Add google activity recognition features

replace/3cc7ab759a6e42b1d655a31b2284800b18c99506
Echhit Joshi 2019-11-06 13:34:47 -05:00
parent 911e183c26
commit bdbb1904c2
3 changed files with 50 additions and 1 deletions

View File

@ -28,6 +28,7 @@ rule all:
expand("data/processed/{pid}/bluetooth_{segment}.csv", expand("data/processed/{pid}/bluetooth_{segment}.csv",
pid=config["PIDS"], pid=config["PIDS"],
segment = config["BLUETOOTH"]["DAY_SEGMENTS"]), segment = config["BLUETOOTH"]["DAY_SEGMENTS"]),
expand("data/processed/{pid}/activity_extracted.csv",pid=config["PIDS"]),
# Reports # Reports
expand("reports/figures/{pid}/{sensor}_heatmap_rows.html", pid=config["PIDS"], sensor=config["SENSORS"]), expand("reports/figures/{pid}/{sensor}_heatmap_rows.html", pid=config["PIDS"], sensor=config["SENSORS"]),
expand("reports/figures/{pid}/compliance_heatmap.html", pid=config["PIDS"], sensor=config["SENSORS"]), expand("reports/figures/{pid}/compliance_heatmap.html", pid=config["PIDS"], sensor=config["SENSORS"]),

View File

@ -51,3 +51,11 @@ rule bluetooth_metrics:
"data/processed/{pid}/bluetooth_{day_segment}.csv" "data/processed/{pid}/bluetooth_{day_segment}.csv"
script: script:
"../src/features/bluetooth_metrics.R" "../src/features/bluetooth_metrics.R"
rule activity_metrics:
input:
"data/raw/{pid}/plugin_google_activity_recognition_with_datetime.csv"
output:
"data/processed/{pid}/activity_extracted.csv"
script:
"../src/features/activity_recognition.py"

View File

@ -0,0 +1,40 @@
import pandas as pd
import numpy as np
import scipy.stats as stats
#Read csv into a pandas dataframe
data = pd.read_csv(snakemake.input[0])
#Resampling each of the required features as a pandas series
data.local_date_time = pd.to_datetime(data.local_date_time)
resampledData = data.set_index(data.local_date_time)
resampledData = resampledData[~resampledData.index.duplicated()]
resampledData.rename_axis('time',axis='columns',inplace=True)
resampledData.drop(columns=['local_date_time'],inplace=True)
#Finding count grouped by day
count = pd.DataFrame()
count = resampledData['activity_type'].resample('D').count()
count = count.rename(columns={"activity_type":"count"})
#Finding most common activity of the day
mostCommonActivity = pd.DataFrame()
mostCommonActivity = resampledData['activity_type'].resample('D').apply(lambda x:stats.mode(x)[0])
mostCommonActivity = mostCommonActivity.rename(columns={'activity_type':'most_common_activity'})
#finding different number of activities during a day
countChanges = pd.DataFrame()
# countChanges = resampledData.to_period('D').groupby(resampledData.index)['activity_type'].value_counts()
countChanges = resampledData['activity_type'].resample('D').nunique()
#Concatenating all the processed data only, no other sensor data is added here for simplicity
finalDataset = pd.DataFrame()
finalDataset = pd.concat([count,mostCommonActivity,countChanges],axis=1)
finalDataset.rename(columns={0:"count",1:'most_common_activity','activity_type':'activity_changes_count'},inplace = True)
#Export final dataframe with extracted features to respective PID
finalDataset.to_csv(snakemake.output[0])