 
     This works similar to adding countif() in Excel to sense check if an
     identifier in one sheet is in fullly in another (presumably master), or
     if there are duplicated keys or orphans/gaps.
-    This routine does both ways so you can quickly check whether you have
-    one to one, many to many etc, and where there may be the anomales.
+
+    This routine does both ways to quickly check whether the relationship is
+    one to one, many to many etc.
+
     There is another function that checks referential integrity and does this
     in a more conceptual way, but often you just need to add some counting
     numbers and filter for >1 or zeroes.

pydit/functions/add_percentile.py

@@ -8,11 +8,13 @@
 
 
 def add_percentile(df, col, col_group=None, inplace=False):
-    """Adds columns for percentile for a chosen column and also
-    within a category group , if provided
-    from https://stackoverflow.com/questions/50804120/how-do-i-get-the-percentile-for-a-row-in-a-pandas-dataframe
-    Using the percentile with linear interpolation method, but kept
-    various ranks calculations for reference
+    """Adds columns for percentile for a chosen column in a DataFrame
+
+    It can also provide it within a category group (col_group)
+    
+    Reference: https://stackoverflow.com/questions/50804120/how-do-i-get-the-percentile-for-a-row-in-a-pandas-dataframe
+    Using the percentile with linear interpolation method, but kept various 
+    ranks calculations for reference
 
     Args:
         df_in (DataFrame): Pandas DataFrame

pydit/functions/cleanup_column_names.py

@@ -72,10 +72,21 @@ def _get_random_string(length):
 
 
 def cleanup_column_names(df, max_field_name_len=40, inplace=False):
-    """ Cleanup the column names of a Pandas dataframe
-        e.g. removes non alphanumeric chars, _ instead of space, perc instead
-        of %, strips trailing spaces, converts to lowercase
-        """
+    """
+    Cleanup the column names of a Pandas dataframe. 
+
+    e.g. removes non alphanumeric chars, _ instead of space, perc instead
+    of %, strips trailing spaces, converts to lowercase.
+
+    Args:
+        df (DataFrame): Pandas DataFrame
+        max_field_name_len (int, optional): Maximum length of field name. Defaults to 40.
+        inplace (bool, optional): If True, the dataframe is modified in place. Defaults to False.
+    Returns:
+        Pandas DataFrame with cleaned column names
+
+
+    """
     prev_cols = list(df.columns)
     new_cols = []
     for e in prev_cols:
@@ -97,7 +108,7 @@ def cleanup_column_names(df, max_field_name_len=40, inplace=False):
     # names, just in case keeping this quite low, feel free to increase or remove
     new_cols = _deduplicate_list(new_cols)
     if not inplace:
-        df=df.copy()
+        df = df.copy()
     df.columns = new_cols
     logger.debug("Previous column names:%s", prev_cols)
     logger.info("New columns names:%s", list(df.columns))