From bdbb1904c2fdaa899f8f47663adba227a127a65c Mon Sep 17 00:00:00 2001
From: Echhit Joshi <32146180+EchhitJoshi@users.noreply.github.com>
Date: Wed, 6 Nov 2019 13:34:47 -0500
Subject: [PATCH] Add google activity recognition features

---
 Snakefile                            |  1 +
 rules/features.snakefile             | 10 ++++++-
 src/features/activity_recognition.py | 40 ++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+), 1 deletion(-)
 create mode 100644 src/features/activity_recognition.py

diff --git a/Snakefile b/Snakefile
index 26f4f1a2..f5829896 100644
--- a/Snakefile
+++ b/Snakefile
@@ -28,6 +28,7 @@ rule all:
         expand("data/processed/{pid}/bluetooth_{segment}.csv",
                             pid=config["PIDS"], 
                             segment = config["BLUETOOTH"]["DAY_SEGMENTS"]),
+        expand("data/processed/{pid}/activity_extracted.csv",pid=config["PIDS"]),
         # Reports
         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"]),
diff --git a/rules/features.snakefile b/rules/features.snakefile
index cfdb5097..e1e98065 100644
--- a/rules/features.snakefile
+++ b/rules/features.snakefile
@@ -50,4 +50,12 @@ rule bluetooth_metrics:
     output:
         "data/processed/{pid}/bluetooth_{day_segment}.csv"
     script:
-        "../src/features/bluetooth_metrics.R"
\ No newline at end of file
+        "../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"
diff --git a/src/features/activity_recognition.py b/src/features/activity_recognition.py
new file mode 100644
index 00000000..0e814e26
--- /dev/null
+++ b/src/features/activity_recognition.py
@@ -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])
+