def execute_job(job_dict):
"""
Takes job_dict as input.
Gets the data from get_db_data so data bounds are correct.
Returns completed data get as results.
"""
data_list = get_db_data(job_dict["start"], job_dict["end"],
job_dict["limit"], job_dict["offset"])
return data_list
def get_year(year):
"""
Takes a year as route argument.
Checks input with input_checker, returns 400 and errors if they exist.
Returns data point dictionary corresponding to year.
"""
start, end, limit, offset, errors = input_checker(year=year)
if errors:
return jsonify(errors), 400
data_list = get_db_data(start, end, limit, offset)
return jsonify(data_list[0])
def get_db_data_with_args():
"""
Takes a start, end, limit, and offset value from route arguments.
Checks input with input_checker, returns 400 and errors if they exist.
Otherwises returns json list of data requested.
"""
start = request.args.get('start')
end = request.args.get('end')
limit = request.args.get('limit')
offset = request.args.get('offset')
start, end, limit, offset, errors = input_checker(start, end, limit,
offset)
if errors:
return jsonify(errors), 400
data_list = get_db_data(start, end, limit, offset)
return jsonify(data_list)
def execute_job(job_dict):
"""
Takes job_dict as input.
Gets the data from get_db_data so data bounds are correct.
Runs 'statistics' operations on the data_set and places in a 'result's dictionary.
Returns dictionary as results
"""
data_list = get_db_data(job_dict["start"], job_dict["end"],
job_dict["limit"], job_dict["offset"])
sun_data = [dict_x["spots"] for dict_x in data_list]
if sun_data:
stats_list = [
{
"mean": statistics.mean(sun_data)
},
{
"harmonic mean": statistics.harmonic_mean(sun_data)
},
{
"median": statistics.median(sun_data)
},
{
"low median": statistics.median_low(sun_data)
},
{
"high median": statistics.median_high(sun_data)
},
{
"mode": statistics.mode(sun_data)
},
{
"variance": statistics.variance(sun_data)
},
{
"standard deviation": statistics.stdev(sun_data)
},
]
return stats_list
def test_limit_no_offset_check():
assert int(open(CSV_FILE).readlines()[0][0:4]) ==\
get_db_data(CSV_FILE, limit=20)[1][0]["year"]
assert int(open(CSV_FILE).readlines()[19][0:4]) ==\
get_db_data(CSV_FILE, limit=20)[1][-1]["year"]
def test_start_greater_than_end_check():
assert get_db_data(CSV_FILE, 1829, 1729)[0] is True
def test_start_and_end_check():
assert int(open(CSV_FILE).readlines()[20][0:4]) ==\
get_db_data(CSV_FILE, 1790, 1840)[1][0]["year"]
assert int(open(CSV_FILE).readlines()[70][0:4]) ==\
get_db_data(CSV_FILE, 1790, 1840)[1][-1]["year"]
def test_end_no_start_check():
assert int(open(CSV_FILE).readlines()[0][0:4]) ==\
get_db_data(CSV_FILE, end=1820)[1][0]["year"]
assert int(open(CSV_FILE).readlines()[50][0:4]) ==\
get_db_data(CSV_FILE, end=1820)[1][-1]["year"]
def test_start_no_end_check():
assert int(open(CSV_FILE).readlines()[60][0:4]) ==\
get_db_data(CSV_FILE, 1830)[1][0]["year"]
assert int(open(CSV_FILE).readlines()[-1][0:4]) ==\
get_db_data(CSV_FILE, 1830)[1][-1]["year"]
def test_list_first_and_last_value_check():
assert int(open(CSV_FILE).readlines()[0][0:4]) == get_db_data(
CSV_FILE)[1][0]["year"]
assert int(open(CSV_FILE).readlines()[-1][0:4]) == get_db_data(
CSV_FILE)[1][-1]["year"]
def test_keys_check():
for line in get_db_data(CSV_FILE)[1]:
assert isinstance(line["id"], int)
assert isinstance(line["year"], int)
assert isinstance(line["spots"], int)
def test_dict_length_check():
for line in get_db_data(CSV_FILE)[1]:
assert len(line) == 3
def test_dict_type_check():
for line in get_db_data(CSV_FILE)[1]:
assert isinstance(line, dict)
def test_list_type_check():
assert isinstance(get_db_data(CSV_FILE)[1], list)
def test_limit_and_offset_check():
assert int(open(CSV_FILE).readlines()[15][0:4]) ==\
get_db_data(CSV_FILE, limit=20, offset=15)[1][0]["year"]
assert int(open(CSV_FILE).readlines()[34][0:4]) ==\
get_db_data(CSV_FILE, limit=20, offset=15)[1][-1]["year"]
import sys
from os import path
sys.path.append(path.abspath(path.join(__file__, '../../database')))
#print(sys.path)
import get_db_data as gdd
from scipy.signal import savgol_filter
from scipy.stats import zscore
import numpy as np
import pandas as pd
data = gdd.get_db_data()
pars = data.get_participants(True)
pars_tuples = {}
for g, p, _ in pars:
pars_tuples[g] = pars_tuples.get(g, []) + [p]
gm_orth = lambda v, u: v - u * (v @ u) / (u @ u)
def yield_group_signals(group_id, series_type, interp_type):
return data.get_signal_by_series_type_and_interp_type(
group_id, series_type, interp_type)
class savitzky_golay:
def __init__(self, group_ids, f1_length, f2_length, series_type,
interp_type):
self.group_ids = group_ids
self.f1_length = f1_length
self.f2_length = f2_length
def test_list_length_check():
assert len(open(CSV_FILE).readlines()) == len(get_db_data(CSV_FILE)[1])
