hxlquickmeta (#9): hxltype, create files with references to the sprea…

…dsheets

bin/hxlquickmeta

@@ -63,18 +63,8 @@ import pandas as pd
 import numpy as np
 import Orange
 
-# import smeta.base
-import meta.base
-
-print(meta.base.test())
-# print(smeta.__file__)
-# print(smeta.__package__)
-
-# meta.base.test()
-# hxlm.base.test()
-
-# for path in sys.path:
-#     print(path)
+# import meta.hxltype.base
+# print(meta.hxltype.base.test())
 
 # In Python2, sys.stdin is a byte stream; in Python3, it's a text stream
 STDIN = sys.stdin.buffer

bin/meta/README.md

@@ -0,0 +1,44 @@
+# About /bin/meta/*
+
+This folder have an very early draft used by
+[/bin/hxlquickmeta](../hxlquickmeta).
+
+The idea is eventually abstract more what was bootstraped on
+EticaAI-Data_HXL-Data-Science-file-formats
+<https://docs.google.com/spreadsheets/d/1vFkBSharAEg5g5K2u_iDLCBvpWWPqpzC1hcL6QpFNZY/edit#gid=1066910203>
+simmilar to what libraries like Pandas and Numpy do it.
+
+TODO: Look at other abstractions beyond numpy
+
+
+<!--
+
+> https://numpy.org/doc/stable/user/basics.rec.html
+> Users looking to manipulate tabular data, such as stored in csv files, may
+find other pydata projects more suitable, such as xarray, pandas, or DataArray.
+These provide a high-level interface for tabular data analysis and are better
+optimized for that use. For instance, the C-struct-like memory layout of
+structured arrays in numpy can lead to poor cache behavior in comparison.
+
+
+>> https://github.com/pydata/xarray
+
+> Xarray introduces labels in the form of dimensions, coordinates and attributes
+on top of raw NumPy-like arrays, which allows for a more intuitive, more
+concise, and less error-prone developer experience. The package includes a
+large and growing library of domain-agnostic functions for advanced analytics
+and visualization with these data structures.
+
+>> Xarray was inspired by and borrows heavily from pandas, the popular data 
+analysis package focused on labelled tabular data. It is particularly tailored
+to working with netCDF files, which were the source of xarray's data model,
+and integrates tightly with dask for parallel computing.
+
+> benchmark https://github.com/pydata/xarray/issues/2799
+
+
+>> netCDF
+
+- https://www.unidata.ucar.edu/software/netcdf/examples/files.html
+
+-->

bin/meta/hxltype/base.py

@@ -0,0 +1,11 @@
+# *HXLtype
+# @see https://github.com/EticaAI/HXL-Data-Science-file-formats/issues/9
+# @see https://docs.google.com/spreadsheets/d/1vFkBSharAEg5g5K2u_iDLCBvpWWPqpzC1hcL6QpFNZY/edit#gid=1066910203
+
+
+def a1_func():
+    print("running a1_func()")
+
+def test():
+    print("hello world")
+

bin/meta/hxltype/data.py

@@ -0,0 +1,3 @@
+# DataHXLtype
+# @see https://github.com/EticaAI/HXL-Data-Science-file-formats/issues/9
+# @see https://docs.google.com/spreadsheets/d/1vFkBSharAEg5g5K2u_iDLCBvpWWPqpzC1hcL6QpFNZY/edit#gid=717813523

bin/meta/hxltype/level.py

@@ -0,0 +1,3 @@
+# LevelHXLtype
+# @see https://github.com/EticaAI/HXL-Data-Science-file-formats/issues/9
+# @see https://docs.google.com/spreadsheets/d/1vFkBSharAEg5g5K2u_iDLCBvpWWPqpzC1hcL6QpFNZY/edit#gid=1053765950

bin/meta/hxltype/storage.py

@@ -0,0 +1,7 @@
+# StorageHXLtype
+# @see https://github.com/EticaAI/HXL-Data-Science-file-formats/issues/9
+# @see https://docs.google.com/spreadsheets/d/1vFkBSharAEg5g5K2u_iDLCBvpWWPqpzC1hcL6QpFNZY/edit#gid=211012023
+
+
+# - https://numpy.org/doc/stable/user/basics.types.html
+# - https://numpy.org/doc/stable/reference/generated/numpy.dtype.html#numpy.dtype

bin/meta/hxltype/usage.py

@@ -0,0 +1,3 @@
+# UsageHXLtype
+# @see https://github.com/EticaAI/HXL-Data-Science-file-formats/issues/9
+# @see https://docs.google.com/spreadsheets/d/1vFkBSharAEg5g5K2u_iDLCBvpWWPqpzC1hcL6QpFNZY/edit#gid=617579056

bin/meta/hxltype/weight.py

@@ -0,0 +1,3 @@
+# WeightHXLtype
+# @see https://github.com/EticaAI/HXL-Data-Science-file-formats/issues/9
+# @see https://docs.google.com/spreadsheets/d/1vFkBSharAEg5g5K2u_iDLCBvpWWPqpzC1hcL6QpFNZY/edit#gid=1507056660