excel.helpers.fill_uid.fill_uid_animals() - Code Metrics - Inspection of ":sparkles: import from Template file" - cnr-ibba/IMAGE-InjectTool - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — master (#40)

by Paolo

created 2019-07-09 15:23 UTC

excel.helpers.fill_uid.fill_uid_animals() B

↳ Parent: excel.helpers.fill_uid

Complexity

Conditions

Size

Total Lines	102
Code Lines	62

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
eloc	62
dl	0
loc	102
rs	7.7769
c	0
b	0
f	0
cc	5
nop	2

How to fix Long Method

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Jul  5 16:37:48 2019

@author: Paolo Cozzi <[email protected]>
"""

import logging

from common.constants import (
    ERROR, LOADED, ACCURACIES, SAMPLE_STORAGE, SAMPLE_STORAGE_PROCESSING)
from common.helpers import image_timedelta, parse_image_timedelta
from image_app.helpers import get_or_create_obj, update_or_create_obj
from image_app.models import (
    DictBreed, DictCountry, DictSpecie, DictSex, DictUberon, Name, Animal,
    Sample, DictDevelStage, DictPhysioStage)
from submissions.helpers import send_message
from validation.helpers import construct_validation_message
from validation.models import ValidationSummary

from .exceptions import ExcelImportError
from .exceltemplate import ExcelTemplateReader

# Get an instance of a logger
logger = logging.getLogger(__name__)


def fill_uid_breeds(submission_obj, template):
    """Fill DictBreed from a excel record"""

    logger.info("fill_uid_breeds() started")

    # ok get languages from submission (useful for translation)
    language = submission_obj.gene_bank_country.label

    # iterate among excel template
    for record in template.get_breed_records():
        # get a DictSpecie object. Species are in latin names, but I can
        # find also a common name in translation tables
        specie = DictSpecie.get_specie_check_synonyms(
            species_label=record.species,
            language=language)

        # get country for breeds. Ideally will be the same of submission,
        # however, it could be possible to store data from other contries
        country = get_or_create_obj(
            DictCountry,
            label=record.efabis_breed_country)

        get_or_create_obj(
            DictBreed,
            supplied_breed=record.supplied_breed,
            specie=specie,
            country=country)

    logger.info("fill_uid_breeds() completed")


def fill_uid_names(submission_obj, template):
    """fill Names table from crbanim record"""

    # debug
    logger.info("called fill_uid_names()")

    # iterate among excel template
    for record in template.get_animal_records():
        # in the same record I have the sample identifier and animal identifier
        # a name record for animal
        get_or_create_obj(
            Name,
            name=record.animal_id_in_data_source,
            submission=submission_obj,
            owner=submission_obj.owner)

    # iterate among excel template
    for record in template.get_sample_records():
        # name record for sample
        get_or_create_obj(
            Name,
            name=record.sample_id_in_data_source,
            submission=submission_obj,
            owner=submission_obj.owner)

    logger.info("fill_uid_names() completed")


def fill_uid_animals(submission_obj, template):
    # debug
    logger.info("called fill_uid_animals()")

    # iterate among excel template
    for record in template.get_animal_records():
        # determine sex. Check for values
        sex = DictSex.objects.get(label__iexact=record.sex)

        # get specie
        specie = DictSpecie.objects.get(label=record.species)

        # how I can get breed from my data?
        breeds = [breed for breed in template.get_breed_records()
                  if breed.supplied_breed == record.breed and
                  breed.species == record.species]

        # breed is supposed to be unique, from UID constraints. However
        # I could place the same breed name for two countries. In that case,
        # I cant derive a unique breed from users data
        if len(breeds) != 1:
            raise ExcelImportError(
                "Can't determine a unique breed for '%s:%s' from user data" %
                (record.breed, record.species))

        # get a country for this breed
        country = DictCountry.objects.get(
            label=breeds[0].efabis_breed_country)

        # ok get a real dictbreed object
        breed = DictBreed.objects.get(
            supplied_breed=record.breed,
            specie=specie,
            country=country)

        logger.debug("Selected breed is %s" % (breed))

        # define names
        name, mother, father = None, None, None

        # get name for this animal and for mother and father
        logger.debug("Getting %s as my name" % (
            record.animal_id_in_data_source))

        name = Name.objects.get(
            name=record.animal_id_in_data_source,
            submission=submission_obj)

        if record.father_id_in_data_source:
            logger.debug("Getting %s as father" % (
                record.father_id_in_data_source))

            father = Name.objects.get(
                name=record.father_id_in_data_source,
                submission=submission_obj)

        if record.mother_id_in_data_source:
            logger.debug("Getting %s as mother" % (
                record.mother_id_in_data_source))

            mother = Name.objects.get(
                name=record.mother_id_in_data_source,
                submission=submission_obj)

        # now get accuracy
        accuracy = ACCURACIES.get_value_by_desc(
            record.birth_location_accuracy)

        # create a new object. Using defaults to avoid collisions when
        # updating data
        defaults = {
            'alternative_id': record.alternative_animal_id,
            'description': record.animal_description,
            'breed': breed,
            'sex': sex,
            'father': father,
            'mother': mother,
            'birth_date': record.birth_date,
            'birth_location': record.birth_location,
            'birth_location_latitude': record.birth_location_latitude,
            'birth_location_longitude': record.birth_location_longitude,
            'birth_location_accuracy': accuracy,
            'owner': submission_obj.owner
        }

        # creating or updating an object
        update_or_create_obj(
            Animal,
            name=name,
            defaults=defaults)

    # create a validation summary object and set all_count
    validation_summary = get_or_create_obj(
        ValidationSummary,
        submission=submission_obj,
        type="animal")

    # reset counts
    validation_summary.reset_all_count()

    # debug
    logger.info("fill_uid_animals() completed")


def fill_uid_samples(submission_obj, template):
    # debug
    logger.info("called fill_uid_samples()")

    # iterate among excel template
    for record in template.get_sample_records():
        # get name for this sample
        name = Name.objects.get(
            name=record.sample_id_in_data_source,
            submission=submission_obj,
            owner=submission_obj.owner)

        # get animal by reading record
        animal = Animal.objects.get(
            name__name=record.animal_id_in_data_source,
            name__submission=submission_obj)

        # get a organism part. Organism parts need to be in lowercases
        organism_part = get_or_create_obj(
            DictUberon,
            label=record.organism_part
        )

        # get developmental_stage and physiological_stage terms
        # they are not mandatory
        devel_stage, physio_stage = None, None

        if record.developmental_stage:
            devel_stage = get_or_create_obj(
                DictDevelStage,
                label=record.developmental_stage
            )

        if record.physiological_stage:
            physio_stage = get_or_create_obj(
                DictPhysioStage,
                label=record.physiological_stage
            )

        # animal age could be present or not
        if record.animal_age_at_collection:
            animal_age_at_collection, time_units = parse_image_timedelta(
                record.animal_age_at_collection)

        else:
            # derive animal age at collection
            animal_age_at_collection, time_units = image_timedelta(
                record.collection_date, animal.birth_date)

        # another time column
        preparation_interval, preparation_interval_units = None, None

        if record.sampling_to_preparation_interval:
            preparation_interval, preparation_interval_units = \
                parse_image_timedelta(record.sampling_to_preparation_interval)

        # now get accuracy
        accuracy = ACCURACIES.get_value_by_desc(
            record.collection_place_accuracy)

        # now get storage and storage processing
        # TODO; check those values in excel columns
        storage = SAMPLE_STORAGE.get_value_by_desc(
            record.sample_storage)

        storage_processing = SAMPLE_STORAGE_PROCESSING.get_value_by_desc(
            record.sample_storage_processing)

        # create a new object. Using defaults to avoid collisions when
        # updating data
        defaults = {
            'alternative_id': record.alternative_sample_id,
            'description': record.sample_description,
            'animal': animal,
            'protocol': record.specimen_collection_protocol,
            'collection_date': record.collection_date,
            'collection_place_latitude': record.collection_place_latitude,
            'collection_place_longitude': record.collection_place_longitude,
            'collection_place': record.collection_place,
            'collection_place_accuracy': accuracy,
            'organism_part': organism_part,
            'developmental_stage': devel_stage,
            'physiological_stage': physio_stage,
            'animal_age_at_collection': animal_age_at_collection,
            'animal_age_at_collection_units': time_units,
            'availability': record.availability,
            'storage': storage,
            'storage_processing': storage_processing,
            'preparation_interval': preparation_interval,
            'preparation_interval_units': preparation_interval_units,
            'owner': submission_obj.owner,
        }

        update_or_create_obj(
            Sample,
            name=name,
            defaults=defaults)

    # create a validation summary object and set all_count
    validation_summary = get_or_create_obj(
        ValidationSummary,
        submission=submission_obj,
        type="sample")

    # reset counts
    validation_summary.reset_all_count()

    # debug
    logger.info("fill_uid_samples() completed")


def upload_template(submission_obj):
    # debug
    logger.info("Importing from Excel template file")

    # this is the full path in docker container
    fullpath = submission_obj.get_uploaded_file_path()

    # read submission data
    reader = ExcelTemplateReader()
    reader.read_file(fullpath)

    # start data loading
    try:
        # check for species and sex in a similar way as cryoweb does
        # TODO: identical to CRBanim. Move to a mixin
        check, not_found = reader.check_sex()

        if not check:
            message = (
                "Not all Sex terms are loaded into database: "
                "check for %s in your dataset" % (not_found))

            raise ExcelImportError(message)

        check, not_found = reader.check_species(
            submission_obj.gene_bank_country)

        if not check:
            raise ExcelImportError(
                "Some species are not loaded in UID database: "
                "%s" % (not_found))

        check, not_found = reader.check_accuracies()

        if not check:
            message = (
                "Not all accuracy levels are defined in database: "
                "check for %s in your dataset" % (not_found))

            raise ExcelImportError(message)

        # BREEDS
        fill_uid_breeds(submission_obj, reader)

        # NAME
        fill_uid_names(submission_obj, reader)

        # ANIMALS
        fill_uid_animals(submission_obj, reader)

        # SAMPLES
        fill_uid_samples(submission_obj, reader)

    except Exception as exc:
        # set message:
        message = "Error in importing data: %s" % (str(exc))

        # save a message in database
        submission_obj.status = ERROR
        submission_obj.message = message
        submission_obj.save()

        # send async message
        send_message(submission_obj)

        # debug
        logger.error("Error in importing from Template: %s" % (exc))
        logger.exception(exc)

        return False

    else:
        message = "Template import completed for submission: %s" % (
            submission_obj.id)

        submission_obj.message = message
        submission_obj.status = LOADED
        submission_obj.save()

        # send async message
        send_message(
            submission_obj,
            validation_message=construct_validation_message(submission_obj))

    logger.info("Import from Template is complete")

    return True


1			#!/usr/bin/env python3
2			# -- coding: utf-8 --
3			"""
4			Created on Fri Jul 5 16:37:48 2019
5
6			@author: Paolo Cozzi <[email protected]>
7			"""
8
9			import logging
10
11			from common.constants import (
12			ERROR, LOADED, ACCURACIES, SAMPLE_STORAGE, SAMPLE_STORAGE_PROCESSING)
13			from common.helpers import image_timedelta, parse_image_timedelta
14			from image_app.helpers import get_or_create_obj, update_or_create_obj
15			from image_app.models import (
16			DictBreed, DictCountry, DictSpecie, DictSex, DictUberon, Name, Animal,
17			Sample, DictDevelStage, DictPhysioStage)
18			from submissions.helpers import send_message
19			from validation.helpers import construct_validation_message
20			from validation.models import ValidationSummary
21
22			from .exceptions import ExcelImportError
23			from .exceltemplate import ExcelTemplateReader
24
25			# Get an instance of a logger
26			logger = logging.getLogger(__name__)
27
28
29			def fill_uid_breeds(submission_obj, template):
30			"""Fill DictBreed from a excel record"""
31
32			logger.info("fill_uid_breeds() started")
33
34			# ok get languages from submission (useful for translation)
35			language = submission_obj.gene_bank_country.label
36
37			# iterate among excel template
38			for record in template.get_breed_records():
39			# get a DictSpecie object. Species are in latin names, but I can
40			# find also a common name in translation tables
41			specie = DictSpecie.get_specie_check_synonyms(
42			species_label=record.species,
43			language=language)
44
45			# get country for breeds. Ideally will be the same of submission,
46			# however, it could be possible to store data from other contries
47			country = get_or_create_obj(
48			DictCountry,
49			label=record.efabis_breed_country)
50
51			get_or_create_obj(
52			DictBreed,
53			supplied_breed=record.supplied_breed,
54			specie=specie,
55			country=country)
56
57			logger.info("fill_uid_breeds() completed")
58
59
60			def fill_uid_names(submission_obj, template):
61			"""fill Names table from crbanim record"""
62
63			# debug
64			logger.info("called fill_uid_names()")
65
66			# iterate among excel template
67			for record in template.get_animal_records():
68			# in the same record I have the sample identifier and animal identifier
69			# a name record for animal
70			get_or_create_obj(
71			Name,
72			name=record.animal_id_in_data_source,
73			submission=submission_obj,
74			owner=submission_obj.owner)
75
76			# iterate among excel template
77			for record in template.get_sample_records():
78			# name record for sample
79			get_or_create_obj(
80			Name,
81			name=record.sample_id_in_data_source,
82			submission=submission_obj,
83			owner=submission_obj.owner)
84
85			logger.info("fill_uid_names() completed")
86
87
88			def fill_uid_animals(submission_obj, template):
89			# debug
90			logger.info("called fill_uid_animals()")
91
92			# iterate among excel template
93			for record in template.get_animal_records():
94			# determine sex. Check for values
95			sex = DictSex.objects.get(label__iexact=record.sex)
96
97			# get specie
98			specie = DictSpecie.objects.get(label=record.species)
99
100			# how I can get breed from my data?
101			breeds = [breed for breed in template.get_breed_records()
102			if breed.supplied_breed == record.breed and
103			breed.species == record.species]
104
105			# breed is supposed to be unique, from UID constraints. However
106			# I could place the same breed name for two countries. In that case,
107			# I cant derive a unique breed from users data
108			if len(breeds) != 1:
109			raise ExcelImportError(
110			"Can't determine a unique breed for '%s:%s' from user data" %
111			(record.breed, record.species))
112
113			# get a country for this breed
114			country = DictCountry.objects.get(
115			label=breeds[0].efabis_breed_country)
116
117			# ok get a real dictbreed object
118			breed = DictBreed.objects.get(
119			supplied_breed=record.breed,
120			specie=specie,
121			country=country)
122
123			logger.debug("Selected breed is %s" % (breed))
124
125			# define names
126			name, mother, father = None, None, None
127
128			# get name for this animal and for mother and father
129			logger.debug("Getting %s as my name" % (
130			record.animal_id_in_data_source))
131
132			name = Name.objects.get(
133			name=record.animal_id_in_data_source,
134			submission=submission_obj)
135
136			if record.father_id_in_data_source:
137			logger.debug("Getting %s as father" % (
138			record.father_id_in_data_source))
139
140			father = Name.objects.get(
141			name=record.father_id_in_data_source,
142			submission=submission_obj)
143
144			if record.mother_id_in_data_source:
145			logger.debug("Getting %s as mother" % (
146			record.mother_id_in_data_source))
147
148			mother = Name.objects.get(
149			name=record.mother_id_in_data_source,
150			submission=submission_obj)
151
152			# now get accuracy
153			accuracy = ACCURACIES.get_value_by_desc(
154			record.birth_location_accuracy)
155
156			# create a new object. Using defaults to avoid collisions when
157			# updating data
158			defaults = {
159			'alternative_id': record.alternative_animal_id,
160			'description': record.animal_description,
161			'breed': breed,
162			'sex': sex,
163			'father': father,
164			'mother': mother,
165			'birth_date': record.birth_date,
166			'birth_location': record.birth_location,
167			'birth_location_latitude': record.birth_location_latitude,
168			'birth_location_longitude': record.birth_location_longitude,
169			'birth_location_accuracy': accuracy,
170			'owner': submission_obj.owner
171			}
172
173			# creating or updating an object
174			update_or_create_obj(
175			Animal,
176			name=name,
177			defaults=defaults)
178
179			# create a validation summary object and set all_count
180			validation_summary = get_or_create_obj(
181			ValidationSummary,
182			submission=submission_obj,
183			type="animal")
184
185			# reset counts
186			validation_summary.reset_all_count()
187
188			# debug
189			logger.info("fill_uid_animals() completed")
190
191
192			def fill_uid_samples(submission_obj, template):
193			# debug
194			logger.info("called fill_uid_samples()")
195
196			# iterate among excel template
197			for record in template.get_sample_records():
198			# get name for this sample
199			name = Name.objects.get(
200			name=record.sample_id_in_data_source,
201			submission=submission_obj,
202			owner=submission_obj.owner)
203
204			# get animal by reading record
205			animal = Animal.objects.get(
206			name__name=record.animal_id_in_data_source,
207			name__submission=submission_obj)
208
209			# get a organism part. Organism parts need to be in lowercases
210			organism_part = get_or_create_obj(
211			DictUberon,
212			label=record.organism_part
213			)
214
215			# get developmental_stage and physiological_stage terms
216			# they are not mandatory
217			devel_stage, physio_stage = None, None
218
219			if record.developmental_stage:
220			devel_stage = get_or_create_obj(
221			DictDevelStage,
222			label=record.developmental_stage
223			)
224
225			if record.physiological_stage:
226			physio_stage = get_or_create_obj(
227			DictPhysioStage,
228			label=record.physiological_stage
229			)
230
231			# animal age could be present or not
232			if record.animal_age_at_collection:
233			animal_age_at_collection, time_units = parse_image_timedelta(
234			record.animal_age_at_collection)
235
236			else:
237			# derive animal age at collection
238			animal_age_at_collection, time_units = image_timedelta(
239			record.collection_date, animal.birth_date)
240
241			# another time column
242			preparation_interval, preparation_interval_units = None, None
243
244			if record.sampling_to_preparation_interval:
245			preparation_interval, preparation_interval_units = \
246			parse_image_timedelta(record.sampling_to_preparation_interval)
247
248			# now get accuracy
249			accuracy = ACCURACIES.get_value_by_desc(
250			record.collection_place_accuracy)
251
252			# now get storage and storage processing
253			# TODO; check those values in excel columns
254			storage = SAMPLE_STORAGE.get_value_by_desc(
255			record.sample_storage)
256
257			storage_processing = SAMPLE_STORAGE_PROCESSING.get_value_by_desc(
258			record.sample_storage_processing)
259
260			# create a new object. Using defaults to avoid collisions when
261			# updating data
262			defaults = {
263			'alternative_id': record.alternative_sample_id,
264			'description': record.sample_description,
265			'animal': animal,
266			'protocol': record.specimen_collection_protocol,
267			'collection_date': record.collection_date,
268			'collection_place_latitude': record.collection_place_latitude,
269			'collection_place_longitude': record.collection_place_longitude,
270			'collection_place': record.collection_place,
271			'collection_place_accuracy': accuracy,
272			'organism_part': organism_part,
273			'developmental_stage': devel_stage,
274			'physiological_stage': physio_stage,
275			'animal_age_at_collection': animal_age_at_collection,
276			'animal_age_at_collection_units': time_units,
277			'availability': record.availability,
278			'storage': storage,
279			'storage_processing': storage_processing,
280			'preparation_interval': preparation_interval,
281			'preparation_interval_units': preparation_interval_units,
282			'owner': submission_obj.owner,
283			}
284
285			update_or_create_obj(
286			Sample,
287			name=name,
288			defaults=defaults)
289
290			# create a validation summary object and set all_count
291			validation_summary = get_or_create_obj(
292			ValidationSummary,
293			submission=submission_obj,
294			type="sample")
295
296			# reset counts
297			validation_summary.reset_all_count()
298
299			# debug
300			logger.info("fill_uid_samples() completed")
301
302
303			def upload_template(submission_obj):
304			# debug
305			logger.info("Importing from Excel template file")
306
307			# this is the full path in docker container
308			fullpath = submission_obj.get_uploaded_file_path()
309
310			# read submission data
311			reader = ExcelTemplateReader()
312			reader.read_file(fullpath)
313
314			# start data loading
315			try:
316			# check for species and sex in a similar way as cryoweb does
317			# TODO: identical to CRBanim. Move to a mixin
318			check, not_found = reader.check_sex()
319
320			if not check:
321			message = (
322			"Not all Sex terms are loaded into database: "
323			"check for %s in your dataset" % (not_found))
324
325			raise ExcelImportError(message)
326
327			check, not_found = reader.check_species(
328			submission_obj.gene_bank_country)
329
330			if not check:
331			raise ExcelImportError(
332			"Some species are not loaded in UID database: "
333			"%s" % (not_found))
334
335			check, not_found = reader.check_accuracies()
336
337			if not check:
338			message = (
339			"Not all accuracy levels are defined in database: "
340			"check for %s in your dataset" % (not_found))
341
342			raise ExcelImportError(message)
343
344			# BREEDS
345			fill_uid_breeds(submission_obj, reader)
346
347			# NAME
348			fill_uid_names(submission_obj, reader)
349
350			# ANIMALS
351			fill_uid_animals(submission_obj, reader)
352
353			# SAMPLES
354			fill_uid_samples(submission_obj, reader)
355
356			except Exception as exc:
357			# set message:
358			message = "Error in importing data: %s" % (str(exc))
359
360			# save a message in database
361			submission_obj.status = ERROR
362			submission_obj.message = message
363			submission_obj.save()
364
365			# send async message
366			send_message(submission_obj)
367
368			# debug
369			logger.error("Error in importing from Template: %s" % (exc))
370			logger.exception(exc)
371
372			return False
373
374			else:
375			message = "Template import completed for submission: %s" % (
376			submission_obj.id)
377
378			submission_obj.message = message
379			submission_obj.status = LOADED
380			submission_obj.save()
381
382			# send async message
383			send_message(
384			submission_obj,
385			validation_message=construct_validation_message(submission_obj))
386
387			logger.info("Import from Template is complete")
388
389			return True
390

cnr-ibba / IMAGE-InjectTool

Pull Request — master (#40)

excel.helpers.fill_uid.fill_uid_animals() B

Complexity

Size

Duplication

Importance

How to fix Long Method

Long Method

Duplication Side-by-Side

Filter issues like