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

Fix NAs are now 0 in some calls and msgs features

pull/103/head
JulioV 2020-10-08 12:23:54 -04:00
parent 236b1cd809
commit 2c7beec1da
2 changed files with 4 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/features/calls/rapids/main.R
View File

@ -33,10 +33,8 @@ call_features_of_type <- function(calls, call_type, day_segment, requested_featu
head(1) %>% # if there are multiple contacts with the same amount of messages pick the first one only
pull(trace)
feature <- calls %>%
filter(trace == mostfrequentcontact) %>%
group_by(local_segment) %>%
summarise(!!paste("calls_rapids", call_type, feature_name, sep = "_") := n()) %>%
replace(is.na(.), 0)
summarise(!!paste("calls_rapids", call_type, feature_name, sep = "_") := sum(trace == mostfrequentcontact))
features <- merge(features, feature, by="local_segment", all = TRUE)
} else {
feature <- calls %>%
@ -58,7 +56,6 @@ call_features_of_type <- function(calls, call_type, day_segment, requested_featu
features <- merge(features, feature, by="local_segment", all = TRUE)
}
}
features <- features %>% mutate_at(vars(contains("countmostfrequentcontact")), list( ~ replace_na(., 0)))
return(features)
}
@ -80,6 +77,6 @@ rapids_features <- function(sensor_data_files, day_segment, provider){
features <- call_features_of_type(calls_of_type, call_type, day_segment, requested_features)
call_features <- merge(call_features, features, all=TRUE)
}
call_features <- call_features %>% mutate_at(vars(contains("countmostfrequentcontact") | contains("distinctcontacts") | contains("count")), list( ~ replace_na(., 0)))
return(call_features)
}

7
src/features/messages/rapids/main.R
View File

@ -28,10 +28,8 @@ message_features_of_type <- function(messages, messages_type, day_segment, reque
head(1) %>% # if there are multiple contacts with the same amount of messages pick the first one only
pull(trace)
feature <- messages %>%
filter(trace == mostfrequentcontact) %>%
group_by(local_segment) %>%
summarise(!!paste("messages_rapids", messages_type, feature_name, sep = "_") := n()) %>%
replace(is.na(.), 0)
summarise(!!paste("messages_rapids", messages_type, feature_name, sep = "_") := sum(trace == mostfrequentcontact))
features <- merge(features, feature, by="local_segment", all = TRUE)
} else {
feature <- messages %>%
@ -46,7 +44,6 @@ message_features_of_type <- function(messages, messages_type, day_segment, reque
features <- merge(features, feature, by="local_segment", all = TRUE)
}
}
features <- features %>% mutate_at(vars(contains("countmostfrequentcontact")), list( ~ replace_na(., 0)))
return(features)
}
@ -68,6 +65,6 @@ rapids_features <- function(sensor_data_files, day_segment, provider){
features <- message_features_of_type(messages_of_type, message_type, day_segment, requested_features)
messages_features <- merge(messages_features, features, all=TRUE)
}
messages_features <- messages_features %>% mutate_at(vars(contains("countmostfrequentcontact") | contains("distinctcontacts") | contains("count")), list( ~ replace_na(., 0)))
return(messages_features)
}