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

Format comments.

master
junos 2023-05-11 16:51:38 +02:00
parent 055e87dbac
commit 3091328fc5
1 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
exploration/ml_pipeline_classification.py
View File

@ -13,7 +13,7 @@
# name: straw2analysis # name: straw2analysis
# --- # ---
# %% jupyter={"source_hidden": false, "outputs_hidden": false} # %% jupyter={"outputs_hidden": false, "source_hidden": false}
# %matplotlib inline # %matplotlib inline
import os import os
import sys import sys
@ -43,19 +43,20 @@ UNDERSAMPLING = False
# (bool) If True this will train and test data on balanced dataset # (bool) If True this will train and test data on balanced dataset
# (using undersampling method) # (using undersampling method)
# %% jupyter={"source_hidden": false, "outputs_hidden": false} # %% jupyter={"outputs_hidden": false, "source_hidden": false}
model_input = pd.read_csv( model_input = pd.read_csv(
"E:/STRAWresults/20230415/daily/input_PANAS_negative_affect_mean.csv" "E:/STRAWresults/20230415/stress_event/input_appraisal_stressfulness_event_mean.csv"
) )
# model_input = # model_input =
# model_input[model_input.columns.drop( # model_input[model_input.columns.drop(
# list(model_input.filter(regex='empatica_temperature')) # list(model_input.filter(regex='empatica_temperature'))
# )] # )]
# model_input = model_input[model_input['local_segment'].str.contains("daily")]
# %% jupyter={"source_hidden": false, "outputs_hidden": false} # %% jupyter={"outputs_hidden": false, "source_hidden": false}
model_input["target"].value_counts() model_input["target"].value_counts()
# %% jupyter={"source_hidden": false, "outputs_hidden": false} # %% jupyter={"outputs_hidden": false, "source_hidden": false}
# bins = [-10, 0, 10] # bins for z-scored targets # bins = [-10, 0, 10] # bins for z-scored targets
bins = [-1, 0, 4] # bins for stressfulness (0-4) target bins = [-1, 0, 4] # bins for stressfulness (0-4) target
model_input["target"], edges = pd.cut( model_input["target"], edges = pd.cut(
@ -69,7 +70,7 @@ model_input["target"] = (
model_input["target"].value_counts() model_input["target"].value_counts()
# %% jupyter={"source_hidden": false, "outputs_hidden": false} # %% jupyter={"outputs_hidden": false, "source_hidden": false}
# UnderSampling # UnderSampling
if UNDERSAMPLING: if UNDERSAMPLING:
no_stress = model_input[model_input["target"] == 0] no_stress = model_input[model_input["target"] == 0]
@ -79,7 +80,7 @@ if UNDERSAMPLING:
model_input = pd.concat([stress, no_stress], axis=0) model_input = pd.concat([stress, no_stress], axis=0)
# %% jupyter={"source_hidden": false, "outputs_hidden": false} # %% jupyter={"outputs_hidden": false, "source_hidden": false}
model_input_encoded = impute_encode_categorical_features(model_input) model_input_encoded = impute_encode_categorical_features(model_input)
# %% # %%
data_x, data_y, data_groups = prepare_sklearn_data_format( data_x, data_y, data_groups = prepare_sklearn_data_format(
@ -98,6 +99,8 @@ data_y.shape
scores = run_all_classification_models(data_x, data_y, data_groups, cross_validator) scores = run_all_classification_models(data_x, data_y, data_groups, cross_validator)
# %% # %%
scores.to_csv( scores.to_csv(
"../presentation/JCQ_supervisor_support_regression_" + CV_METHOD + ".csv", "../presentation/appraisal_stressfulness_event_classification_"
+ CV_METHOD
+ ".csv",
index=False, index=False,
) )