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: 1.13.0
#   kernelspec:
#     display_name: straw2analysis
#     language: python
#     name: straw2analysis
# ---

# %% jupyter={"source_hidden": true}
# %matplotlib inline
import datetime
import importlib
import os
import sys

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
import yaml
from pyprojroot import here
from sklearn import linear_model, svm, kernel_ridge, gaussian_process
from sklearn.model_selection import LeaveOneGroupOut, cross_val_score, cross_validate
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.impute import SimpleImputer
from sklearn.dummy import DummyRegressor
import xgboost as xg
from IPython.core.interactiveshell import InteractiveShell
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)

import machine_learning.features_sensor
import machine_learning.labels
import machine_learning.model

# %% [markdown]
# # RAPIDS models

# %% [markdown]
# ## PANAS negative affect

# %% jupyter={"source_hidden": true}
model_input = pd.read_csv("../data/intradaily_30_min_all_targets/input_JCQ_job_demand_mean.csv")

# %% jupyter={"source_hidden": true}
index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
#if "pid" in model_input.columns:
#    index_columns.append("pid")
model_input.set_index(index_columns, inplace=True)

cv_method = 'half_logo' # logo, half_logo, 5kfold
if cv_method == 'logo':
    data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]
else:
    model_input['pid_index'] = model_input.groupby('pid').cumcount()
    model_input['pid_count'] = model_input.groupby('pid')['pid'].transform('count')

    model_input["pid_index"] = (model_input['pid_index'] / model_input['pid_count'] + 1).round()
    model_input["pid_half"] = model_input["pid"] + "_" +  model_input["pid_index"].astype(int).astype(str)

    data_x, data_y, data_groups = model_input.drop(["target", "pid", "pid_index", "pid_half"], axis=1), model_input["target"], model_input["pid_half"]

# %% jupyter={"source_hidden": true}
categorical_feature_colnames = ["gender", "startlanguage"]
additional_categorical_features = [col for col in data_x.columns if "mostcommonactivity" in col or "homelabel" in col]
categorical_feature_colnames += additional_categorical_features

# %% jupyter={"source_hidden": true}
categorical_features = data_x[categorical_feature_colnames].copy()

# %% jupyter={"source_hidden": true}
mode_categorical_features = categorical_features.mode().iloc[0]

# %% jupyter={"source_hidden": true}
# fillna with mode
categorical_features = categorical_features.fillna(mode_categorical_features)

# %% jupyter={"source_hidden": true}
# one-hot encoding
categorical_features = categorical_features.apply(lambda col: col.astype("category"))
if not categorical_features.empty:
    categorical_features = pd.get_dummies(categorical_features)

# %% jupyter={"source_hidden": true}
numerical_features = data_x.drop(categorical_feature_colnames, axis=1)

# %% jupyter={"source_hidden": true}
train_x = pd.concat([numerical_features, categorical_features], axis=1)

# %% jupyter={"source_hidden": true}
train_x.dtypes

# %% jupyter={"source_hidden": true}
logo = LeaveOneGroupOut()
logo.get_n_splits(
    train_x,
    data_y,
    groups=data_groups,
)

# Defaults to 5 k folds in cross_validate method
if cv_method != 'logo' and cv_method != 'half_logo':
    logo = None

# %% jupyter={"source_hidden": true}
sum(data_y.isna())

# %% [markdown]
# ### Baseline: Dummy Regression (mean)
dummy_regr = DummyRegressor(strategy="mean")

# %% jupyter={"source_hidden": true}
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')

# %% jupyter={"source_hidden": true}
dummy_regressor = cross_validate(
    dummy_regr,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(dummy_regressor['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(dummy_regressor['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(dummy_regressor['test_neg_root_mean_squared_error']))
print("R2", np.median(dummy_regressor['test_r2']))

# %% [markdown]
# ### Linear Regression

# %% jupyter={"source_hidden": true}
lin_reg_rapids = linear_model.LinearRegression()
# %% jupyter={"source_hidden": true}
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')

# %% jupyter={"source_hidden": true}
lin_reg_scores = cross_validate(
    lin_reg_rapids,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(lin_reg_scores['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(lin_reg_scores['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(lin_reg_scores['test_neg_root_mean_squared_error']))
print("R2", np.median(lin_reg_scores['test_r2']))

# %% [markdown]
# ### XGBRegressor Linear Regression
# %% jupyter={"source_hidden": true}
xgb_r = xg.XGBRegressor(objective ='reg:squarederror', n_estimators = 10)
# %% jupyter={"source_hidden": true}
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')

# %% jupyter={"source_hidden": true}
xgb_reg_scores = cross_validate(
    xgb_r,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(xgb_reg_scores['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(xgb_reg_scores['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(xgb_reg_scores['test_neg_root_mean_squared_error']))
print("R2", np.median(xgb_reg_scores['test_r2']))

# %% [markdown]
# ### XGBRegressor Pseudo Huber Error Regression
# %% jupyter={"source_hidden": true}
xgb_psuedo_huber_r = xg.XGBRegressor(objective ='reg:pseudohubererror', n_estimators = 10)
# %% jupyter={"source_hidden": true}
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')

# %% jupyter={"source_hidden": true}
xgb_psuedo_huber_reg_scores = cross_validate(
    xgb_psuedo_huber_r,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(xgb_psuedo_huber_reg_scores['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(xgb_psuedo_huber_reg_scores['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(xgb_psuedo_huber_reg_scores['test_neg_root_mean_squared_error']))
print("R2", np.median(xgb_psuedo_huber_reg_scores['test_r2']))

# %% [markdown]
# ### Ridge regression

# %% jupyter={"source_hidden": true}
ridge_reg = linear_model.Ridge(alpha=.5)

# %% tags=[] jupyter={"source_hidden": true}
ridge_reg_scores = cross_validate(
    ridge_reg,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(ridge_reg_scores['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(ridge_reg_scores['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(ridge_reg_scores['test_neg_root_mean_squared_error']))
print("R2", np.median(ridge_reg_scores['test_r2']))

# %% [markdown]
# ### Lasso

# %% jupyter={"source_hidden": true}
lasso_reg = linear_model.Lasso(alpha=0.1)

# %% jupyter={"source_hidden": true}
lasso_reg_score = cross_validate(
    lasso_reg,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(lasso_reg_score['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(lasso_reg_score['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(lasso_reg_score['test_neg_root_mean_squared_error']))
print("R2", np.median(lasso_reg_score['test_r2']))

# %% [markdown]
# ### Bayesian Ridge

# %% jupyter={"source_hidden": true}
bayesian_ridge_reg = linear_model.BayesianRidge()

# %% jupyter={"source_hidden": true}
bayesian_ridge_reg_score = cross_validate(
    bayesian_ridge_reg,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(bayesian_ridge_reg_score['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(bayesian_ridge_reg_score['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(bayesian_ridge_reg_score['test_neg_root_mean_squared_error']))
print("R2", np.median(bayesian_ridge_reg_score['test_r2']))

# %% [markdown]
# ### RANSAC (outlier robust regression)

# %% jupyter={"source_hidden": true}
ransac_reg = linear_model.RANSACRegressor()

# %% jupyter={"source_hidden": true}
ransac_reg_scores = cross_validate(
    ransac_reg,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(ransac_reg_scores['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(ransac_reg_scores['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(ransac_reg_scores['test_neg_root_mean_squared_error']))
print("R2", np.median(ransac_reg_scores['test_r2']))

# %% [markdown]
# ### Support vector regression

# %% jupyter={"source_hidden": true}
svr = svm.SVR()

# %% jupyter={"source_hidden": true}
svr_scores = cross_validate(
    svr,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(svr_scores['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(svr_scores['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(svr_scores['test_neg_root_mean_squared_error']))
print("R2", np.median(svr_scores['test_r2']))

# %% [markdown]
# ### Kernel Ridge regression

# %% jupyter={"source_hidden": true}
kridge = kernel_ridge.KernelRidge()

# %% jupyter={"source_hidden": true}
kridge_scores = cross_validate(
    kridge,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(kridge_scores['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(kridge_scores['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(kridge_scores['test_neg_root_mean_squared_error']))
print("R2", np.median(kridge_scores['test_r2']))

# %% [markdown]
# ### Gaussian Process Regression

# %% jupyter={"source_hidden": true}
gpr = gaussian_process.GaussianProcessRegressor()

# %% jupyter={"source_hidden": true}

gpr_scores = cross_validate(
    gpr,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=logo,
    n_jobs=-1,
    scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
)
print("Negative Mean Squared Error", np.median(gpr_scores['test_neg_mean_squared_error']))
print("Negative Mean Absolute Error", np.median(gpr_scores['test_neg_mean_absolute_error']))
print("Negative Root Mean Squared Error", np.median(gpr_scores['test_neg_root_mean_squared_error']))
print("R2", np.median(gpr_scores['test_r2']))

# %%