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

Splitting Energy Feature in Conversation to Voice and Noise.

pull/98/head
nikunjgoel95 2020-08-23 13:20:19 -04:00
parent a480917b52
commit 6a5470e338
2 changed files with 31 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
config.yaml
View File

@ -199,8 +199,9 @@ CONVERSATION:
IOS: plugin_studentlife_audio IOS: plugin_studentlife_audio
DAY_SEGMENTS: *day_segments DAY_SEGMENTS: *day_segments
FEATURES: ["minutessilence", "minutesnoise", "minutesvoice", "minutesunknown","sumconversationduration","avgconversationduration", FEATURES: ["minutessilence", "minutesnoise", "minutesvoice", "minutesunknown","sumconversationduration","avgconversationduration",
"sdconversationduration","minconversationduration","maxconversationduration","timefirstconversation","timelastconversation","sumenergy", "sdconversationduration","minconversationduration","maxconversationduration","timefirstconversation","timelastconversation","noisesumenergy",
"avgenergy","sdenergy","minenergy","maxenergy","silencesensedfraction","noisesensedfraction", "noiseavgenergy","noisesdenergy","noiseminenergy","noisemaxenergy","voicesumenergy",
"voiceavgenergy","voicesdenergy","voiceminenergy","voicemaxenergy","silencesensedfraction","noisesensedfraction",
"voicesensedfraction","unknownsensedfraction","silenceexpectedfraction","noiseexpectedfraction","voiceexpectedfraction", "voicesensedfraction","unknownsensedfraction","silenceexpectedfraction","noiseexpectedfraction","voiceexpectedfraction",
"unknownexpectedfraction","countconversation"] "unknownexpectedfraction","countconversation"]
RECORDINGMINUTES: 1 RECORDINGMINUTES: 1

41
src/features/conversation/conversation_base.py
View File

@ -3,8 +3,9 @@ import pandas as pd
def base_conversation_features(conversation_data, day_segment, requested_features,recordingMinutes,pausedMinutes,expectedMinutes): def base_conversation_features(conversation_data, day_segment, requested_features,recordingMinutes,pausedMinutes,expectedMinutes):
# name of the features this function can compute # name of the features this function can compute
base_features_names = ["minutessilence", "minutesnoise", "minutesvoice", "minutesunknown","sumconversationduration","avgconversationduration", base_features_names = ["minutessilence", "minutesnoise", "minutesvoice", "minutesunknown","sumconversationduration","avgconversationduration",
"sdconversationduration","minconversationduration","maxconversationduration","timefirstconversation","timelastconversation","sumenergy", "sdconversationduration","minconversationduration","maxconversationduration","timefirstconversation","timelastconversation","noisesumenergy",
"avgenergy","sdenergy","minenergy","maxenergy","silencesensedfraction","noisesensedfraction", "noiseavgenergy","noisesdenergy","noiseminenergy","noisemaxenergy","voicesumenergy",
"voiceavgenergy","voicesdenergy","voiceminenergy","voicemaxenergy","silencesensedfraction","noisesensedfraction",
"voicesensedfraction","unknownsensedfraction","silenceexpectedfraction","noiseexpectedfraction","voiceexpectedfraction", "voicesensedfraction","unknownsensedfraction","silenceexpectedfraction","noiseexpectedfraction","voiceexpectedfraction",
"unknownexpectedfraction","countconversation"] "unknownexpectedfraction","countconversation"]
@ -96,22 +97,36 @@ def base_conversation_features(conversation_data, day_segment, requested_feature
else: else:
conversation_features["conversation_" + day_segment + "_timelastconversation"] = 0 conversation_features["conversation_" + day_segment + "_timelastconversation"] = 0
if "sumenergy" in features_to_compute: if "noisesumenergy" in features_to_compute:
conversation_features["conversation_" + day_segment + "_sumenergy"] = conversation_data.groupby(["local_date"])["double_energy"].sum() conversation_features["conversation_" + day_segment + "_noisesumenergy"] = conversation_data[conversation_data['inference']==1].groupby(["local_date"])["double_energy"].sum()
if "avgenergy" in features_to_compute: if "noiseavgenergy" in features_to_compute:
conversation_features["conversation_" + day_segment + "_avgenergy"] = conversation_data.groupby(["local_date"])["double_energy"].mean() conversation_features["conversation_" + day_segment + "_noiseavgenergy"] = conversation_data[conversation_data['inference']==1].groupby(["local_date"])["double_energy"].mean()
if "sdenergy" in features_to_compute: if "noisesdenergy" in features_to_compute:
conversation_features["conversation_" + day_segment + "_sdenergy"] = conversation_data.groupby(["local_date"])["double_energy"].std() conversation_features["conversation_" + day_segment + "_noisesdenergy"] = conversation_data[conversation_data['inference']==1].groupby(["local_date"])["double_energy"].std()
if "minenergy" in features_to_compute: if "noiseminenergy" in features_to_compute:
conversation_features["conversation_" + day_segment + "_minenergy"] = conversation_data.groupby(["local_date"])["double_energy"].min() conversation_features["conversation_" + day_segment + "_noiseminenergy"] = conversation_data[conversation_data['inference']==1].groupby(["local_date"])["double_energy"].min()
if "maxenergy" in features_to_compute: if "noisemaxenergy" in features_to_compute:
conversation_features["conversation_" + day_segment + "_maxenergy"] = conversation_data.groupby(["local_date"])["double_energy"].max() conversation_features["conversation_" + day_segment + "_noisemaxenergy"] = conversation_data[conversation_data['inference']==1].groupby(["local_date"])["double_energy"].max()
if "voicesumenergy" in features_to_compute:
conversation_features["conversation_" + day_segment + "_voicesumenergy"] = conversation_data[conversation_data['inference']==2].groupby(["local_date"])["double_energy"].sum()
if "voiceavgenergy" in features_to_compute:
conversation_features["conversation_" + day_segment + "_voiceavgenergy"] = conversation_data[conversation_data['inference']==2].groupby(["local_date"])["double_energy"].mean()
if "voicesdenergy" in features_to_compute:
conversation_features["conversation_" + day_segment + "_voicesdenergy"] = conversation_data[conversation_data['inference']==2].groupby(["local_date"])["double_energy"].std()
if "voiceminenergy" in features_to_compute:
conversation_features["conversation_" + day_segment + "_voiceminenergy"] = conversation_data[conversation_data['inference']==2].groupby(["local_date"])["double_energy"].min()
if "voicemaxenergy" in features_to_compute:
conversation_features["conversation_" + day_segment + "_voicemaxenergy"] = conversation_data[conversation_data['inference']==2].groupby(["local_date"])["double_energy"].max()
conversation_features = conversation_features.reset_index() conversation_features = conversation_features.reset_index()
return conversation_features return conversation_features