Refactor light features
parent
ac9fb487a6
commit
1ce76a5380
|
@ -0,0 +1,34 @@
|
|||
import pandas as pd
|
||||
|
||||
def base_light_features(light_data, day_segment, requested_features):
|
||||
# name of the features this function can compute
|
||||
base_features_names = ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
|
||||
# the subset of requested features this function can compute
|
||||
features_to_compute = list(set(requested_features) & set(base_features_names))
|
||||
|
||||
if light_data.empty:
|
||||
light_features = pd.DataFrame(columns=["local_date"] + ["light_" + day_segment + "_" + x for x in features_to_compute])
|
||||
else:
|
||||
if day_segment != "daily":
|
||||
light_data =light_data[light_data["local_day_segment"] == day_segment]
|
||||
|
||||
if not light_data.empty:
|
||||
light_features = pd.DataFrame()
|
||||
if "count" in features_to_compute:
|
||||
light_features["light_" + day_segment + "_count"] = light_data.groupby(["local_date"]).count()["timestamp"]
|
||||
|
||||
# get light ambient luminance related features
|
||||
if "maxlux" in features_to_compute:
|
||||
light_features["light_" + day_segment + "_maxlux"] = light_data.groupby(["local_date"])["double_light_lux"].max()
|
||||
if "minlux" in features_to_compute:
|
||||
light_features["light_" + day_segment + "_minlux"] = light_data.groupby(["local_date"])["double_light_lux"].min()
|
||||
if "avglux" in features_to_compute:
|
||||
light_features["light_" + day_segment + "_avglux"] = light_data.groupby(["local_date"])["double_light_lux"].mean()
|
||||
if "medianlux" in features_to_compute:
|
||||
light_features["light_" + day_segment + "_medianlux"] = light_data.groupby(["local_date"])["double_light_lux"].median()
|
||||
if "stdlux" in features_to_compute:
|
||||
light_features["light_" + day_segment + "_stdlux"] = light_data.groupby(["local_date"])["double_light_lux"].std()
|
||||
|
||||
light_features = light_features.reset_index()
|
||||
|
||||
return light_features
|
|
@ -1,32 +1,13 @@
|
|||
import pandas as pd
|
||||
import numpy as np
|
||||
from light.light_base import base_light_features
|
||||
|
||||
light_data = pd.read_csv(snakemake.input[0], parse_dates=["local_date_time", "local_date"])
|
||||
day_segment = snakemake.params["day_segment"]
|
||||
metrics = snakemake.params["metrics"]
|
||||
light_features = pd.DataFrame(columns=["local_date"])
|
||||
|
||||
light_features = pd.DataFrame(columns=["local_date"] + ["light_" + day_segment + "_" + x for x in metrics])
|
||||
if not light_data.empty:
|
||||
if day_segment != "daily":
|
||||
light_data =light_data[light_data["local_day_segment"] == day_segment]
|
||||
light_features = light_features.merge(base_light_features(light_data, day_segment, metrics), on="local_date", how="outer")
|
||||
|
||||
if not light_data.empty:
|
||||
light_features = pd.DataFrame()
|
||||
if "count" in metrics:
|
||||
light_features["light_" + day_segment + "_count"] = light_data.groupby(["local_date"]).count()["timestamp"]
|
||||
|
||||
# get light ambient luminance related features
|
||||
if "maxlux" in metrics:
|
||||
light_features["light_" + day_segment + "_maxlux"] = light_data.groupby(["local_date"])["double_light_lux"].max()
|
||||
if "minlux" in metrics:
|
||||
light_features["light_" + day_segment + "_minlux"] = light_data.groupby(["local_date"])["double_light_lux"].min()
|
||||
if "avglux" in metrics:
|
||||
light_features["light_" + day_segment + "_avglux"] = light_data.groupby(["local_date"])["double_light_lux"].mean()
|
||||
if "medianlux" in metrics:
|
||||
light_features["light_" + day_segment + "_medianlux"] = light_data.groupby(["local_date"])["double_light_lux"].median()
|
||||
if "stdlux" in metrics:
|
||||
light_features["light_" + day_segment + "_stdlux"] = light_data.groupby(["local_date"])["double_light_lux"].std()
|
||||
|
||||
light_features = light_features.reset_index()
|
||||
assert len(metrics) + 1 == light_features.shape[1], "The number of features in the output dataframe (=" + str(light_features.shape[1]) + ") does not match the expected value (=" + str(len(metrics)) + " + 1). Verify your light feature extraction functions"
|
||||
|
||||
light_features.to_csv(snakemake.output[0], index=False)
|
Loading…
Reference in New Issue