activity_data.py

import numpy as np
import pandas as pd
from collections import Counter
from bs4 import BeautifulSoup
from scipy import stats
from matplotlib import pyplot as plt


path = '/path/to/export.xml'
with open(path) as f:
    raw = f.read()
    soup = BeautifulSoup(raw, 'xml')

cnt_runn_min = Counter()
cnt_runn_cal = Counter()
tag_runn = soup.find_all('Workout', {'workoutActivityType': 'HKWorkoutActivityTypeRunning'})
for e in tag_runn:
    date = e['creationDate'].split()[0]
    runn_min = float(e['duration'])
    runn_cal = float(e['totalEnergyBurned'])
    cnt_runn_min[date] += runn_min
    cnt_runn_cal[date] += runn_cal

l = []
for key in cnt_runn_min.keys():
    l.append((key, cnt_runn_min[key]))
df = pd.DataFrame(l)
df.columns = ['date', 'running_minutes']
df.to_csv('running_minutes.csv', index = False)

l = []
for key in cnt_runn_cal.keys():
    l.append((key, cnt_runn_cal[key]))
df = pd.DataFrame(l)
df.columns = ['date', 'running_calories']
df.to_csv('running_calories.csv', index = False)

cnt_lift_min = Counter()
cnt_lift_cal = Counter()
tag_lift = soup.find_all('Workout', {'workoutActivityType': 'HKWorkoutActivityTypeOther'})
for e in tag_lift:
    date = e['creationDate'].split()[0]
    lift_min = float(e['duration'])
    lift_cal = float(e['totalEnergyBurned'])
    cnt_lift_min[date] += lift_min
    cnt_lift_cal[date] += lift_cal

l = []
for key in cnt_lift_min.keys():
    l.append((key, cnt_lift_min[key]))
df = pd.DataFrame(l)
df.columns = ['date', 'lifting_minutes']
df.to_csv('lifting_minutes.csv', index = False)

l = []
for key in cnt_lift_cal.keys():
    l.append((key, cnt_lift_cal[key]))
df = pd.DataFrame(l)
df.columns = ['date', 'lifting_calories']
df.to_csv('lifting_calories.csv', index = False)

cnt_calr = Counter()
tag_cal1 = soup.find_all('Record', {'type': 'HKQuantityTypeIdentifierActiveEnergyBurned'})
for e in tag_cal1:
    date = e['creationDate'].split()[0]
    calr = float(e['value'])
    cnt_calr[date] += calr

tag_cal2 = soup.find_all('Record', {'type': 'HKQuantityTypeIdentifierBasalEnergyBurned'})
for e in tag_cal2:
    date = e['creationDate'].split()[0]
    calr = float(e['value'])
    cnt_calr[date] += calr

l = []
for key in cnt_calr.keys():
    l.append((key, cnt_calr[key]))
df = pd.DataFrame(l)
df.columns = ['date', 'calories']
df.to_csv('calories.csv', index = False)

cnt_step = Counter()
tag_step = soup.find_all('Record', {'type': 'HKQuantityTypeIdentifierStepCount'})
for e in tag_step:
    date = e['creationDate'].split()[0]
    step = int(e['value']) # number of steps
    cnt_step[date] += step

l = []
for key in cnt_step.keys():
    l.append((key, cnt_step[key]))
df = pd.DataFrame(l)
df.columns = ['date', 'steps']
df.to_csv('steps.csv', index = False)

cnt_dist = Counter()
tag_dist = soup.find_all('Record', {'type': 'HKQuantityTypeIdentifierDistanceWalkingRunning'})
for e in tag_dist:
    date = e['creationDate'].split()[0]
    dist = float(e['value']) # distance in km
    cnt_dist[date] += dist

l = []
for key in cnt_dist.keys():
    l.append((key, cnt_dist[key]))
df = pd.DataFrame(l)
df.columns = ['date', 'distance']
df.to_csv('distance.csv', index = False)

filenames = [
    'calories.csv',
    'distance.csv',
    'lifting_calories.csv',
    'lifting_minutes.csv',
    'running_calories.csv',
    'running_minutes.csv',
    'steps.csv'
    ]

for filename in filenames:
    df = pd.read_csv(filename)
    df['date'] = pd.to_datetime(df['date'])
    df.index = df['date']
    del df['date']
    print(df)
    print(type(df))
    df = df[(np.abs(stats.zscore(df)) < 3).all(axis = 1)]
    df = df.rolling(window = 14).mean()
    df.plot()
    plt.axvline('2019-08-01', color = 'red')
    plt.show()