Add zones to plant fixture creation and extract spreadsheet constants

This commit is contained in:
Dana Lambert 2021-11-04 14:11:50 +13:00
parent d48f202634
commit 625c637f99
3 changed files with 112 additions and 57 deletions

View file

@ -0,0 +1,65 @@
from pathlib import Path
import right_tree.api.data
from ._spreadsheet_helpers import *
from right_tree.api.models import EcologicalRegion, SoilOrder, SoilVariant, ToleranceLevel, Zone
# Mapping adjustments between the shapefile ecological regions and those in the spreadsheet
ECO_REGION_ADJUSTMENTS = {
"Whakatane": "Whatkatane",
"North West Nelson": "North-west Nelson",
"Aorangi": "Aorrangi",
"Mackenzie": "MacKenzie",
"Southland Hills": "Southland Foothills",
"Sounds Wellington": "Sounds-Wellington"
}
# Relevant columns and information used to retrieve information from the spreadsheet
PLANT_COLS = {
'SCIENTIFIC NAME': {"str": "name", "expected_type": str, "max_length": 50},
'MAX HT': {"str": "maxheight", "expected_type": float},
'SPACING': {"str": "spacing", "expected_type": float},
'COMMON NAME': {"str": "commonname", "expected_type": str, "null_allowed": True, "max_length": 200},
'SYNONYM': {"str": "synonym", "expected_type": str, "null_allowed": True, "max_length": 200},
'ECOLOGICAL REGION': {"str": "region", "expected_type": list, "model_name": "ecological_regions"},
'SOIL ORDER': {"str": "soilorder", "expected_type": list, "model_name": "soil_order"},
'Wet': {"str": "wet", "expected_type": list, "model_name": "soil_variants"},
'Mesic': {"str": "mesic", "expected_type": list, "model_name": "soil_variants"},
'Dry': {"str": "dry", "expected_type": list, "model_name": "soil_variants"},
'Water': {"str": "water", "expected_type": int, "model_name": "water_tolerance"},
'Drought': {"str": "drought", "expected_type": int, "model_name": "drought_tolerance"},
'Frost': {"str": "frost", "expected_type": int, "model_name": "frost_tolerance"},
'Salinity': {"str": "salinity", "expected_type": int, "model_name": "salinity_tolerance"},
'ES': {"str": "purpose", "expected_type": str, "null_allowed": True},
'STAGE': {"str": "stage", "expected_type": int},
'GrowthForm': {"str": "growthform", "expected_type": str, "model_name": "growth_form", "null_allowed": True, "max_length": 50}
}
# Spreadsheet constants
SPREADSHEET_FILENAME = 'plant_data.xlsx'
DATA_START_COL = 3
DATA_START_ROW = 6
INFO_HEADER_ROW = 4
# Site col and row contants
SITE_DATA_START_COL = 25
SITE_DATA_STOP_COL = 157
HABITAT_ROW = 2
ZONE_NAME_ROW = 3
ZONE_VARIANT_ROW = 4
ZONE_REFINED_VARIANT_ROW = 5
# Data directory path
DATA_DIR_PATH = Path(right_tree.api.data.__file__).resolve().parent
# Mappings between values in the spreadsheet and primary key values in the database
ECO_REGION_PK_MAPPING = get_pk_mapping(EcologicalRegion)
SOIL_ORDER_PK_MAPPING = get_pk_mapping(SoilOrder)
SOIL_VARIANT_PK_MAPPING = get_pk_mapping(SoilVariant)
TOLERANCE_PK_MAPPING = get_pk_mapping(ToleranceLevel, "level")
ZONE_PK_MAPPING = get_zone_pk_mapping(Zone)
# Spreadsheet and corresponding value to column index mappings
SPREADSHEET = get_spreadsheet(DATA_DIR_PATH, SPREADSHEET_FILENAME)
INFO_COL_INDEXES = get_col_mappings(SPREADSHEET, DATA_START_COL, SITE_DATA_START_COL-1, INFO_HEADER_ROW)
ZONE_COL_INDEXES = get_zone_col_mappings(SPREADSHEET, SITE_DATA_START_COL, SITE_DATA_STOP_COL, ZONE_NAME_ROW, ZONE_REFINED_VARIANT_ROW)

View file

@ -1,4 +1,5 @@
from openpyxl import load_workbook
from right_tree.api.models import Zone
def get_pk_mapping(object, mapping_key="name"):
@ -11,17 +12,52 @@ def get_pk_mapping(object, mapping_key="name"):
return pk_mapping
def get_col_mappings(sheet, start_col, row_index):
def get_zone_pk_mapping(zone_model):
""" Maps the string instance (unique) of a zone to its corresponding primary key.
"""
zone_pk_mapping = {}
for instance in zone_model.objects.all():
zone_pk_mapping[str(instance)] = instance.pk
return zone_pk_mapping
def get_col_mappings(sheet, start_col, stop_col, row_index):
""" Returns a dictionary that maps a spreadsheet cell value to a corresponding column index.
"""
col_mappings = {}
for row in sheet.iter_rows(min_col=start_col, min_row=row_index, max_row=row_index, values_only=True):
for row in sheet.iter_rows(min_col=start_col, max_col=stop_col, min_row=row_index, max_row=row_index, values_only=True):
for i, col_name in enumerate(row):
col_mappings[col_name] = i
return col_mappings
def get_zone_col_mappings(sheet, start_col, stop_col, start_row, stop_row):
""" Returns a dictionary that maps a spreadsheet zone string object to a column index.
"""
zone_col_mappings = {}
current_zone = current_variant = current_refined_variant = None
for i, col in enumerate(sheet.iter_cols(min_col=start_col, max_col=stop_col, min_row=start_row, max_row=stop_row, values_only=True)):
zone_name, zone_variant, zone_refined_variant = col
if zone_name is not None:
current_zone = zone_name
current_variant = current_refined_variant = None
if zone_variant is not None:
current_variant = zone_variant
current_refined_variant = None
current_refined_variant = zone_refined_variant if zone_refined_variant is not None else current_refined_variant
zone_obj = Zone(name=current_zone, variant=current_variant,
refined_variant=current_refined_variant)
zone_col_mappings[str(zone_obj)] = i + start_col
return zone_col_mappings
def get_pk_list_from_str(values_str, pk_mapping, fixes={}):
""" Given a list of comma separated values from the spreadsheet. Returns a list of primary keys that
correspond to the relevant values with any given mapping fixes applied.

View file

@ -1,62 +1,8 @@
from django.core.management.base import BaseCommand
import json
from pathlib import Path
import right_tree.api.data
from ._spreadsheet_helpers import *
from right_tree.api.models import EcologicalRegion, SoilOrder, SoilVariant, ToleranceLevel
# Mapping adjustments between the shapefile ecological regions and those in the spreadsheet
ECO_REGION_ADJUSTMENTS = {
"Whakatane": "Whatkatane",
"North West Nelson": "North-west Nelson",
"Aorangi": "Aorrangi",
"Mackenzie": "MacKenzie",
"Southland Hills": "Southland Foothills",
"Sounds Wellington": "Sounds-Wellington"
}
# Relevant columns and information used to retrieve information from the spreadsheet
PLANT_COLS = {
'SCIENTIFIC NAME': {"str": "name", "expected_type": str, "max_length": 50},
'MAX HT': {"str": "maxheight", "expected_type": float},
'SPACING': {"str": "spacing", "expected_type": float},
'COMMON NAME': {"str": "commonname", "expected_type": str, "null_allowed": True, "max_length": 200},
'SYNONYM': {"str": "synonym", "expected_type": str, "null_allowed": True, "max_length": 200},
'ECOLOGICAL REGION': {"str": "region", "expected_type": list, "model_name": "ecological_regions"},
'SOIL ORDER': {"str": "soilorder", "expected_type": list, "model_name": "soil_order"},
'Wet': {"str": "wet", "expected_type": list, "model_name": "soil_variants"},
'Mesic': {"str": "mesic", "expected_type": list, "model_name": "soil_variants"},
'Dry': {"str": "dry", "expected_type": list, "model_name": "soil_variants"},
'Water': {"str": "water", "expected_type": int, "model_name": "water_tolerance"},
'Drought': {"str": "drought", "expected_type": int, "model_name": "drought_tolerance"},
'Frost': {"str": "frost", "expected_type": int, "model_name": "frost_tolerance"},
'Salinity': {"str": "salinity", "expected_type": int, "model_name": "salinity_tolerance"},
'ES': {"str": "purpose", "expected_type": str, "null_allowed": True},
'STAGE': {"str": "stage", "expected_type": int},
'GrowthForm': {"str": "growthform", "expected_type": str, "model_name": "growth_form", "null_allowed": True, "max_length": 50}
}
# Spreadsheet constants
SPREADSHEET_FILENAME = 'plant_data.xlsx'
DATA_START_COL = 3
DATA_START_ROW = 6
INFO_HEADER_ROW = 4
# Data directory path
DATA_DIR_PATH = Path(right_tree.api.data.__file__).resolve().parent
# Mappings between values in the spreadsheet and primary key values in the database
ECO_REGION_PK_MAPPING = get_pk_mapping(EcologicalRegion)
SOIL_ORDER_PK_MAPPING = get_pk_mapping(SoilOrder)
SOIL_VARIANT_PK_MAPPING = get_pk_mapping(SoilVariant)
TOLERANCE_PK_MAPPING = get_pk_mapping(ToleranceLevel, "level")
# Spreadsheet and corresponding value to column index mappings
SPREADSHEET = get_spreadsheet(DATA_DIR_PATH, SPREADSHEET_FILENAME)
INFO_COL_INDEXES = get_col_mappings(
SPREADSHEET, DATA_START_COL, INFO_HEADER_ROW)
from ._spreadsheet_constants import *
# Template for the plant json to add as an entry for the fixtures
PLANT_JSON_TEMPLATE = {
@ -136,6 +82,14 @@ def get_plant_json_from_row(row_data):
return {}
# Add zone spreadsheet data to the plant json fields.
zone_list = []
for zone, zone_index in ZONE_COL_INDEXES.items():
if row_data[zone_index-DATA_START_COL] != None:
zone_list.append(ZONE_PK_MAPPING[zone])
plant_json_fields['zones'] = zone_list
# Create a plant json object using the defined template
plant_json = PLANT_JSON_TEMPLATE.copy()
plant_json["fields"] = plant_json_fields