From 5578e60639c453399bbb119b6ae50a3e343437cd Mon Sep 17 00:00:00 2001 From: perezgonzalez-irene <iregon@noc.ac.uk> Date: Mon, 24 Feb 2020 09:44:44 +0000 Subject: [PATCH] New comments --- reader/get_sections.py | 5 ++++- reader/import_data.py | 3 +-- reader/read_sections.py | 2 +- 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/reader/get_sections.py b/reader/get_sections.py index ef43f7f..acb0f2b 100644 --- a/reader/get_sections.py +++ b/reader/get_sections.py @@ -6,7 +6,7 @@ Created on Tue Apr 30 09:38:17 2019 Splits string reports in sections using a data model layout. Input and output are simple pandas dataframes, with the output dataframe -column names being section names +column names being the section names To work with a pandas TextParser, loop through this module. @@ -29,6 +29,9 @@ use, also support to chunking would make converting to series a bit dirty... provided the section is in a sequential parsing_order group @author: iregon + +Have to documents the threads approach!!!! + """ import pandas as pd diff --git a/reader/import_data.py b/reader/import_data.py index 7ecf0c8..889c5f5 100644 --- a/reader/import_data.py +++ b/reader/import_data.py @@ -6,7 +6,7 @@ Created on Fri Jan 10 13:17:43 2020 FUNCTION TO PREPARE SOURCE DATA TO WHAT GET_SECTIONS() EXPECTS: AN ITERABLE WITH DATAFRAMES -INPUT IS EITHER NOW ONLY A FILE PATH +INPUT IS NOW ONLY A FILE PATH. COULD OPTIONALLY GET OTHER TYPE OBJECTS... OUTPUT IS AN ITERABLE, DEPENDING ON CHUNKSIZE BEING SET: - a single dataframe in a list @@ -38,7 +38,6 @@ OPTIONS IN OLD DEVELOPMENT: import pandas as pd import os -import io from .. import properties diff --git a/reader/read_sections.py b/reader/read_sections.py index bfaf4ae..5beab89 100644 --- a/reader/read_sections.py +++ b/reader/read_sections.py @@ -13,7 +13,7 @@ where appropriate and ensure its data type consistency. Output is a dataframe with columns as follows depending on the data model structure: - 1) Data model with sections (1 or more): [(section0,element0),.......(sectionN,elementN)] + 1) Data model with sections (1 or more): [(section0,element0),.......(sectionN,elementM)] 2) Data model with no sections[element0...element1] -- GitLab