Add TEMP lime_survey cols

ml_pipeline
Primoz 2022-11-22 14:44:33 +01:00
parent 183758cd37
commit 7afef5582f
1 changed files with 7 additions and 0 deletions

View File

@ -51,6 +51,13 @@ import machine_learning.model
# %% jupyter={"source_hidden": true} # %% jupyter={"source_hidden": true}
model_input = pd.read_csv("../data/intradaily_30_min_all_targets/input_JCQ_job_demand_mean.csv") model_input = pd.read_csv("../data/intradaily_30_min_all_targets/input_JCQ_job_demand_mean.csv")
lime_cols = [col for col in model_input if col.startswith('limesurvey_demand')]
model_input['limesurvey_demand_control_ratio'].describe()
lime_cols
# TODO: prek lime_cols ustvari klastre, ki jih nato kasneje ločeno preveriš z modeli (npr. k=5). Potrebno bo trikrat ponoviti spodnji postopek.
# Pomisli, če gre kaj zavizi v for loop (npr. modeli v seznamu)
# %% jupyter={"source_hidden": true} # %% jupyter={"source_hidden": true}
index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"] index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
model_input.set_index(index_columns, inplace=True) model_input.set_index(index_columns, inplace=True)