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

removed cleaning to make it run

sociality-task
Marcel Martinšek 2023-03-31 13:27:01 +00:00
parent da77f7476c
commit fb8868b77d
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
config.yaml
View File

@ -663,9 +663,9 @@ HEATMAP_FEATURE_CORRELATION_MATRIX:
ALL_CLEANING_INDIVIDUAL:
PROVIDERS:
RAPIDS:
COMPUTE: True
COMPUTE: False
IMPUTE_SELECTED_EVENT_FEATURES:
COMPUTE: True
COMPUTE: False
MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33
COLS_NAN_THRESHOLD: 1 # set to 1 to disable
COLS_VAR_THRESHOLD: True
@ -673,12 +673,12 @@ ALL_CLEANING_INDIVIDUAL:
DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
DATA_YIELD_RATIO_THRESHOLD: 0 # set to 0 to disable
DROP_HIGHLY_CORRELATED_FEATURES:
COMPUTE: True
COMPUTE: False
MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
CORR_THRESHOLD: 0.95
SRC_SCRIPT: src/features/all_cleaning_individual/rapids/main.R
STRAW:
COMPUTE: True
COMPUTE: False
PHONE_DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_MINUTES # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
PHONE_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
EMPATICA_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
@ -686,7 +686,7 @@ ALL_CLEANING_INDIVIDUAL:
COLS_NAN_THRESHOLD: 0.9 # set to 1 to remove only columns that contains all (100% of) NaN
COLS_VAR_THRESHOLD: True
DROP_HIGHLY_CORRELATED_FEATURES:
COMPUTE: True
COMPUTE: False
MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
CORR_THRESHOLD: 0.95
STANDARDIZATION: True
@ -705,12 +705,12 @@ ALL_CLEANING_OVERALL:
DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
DATA_YIELD_RATIO_THRESHOLD: 0 # set to 0 to disable
DROP_HIGHLY_CORRELATED_FEATURES:
COMPUTE: True
COMPUTE: False
MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
CORR_THRESHOLD: 0.95
SRC_SCRIPT: src/features/all_cleaning_overall/rapids/main.R
STRAW:
COMPUTE: True
COMPUTE: False
PHONE_DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_MINUTES # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
PHONE_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
EMPATICA_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
@ -718,7 +718,7 @@ ALL_CLEANING_OVERALL:
COLS_NAN_THRESHOLD: 0.8 # set to 1 to remove only columns that contains all (100% of) NaN
COLS_VAR_THRESHOLD: True
DROP_HIGHLY_CORRELATED_FEATURES:
COMPUTE: True
COMPUTE: False
MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
CORR_THRESHOLD: 0.95
STANDARDIZATION: True