class MixedFoodCatalog(Catalog):
def get_list(self):
return self.__food
def __str__(self):
return "mixed food catalog"
def __init__(self, mixed_tidy_food_file_path):
super().__init__()
self.mixed_tidy_food_file_path = mixed_tidy_food_file_path
self.__hash_tree = None
self.__food = None
def initialize(self):
t1 = time()
logger.info('Creating mixed food catalog...')
with open(self.mixed_tidy_food_file_path) as file:
food = file.read().splitlines()
self.__hash_tree = HashTree(food)
self.__food = food
t2 = time()
logger.info('Done creating mixed food catalog. Total time: %.2f sec.' % (t2 - t1))
def find(self, sentence_text):
food_names = self.__hash_tree.search(sentence_text)
entities = EntityCollection([Entity(name, 'nogroup', FOOD_TAG) for name in food_names], FOOD_TAG)
return entities
class PrebioticsCatalog(Catalog):
def get_list(self):
pass
def __init__(self, tidy_csv_path):
super().__init__()
self.tidy_csv_path = tidy_csv_path
self.__hash_tree = None
self.__prebiotics = None
def initialize(self):
t1 = time()
logger.info('Creating prebiotics catalog...')
with open(self.tidy_csv_path) as file:
prebiotics = file.read().splitlines()
self.__hash_tree = HashTree(prebiotics)
self.__prebiotics = prebiotics
t2 = time()
logger.info('Done creating prebiotics catalog. Total time: %.2f sec.' % (t2 - t1))
def find(self, sentence_text):
prebiotic_names = self.__hash_tree.search(sentence_text)
entities = EntityCollection([Entity(name, 'noid', PREBIOTIC_TAG) for name in prebiotic_names], PREBIOTIC_TAG)
return entities
class UsdaFoodCatalog(Catalog):
def get_list(self):
return list(self.__food_data_frame['group'].drop_duplicates()) + list(self.__food_data_frame['name'])
def __str__(self):
return "usda food catalog"
def __init__(self, food_file_path):
super().__init__()
self.food_file_path = food_file_path
self.__hash_tree = None
self.__food_dict = None
self.__group_by_food_name = None
self.__food_data_frame = None
def initialize(self):
t1= time()
logger.info('Creating food catalog...')
self.__food_data_frame = pd.read_table(self.food_file_path, sep=',')
self.__food_dict = {food_group: [] for food_group in self.__food_data_frame['group'].values}
for index, record in self.__food_data_frame.iterrows():
self.__food_dict[record['group']].append(record['name'].strip())
self.__group_by_food_name = {food: group for group, food_list in self.__food_dict.items() for food in food_list}
self.__hash_tree = HashTree(self.__group_by_food_name.keys())
t2 = time()
logger.info('Done creating food catalog. Total time: %.2f sec.' % (t2 - t1))
def find(self, sentence_text):
food_names = self.__hash_tree.search(sentence_text)
entities = EntityCollection([Entity(name, self.__group_by_food_name[name], FOOD_TAG) for name in food_names],
FOOD_TAG)
return entities
def initialize(self):
t1 = time()
logger.info('Creating mixed food catalog...')
with open(self.mixed_tidy_food_file_path) as file:
food = file.read().splitlines()
self.__hash_tree = HashTree(food)
self.__food = food
t2 = time()
logger.info('Done creating mixed food catalog. Total time: %.2f sec.' % (t2 - t1))
def initialize(self):
t1 = time()
logger.info('Creating prebiotics catalog...')
with open(self.tidy_csv_path) as file:
prebiotics = file.read().splitlines()
self.__hash_tree = HashTree(prebiotics)
self.__prebiotics = prebiotics
t2 = time()
logger.info('Done creating prebiotics catalog. Total time: %.2f sec.' % (t2 - t1))
def initialize(self):
t1= time()
logger.info('Creating food catalog...')
self.__food_data_frame = pd.read_table(self.food_file_path, sep=',')
self.__food_dict = {food_group: [] for food_group in self.__food_data_frame['group'].values}
for index, record in self.__food_data_frame.iterrows():
self.__food_dict[record['group']].append(record['name'].strip())
self.__group_by_food_name = {food: group for group, food_list in self.__food_dict.items() for food in food_list}
self.__hash_tree = HashTree(self.__group_by_food_name.keys())
t2 = time()
logger.info('Done creating food catalog. Total time: %.2f sec.' % (t2 - t1))
def initialize(self):
t1 = time()
constants.logger.info('Creating diseases catalog...')
data = pd.read_csv(self.diseases_csv_path, sep="\t")
data = data[['id', 'name']]
data_dict = data.to_dict("records")
for row in data_dict:
self.disease_dictionary[row['name']] = row['id']
self.hash_tree = HashTree(self.disease_dictionary.keys())
t2 = time()
constants.logger.info('Done creating diseases catalog. Total time: %.2f sec.' % (t2 - t1))
def initialize(self):
t1 = time()
constants.logger.info('Creating nutrients catalog...')
data = pd.read_csv(self.path, sep="\t")
self.__nutrients_by_idname = {idname: [] for idname in data['idname'].values}
for index, record in data.iterrows():
self.__nutrients_by_idname[record['idname']].append(record['name'])
self.__idname_by_nutrient = {name: idname for idname, name_list in
self.__nutrients_by_idname.items() for name in name_list}
self.__hash_tree = HashTree(self.__idname_by_nutrient.keys())
t2 = time()
constants.logger.info('Done creating nutrients catalog. Total time: %.2f sec.' % (t2 - t1))
class NutrientsCatalogNikogosov(Catalog):
"""Object holding nutrient ontology"""
def __init__(self, path):
self.path = path
self.__nutrients_by_idname = None
self.__idname_by_nutrient = None
self.__hash_tree = None
def initialize(self):
t1 = time()
constants.logger.info('Creating nutrients catalog...')
data = pd.read_csv(self.path, sep="\t")
self.__nutrients_by_idname = {idname: [] for idname in data['idname'].values}
for index, record in data.iterrows():
self.__nutrients_by_idname[record['idname']].append(record['name'])
self.__idname_by_nutrient = {name: idname for idname, name_list in
self.__nutrients_by_idname.items() for name in name_list}
self.__hash_tree = HashTree(self.__idname_by_nutrient.keys())
t2 = time()
constants.logger.info('Done creating nutrients catalog. Total time: %.2f sec.' % (t2 - t1))
def find(self, sentence_text):
""" Uses previously generated hash tree to search sentence for nutrient names
input:
sentence: sentence to search for nutrient names
returns:
list of nutrient_names
"""
nutr_names = self.__hash_tree.search(sentence_text)
entities = EntityCollection([Entity(nutrient,
self.__idname_by_nutrient[nutrient],
NUTRIENT_TAG) for nutrient in nutr_names])
return entities
def get_list(self):
nutrients = []
for key, value in self.__nutrients_by_idname.items():
nutrients.append(value[0])
return nutrients
def initialize(self):
"""Creation of catalog object
input:
:param verbose:
creates:
self.__scientific_names: dictionary with NCBI_id as key and scientific bacteria name as value
self.__bact_id_dict: dictionary with various versions of bacterial names as keys and NCBI_id as value
self.hash_tree_root: root node of hash tree
"""
t1 = time()
logger.info('Creating all bacterial catalog...')
names = pd.read_table(self.all_bact_path, sep=',')
names_scientific = self.sci_names(table_names=names)
self.__scientific_names = names_scientific.set_index('id').T.to_dict('records')[0]
self.__bact_id_dict = names[['name', 'id']].set_index('name').T.to_dict('records')[0]
self.__hash_tree = HashTree(self.__bact_id_dict.keys())
t2 = time()
logger.info('Done creating bacterial catalog. Total time: %.2f sec.' % (t2 - t1))
class DiseasesCatalog(Catalog):
def get_list(self):
pass
def __str__(self):
return "diseases catalog"
def __init__(self, diseases_csv_path):
self.disease_dictionary = {}
self.hash_tree = None
self.diseases_csv_path = diseases_csv_path
def initialize(self):
t1 = time()
constants.logger.info('Creating diseases catalog...')
data = pd.read_csv(self.diseases_csv_path, sep="\t")
data = data[['id', 'name']]
data_dict = data.to_dict("records")
for row in data_dict:
self.disease_dictionary[row['name']] = row['id']
self.hash_tree = HashTree(self.disease_dictionary.keys())
t2 = time()
constants.logger.info('Done creating diseases catalog. Total time: %.2f sec.' % (t2 - t1))
def find(self, sentence_text):
""" Uses previously generated hash tree to search sentence for nutrient names
input:
sentence: sentence to search for nutrient names
returns:
list of nutrient_names
"""
sentence_text = re.sub('[’\']', '', sentence_text)
diseases_names = self.hash_tree.search(sentence_text)
entities = EntityCollection([Entity(name,
self.disease_dictionary[name],
DISEASE_TAG) for name in diseases_names], DISEASE_TAG)
return entities
class AllBacteriaCatalog(Catalog):
"""Object holding NCBI ontology"""
def get_list(self):
pass
def __str__(self):
return "all bacteria catalog"
def __init__(self, all_bact_path):
self.all_bact_path = all_bact_path
self.__scientific_names = None
self.__bact_id_dict = None
self.__hash_tree = None
def initialize(self):
"""Creation of catalog object
input:
:param verbose:
creates:
self.__scientific_names: dictionary with NCBI_id as key and scientific bacteria name as value
self.__bact_id_dict: dictionary with various versions of bacterial names as keys and NCBI_id as value
self.hash_tree_root: root node of hash tree
"""
t1 = time()
logger.info('Creating all bacterial catalog...')
names = pd.read_table(self.all_bact_path, sep=',')
names_scientific = self.sci_names(table_names=names)
self.__scientific_names = names_scientific.set_index('id').T.to_dict('records')[0]
self.__bact_id_dict = names[['name', 'id']].set_index('name').T.to_dict('records')[0]
self.__hash_tree = HashTree(self.__bact_id_dict.keys())
t2 = time()
logger.info('Done creating bacterial catalog. Total time: %.2f sec.' % (t2 - t1))
def find(self, sentence_text):
""" Uses previously generated hash tree to search sentence for bacterial names
input:
sentence: sentence to search for bacterial names
returns:
list of (bactrium_name, NCBI_id) tuples found in sentence
:param sentence_text:
"""
bact_names = self.__hash_tree.search(sentence_text)
bact_ids = [self.__bact_id_dict[name] for name in bact_names]
output_list = list(zip(bact_names, bact_ids))
entities = EntityCollection([Entity(name,
code,
BACTERIA_TAG,
[ALL_BACTERIA_TAG]) for name, code in output_list], BACTERIA_TAG)
return entities
def get_scientific_name(self, ncbi_id):
return self.__scientific_names[ncbi_id]
def sci_names(self, table_names):
names_scientific = table_names.loc[(table_names['class'] == 'scientific name') &
(~table_names['id'].isnull()),
['name', 'id']].drop_duplicates(subset=['id'])
return names_scientific
