31 lines
1.7 KiB
Python
31 lines
1.7 KiB
Python
import pandas as pd
|
|
|
|
|
|
def straw_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
|
|
speech_data = pd.read_csv(sensor_data_files["sensor_data"])
|
|
requested_features = provider["FEATURES"]
|
|
# name of the features this function can compute+
|
|
base_features_names = ["meanspeech", "stdspeech", "nlargest", "nsmallest", "medianspeech"]
|
|
features_to_compute = list(set(requested_features) & set(base_features_names))
|
|
speech_features = pd.DataFrame(columns=["local_segment"] + features_to_compute)
|
|
|
|
if not speech_data.empty:
|
|
speech_data = filter_data_by_segment(speech_data, time_segment)
|
|
|
|
if not speech_data.empty:
|
|
speech_features = pd.DataFrame()
|
|
if "meanspeech" in features_to_compute:
|
|
speech_features["meanspeech"] = speech_data.groupby(["local_segment"])['speech_proportion'].mean()
|
|
if "stdspeech" in features_to_compute:
|
|
speech_features["stdspeech"] = speech_data.groupby(["local_segment"])['speech_proportion'].std()
|
|
if "nlargest" in features_to_compute:
|
|
speech_features["nlargest"] = speech_data.groupby(["local_segment"])['speech_proportion'].apply(lambda x: x.nlargest(5).mean())
|
|
if "nsmallest" in features_to_compute:
|
|
speech_features["nsmallest"] = speech_data.groupby(["local_segment"])['speech_proportion'].apply(lambda x: x.nsmallest(5).mean())
|
|
if "medianspeech" in features_to_compute:
|
|
speech_features["medianspeech"] = speech_data.groupby(["local_segment"])['speech_proportion'].median()
|
|
|
|
speech_features = speech_features.reset_index()
|
|
|
|
return speech_features
|