rapids/src/data/fitbit_parse_calories.py

54 lines
2.4 KiB
Python
Raw Normal View History

import json
2020-10-22 20:38:40 +02:00
import numpy as np
import pandas as pd
from datetime import datetime
CALORIES_INTRADAY_COLUMNS = ("device_id",
"level", "mets", "value",
2020-10-22 19:08:52 +02:00
"local_date_time", "timestamp")
2020-10-22 19:08:52 +02:00
def parseCaloriesData(calories_data):
if calories_data.empty:
return pd.DataFrame(), pd.DataFrame(columns=CALORIES_INTRADAY_COLUMNS)
device_id = calories_data["device_id"].iloc[0]
records_intraday = []
# Parse JSON into individual records
for record in calories_data.fitbit_data:
record = json.loads(record) # Parse text into JSON
curr_date = datetime.strptime(
record["activities-calories"][0]["dateTime"], "%Y-%m-%d")
dataset = record["activities-calories-intraday"]["dataset"]
for data in dataset:
d_time = datetime.strptime(data["time"], '%H:%M:%S').time()
d_datetime = datetime.combine(curr_date, d_time)
row_intraday = (device_id,
data["level"], data["mets"], data["value"],
2020-10-22 19:08:52 +02:00
d_datetime, 0)
records_intraday.append(row_intraday)
2020-10-22 20:38:40 +02:00
return pd.DataFrame(data=[], columns=["local_date_time", "timestamp"]), pd.DataFrame(data=records_intraday, columns=CALORIES_INTRADAY_COLUMNS)
2020-10-22 19:08:52 +02:00
table_format = snakemake.params["table_format"]
2020-10-22 20:38:40 +02:00
timezone = snakemake.params["timezone"]
2020-10-22 19:08:52 +02:00
if table_format == "JSON":
json_raw = pd.read_csv(snakemake.input[0])
summary, intraday = parseCaloriesData(json_raw)
elif table_format == "CSV":
summary = pd.read_csv(snakemake.input[0], parse_dates=["local_date_time"], date_parser=lambda col: pd.to_datetime(col).tz_localize(None))
intraday = pd.read_csv(snakemake.input[1], parse_dates=["local_date_time"], date_parser=lambda col: pd.to_datetime(col).tz_localize(None))
2020-10-22 19:08:52 +02:00
# if not pd.isnull(local_start_date) and not pd.isnull(local_end_date):
2020-10-22 20:38:40 +02:00
if summary.shape[0] > 0:
summary["timestamp"] = summary["local_date_time"].dt.tz_localize(timezone, ambiguous=False, nonexistent="NaT").dropna().astype(np.int64) // 10**6
summary.dropna(subset=['timestamp'], inplace=True)
2020-10-22 20:38:40 +02:00
if intraday.shape[0] > 0:
intraday["timestamp"] = intraday["local_date_time"].dt.tz_localize(timezone, ambiguous=False, nonexistent="NaT").dropna().astype(np.int64) // 10**6
intraday.dropna(subset=['timestamp'], inplace=True)
2020-10-22 19:08:52 +02:00
summary.to_csv(snakemake.output["summary_data"], index=False)
intraday.to_csv(snakemake.output["intraday_data"], index=False)