junos
/
rapids
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fill NA with 0 for the selected applications foreground features

data_cleaning
Meng Li 2021-10-03 15:45:11 -04:00
parent 871cdbbcd3
commit 50ed8a9536
1 changed files with 8 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
src/features/phone_applications_foreground/rapids/main.py
View File

@ -26,40 +26,23 @@ def compute_features(filtered_data, apps_type, requested_features, apps_features
apps_features["frequencyentropy" + apps_type] = apps_with_count.groupby("local_segment")["timestamp"].agg(entropy) apps_features["frequencyentropy" + apps_type] = apps_with_count.groupby("local_segment")["timestamp"].agg(entropy)
if "countevent" in requested_features: if "countevent" in requested_features:
apps_features["countevent" + apps_type] = filtered_data.groupby(["local_segment"]).count()["timestamp"] apps_features["countevent" + apps_type] = filtered_data.groupby(["local_segment"]).count()["timestamp"]
apps_features.fillna(value={"countevent" + apps_type: 0}, inplace=True)
if "countepisode" in requested_features: if "countepisode" in requested_features:
apps_features["countepisode" + apps_type] = filtered_data.groupby(["local_segment"]).count()["start_timestamp"] apps_features["countepisode" + apps_type] = filtered_data.groupby(["local_segment"]).count()["start_timestamp"]
apps_features.fillna(value={"countepisode" + apps_type: 0}, inplace=True)
if "minduration" in requested_features: if "minduration" in requested_features:
grouped_data = filtered_data.groupby(by = ['local_segment'])['duration'].min() apps_features["minduration" + apps_type] = filtered_data.groupby(by = ["local_segment"])["duration"].min()
if grouped_data.empty:
apps_features["minduration" + apps_type] = np.nan
else:
apps_features["minduration" + apps_type] = grouped_data
if "maxduration" in requested_features: if "maxduration" in requested_features:
grouped_data = filtered_data.groupby(by = ['local_segment'])['duration'].max() apps_features["maxduration" + apps_type] = filtered_data.groupby(by = ["local_segment"])["duration"].max()
if grouped_data.empty:
apps_features["maxduration" + apps_type] = np.nan
else:
apps_features["maxduration" + apps_type] = grouped_data
if "meanduration" in requested_features: if "meanduration" in requested_features:
grouped_data = filtered_data.groupby(by = ['local_segment'])['duration'].mean() apps_features["meanduration" + apps_type] = filtered_data.groupby(by = ["local_segment"])["duration"].mean()
if grouped_data.empty:
apps_features["meanduration" + apps_type] = np.nan
else:
apps_features["meanduration" + apps_type] = grouped_data
if "sumduration" in requested_features: if "sumduration" in requested_features:
grouped_data = filtered_data.groupby(by = ['local_segment'])['duration'].sum() apps_features["sumduration" + apps_type] = filtered_data.groupby(by = ["local_segment"])["duration"].sum()
if grouped_data.empty:
apps_features["sumduration" + apps_type] = np.nan apps_features.index.names = ["local_segment"]
else:
apps_features["sumduration" + apps_type] = grouped_data
apps_features.index.names = ['local_segment']
return apps_features return apps_features
def process_app_features(data, requested_features, time_segment, provider, filter_data_by_segment): def process_app_features(data, requested_features, time_segment, provider, filter_data_by_segment):
@ -145,4 +128,6 @@ def rapids_features(sensor_data_files, time_segment, provider, filter_data_by_se
features = pd.merge(episodes_features, features, how='outer', on='local_segment') features = pd.merge(episodes_features, features, how='outer', on='local_segment')
features.fillna(value={feature_name: 0 for feature_name in features.columns if feature_name.startswith(("countevent", "countepisode", "minduration", "maxduration", "meanduration", "sumduration"))}, inplace=True)
return features return features