Add battery daily features and daily consumption rate plot

Snakefile

@@ -22,9 +22,11 @@ rule all:
                             pid=config["PIDS"], 
                             segment = config["BLUETOOTH"]["DAY_SEGMENTS"]),
         expand("data/processed/{pid}/google_activity_recognition.csv",pid=config["PIDS"]),
+        expand("data/processed/{pid}/battery_daily.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"]),
+        expand("reports/figures/{pid}/battery_consumption_rates_barchart.html", pid=config["PIDS"]),
 
 # --- Packrat Rules --- #
 ## Taken from https://github.com/lachlandeer/snakemake-econ-r

rules/features.snakefile

@@ -59,3 +59,11 @@ rule activity_metrics:
         "data/processed/{pid}/google_activity_recognition.csv"
     script:
         "../src/features/google_activity_recognition.py"
+
+rule battery_metrics:
+    input:
+        "data/processed/{pid}/battery_deltas.csv"
+    output:
+        "data/processed/{pid}/battery_daily.csv"
+    script:
+        "../src/features/battery_metrics.py"

rules/reports.snakefile

@@ -18,3 +18,13 @@ rule compliance_heatmap:
         "reports/figures/{pid}/compliance_heatmap.html"
     script:
         "../src/visualization/compliance_heatmap.py"
+
+rule battery_consumption_rates_barchart:
+    input:
+        "data/processed/{pid}/battery_daily.csv"
+    params:
+        pid = "{pid}"
+    output:
+        "reports/figures/{pid}/battery_consumption_rates_barchart.html"
+    script:
+        "../src/visualization/battery_consumption_rates_barchart.py"

src/features/battery_metrics.py

@@ -0,0 +1,60 @@
+import pandas as pd
+import datetime
+
+
+battery_data = pd.read_csv(snakemake.input[0])
+if battery_data.empty:
+    battery_features = pd.DataFrame(columns=["battery_diff", "time_diff", "battery_decrease_times","battery_consumption_rate", "local_date"])
+else:
+    for col in ["local_start_date_time", "local_end_date_time", "local_start_date", "local_end_date"]:
+        battery_data[col] = pd.to_datetime(battery_data[col])
+
+    # split the row into 2 rows when local_start_date + 1 = local_end_date
+    battery_data_overnight = battery_data[battery_data["local_start_date"] + datetime.timedelta(days=1) == battery_data["local_end_date"]]
+    if not battery_data_overnight.empty:
+        battery_data_overnight_first, battery_data_overnight_second = pd.DataFrame(columns=battery_data.columns), pd.DataFrame(columns=battery_data.columns)
+        battery_data_overnight_first["total_battery_diff"], battery_data_overnight_second["total_battery_diff"] = battery_data_overnight["battery_diff"], battery_data_overnight["battery_diff"]
+        battery_data_overnight_first["total_time_diff"], battery_data_overnight_second["total_time_diff"] = battery_data_overnight["time_diff"], battery_data_overnight["time_diff"]
+        # let start = start OR end = end, then fill the left col with the start+23:59:59.
+        battery_data_overnight_first["local_start_date_time"] = battery_data_overnight["local_start_date_time"]
+        battery_data_overnight_first["local_end_date_time"] = battery_data_overnight["local_start_date"].apply(lambda x: datetime.datetime.combine(x, datetime.time(23,59,59)))
+        battery_data_overnight_first["local_start_date"] = battery_data_overnight["local_start_date"]
+        battery_data_overnight_second["local_end_date_time"] = battery_data_overnight["local_end_date_time"]
+        battery_data_overnight_second["local_start_date_time"] = battery_data_overnight["local_start_date"].apply(lambda x: datetime.datetime.combine(x, datetime.time(23,59,59)))
+        battery_data_overnight_second["local_start_date"] = battery_data_overnight["local_end_date"]
+        battery_data_overnight = pd.concat([battery_data_overnight_first, battery_data_overnight_second])
+        # calculate battery_diff and time_diff
+        battery_data_overnight["time_diff"] = (battery_data_overnight["local_end_date_time"]-battery_data_overnight["local_start_date_time"]).apply(lambda x: x.total_seconds()/3600)
+        battery_data_overnight["battery_diff"] = battery_data_overnight["total_battery_diff"]*(battery_data_overnight["time_diff"]/battery_data_overnight["total_time_diff"])
+        del battery_data_overnight["total_battery_diff"], battery_data_overnight["total_time_diff"]
+
+    # filter out the rows when local_start_date + 1 < local_end_date
+    battery_data = battery_data[battery_data["local_start_date"] == battery_data["local_end_date"]]
+
+    # combine
+    battery_data = pd.concat([battery_data, battery_data_overnight])
+
+    # split into decrease table and charge table
+    battery_data_decrease = battery_data[battery_data["battery_diff"] > 0]
+    battery_data_charge = battery_data[battery_data["battery_diff"] <= 0]
+
+    # for battery_data_decrease:
+    battery_decrease_count = battery_data_decrease.groupby(["local_start_date"])["local_start_date"].count()
+    battery_data_decrease = battery_data_decrease.groupby(["local_start_date"]).sum()
+    battery_data_decrease["battery_decrease_count"] = battery_decrease_count
+    battery_data_decrease["battery_decrease_duration"] = battery_data_decrease["time_diff"]
+    battery_data_decrease["battery_consumption_rate"] = battery_data_decrease["battery_diff"]/battery_data_decrease["time_diff"]
+    del battery_data_decrease["battery_diff"], battery_data_decrease["time_diff"]
+
+    # for battery_data_charge:
+    battery_charge_count = battery_data_charge.groupby(["local_start_date"])["local_start_date"].count()
+    battery_data_charge = battery_data_charge.groupby(["local_start_date"]).sum()
+    battery_data_charge["battery_charge_count"] = battery_charge_count
+    battery_data_charge["battery_charge_duration"] = battery_data_charge["time_diff"]
+    del battery_data_charge["battery_diff"], battery_data_charge["time_diff"]
+
+    # combine decrease features and charge features
+    battery_features = pd.concat([battery_data_decrease, battery_data_charge], axis=1, sort=True)
+    battery_features["local_date"] = battery_features.index
+    battery_features.reset_index(inplace=True, drop=True)
+battery_features.to_csv(snakemake.output[0], index=False)

src/visualization/battery_consumption_rates_barchart.py

@@ -0,0 +1,26 @@
+import pandas as pd
+import datetime
+import plotly.io as pio
+import plotly.graph_objects as go
+
+def getBatteryConsumptionRatesBarChart(battery_data, pid):
+    plot = go.Figure(go.Bar(
+                    x=battery_data["battery_consumption_rate"],
+                    y=battery_data["local_date"].apply(lambda x: x.replace("-","/")).tolist(),
+                    orientation='h'))
+    plot.update_layout(title="Daily battery consumption rates bar chart for " + pid,
+                    xaxis_title="battery drains % per hour",
+                    )
+    return plot
+    
+
+
+battery_data = pd.read_csv(snakemake.input[0])
+pid = snakemake.params["pid"]
+if battery_data.empty:
+    empty_html = open(snakemake.output[0], "w")
+    empty_html.write("There is no "+ sensor_name + " data for "+pid)
+    empty_html.close()
+else:
+    plot = getBatteryConsumptionRatesBarChart(battery_data, pid)
+    pio.write_html(plot, file=snakemake.output[0], auto_open=False)