Event segments' device id can be one of any assigned to a participant

pull/103/head
JulioV 2020-12-02 17:17:55 -05:00
parent 0bd43c139c
commit c24cba8679
2 changed files with 12 additions and 9 deletions

View File

@ -288,12 +288,12 @@ Day segments (or epochs) are the time windows on which you want to extract behav
| Column | Description |
|---------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| label | A string that is used as a prefix in the name of your day segments. If labels are unique, every segment is independent; if two or more segments have the same label, their data will be grouped when computing features like the `most frequent contact` for calls (the most frequent contact will be computed across all these segments) |
| label | A string that is used as a prefix in the name of your day segments. If labels are unique, every segment is independent; if two or more segments have the same label, their data will be grouped when computing auxiliary data for features like the `most frequent contact` for calls (the most frequent contact will be computed across all these segments). There cannot be two *overlaping* event segments with the same label (RAPIDS will throw an error) |
| event_timestamp | A UNIX timestamp that represents the moment an event of interest happened (clinical relapse, survey, readmission, etc.). The corresponding day segment will be computed around this moment using `length`, `shift`, and `shift_direction` |
| length | A string representing the length of this segment. It can have one or more of the following keys `XXD XXH XXM XXS` to represent a number of days, hours, minutes, and seconds. For example `7D 23H 59M 59S` |
| shift | A string representing the time shift from `event_timestamp`. It can have one or more of the following keys `XXD XXH XXM XXS` to represent a number of days, hours, minutes and seconds. For example `7D 23H 59M 59S`. Use this value to change the start of a segment with respect to its `event_timestamp`. For example, set this variable to `1H` to create a segment that starts 1 hour from an event of interest (`shift_direction` determines if it's before or after). |
| shift_direction | An integer representing whether the `shift` is before (`-1`) or after (`1`) an `event_timestamp` |
|device_id| The device id (smartphone or fitbit) to whom this segment belongs to. You have to create a line in the event segment file for each event of a participant that you want to analyse|
|device_id| The device id (smartphone or fitbit) to whom this segment belongs to. You have to create a line in this event segment file for each event of a participant that you want to analyse. If you have participants with multiple device ids you can choose any of them|
!!! example
```csv

View File

@ -168,10 +168,10 @@ def parse_periodic_segments(day_segments):
day_segments.loc[day_segments["repeats_on"] == "every_day", "repeats_value"] = 0
return day_segments
def parse_event_segments(day_segments, device_id):
return day_segments.query("device_id == @device_id")
def parse_event_segments(day_segments, device_ids):
return day_segments.query("device_id == @device_ids")
def parse_day_segments(day_segments_file, segments_type, device_id):
def parse_day_segments(day_segments_file, segments_type, device_ids):
# Add code to validate and parse frequencies, intervals, and events
# Expected formats:
# Frequency: label, length columns (e.g. my_prefix, 5) length has to be in minutes (int)
@ -196,15 +196,18 @@ def parse_day_segments(day_segments_file, segments_type, device_id):
elif(segments_type == "PERIODIC" and is_valid_periodic_segments(day_segments, day_segments_file)):
day_segments = parse_periodic_segments(day_segments)
elif(segments_type == "EVENT" and is_valid_event_segments(day_segments, day_segments_file)):
day_segments = parse_event_segments(day_segments, device_id)
day_segments = parse_event_segments(day_segments, device_ids)
else:
raise ValueError("{} does not have a format compatible with frequency, periodic or event day segments. Please refer to [LINK]".format(day_segments_file))
return day_segments
participant_file = yaml.load(open(snakemake.input[1], 'r'), Loader=yaml.FullLoader)
device_id = participant_file["PHONE"]["DEVICE_IDS"]
device_id = device_id[len(device_id) -1 ]
final_day_segments = parse_day_segments(snakemake.input[0], snakemake.params["day_segments_type"], device_id)
device_ids = []
for key in participant_file.keys():
if "DEVICE_IDS" in participant_file[key]:
device_ids = device_ids + participant_file[key]["DEVICE_IDS"]
final_day_segments = parse_day_segments(snakemake.input[0], snakemake.params["day_segments_type"], device_ids)
if snakemake.params["day_segments_type"] == "EVENT" and final_day_segments.shape[0] == 0:
warnings.warn("There are no event day segments for {}. Check your day segment file {}".format(snakemake.params["pid"], snakemake.input[0]))