def get_general_info():
return jsonify({
'all datasets': dt.list_datasets(),
'id types': dt.list_idtypes(),
'id manager': dt.get_idmanager(),
'mapping manager': dt.get_mappingmanager()
})
def update_weights(values):
partial_header = ["CCI_SCORE"]
split_values = values.split('+')
for i in range(0, len(partial_header)):
weights_CCI[partial_header[i]] = int(split_values[i])
return jsonify({'weights': weights_CCI})
def display_descriptions(term):
concept1 = mongo.db.s20160901
output1 = []
for q1 in concept1.find({'sctName': {"$regex": term, "$options": "i"}}):
output1.append(q1)
return jsonify(output1)
def get_pat_info(PAT_ID, dataset):
return jsonify({
'Demo':
get_info([int(PAT_ID)], dataset_hash['Demo'][dataset]),
'Orders':
get_info([int(PAT_ID)], dataset_hash['Orders'][dataset]),
'PRO':
get_info([int(PAT_ID)], dataset_hash['PRO'][dataset])
})
def display_icd10codes(name):
concept = mongo.db.s20160901
output = []
for q in concept.find({'mapTarget': name}):
output.append(q)
return jsonify(output)
def display_concepts(name):
concept = mongo.db.s20160901
output = []
for q in concept.find({'referencedComponentId': name}):
output.append(q)
return jsonify(output)
def display_initial():
concept = mongo.db.s20160901
output = []
for q in concept.find({}).limit(300):
output.append(q)
return jsonify(output)
def get_result(task_id):
"""
returns the result of a task with blocking
:param task_id:
:return:
"""
from phovea_processing_queue.task_definition import get_result
res = get_result(task_id)
return jsonify(res.get())
def update_weights(values):
partial_header = [
"PAT_BIRTHDATE", "PAT_GENDER", "PAT_ETHNICITY", "PAT_RACE",
"PAT_MARITAL_STAT", "BMI", "HEIGHT_CM", "WEIGHT_KG", "TOBACCO_USER",
"ALCOHOL_USER", "ILLICIT_DRUG_USER"
]
split_values = values.split('+')
for i in range(0, len(partial_header)):
weights_Demo[partial_header[i]] = int(split_values[i])
return jsonify({'weights': weights_Demo})
def get_generated_username():
# use additional random integer to increase possible combinations
# import random
# new_username = f"{pydng.generate_name()}_{random.randint(1, 10)}"
new_username = pydng.generate_name(
) # 108 adjectives * 237 lastnames = 25.596 combinations
if (username_exists(new_username)):
_log.info(F"Generated user {new_username} already exists. Retrying...")
return get_generated_username()
return jsonify(new_username)
def get_similar_rows(PAT_ID, number, dataset):
Demo_score = handle_Demo.get_similarity_score(
int(PAT_ID), dataset_hash['Demo'][dataset])
CCI_score = handle_CCI.get_similarity_score(int(PAT_ID),
dataset_hash['CCI'][dataset])
Pro_score = handle_pro.get_similarity_score(int(PAT_ID),
dataset_hash['PRO'][dataset])
id_scores = []
pat_ids = set(list(Demo_score.keys()) + (list(CCI_score.keys())))
for id in pat_ids:
temp = 0
if id in Demo_score:
temp += Demo_score[id]
if id in CCI_score:
temp += CCI_score[id]
if id in Pro_score:
temp += Pro_score[id]
id_scores.append([id, temp])
id_scores.sort(key=lambda r: r[1], reverse=True)
ids = [d[0] for d in id_scores[:number]]
scores = [d[1] for d in id_scores[:number]]
all_scores = [d[1] for d in id_scores]
pat_demo_info = get_info([int(PAT_ID)], dataset_hash['Demo'][dataset])
demo_info = get_info(ids, dataset_hash['Demo'][dataset])
pat_pro_info = get_info([int(PAT_ID)], dataset_hash['PRO'][dataset])
pro_info = get_info(ids, dataset_hash['PRO'][dataset])
pat_orders_info = get_info([int(PAT_ID)], dataset_hash['Orders'][dataset])
orders_info = get_info(ids, dataset_hash['Orders'][dataset])
#difference = handle_Demo.get_difference(int(PAT_ID), ids) # maybe in the client?!
return jsonify({
'PAT_ID': PAT_ID,
'ids': ids,
'all_scores': all_scores,
'similarity_scores': scores,
'pat_Demo': pat_demo_info,
'pat_PRO': pat_pro_info,
'pat_Orders': pat_orders_info,
'similar_Demo': demo_info,
'similar_PRO': pro_info,
'similar_Orders': orders_info
#'difference': difference
#'all_pro_rows': sum(pro_rows, get_all_info_for_pat('PRO', int(PAT_ID)))
})
def get_latest_info():
data = dt.get('Demo').aslist()
pat_ids = set([int(d['PAT_ID']) for d in data])
pats = []
pat_weights = []
for id in pat_ids:
temp_pat = []
for row in data:
if row['PAT_ID'] == id:
temp_pat.append(row)
temp_pat.sort(key=lambda x: to_date_time(x['ADM_DATE']), reverse=True)
pats.append(temp_pat[0])
pat_weights.append(
[t['WEIGHT_KG'] for t in temp_pat if t['WEIGHT_KG']])
return jsonify({'rows': pats, 'WEIGHT_KG': pat_weights})
def get_info_by_functions(id):
my_data = dt.get(id)
#range = rng.RangeElem(2, 5, 1)
return jsonify({
'id': id,
'my_data': my_data,
'rows': my_data.rows(),
'data': my_data.asjson(),
'rowids': my_data.rowids(),
'aslist': my_data.aslist(),
'aspandas': my_data.aspandas(),
'columns': my_data.columns,
'CSVEntry.to_description': my_data.to_description(),
'CSVEntry.idtypes': my_data.idtypes() #,
#'asList( range(2,5,1) )': my_data.aslist(range),
#'rows( range(2,5,1) )': my_data.rows(range),
#'aspandas( range(2,5,1) )': my_data.aspandas(range)
})
def get_stat(dataset):
my_data = dt.get(dataset_hash['Demo'][dataset])
data = my_data.aslist()
length = 0
gender = [0, 0]
bmi = [0, 0, 0, 0, 0, 0, 0]
age = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
today = pd.datetime.today()
for row in data:
length += 1
if row['PAT_GENDER'] == 'F':
gender[0] += 1
elif row['PAT_GENDER'] == 'M':
gender[1] += 1
if not row['BMI']:
bmi[0] += 1
elif row['BMI'] <= 18:
bmi[1] += 1
elif row['BMI'] > 30:
bmi[6] += 1
else:
bmi[int(math.ceil((row['BMI'] - 15) / 3))] += 1
pat_age = int(
(today - to_date_time(row['PAT_BIRTHDATE'])).days / 365.25)
if pat_age <= 10:
age[0] += 1
elif pat_age > 100:
age[10] += 1
else:
age[int(math.floor((pat_age - 1) / 10))] += 1
return jsonify({
'length': length,
'GENDER': gender,
'BMI': bmi,
'AGE': age
})
def get_order_type(dataset, ordertype):
filtered_orders = handle_Orders.get_order_type(
dataset_hash['Orders'][dataset], ordertype)
return jsonify({'filtered_Orders': filtered_orders})
def get_filtered_orders_by_month(dataset, order):
filtered_orders = handle_Orders.get_filteres_orders(
dataset_hash['Orders'][dataset], order)
return jsonify({'filtered_Orders': filtered_orders})
def get_latest_info(dataset_id):
if dataset_id == 'Demo':
return handle_Demo.get_latest_info()
return jsonify({'message': 'error'})
def get_weights():
return jsonify({'weights': weights_Demo})
def _func():
return jsonify({'message': 'Get method'})
def get_weights():
return jsonify({'weights': weights_CCI})
def _test():
return jsonify({'message': simplePythonFile.simple_python_method()})
def get_col_titles(id):
my_data = dt.get(id)
return jsonify({'cols': my_data.columns})
def get_col_by_name(id, col_name):
my_data = dt.get(id)
cols = my_data.aspandas()
return jsonify({'cols': cols[col_name]})
def get_all_rows(dataset_id):
my_data = dt.get(dataset_id)
rows = my_data.aslist()
return jsonify({dataset_id: rows[:50]})
def hist():
# hist?cohortId=2&type=dataCat&attribute=race
# hist?cohortId=2&type=dataNum&attribute=age
# hist?cohortId=2&type=geneScoreCat&attribute=aa_mutated&table=mutation&ensg=ENSG00000141510
# hist?cohortId=2&type=geneScoreNum&attribute=relativecopynumber&table=copynumber&ensg=ENSG00000141510
# hist?cohortId=3&type=depletionScore&attribute=rsa&table=depletionscore&ensg=ENSG00000141510&depletionscreen=Drive
# hist?cohortId=2&type=panelAnnotation&panel=TCGA normals
error_msg = """Paramerter missing or wrong!
For the {route} query the following parameter is needed:
- cohortId: id of the cohort parent cohort
- type: dataCat | dataNum | geneScoreCat | geneScoreNum | depletionScore | panelAnnotation
Depending on the 'type' different additional parameters have to exist
--> Type: dataCat | dataNum
- attribute: the entity attribute
--> Type: geneScoreCat | geneScoreNum
- table: the score table, which contains the attribute
- attribute: the score attribute
- ensg: name of the gene
--> Type: depletionScore
- table: the score table, which contains the attribute
- attribute: the score attribute
- ensg: name of the gene
- depletionscreen: name of the screen
--> Type: panelAnnotation
- panel: name of the panel""".format(route='hist')
try:
query = QueryElements()
type = request.values.get('type') # get type of hist
if type is None:
raise RuntimeError(error_msg)
hist = jsonify([])
cohort = query.get_cohort_from_db(request.values,
error_msg) # get cohort
database = cohort.entity_database
num_bins = 10
if type == 'dataCat':
# - cohortId: id of the cohort
# - attribute: the entity attribute
sql_text = query.get_hist_cat_sql(request.values, cohort,
error_msg)
hist = query.execute_sql_query(
sql_text, database,
config.supp_statement_timeout) # execute sql statement
elif type == 'dataNum':
# - cohortId: id of the cohort
# - attribute: the entity attribute
sql_text = query.get_hist_num_sql(request.values, cohort, num_bins,
error_msg)
hist_dict = query.execute_sql_query_as_dict(
sql_text, database,
config.supp_statement_timeout) # execute sql statement
hist = query.format_num_hist(hist_dict, num_bins)
elif type == 'geneScoreCat':
# - cohortId: id of the cohort
# - table: the score table, which contains the attribute
# - attribute: the score attribute
# - ensg: name of the gene
sql_text = query.get_hist_gene_cat_sql(request.values, cohort,
error_msg)
hist = query.execute_sql_query(
sql_text, database,
config.supp_statement_timeout) # execute sql statement
elif type == 'geneScoreNum':
# - cohortId: id of the cohort
# - table: the score table, which contains the attribute
# - attribute: the score attribute
# - ensg: name of the gene
sql_text = query.get_hist_gene_num_sql(request.values, cohort,
num_bins, error_msg)
hist_dict = query.execute_sql_query_as_dict(
sql_text, database,
config.supp_statement_timeout) # execute sql statement
hist = query.format_num_hist(hist_dict, num_bins)
elif type == 'depletionScore':
# - cohortId: id of the cohort
# - table: the score table, which contains the attribute
# - attribute: the score attribute
# - ensg: name of the gene
# - depletionscreen: name of the screen
sql_text = query.get_hist_depletion_sql(request.values, cohort,
num_bins, error_msg)
hist_dict = query.execute_sql_query_as_dict(
sql_text, database,
config.supp_statement_timeout) # execute sql statement
hist = query.format_num_hist(hist_dict, num_bins)
elif type == 'panelAnnotation':
# - cohortId: id of the cohort
# - panel: name of the panel
sql_text = query.get_hist_panel_sql(request.values, cohort,
error_msg)
hist = query.execute_sql_query(
sql_text, database,
config.supp_statement_timeout) # execute sql statement
return hist
except RuntimeError as error:
abort(400, error)
def _hello():
return jsonify({'message': 'Hello World'})
def get_weights(dataset_id):
if dataset_id == 'Demo':
return handle_Demo.get_weights()
if dataset_id == 'CCI':
return handle_CCI.get_weights()
return jsonify({'message': 'error'})
def get_group(dataset, group):
if '/' + dataset + '/' + group not in h5:
abort(404)
g = h5.get_node('/' + dataset + '/' + group)
return jsonify(g)
def update_weights(dataset_id, values):
if dataset_id == 'Demo':
return handle_Demo.update_weights(values)
if dataset_id == 'CCI':
return handle_CCI.update_weights(values)
return jsonify({'message': 'error'})
def get_row_by_index(id, index):
my_data = dt.get(id)
rows = my_data.aslist()
return jsonify({'row': rows[int(index)]})
def get_data(id):
return jsonify({'data': dt.get(id)})
