__author__ = 'Andrew'
import FakePatients as fp
import time
import matplotlib.pyplot as plt
import scipy.stats as stats
import math
from FakePatients import split_age
all_data = fp.load_data_with_sline()
# Here are sline which are presented almost every day (at least 360 days in year )
fit_sline = ['276', '070', '090', '390', '274', '135', '129', '250', '050', '255', '280', '283', '145', '065', '085'
, '245', '262', '267', '125', '387', '165', '132', '296']
YEAR = 2012
FULL_YEARS = [2011, 2012, 2013]
def show_sline_freq(year=YEAR):
"""Prints sline counts for a year"""
sline_freq = {}
for tuple in all_data:
sline = tuple[14]
if sline is None:
continue
admit_date = tuple[2]
if len(admit_date) == 0:
continue
datetime = time.strptime(admit_date, "%Y-%m-%d")
if int(datetime.tm_year) != year:
continue
__author__ = 'Andrew'
import FakePatients as fp
import matplotlib.pyplot as plt
from sklearn.neighbors.kde import KernelDensity
import numpy as np
import random
import csv
from datetime import timedelta
import math
training_threshold = 10
alert_count = 50
raw_data, missed_drg = fp.load_data_with_sline()
data = fp.change_to_dict(fp.filter_incomplete_data(raw_data))
print "Rows with following DRG were skipped:",
print missed_drg
print "Filter out %d of %d" % (len(raw_data) - len(data), len(raw_data))
def history(all_data, (sex, age, sline), days=30):
"""Return historical data for selected combination of (sex, age, sline)"""
start_date = None
end_date = None
hist_data = {}
for row in all_data:
admit_date = row[2]
agef_in_years = int(row[9])
agef = fp.split_age(agef_in_years)
sexf = int(row[10])
slinef = row[14]
rlos = row[5]