135 lines
3.9 KiB
Python
135 lines
3.9 KiB
Python
# ---
|
|
# 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
|
|
# ---
|
|
|
|
# %% jupyter={"outputs_hidden": false, "source_hidden": false}
|
|
# from IPython.core.interactiveshell import InteractiveShell
|
|
from pathlib import Path
|
|
|
|
# matplotlib inline
|
|
# 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_classification_models,
|
|
)
|
|
|
|
# InteractiveShell.ast_node_interactivity = "all"
|
|
#
|
|
# nb_dir = os.path.split(os.getcwd())[0]
|
|
# if nb_dir not in sys.path:
|
|
# sys.path.append(nb_dir)
|
|
|
|
|
|
# %%
|
|
CV_METHOD = "logo" # logo, half_logo, 5kfold
|
|
# Cross-validation method (could be regarded as a hyperparameter)
|
|
print("CV_METHOD: " + CV_METHOD)
|
|
N_SL = 3 # Number of largest/smallest accuracies (of particular CV) outputs
|
|
UNDERSAMPLING = False
|
|
# (bool) If True this will train and test data on balanced dataset
|
|
# (using undersampling method)
|
|
|
|
# %% jupyter={"outputs_hidden": false, "source_hidden": false}
|
|
PATH_BASE = Path("E:/STRAWresults/20230415")
|
|
|
|
SEGMENT_TYPE = "period"
|
|
print("SEGMENT_TYPE: " + SEGMENT_TYPE)
|
|
SEGMENT_LENGTH = "30_minutes_before"
|
|
print("SEGMENT_LENGTH: " + SEGMENT_LENGTH)
|
|
TARGET_VARIABLE = "JCQ_job_control"
|
|
print("TARGET_VARIABLE: " + TARGET_VARIABLE)
|
|
|
|
if ("appraisal" in TARGET_VARIABLE) and ("stressfulness" in TARGET_VARIABLE):
|
|
TARGET_VARIABLE += "_"
|
|
TARGET_VARIABLE += SEGMENT_TYPE
|
|
|
|
PATH_FULL = PATH_BASE / SEGMENT_LENGTH / ("input_" + TARGET_VARIABLE + "_mean.csv")
|
|
|
|
model_input = pd.read_csv(PATH_FULL)
|
|
|
|
if SEGMENT_LENGTH == "daily":
|
|
DAY_LENGTH = "daily" # or "working"
|
|
print(DAY_LENGTH)
|
|
model_input = model_input[model_input["local_segment"].str.contains(DAY_LENGTH)]
|
|
|
|
# %% jupyter={"outputs_hidden": false, "source_hidden": false}
|
|
model_input["target"].value_counts()
|
|
|
|
# %% jupyter={"outputs_hidden": false, "source_hidden": false}
|
|
# bins = [-10, 0, 10] # bins for z-scored targets
|
|
BINS = [-1, 0, 4] # bins for stressfulness (0-4) target
|
|
print("BINS: ", BINS)
|
|
model_input["target"], edges = pd.cut(
|
|
model_input.target, bins=BINS, labels=["low", "high"], retbins=True, right=True
|
|
) # ['low', 'medium', 'high']
|
|
print(model_input["target"].value_counts())
|
|
REMOVE_MEDIUM = True
|
|
if ("medium" in model_input["target"]) and REMOVE_MEDIUM:
|
|
model_input = model_input[model_input["target"] != "medium"]
|
|
model_input["target"] = (
|
|
model_input["target"].astype(str).apply(lambda x: 0 if x == "low" else 1)
|
|
)
|
|
else:
|
|
model_input["target"] = model_input["target"].map(
|
|
{"low": 0, "medium": 1, "high": 2}
|
|
)
|
|
print(model_input["target"].value_counts())
|
|
|
|
|
|
# %% jupyter={"outputs_hidden": false, "source_hidden": false}
|
|
# UnderSampling
|
|
if UNDERSAMPLING:
|
|
no_stress = model_input[model_input["target"] == 0]
|
|
stress = model_input[model_input["target"] == 1]
|
|
|
|
no_stress = no_stress.sample(n=len(stress))
|
|
model_input = pd.concat([stress, no_stress], axis=0)
|
|
|
|
|
|
# %% jupyter={"outputs_hidden": false, "source_hidden": false}
|
|
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_classification_models(data_x, data_y, data_groups, cross_validator)
|
|
# %%
|
|
PATH_OUTPUT = Path("..") / Path("presentation/results")
|
|
path_output_full = PATH_OUTPUT / (
|
|
TARGET_VARIABLE
|
|
+ "_"
|
|
+ SEGMENT_LENGTH
|
|
+ "_classification"
|
|
+ str(BINS)
|
|
+ "_"
|
|
+ CV_METHOD
|
|
+ ".csv"
|
|
)
|
|
scores.to_csv(path_output_full, index=False)
|