Refactor screen features: replace "metrics" with "features"

Co-authored-by: Meng Li <AnnieLM1996@gmail.com>
pull/95/head
Mingze Cao 2020-04-08 10:05:16 -05:00
parent 8d4a0718e8
commit e0d19cbc1b
4 changed files with 31 additions and 31 deletions

View File

@ -89,7 +89,7 @@ BATTERY:
SCREEN:
DAY_SEGMENTS: *day_segments
REFERENCE_HOUR_FIRST_USE: 0
METRICS_DELTAS: ["countepisode", "episodepersensedminutes", "sumduration", "maxduration", "minduration", "avgduration", "stdduration", "firstuseafter"]
FEATURES_DELTAS: ["countepisode", "episodepersensedminutes", "sumduration", "maxduration", "minduration", "avgduration", "stdduration", "firstuseafter"]
EPISODE_TYPES: ["unlock"]
LIGHT:

View File

@ -885,7 +885,7 @@ See `Screen Config Code`_
- Apply readable dateime to Screen dataset: ``expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["SENSORS"]),``
- Extract the deltas from the Screen dataset: expand("data/processed/{pid}/screen_deltas.csv", pid=config["PIDS"]),
- Extract Screen Metrics:
- Extract Screen Features:
| ``expand("data/processed/{pid}/screen_{day_segment}.csv",``
| ``pid=config["PIDS"],``
@ -905,9 +905,9 @@ See `Screen Config Code`_
- **Script:** ``src/features/screen_deltas.R`` - See the screen_deltas.R_ script.
- **Rule:** ``rules/features.snakefile/screen_metrics`` - See the screen_metrics_ rule.
- **Rule:** ``rules/features.snakefile/screen_features`` - See the screen_features_ rule.
- **Script:** ``src/features/screen_metrics.py`` - See the screen_metrics.py_ script.
- **Script:** ``src/features/screen_features.py`` - See the screen_features.py_ script.
.. _screen-parameters:
@ -917,16 +917,16 @@ See `Screen Config Code`_
Name Description
=============== ===================
day_segment The particular ``day_segments`` that will be analyzed. The available options are ``daily``, ``morning``, ``afternoon``, ``evening``, ``night``
metrics_events The different measures that can be retrieved from the events in the Screen dataset. See :ref:`Available Screen Events Metrics <screen-events-available-metrics>` Table below
metrics_deltas The different measures that can be retrieved from the episodes extracted from the Screen dataset. See :ref:`Available Screen Episodes Metrics <screen-episodes-available-metrics>` Table below
features_events The different measures that can be retrieved from the events in the Screen dataset. See :ref:`Available Screen Events Features <screen-events-available-features>` Table below
features_deltas The different measures that can be retrieved from the episodes extracted from the Screen dataset. See :ref:`Available Screen Episodes Features <screen-episodes-available-features>` Table below
episodes The action that defines an episode
=============== ===================
.. _screen-events-available-metrics:
.. _screen-events-available-features:
..
**Available Screen Events Metrics**
The following table shows a list of the available metrics for Screen Events.
**Available Screen Events Features**
The following table shows a list of the available features for Screen Events.
================= ============== =============
Name Units Description
================= ============== =============
@ -935,11 +935,11 @@ episodes The action that defines an episode
unlocksperminute Unlock events Unlock events per minute: The average of the number of unlock events that occur in a minute
================= ============== =============
.. _screen-episodes-available-metrics:
.. _screen-episodes-available-features:
**Available Screen Episodes Metrics**
**Available Screen Episodes Features**
The following table shows a list of the available metrics for Screen Episodes.
The following table shows a list of the available features for Screen Episodes.
============= ========= =============
Name Units Description
@ -1187,8 +1187,8 @@ stddurationactivebout minutes Std duration active bout: The standard
.. _`Screen Config Code`: https://github.com/carissalow/rapids/blob/765bb462636d5029a05f54d4c558487e3786b90b/config.yaml#L88
.. _screen_deltas: https://github.com/carissalow/rapids/blob/765bb462636d5029a05f54d4c558487e3786b90b/rules/features.snakefile#L33
.. _screen_deltas.R: https://github.com/carissalow/rapids/blob/master/src/features/screen_deltas.R
.. _screen_metrics: https://github.com/carissalow/rapids/blob/765bb462636d5029a05f54d4c558487e3786b90b/rules/features.snakefile#L97
.. _screen_metrics.py: https://github.com/carissalow/rapids/blob/master/src/features/screen_metrics.py
.. _screen_features: https://github.com/carissalow/rapids/blob/765bb462636d5029a05f54d4c558487e3786b90b/rules/features.snakefile#L97
.. _screen_features.py: https://github.com/carissalow/rapids/blob/master/src/features/screen_features.py
.. _`Fitbit: Heart Rate Config Code`: https://github.com/carissalow/rapids/blob/765bb462636d5029a05f54d4c558487e3786b90b/config.yaml#L113
.. _fitbit_with_datetime: https://github.com/carissalow/rapids/blob/765bb462636d5029a05f54d4c558487e3786b90b/rules/preprocessing.snakefile#L94
.. _fitbit_readable_datetime.py: https://github.com/carissalow/rapids/blob/master/src/data/fitbit_readable_datetime.py

View File

@ -96,20 +96,20 @@ rule battery_metrics:
script:
"../src/features/battery_metrics.py"
rule screen_metrics:
rule screen_features:
input:
screen_deltas = "data/processed/{pid}/screen_deltas.csv",
phone_sensed_bins = "data/interim/{pid}/phone_sensed_bins.csv"
params:
day_segment = "{day_segment}",
reference_hour_first_use = config["SCREEN"]["REFERENCE_HOUR_FIRST_USE"],
metrics_deltas = config["SCREEN"]["METRICS_DELTAS"],
features_deltas = config["SCREEN"]["FEATURES_DELTAS"],
episode_types = config["SCREEN"]["EPISODE_TYPES"],
bin_size = config["PHONE_VALID_SENSED_DAYS"]["BIN_SIZE"]
output:
"data/processed/{pid}/screen_{day_segment}.csv"
script:
"../src/features/screen_metrics.py"
"../src/features/screen_features.py"
rule light_metrics:
input:

View File

@ -5,27 +5,27 @@ import itertools
from datetime import datetime, timedelta, time
from features_utils import splitOvernightEpisodes, splitMultiSegmentEpisodes
def getEpisodeDurationFeatures(screen_deltas, episode, metrics, phone_sensed_bins, bin_size, reference_hour_first_use):
def getEpisodeDurationFeatures(screen_deltas, episode, features, phone_sensed_bins, bin_size, reference_hour_first_use):
screen_deltas_episode = screen_deltas[screen_deltas["episode"] == episode]
duration_helper = pd.DataFrame()
if "countepisode" in metrics:
if "countepisode" in features:
duration_helper = pd.concat([duration_helper, screen_deltas_episode.groupby(["local_start_date"]).count()[["time_diff"]].rename(columns = {"time_diff": "screen_" + day_segment + "_countepisode" + episode})], axis = 1)
if "episodepersensedminutes" in metrics:
if "episodepersensedminutes" in features:
for date, row in screen_deltas_episode.groupby(["local_start_date"]).count()[["time_diff"]].iterrows():
sensed_minutes = phone_sensed_bins.loc[date, :].sum() * bin_size
episode_per_sensedminutes = row["time_diff"] / (1 if sensed_minutes == 0 else sensed_minutes)
duration_helper.loc[date, "screen_" + day_segment + "_episodepersensedminutes" + episode] = episode_per_sensedminutes
if "sumduration" in metrics:
if "sumduration" in features:
duration_helper = pd.concat([duration_helper, screen_deltas_episode.groupby(["local_start_date"]).sum()[["time_diff"]].rename(columns = {"time_diff": "screen_" + day_segment + "_sumduration" + episode})], axis = 1)
if "maxduration" in metrics:
if "maxduration" in features:
duration_helper = pd.concat([duration_helper, screen_deltas_episode.groupby(["local_start_date"]).max()[["time_diff"]].rename(columns = {"time_diff": "screen_" + day_segment + "_maxduration" + episode})], axis = 1)
if "minduration" in metrics:
if "minduration" in features:
duration_helper = pd.concat([duration_helper, screen_deltas_episode.groupby(["local_start_date"]).min()[["time_diff"]].rename(columns = {"time_diff": "screen_" + day_segment + "_minduration" + episode})], axis = 1)
if "avgduration" in metrics:
if "avgduration" in features:
duration_helper = pd.concat([duration_helper, screen_deltas_episode.groupby(["local_start_date"]).mean()[["time_diff"]].rename(columns = {"time_diff":"screen_" + day_segment + "_avgduration" + episode})], axis = 1)
if "stdduration" in metrics:
if "stdduration" in features:
duration_helper = pd.concat([duration_helper, screen_deltas_episode.groupby(["local_start_date"]).std()[["time_diff"]].rename(columns = {"time_diff":"screen_" + day_segment + "_stdduration" + episode})], axis = 1)
if "firstuseafter" + "{0:0=2d}".format(reference_hour_first_use) in metrics:
if "firstuseafter" + "{0:0=2d}".format(reference_hour_first_use) in features:
duration_helper = pd.concat([duration_helper, pd.DataFrame(screen_deltas_episode.groupby(["local_start_date"]).first()[["local_start_date_time"]].local_start_date_time.apply(lambda x: (x.to_pydatetime().hour - reference_hour_first_use) * 3600 + x.to_pydatetime().minute * 60 + x.to_pydatetime().second)).rename(columns = {"local_start_date_time":"screen_" + day_segment + "_firstuseafter" + "{0:0=2d}".format(reference_hour_first_use) + episode})], axis = 1)
return duration_helper
@ -36,15 +36,15 @@ phone_sensed_bins[phone_sensed_bins > 0] = 1
day_segment = snakemake.params["day_segment"]
reference_hour_first_use = snakemake.params["reference_hour_first_use"]
metrics_deltas = snakemake.params["metrics_deltas"]
features_deltas = snakemake.params["features_deltas"]
episode_types = snakemake.params["episode_types"]
bin_size = snakemake.params["bin_size"]
metrics_deltas = ["firstuseafter" + "{0:0=2d}".format(reference_hour_first_use) if feature_name == "firstuseafter" else feature_name for feature_name in metrics_deltas]
features_deltas = ["firstuseafter" + "{0:0=2d}".format(reference_hour_first_use) if feature_name == "firstuseafter" else feature_name for feature_name in features_deltas]
metrics_deltas_name = ["".join(metric) for metric in itertools.product(metrics_deltas, episode_types)]
features_deltas_name = ["".join(feature) for feature in itertools.product(features_deltas, episode_types)]
screen_features = pd.DataFrame(columns=["local_date"]+["screen_" + day_segment + "_" + x for x in metrics_deltas_name])
screen_features = pd.DataFrame(columns=["local_date"]+["screen_" + day_segment + "_" + x for x in features_deltas_name])
if not screen_deltas.empty:
# preprocess day_segment and episodes
screen_deltas = splitOvernightEpisodes(screen_deltas, [], ["episode"])
@ -55,7 +55,7 @@ if not screen_deltas.empty:
if not screen_deltas.empty:
screen_features = pd.DataFrame()
for episode in episode_types:
screen_features = pd.concat([screen_features, getEpisodeDurationFeatures(screen_deltas, episode, metrics_deltas, phone_sensed_bins, bin_size, reference_hour_first_use)], axis=1)
screen_features = pd.concat([screen_features, getEpisodeDurationFeatures(screen_deltas, episode, features_deltas, phone_sensed_bins, bin_size, reference_hour_first_use)], axis=1)
if not screen_features.empty:
screen_features = screen_features.rename_axis("local_date").reset_index()