stress_at_work_analysis/exploration/ex_ml_pipeline.py

261 lines
6.1 KiB
Python

# ---
# jupyter:
# jupytext:
# formats: ipynb,py:percent
# text_representation:
# extension: .py
# format_name: percent
# format_version: '1.3'
# jupytext_version: 1.12.0
# kernelspec:
# display_name: straw2analysis
# language: python
# name: straw2analysis
# ---
# %%
# %matplotlib inline
import datetime
import importlib
import os
import sys
import numpy as np
import pandas as pd
import seaborn as sns
import yaml
from sklearn import linear_model
from sklearn.model_selection import LeaveOneGroupOut, cross_val_score
nb_dir = os.path.split(os.getcwd())[0]
if nb_dir not in sys.path:
sys.path.append(nb_dir)
import machine_learning.features_sensor
import machine_learning.labels
import machine_learning.model
# %%
import participants.query_db
from features import esm, helper, proximity
# %% [markdown] tags=[]
# # 1. Get the relevant data
# %%
participants_inactive_usernames = participants.query_db.get_usernames(
collection_start=datetime.date.fromisoformat("2020-08-01")
)
# Consider only two participants to simplify.
ptcp_2 = participants_inactive_usernames[0:2]
# %% [markdown] jp-MarkdownHeadingCollapsed=true tags=[]
# ## 1.1 Labels
# %%
df_esm = esm.get_esm_data(ptcp_2)
df_esm_preprocessed = esm.preprocess_esm(df_esm)
# %%
df_esm_PANAS = df_esm_preprocessed[
(df_esm_preprocessed["questionnaire_id"] == 8)
| (df_esm_preprocessed["questionnaire_id"] == 9)
]
df_esm_PANAS_clean = esm.clean_up_esm(df_esm_PANAS)
# %% [markdown]
# ## 1.2 Sensor data
# %%
df_proximity = proximity.get_proximity_data(ptcp_2)
df_proximity = helper.get_date_from_timestamp(df_proximity)
df_proximity = proximity.recode_proximity(df_proximity)
# %% [markdown]
# ## 1.3 Standardization/personalization
# %% [markdown]
# # 2. Grouping/segmentation
# %%
df_esm_PANAS_daily_means = (
df_esm_PANAS_clean.groupby(["participant_id", "date_lj", "questionnaire_id"])
.esm_user_answer_numeric.agg("mean")
.reset_index()
.rename(columns={"esm_user_answer_numeric": "esm_numeric_mean"})
)
# %%
df_esm_PANAS_daily_means = (
df_esm_PANAS_daily_means.pivot(
index=["participant_id", "date_lj"],
columns="questionnaire_id",
values="esm_numeric_mean",
)
.reset_index(col_level=1)
.rename(columns={8.0: "PA", 9.0: "NA"})
.set_index(["participant_id", "date_lj"])
)
# %%
df_proximity_daily_counts = proximity.count_proximity(df_proximity, ["date_lj"])
# %%
df_proximity_daily_counts
# %% [markdown]
# # 3. Join features (and export to csv?)
# %%
df_full_data_daily_means = df_esm_PANAS_daily_means.join(
df_proximity_daily_counts
).reset_index()
# %% [markdown]
# # 4. Machine learning model and parameters
# %%
lin_reg_proximity = linear_model.LinearRegression()
# %% [markdown]
# ## 4.1 Validation method
# %%
logo = LeaveOneGroupOut()
logo.get_n_splits(
df_full_data_daily_means[["freq_prox_near", "prop_prox_near"]],
df_full_data_daily_means["PA"],
groups=df_full_data_daily_means["participant_id"],
)
# %% [markdown]
# ## 4.2 Fit results (export?)
# %%
cross_val_score(
lin_reg_proximity,
df_full_data_daily_means[["freq_prox_near", "prop_prox_near"]],
df_full_data_daily_means["PA"],
groups=df_full_data_daily_means["participant_id"],
cv=logo,
n_jobs=-1,
scoring="r2",
)
# %%
lin_reg_proximity.fit(
df_full_data_daily_means[["freq_prox_near", "prop_prox_near"]],
df_full_data_daily_means["PA"],
)
# %%
lin_reg_proximity.score(
df_full_data_daily_means[["freq_prox_near", "prop_prox_near"]],
df_full_data_daily_means["PA"],
)
# %% [markdown]
# # Merging these into a pipeline
# %%
from machine_learning import features_sensor, labels, model, pipeline
# %%
importlib.reload(features_sensor)
# %%
with open("../machine_learning/config/minimal_features.yaml", "r") as file:
sensor_features_params = yaml.safe_load(file)
print(sensor_features_params)
# %%
sensor_features = machine_learning.features_sensor.SensorFeatures(
**sensor_features_params
)
sensor_features.data_types
# %%
sensor_features.set_participants_label("nokia_0000003")
# %%
sensor_features.data_types = ["proximity", "communication"]
sensor_features.participants_usernames = ptcp_2
# %%
sensor_features.get_sensor_data("proximity")
# %%
sensor_features.set_sensor_data()
# %%
sensor_features.get_sensor_data("proximity")
# %%
sensor_features.calculate_features(cached=False)
features_all_calculated = sensor_features.get_features("all", "all")
# %%
sensor_features.calculate_features(cached=True)
features_all_read = sensor_features.get_features("all", "all")
# %%
features_all_read = features_all_read.reset_index()
features_all_read["date_lj"] = features_all_read["date_lj"].dt.date
features_all_read.set_index(["participant_id", "date_lj"], inplace=True)
# date_lj column is parsed as a date and represented as Timestamp, when read from csv.
# When calculated, it is represented as date.
# %%
np.isclose(features_all_read, features_all_calculated).all()
# %%
with open("../machine_learning/config/minimal_labels.yaml", "r") as file:
labels_params = yaml.safe_load(file)
# %%
labels = machine_learning.labels.Labels(**labels_params)
labels.participants_usernames = ptcp_2
labels.set_participants_label("nokia_0000003")
labels.questionnaires
# %%
labels.set_labels()
# %%
labels.get_labels("PANAS")
# %%
labels.aggregate_labels(cached=False)
labels_calculated = labels.get_aggregated_labels()
# %%
labels.aggregate_labels(cached=True)
labels_read = labels.get_aggregated_labels()
labels_read = labels_read.reset_index()
labels_read["date_lj"] = labels_read["date_lj"].dt.date
labels_read.set_index(["participant_id", "date_lj"], inplace=True)
# date_lj column is parsed as a date and represented as Timestamp, when read from csv.
# When calculated, it is represented as date.
# %%
np.isclose(labels_read, labels_calculated).all()
# %%
model_validation = machine_learning.model.ModelValidation(
sensor_features.get_features("all", "all"),
labels.get_aggregated_labels(),
group_variable="participant_id",
cv_name="loso",
)
model_validation.model = linear_model.LinearRegression()
model_validation.set_cv_method()
# %%
model_validation.cross_validate()
# %%
model_validation.groups
# %%