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

Remove standardization script.

notes
Primoz 2022-09-19 07:25:16 +00:00
parent 18b63127de
commit 92aff93e65
1 changed files with 0 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
src/features/standardization/main.py
View File

@ -1,50 +0,0 @@
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
import sys
sensor_data_files = dict(snakemake.input)
provider = snakemake.params["provider"]
provider_key = snakemake.params["provider_key"]
sensor_key = snakemake.params["sensor_key"]
pd.set_option('display.max_columns', None)
if provider_key == "cr":
sys.path.append('/rapids/src/features/')
from cr_features_helper_methods import extract_second_order_features
provider_main = snakemake.params["provider_main"]
prefix = sensor_key + "_" + provider_key + "_"
windows_features_data = pd.read_csv(sensor_data_files["windows_features_data"])
excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime', prefix + "level_1"]
if windows_features_data.empty:
windows_features_data.to_csv(snakemake.output[1], index=False)
windows_features_data.to_csv(snakemake.output[0], index=False)
else:
windows_features_data.loc[:, ~windows_features_data.columns.isin(excluded_columns)] = StandardScaler().fit_transform(windows_features_data.loc[:, ~windows_features_data.columns.isin(excluded_columns)])
windows_features_data.to_csv(snakemake.output[1], index=False)
if provider_main["WINDOWS"]["COMPUTE"] and "SECOND_ORDER_FEATURES" in provider_main["WINDOWS"]:
so_features_names = provider_main["WINDOWS"]["SECOND_ORDER_FEATURES"]
windows_so_features_data = extract_second_order_features(windows_features_data, so_features_names, prefix)
windows_so_features_data.to_csv(snakemake.output[0], index=False)
else:
pd.DataFrame().to_csv(snakemake.output[0], index=False)
else:
for sensor_features in sensor_data_files["sensor_features"]:
if "/" + sensor_key + ".csv" in sensor_features:
sensor_data = pd.read_csv(sensor_features)
excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime']
if not sensor_data.empty:
sensor_data.loc[:, ~sensor_data.columns.isin(excluded_columns)] = StandardScaler().fit_transform(sensor_data.loc[:, ~sensor_data.columns.isin(excluded_columns)])
sensor_data.to_csv(snakemake.output[0], index=False)
break