From 87423cabdaa7ae76264c74ff72798b6e92683941 Mon Sep 17 00:00:00 2001
From: DAWells <david.arthur.wells@gmail.com>
Date: Thu, 29 Aug 2024 09:36:34 +0100
Subject: [PATCH] Remove data loaders as they are not working and not needed

---
 MANIFEST.in                 |  1 -
 README.md                   |  4 +---
 setup.py                    |  1 -
 src/HLAfreq/HLAfreq_data.py | 30 ------------------------------
 4 files changed, 1 insertion(+), 35 deletions(-)
 delete mode 100644 MANIFEST.in
 delete mode 100644 src/HLAfreq/HLAfreq_data.py

diff --git a/MANIFEST.in b/MANIFEST.in
deleted file mode 100644
index 6961c5e..0000000
--- a/MANIFEST.in
+++ /dev/null
@@ -1 +0,0 @@
-include src/HLAfreq/data/*.csv
\ No newline at end of file
diff --git a/README.md b/README.md
index 190d194..5c67fd2 100644
--- a/README.md
+++ b/README.md
@@ -10,7 +10,7 @@ ability to mount an immune response to specific epitopes.
 Automated download of allele frequency data download from 
 [allele frequencies.net](http://www.allelefrequencies.net/).
 
-Source code is available at [BarinthusBio/HLAfreq](https://github.com/BarinthusBio/HLAfreq).
+Full documentation at [HLAfreq/docs](https://BarinthusBio.github.io/HLAfreq/HLAfreq.html). Source code is available at [BarinthusBio/HLAfreq](https://github.com/BarinthusBio/HLAfreq).
 
 ## Details
 Estimates are combined by modelling allele frequency as a 
@@ -107,8 +107,6 @@ API documentation for functions are under the submodules on the left.
 - `HLAfreq.HLAfreq` documents most functions, specifically download and combine
 allele data.
 - `HLAfreq.HLAfreq_pymc` is functions using pymc to acurately estimate credible intervals on allele frequency estimates.
-- `HLAfreq.HLAfreq_data` contains data loaders to get countries available on
-allelefrequencies.net.
 
 For help on specific functions view the docstring, `help(function_name)`.
 
diff --git a/setup.py b/setup.py
index 722b310..1f27c6a 100644
--- a/setup.py
+++ b/setup.py
@@ -31,5 +31,4 @@
     packages=find_packages(
         where='src'
     ),
-    include_package_data=True,
 )
\ No newline at end of file
diff --git a/src/HLAfreq/HLAfreq_data.py b/src/HLAfreq/HLAfreq_data.py
deleted file mode 100644
index 9fc0399..0000000
--- a/src/HLAfreq/HLAfreq_data.py
+++ /dev/null
@@ -1,30 +0,0 @@
-"""
-Data loaders
-"""
-
-import pkg_resources
-import pandas as pd
-
-
-def load_countries():
-    """Load dataframe of countries and regions available on [allele frequencies.net](http://www.allelefrequencies.net/).
-
-    Returns:
-        pd.DataFrame: Three columns: `Country`, `Region`, and `largeRegion`.
-        `largeRegion` is based on `Region` with with fewer categories to improve
-        plotting.
-    """
-    stream = pkg_resources.resource_stream(__name__, "data/countries.csv")
-    return pd.read_csv(stream, encoding="latin-1")
-
-
-def load_HLA1supertypes_Sidney2008():
-    """Load HLA alleles and their supertype as defined in Sidney2008
-
-    Returns:
-        pd.DataFrame: DataFrame of alleles and their supertype
-    """
-    stream = pkg_resources.resource_stream(
-        __name__, "data/HLA1supertypes_Sidney2008.csv"
-    )
-    return pd.read_csv(stream, encoding="latin-1")