stress_at_work_analysis/exploration/ml_pipeline_regression.py

# ---
# jupyter:
#   jupytext:
#     formats: ipynb,py:percent
#     text_representation:
#       extension: .py
#       format_name: percent
#       format_version: '1.3'
#       jupytext_version: 1.14.5
#   kernelspec:
#     display_name: straw2analysis
#     language: python
#     name: straw2analysis
# ---

# %%
import os
import sys

import pandas as pd

from machine_learning.helper import (
    impute_encode_categorical_features,
    prepare_cross_validator,
    prepare_sklearn_data_format,
    run_all_regression_models,
)

nb_dir = os.path.split(os.getcwd())[0]
if nb_dir not in sys.path:
    sys.path.append(nb_dir)

# %%
model_input = pd.read_csv(
    "../data/intradaily_30_min_all_targets/input_JCQ_job_demand_mean.csv"
)

# %%
model_input = model_input[model_input["local_segment"].str.contains("daily")]

# %%
CV_METHOD = "logo"  # logo, half_logo, 5kfold

model_input_encoded = impute_encode_categorical_features(model_input)
# %%
data_x, data_y, data_groups = prepare_sklearn_data_format(
    model_input_encoded, CV_METHOD
)
cross_validator = prepare_cross_validator(data_x, data_y, data_groups, CV_METHOD)
# %%
data_y.head()

# %%
data_y.tail()

# %%
data_y.shape

# %%
scores = run_all_regression_models(data_x, data_y, data_groups, cross_validator)

# %%
scores.to_csv(
    "../presentation/JCQ_supervisor_support_regression_" + CV_METHOD + ".csv",
    index=False,
)