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

Refactor battery features

pull/95/head
Meng Li 2020-06-03 17:36:52 -04:00
parent a8eb5a83f8
commit 6562754777
2 changed files with 54 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
src/features/battery/battery_base.py 100644
View File

@ -0,0 +1,48 @@
import pandas as pd
from datetime import datetime, timedelta, time
from features_utils import splitOvernightEpisodes, splitMultiSegmentEpisodes
def base_battery_features(battery_data, day_segment, requested_features):
# name of the features this function can compute
base_features_names = ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
# the subset of requested features this function can compute
features_to_compute = list(set(requested_features) & set(base_features_names))
if battery_data.empty:
battery_features = pd.DataFrame(columns=["local_date"] + ["battery_" + day_segment + "_" + x for x in features_to_compute])
else:
battery_data = splitOvernightEpisodes(battery_data, ["battery_diff"], [])
if day_segment != "daily":
battery_data = splitMultiSegmentEpisodes(battery_data, day_segment, ["battery_diff"])
battery_data["battery_consumption_rate"] = battery_data["battery_diff"] / battery_data["time_diff"]
# for battery_data_discharge:
battery_data_discharge = battery_data[battery_data["battery_diff"] > 0]
battery_discharge_features = pd.DataFrame()
if "countdischarge" in features_to_compute:
battery_discharge_features["battery_"+day_segment+"_countdischarge"] = battery_data_discharge.groupby(["local_start_date"])["local_start_date"].count()
if "sumdurationdischarge" in features_to_compute:
battery_discharge_features["battery_"+day_segment+"_sumdurationdischarge"] = battery_data_discharge.groupby(["local_start_date"])["time_diff"].sum()
if "avgconsumptionrate" in features_to_compute:
battery_discharge_features["battery_"+day_segment+"_avgconsumptionrate"] = battery_data_discharge.groupby(["local_start_date"])["battery_consumption_rate"].mean()
if "maxconsumptionrate" in features_to_compute:
battery_discharge_features["battery_"+day_segment+"_maxconsumptionrate"] = battery_data_discharge.groupby(["local_start_date"])["battery_consumption_rate"].max()
# for battery_data_charge:
battery_data_charge = battery_data[battery_data["battery_diff"] <= 0]
battery_charge_features = pd.DataFrame()
if "countcharge" in features_to_compute:
battery_charge_features["battery_"+day_segment+"_countcharge"] = battery_data_charge.groupby(["local_start_date"])["local_start_date"].count()
if "sumdurationcharge" in features_to_compute:
battery_charge_features["battery_"+day_segment+"_sumdurationcharge"] = battery_data_charge.groupby(["local_start_date"])["time_diff"].sum()
# combine discharge features and charge features; fill the missing values with ZERO
battery_features = pd.concat([battery_discharge_features, battery_charge_features], axis=1, sort=True).fillna(0)
battery_features.index.rename("local_date", inplace=True)
battery_features = battery_features.reset_index()
return battery_features

41
src/features/battery_features.py
View File

@ -1,42 +1,13 @@
import pandas as pd
from datetime import datetime, timedelta, time
from features_utils import splitOvernightEpisodes, splitMultiSegmentEpisodes
from battery.battery_base import base_battery_features
battery_data = pd.read_csv(snakemake.input[0], parse_dates=["local_start_date_time", "local_end_date_time", "local_start_date", "local_end_date"])
day_segment = snakemake.params["day_segment"]
features = snakemake.params["features"]
requested_features = snakemake.params["features"]
battery_features = pd.DataFrame(columns=["local_date"])
if battery_data.empty:
battery_features = pd.DataFrame(columns=["local_date"] + ["battery_" + day_segment + "_" + x for x in features])
else:
battery_data = splitOvernightEpisodes(battery_data, ["battery_diff"], [])
battery_features = battery_features.merge(base_battery_features(battery_data, day_segment, requested_features), on="local_date", how="outer")
if day_segment != "daily":
battery_data = splitMultiSegmentEpisodes(battery_data, day_segment, ["battery_diff"])
assert len(requested_features) + 1 == battery_features.shape[1], "The number of features in the output dataframe (=" + str(battery_features.shape[1]) + ") does not match the expected value (=" + str(len(requested_features)) + " + 1). Verify your battery feature extraction functions"
battery_data["battery_consumption_rate"] = battery_data["battery_diff"] / battery_data["time_diff"]
# for battery_data_discharge:
battery_data_discharge = battery_data[battery_data["battery_diff"] > 0]
battery_discharge_features = pd.DataFrame()
if "countdischarge" in features:
battery_discharge_features["battery_"+day_segment+"_countdischarge"] = battery_data_discharge.groupby(["local_start_date"])["local_start_date"].count()
if "sumdurationdischarge" in features:
battery_discharge_features["battery_"+day_segment+"_sumdurationdischarge"] = battery_data_discharge.groupby(["local_start_date"])["time_diff"].sum()
if "avgconsumptionrate" in features:
battery_discharge_features["battery_"+day_segment+"_avgconsumptionrate"] = battery_data_discharge.groupby(["local_start_date"])["battery_consumption_rate"].mean()
if "maxconsumptionrate" in features:
battery_discharge_features["battery_"+day_segment+"_maxconsumptionrate"] = battery_data_discharge.groupby(["local_start_date"])["battery_consumption_rate"].max()
# for battery_data_charge:
battery_data_charge = battery_data[battery_data["battery_diff"] <= 0]
battery_charge_features = pd.DataFrame()
if "countcharge" in features:
battery_charge_features["battery_"+day_segment+"_countcharge"] = battery_data_charge.groupby(["local_start_date"])["local_start_date"].count()
if "sumdurationcharge" in features:
battery_charge_features["battery_"+day_segment+"_sumdurationcharge"] = battery_data_charge.groupby(["local_start_date"])["time_diff"].sum()
# combine discharge features and charge features; fill the missing values with ZERO
battery_features = pd.concat([battery_discharge_features, battery_charge_features], axis=1, sort=True).fillna(0)
battery_features.index.rename("local_date", inplace=True)
battery_features.to_csv(snakemake.output[0], index=True)
battery_features.to_csv(snakemake.output[0], index=False)