Fillna for app foreground and activity recognition

notes
Primoz 2022-09-29 11:44:27 +00:00
parent 6286e7a44c
commit a4f0d056a0
2 changed files with 5 additions and 4 deletions

View File

@ -37,6 +37,6 @@ def rapids_features(sensor_data_files, time_segment, provider, filter_data_by_se
ar_features.index.names = ["local_segment"]
ar_features = ar_features.reset_index()
ar_features.fillna(value={"count": 0, "countuniqueactivities": 0, "durationstationary": 0, "durationmobile": 0, "durationvehicle": 0}, inplace=True)
ar_features.fillna(value={"count": 0, "countuniqueactivities": 0, "durationstationary": 0, "durationmobile": 0, "durationvehicle": 0, "mostcommonactivity": 4}, inplace=True)
return ar_features

View File

@ -9,19 +9,19 @@ def compute_features(filtered_data, apps_type, requested_features, apps_features
if "timeoffirstuse" in requested_features:
time_first_event = filtered_data.sort_values(by="timestamp", ascending=True).drop_duplicates(subset="local_segment", keep="first").set_index("local_segment")
if time_first_event.empty:
apps_features["timeoffirstuse" + apps_type] = np.nan
apps_features["timeoffirstuse" + apps_type] = 1000000 # np.nan
else:
apps_features["timeoffirstuse" + apps_type] = time_first_event["local_hour"] * 60 + time_first_event["local_minute"]
if "timeoflastuse" in requested_features:
time_last_event = filtered_data.sort_values(by="timestamp", ascending=False).drop_duplicates(subset="local_segment", keep="first").set_index("local_segment")
if time_last_event.empty:
apps_features["timeoflastuse" + apps_type] = np.nan
apps_features["timeoflastuse" + apps_type] = 1000000 # np.nan
else:
apps_features["timeoflastuse" + apps_type] = time_last_event["local_hour"] * 60 + time_last_event["local_minute"]
if "frequencyentropy" in requested_features:
apps_with_count = filtered_data.groupby(["local_segment","application_name"]).count().sort_values(by="timestamp", ascending=False).reset_index()
if (len(apps_with_count.index) < 2 ):
apps_features["frequencyentropy" + apps_type] = np.nan
apps_features["frequencyentropy" + apps_type] = 0 # np.nan
else:
apps_features["frequencyentropy" + apps_type] = apps_with_count.groupby("local_segment")["timestamp"].agg(entropy)
if "countevent" in requested_features:
@ -43,6 +43,7 @@ def compute_features(filtered_data, apps_type, requested_features, apps_features
apps_features["sumduration" + apps_type] = filtered_data.groupby(by = ["local_segment"])["duration"].sum()
apps_features.index.names = ["local_segment"]
return apps_features
def process_app_features(data, requested_features, time_segment, provider, filter_data_by_segment):