From 1dc1aff0026aff353a2214b89bd901d09c07acb5 Mon Sep 17 00:00:00 2001
From: tm689 <tm689@cam.ac.uk>
Date: Thu, 29 Feb 2024 17:18:57 +0000
Subject: [PATCH] feat: converting double nested Race and Genotype information
in to string. (Adding missing columns)
---
coordinator/ProcessorSurveysWRT.py | 20 +++++++++++++-------
1 file changed, 13 insertions(+), 7 deletions(-)
diff --git a/coordinator/ProcessorSurveysWRT.py b/coordinator/ProcessorSurveysWRT.py
index 1a1751c..d2a50c2 100644
--- a/coordinator/ProcessorSurveysWRT.py
+++ b/coordinator/ProcessorSurveysWRT.py
@@ -101,6 +101,7 @@ def nested_to_flattened(df):
RAW_COLUMNS = [
"ObservationID",
"OriginalID",
+ "PublishedLevel",
"Origin",
"Country",
"Latitude",
@@ -108,6 +109,7 @@ def nested_to_flattened(df):
"FieldArea",
"Cultivar",
"CollectionDate",
+ "UpdateDate",
"GrowthStage",
"listDisease"]
for i in RAW_COLUMNS:
@@ -177,14 +179,16 @@ def nested_to_flattened(df):
row[nested_row[rr]['DiseaseName'] + '.Incident'] = nested_row[rr]['IncidenceCategory']
row[nested_row[rr]['DiseaseName'] + '.Severity'] = nested_row[rr]['SeverityCategory']
- race_list = []
- geno_list = []
+ nested_row[rr]['listResult'] = [{'Race': 'Alma', 'Genotype': 'Korte'},{'Race': 'Banan', 'Genotype': 'Malna'}] # !!!!!!!!! DELETE THIS LINE !!!!!!!!!!
for i in range(len(nested_row[rr]['listResult'])):
- race_list.append(nested_row[rr]['listResult'][i]['Race'])
- geno_list.append(nested_row[rr]['listResult'][i]['Genotype'])
+ # TODO: check if the separation symbol is in the string or not
+ row[nested_row[rr]['DiseaseName'] + '.Race'] += nested_row[rr]['listResult'][i]['Race']
+ row[nested_row[rr]['DiseaseName'] + '.Genotype'] += nested_row[rr]['listResult'][i]['Genotype']
+
+ if i != len(nested_row[rr]['listResult'])-1:
+ row[nested_row[rr]['DiseaseName'] + '.Race'] += '+'
+ row[nested_row[rr]['DiseaseName'] + '.Genotype'] += '+'
- row[nested_row[rr]['DiseaseName'] + '.Race'] = race_list
- row[nested_row[rr]['DiseaseName'] + '.Genotype'] = geno_list
df.loc[index] = row
return df
@@ -206,13 +210,15 @@ def get_WRT_form_as_csv(form_credentials: dict, jobPath: str, config: dict, stat
column_parser_dict = {
"ObservationID" : 'KEY',
"OriginalID" : 'None',
- "Origin" : "Origin",
+ "PublishedLevel" : 'PublishedLevel',
+ "Origin" : 'Origin',
"Country" : ('parse_cases',(('name_out','surveyor_infromation-country'),('cases', COUNTRY_ABBREVIATIONS_DICT))),
"Latitude" : 'survey_infromation-location-Latitude',
"Longitude" : 'survey_infromation-location-Longitude',
"FieldArea" : 'site_information-field_area',
"Cultivar" : 'site_information-variety',
"CollectionDate" : ('parse_date',(('name_out','survey_infromation-survey_date'),('fmt_in','%m/%d/%Y'))),
+ "UpdateDate" : 'None',
"GrowthStage" : 'site_information-growth_stage',
"listDisease" : 'None',
"YR.Severity" : ('parse_cases',(('name_out','yellow_rust-yellowrust_severity'),('cases', cases_severity),('dtype', int))),
--
GitLab