Merge remote-tracking branch 'origin/master'

models
junos 2022-04-12 17:27:25 +02:00
commit ed5314aa98
9 changed files with 452 additions and 6 deletions

View File

@ -1,4 +1,9 @@
# Change Log # Change Log
## v1.8.0
- Add data stream for AWARE Micro server
- Fix the NA bug in PHONE_LOCATIONS BARNETT provider
- Fix the bug of data type for call_duration field
- Fix the index bug of heatmap_sensors_per_minute_per_time_segment
## v1.7.1 ## v1.7.1
- Update docs for Git Flow section - Update docs for Git Flow section
- Update RAPIDS paper information - Update RAPIDS paper information

View File

@ -0,0 +1,15 @@
# `aware_micro_mysql`
This [data stream](../../datastreams/data-streams-introduction) handles iOS and Android sensor data collected with the [AWARE Framework's](https://awareframework.com/) [AWARE Micro](https://github.com/denzilferreira/aware-micro) server and stored in a MySQL database.
## Container
A MySQL database with a table per sensor, each containing the data for all participants. Sensor data is stored in a JSON field within each table called `data`
The script to connect and download data from this container is at:
```bash
src/data/streams/aware_micro_mysql/container.R
```
## Format
--8<---- "docs/snippets/aware_format.md"

View File

@ -16,6 +16,7 @@ For reference, these are the data streams we currently support:
| Data Stream | Device | Format | Container | Docs | Data Stream | Device | Format | Container | Docs
|--|--|--|--|--| |--|--|--|--|--|
| `aware_mysql`| Phone | AWARE app | MySQL | [link](../aware-mysql) | `aware_mysql`| Phone | AWARE app | MySQL | [link](../aware-mysql)
| `aware_micro_mysql`| Phone | AWARE Micro server | MySQL | [link](../aware-micro-mysql)
| `aware_csv`| Phone | AWARE app | CSV files | [link](../aware-csv) | `aware_csv`| Phone | AWARE app | CSV files | [link](../aware-csv)
| `aware_influxdb` (beta)| Phone | AWARE app | InfluxDB | [link](../aware-influxdb) | `aware_influxdb` (beta)| Phone | AWARE app | InfluxDB | [link](../aware-influxdb)
| `fitbitjson_mysql`| Fitbit | JSON (per [Fitbit's API](https://dev.fitbit.com/build/reference/web-api/)) | MySQL | [link](../fitbitjson-mysql) | `fitbitjson_mysql`| Fitbit | JSON (per [Fitbit's API](https://dev.fitbit.com/build/reference/web-api/)) | MySQL | [link](../fitbitjson-mysql)

View File

@ -85,6 +85,7 @@ nav:
- Introduction: datastreams/data-streams-introduction.md - Introduction: datastreams/data-streams-introduction.md
- Phone: - Phone:
- aware_mysql: datastreams/aware-mysql.md - aware_mysql: datastreams/aware-mysql.md
- aware_micro_mysql: datastreams/aware-micro-mysql.md
- aware_csv: datastreams/aware-csv.md - aware_csv: datastreams/aware-csv.md
- aware_influxdb (beta): datastreams/aware-influxdb.md - aware_influxdb (beta): datastreams/aware-influxdb.md
- Mandatory Phone Format: datastreams/mandatory-phone-format.md - Mandatory Phone Format: datastreams/mandatory-phone-format.md

View File

@ -0,0 +1,85 @@
# if you need a new package, you should add it with renv::install(package) so your renv venv is updated
library(RMariaDB)
library(yaml)
#' @description
#' Auxiliary function to parse the connection credentials from a specifc group in ./credentials.yaml
#' You can reause most of this function if you are connection to a DB or Web API.
#' It's OK to delete this function if you don't need credentials, e.g., you are pulling data from a CSV for example.
#' @param group the yaml key containing the credentials to connect to a database
#' @preturn dbEngine a database engine (connection) ready to perform queries
get_db_engine <- function(group){
# The working dir is aways RAPIDS root folder, so your credentials file is always /credentials.yaml
credentials <- read_yaml("./credentials.yaml")
if(!group %in% names(credentials))
stop(paste("The credentials group",group, "does not exist in ./credentials.yaml. The only groups that exist in that file are:", paste(names(credentials), collapse = ","), ". Did you forget to set the group in [PHONE_DATA_STREAMS][aware_mysql][DATABASE_GROUP] in config.yaml?"))
dbEngine <- dbConnect(MariaDB(), db = credentials[[group]][["database"]],
username = credentials[[group]][["user"]],
password = credentials[[group]][["password"]],
host = credentials[[group]][["host"]],
port = credentials[[group]][["port"]])
return(dbEngine)
}
# This file gets executed for each PHONE_SENSOR of each participant
# If you are connecting to a database the env file containing its credentials is available at "./.env"
# If you are reading a CSV file instead of a DB table, the @param sensor_container wil contain the file path as set in config.yaml
# You are not bound to databases or files, you can query a web API or whatever data source you need.
#' @description
#' RAPIDS allows users to use the keyword "infer" (previously "multiple") to automatically infer the mobile Operative System a device was running.
#' If you have a way to infer the OS of a device ID, implement this function. For example, for AWARE data we use the "aware_device" table.
#'
#' If you don't have a way to infer the OS, call stop("Error Message") so other users know they can't use "infer" or the inference failed,
#' and they have to assign the OS manually in the participant file
#'
#' @param stream_parameters The PHONE_STREAM_PARAMETERS key in config.yaml. If you need specific parameters add them there.
#' @param device A device ID string
#' @return The OS the device ran, "android" or "ios"
infer_device_os <- function(stream_parameters, device){
dbEngine <- get_db_engine(stream_parameters$DATABASE_GROUP)
query <- paste0("SELECT device_id,brand FROM aware_device WHERE device_id = '", device, "'")
message(paste0("Executing the following query to infer phone OS: ", query))
os <- dbGetQuery(dbEngine, query)
dbDisconnect(dbEngine)
if(nrow(os) > 0)
return(os %>% mutate(os = ifelse(brand == "iPhone", "ios", "android")) %>% pull(os))
else
stop(paste("We cannot infer the OS of the following device id because it does not exist in the aware_device table:", device))
return(os)
}
#' @description
#' Gets the sensor data for a specific device id from a database table, file or whatever source you want to query
#'
#' @param stream_parameters The PHONE_STREAM_PARAMETERS key in config.yaml. If you need specific parameters add them there.
#' @param device A device ID string
#' @param sensor_container database table or file containing the sensor data for all participants. This is the PHONE_SENSOR[CONTAINER] key in config.yaml
#' @param columns the columns needed from this sensor (we recommend to only return these columns instead of every column in sensor_container)
#' @return A dataframe with the sensor data for device
pull_data <- function(stream_parameters, device, sensor, sensor_container, columns){
dbEngine <- get_db_engine(stream_parameters$DATABASE_GROUP)
select_items <- c()
for (column in columns) {
select_items <- append(select_items, paste0("data->>'$.", column, "' ", column))
}
query <- paste0("SELECT ", paste(select_items, collapse = ",")," FROM ", sensor_container, " WHERE ", columns$DEVICE_ID ," = '", device,"'")
# Letting the user know what we are doing
message(paste0("Executing the following query to download data: ", query))
sensor_data <- dbGetQuery(dbEngine, query)
dbDisconnect(dbEngine)
if(nrow(sensor_data) == 0)
warning(paste("The device '", device,"' did not have data in ", sensor_container))
return(sensor_data)
}

View File

@ -0,0 +1,337 @@
PHONE_ACCELEROMETER:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
DOUBLE_VALUES_0: double_values_0
DOUBLE_VALUES_1: double_values_1
DOUBLE_VALUES_2: double_values_2
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
DOUBLE_VALUES_0: double_values_0
DOUBLE_VALUES_1: double_values_1
DOUBLE_VALUES_2: double_values_2
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_ACTIVITY_RECOGNITION:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
ACTIVITY_NAME: activity_name
ACTIVITY_TYPE: activity_type
CONFIDENCE: confidence
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
ACTIVITY_NAME: FLAG_TO_MUTATE
ACTIVITY_TYPE: FLAG_TO_MUTATE
CONFIDENCE: FLAG_TO_MUTATE
MUTATION:
COLUMN_MAPPINGS:
ACTIVITIES: activities
CONFIDENCE: confidence
SCRIPTS: # List any python or r scripts that mutate your raw data
- "src/data/streams/mutations/phone/aware/activity_recogniton_ios_unification.R"
PHONE_APPLICATIONS_CRASHES:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
PACKAGE_NAME: package_name
APPLICATION_NAME: application_name
APPLICATION_VERSION: application_version
ERROR_SHORT: error_short
ERROR_LONG: error_long
ERROR_CONDITION: error_condition
IS_SYSTEM_APP: is_system_app
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_APPLICATIONS_FOREGROUND:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
PACKAGE_NAME: package_name
APPLICATION_NAME: application_name
IS_SYSTEM_APP: is_system_app
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_APPLICATIONS_NOTIFICATIONS:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
PACKAGE_NAME: package_name
APPLICATION_NAME: application_name
TEXT: text
SOUND: sound
VIBRATE: vibrate
DEFAULTS: defaults
FLAGS: flags
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_BATTERY:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
BATTERY_STATUS: battery_status
BATTERY_LEVEL: battery_level
BATTERY_SCALE: battery_scale
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
BATTERY_STATUS: FLAG_TO_MUTATE
BATTERY_LEVEL: battery_level
BATTERY_SCALE: battery_scale
MUTATION:
COLUMN_MAPPINGS:
BATTERY_STATUS: battery_status
SCRIPTS:
- "src/data/streams/mutations/phone/aware/battery_ios_unification.R"
PHONE_BLUETOOTH:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
BT_ADDRESS: bt_address
BT_NAME: bt_name
BT_RSSI: bt_rssi
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
BT_ADDRESS: bt_address
BT_NAME: bt_name
BT_RSSI: bt_rssi
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_CALLS:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
CALL_TYPE: call_type
CALL_DURATION: call_duration
TRACE: trace
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
CALL_TYPE: FLAG_TO_MUTATE
CALL_DURATION: call_duration
TRACE: trace
MUTATION:
COLUMN_MAPPINGS:
CALL_TYPE: call_type
SCRIPTS:
- "src/data/streams/mutations/phone/aware/calls_ios_unification.R"
PHONE_CONVERSATION:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
DOUBLE_ENERGY: double_energy
INFERENCE: inference
DOUBLE_CONVO_START: double_convo_start
DOUBLE_CONVO_END: double_convo_end
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
DOUBLE_ENERGY: double_energy
INFERENCE: inference
DOUBLE_CONVO_START: double_convo_start
DOUBLE_CONVO_END: double_convo_end
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
- "src/data/streams/mutations/phone/aware/conversation_ios_timestamp.R"
PHONE_KEYBOARD:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
PACKAGE_NAME: package_name
BEFORE_TEXT: before_text
CURRENT_TEXT: current_text
IS_PASSWORD: is_password
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_LIGHT:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
DOUBLE_LIGHT_LUX: double_light_lux
ACCURACY: accuracy
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_LOCATIONS:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
DOUBLE_LATITUDE: double_latitude
DOUBLE_LONGITUDE: double_longitude
DOUBLE_BEARING: double_bearing
DOUBLE_SPEED: double_speed
DOUBLE_ALTITUDE: double_altitude
PROVIDER: provider
ACCURACY: accuracy
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
DOUBLE_LATITUDE: double_latitude
DOUBLE_LONGITUDE: double_longitude
DOUBLE_BEARING: double_bearing
DOUBLE_SPEED: double_speed
DOUBLE_ALTITUDE: double_altitude
PROVIDER: provider
ACCURACY: accuracy
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_LOG:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
LOG_MESSAGE: log_message
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
LOG_MESSAGE: log_message
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_MESSAGES:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
MESSAGE_TYPE: message_type
TRACE: trace
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_SCREEN:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
SCREEN_STATUS: screen_status
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
SCREEN_STATUS: FLAG_TO_MUTATE
MUTATION:
COLUMN_MAPPINGS:
SCREEN_STATUS: screen_status
SCRIPTS: # List any python or r scripts that mutate your raw data
- "src/data/streams/mutations/phone/aware/screen_ios_unification.R"
PHONE_WIFI_CONNECTED:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
MAC_ADDRESS: mac_address
SSID: ssid
BSSID: bssid
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
MAC_ADDRESS: mac_address
SSID: ssid
BSSID: bssid
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_WIFI_VISIBLE:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
SSID: ssid
BSSID: bssid
SECURITY: security
FREQUENCY: frequency
RSSI: rssi
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
SSID: ssid
BSSID: bssid
SECURITY: security
FREQUENCY: frequency
RSSI: rssi
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data

View File

@ -39,7 +39,7 @@ unify_ios_calls <- function(ios_calls){
assigned_segments = first(assigned_segments)) assigned_segments = first(assigned_segments))
} }
else { else {
ios_calls <- ios_calls %>% summarise(call_type_sequence = paste(call_type, collapse = ","), call_duration = sum(call_duration), timestamp = first(timestamp), device_id = first(device_id)) ios_calls <- ios_calls %>% summarise(call_type_sequence = paste(call_type, collapse = ","), call_duration = sum(as.numeric(call_duration)), timestamp = first(timestamp), device_id = first(device_id))
} }
ios_calls <- ios_calls %>% mutate(call_type = case_when( ios_calls <- ios_calls %>% mutate(call_type = case_when(
call_type_sequence == "1,2,4" | call_type_sequence == "2,1,4" ~ 1, # incoming call_type_sequence == "1,2,4" | call_type_sequence == "2,1,4" ~ 1, # incoming

View File

@ -25,9 +25,11 @@ barnett_daily_features <- function(snakemake){
datetime_end_regex = "[0-9]{4}[\\-|\\/][0-9]{2}[\\-|\\/][0-9]{2} 23:59:59" datetime_end_regex = "[0-9]{4}[\\-|\\/][0-9]{2}[\\-|\\/][0-9]{2} 23:59:59"
location <- location %>% location <- location %>%
mutate(is_daily = str_detect(assigned_segments, paste0(".*#", datetime_start_regex, ",", datetime_end_regex, ".*"))) mutate(is_daily = str_detect(assigned_segments, paste0(".*#", datetime_start_regex, ",", datetime_end_regex, ".*")))
if(nrow(segment_labels) == 0 || nrow(location) == 0 || all(location$is_daily == FALSE) || (max(location$timestamp) - min(location$timestamp) < 86400000)){ does_not_span = nrow(segment_labels) == 0 || nrow(location) == 0 || all(location$is_daily == FALSE) || (max(location$timestamp) - min(location$timestamp) < 86400000)
warning("Barnett's location features cannot be computed for data or time segments that do not span one or more entire days (00:00:00 to 23:59:59). Values below point to the problem:",
if(is.na(does_not_span) || does_not_span){
warning("Barnett's location features cannot be computed for data or time segments that do not span one or more entire days (00:00:00 to 23:59:59). Values below point to the problem:",
"\nLocation data rows within a daily time segment: ", nrow(filter(location, is_daily)), "\nLocation data rows within a daily time segment: ", nrow(filter(location, is_daily)),
"\nLocation data time span in days: ", round((max(location$timestamp) - min(location$timestamp)) / 86400000, 2) "\nLocation data time span in days: ", round((max(location$timestamp) - min(location$timestamp)) / 86400000, 2)
) )

View File

@ -24,12 +24,12 @@ def colors2colorscale(colors):
def getDataForPlot(phone_data_yield_per_segment): def getDataForPlot(phone_data_yield_per_segment):
# calculate the length (in minute) of per segment instance # calculate the length (in minute) of per segment instance
phone_data_yield_per_segment["length"] = phone_data_yield_per_segment["timestamps_segment"].str.split(",").apply(lambda x: int((int(x[1])-int(x[0])) / (1000 * 60))) phone_data_yield_per_segment["length"] = phone_data_yield_per_segment["timestamps_segment"].str.split(",").apply(lambda x: int((int(x[1])-int(x[0])) / (1000 * 60)))
# calculate the number of sensors logged at least one row of data per minute.
phone_data_yield_per_segment = phone_data_yield_per_segment.groupby(["local_segment", "length", "local_date", "local_hour", "local_minute"])[["sensor", "local_date_time"]].max().reset_index()
# extract local start datetime of the segment from "local_segment" column # extract local start datetime of the segment from "local_segment" column
phone_data_yield_per_segment["local_segment_start_datetimes"] = pd.to_datetime(phone_data_yield_per_segment["local_segment"].apply(lambda x: x.split("#")[1].split(",")[0])) phone_data_yield_per_segment["local_segment_start_datetimes"] = pd.to_datetime(phone_data_yield_per_segment["local_segment"].apply(lambda x: x.split("#")[1].split(",")[0]))
# calculate the number of minutes after local start datetime of the segment # calculate the number of minutes after local start datetime of the segment
phone_data_yield_per_segment["minutes_after_segment_start"] = ((phone_data_yield_per_segment["local_date_time"] - phone_data_yield_per_segment["local_segment_start_datetimes"]) / pd.Timedelta(minutes=1)).astype("int") phone_data_yield_per_segment["minutes_after_segment_start"] = ((phone_data_yield_per_segment["local_date_time"] - phone_data_yield_per_segment["local_segment_start_datetimes"]) / pd.Timedelta(minutes=1)).astype("int")
# calculate the number of sensors logged at least one row of data per minute.
phone_data_yield_per_segment = phone_data_yield_per_segment.groupby(["local_segment", "length", "local_segment_start_datetimes", "minutes_after_segment_start"])[["sensor"]].max().reset_index()
# impute missing rows with 0 # impute missing rows with 0
columns_for_full_index = phone_data_yield_per_segment[["local_segment_start_datetimes", "length"]].drop_duplicates(keep="first") columns_for_full_index = phone_data_yield_per_segment[["local_segment_start_datetimes", "length"]].drop_duplicates(keep="first")