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

Thoroughly refactor regression runner.

master
junos 2023-05-10 20:30:51 +02:00
parent 47b1ecdbb9
commit b505fb2b6a
2 changed files with 104 additions and 488 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

438
exploration/ml_pipeline_regression.py
View File

@ -13,438 +13,36 @@
# name: straw2analysis
# ---
# %% jupyter={"source_hidden": true}
# %matplotlib inline
# %%
import os
import sys
import numpy as np
import pandas as pd
import xgboost as xg
from machine_learning.helper import prepare_regression_model_input
from sklearn import gaussian_process, kernel_ridge, linear_model, svm
from sklearn.dummy import DummyRegressor
from sklearn.impute import SimpleImputer
from sklearn.model_selection import LeaveOneGroupOut, cross_validate
# from IPython.core.interactiveshell import InteractiveShell
# InteractiveShell.ast_node_interactivity = "all"
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)
# %% 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}
cv_method = "half_logo" # logo, half_logo, 5kfold
train_x, data_y, data_groups = prepare_regression_model_input(model_input, cv_method)
# %% 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=0.5)
# %% 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"]))
# %%
CV_METHOD = "half_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)
# %%
scores = run_all_regression_models(data_x, data_y, data_groups, cross_validator)

152
machine_learning/helper.py
View File

@ -11,7 +11,12 @@ from sklearn import (
svm,
)
from sklearn.dummy import DummyClassifier, DummyRegressor
from sklearn.model_selection import LeaveOneGroupOut, cross_validate
from sklearn.model_selection import (
BaseCrossValidator,
LeaveOneGroupOut,
StratifiedKFold,
cross_validate,
)
from xgboost import XGBClassifier, XGBRegressor
@ -73,7 +78,40 @@ def insert_row(df, row):
return pd.concat([df, pd.DataFrame([row], columns=df.columns)], ignore_index=True)
def prepare_sklearn_data_format(model_input, cv_method="logo"):
def impute_encode_categorical_features(model_input: pd.DataFrame) -> pd.DataFrame:
categorical_feature_col_names = [
"gender",
"startlanguage",
"limesurvey_demand_control_ratio_quartile",
]
additional_categorical_features = [
col
for col in model_input.columns
if "mostcommonactivity" in col or "homelabel" in col
]
categorical_feature_col_names += additional_categorical_features
categorical_features = model_input[categorical_feature_col_names].copy()
mode_categorical_features = categorical_features.mode().iloc[0]
# fillna with mode
categorical_features = categorical_features.fillna(mode_categorical_features)
# 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)
numerical_features = model_input.drop(categorical_feature_col_names, axis=1)
model_input = pd.concat([numerical_features, categorical_features], axis=1)
return model_input
def prepare_sklearn_data_format(
model_input: pd.DataFrame, cv_method: str = "logo"
) -> tuple:
index_columns = [
"local_segment",
"local_segment_label",
@ -107,50 +145,30 @@ def prepare_sklearn_data_format(model_input, cv_method="logo"):
return data_x, data_y, data_groups
def prepare_regression_model_input(model_input, cv_method="logo"):
data_x, data_y, data_groups = prepare_sklearn_data_format(
model_input, cv_method=cv_method
)
categorical_feature_colnames = [
"gender",
"startlanguage",
"limesurvey_demand_control_ratio_quartile",
]
additional_categorical_features = [
col
for col in data_x.columns
if "mostcommonactivity" in col or "homelabel" in col
]
categorical_feature_colnames += additional_categorical_features
categorical_features = data_x[categorical_feature_colnames].copy()
mode_categorical_features = categorical_features.mode().iloc[0]
# fillna with mode
categorical_features = categorical_features.fillna(mode_categorical_features)
# 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)
numerical_features = data_x.drop(categorical_feature_colnames, axis=1)
train_x = pd.concat([numerical_features, categorical_features], axis=1)
return train_x, data_y, data_groups
def run_all_regression_models(train_x, data_y, data_groups):
# Prepare cross validation
logo = LeaveOneGroupOut()
logo.get_n_splits(
train_x,
def prepare_cross_validator(
data_x: pd.DataFrame,
data_y: pd.DataFrame,
data_groups: pd.DataFrame,
cv_method: str = "logo",
) -> BaseCrossValidator:
if cv_method == "logo" or cv_method == "half_logo":
cv = LeaveOneGroupOut()
cv.get_n_splits(
data_x,
data_y,
groups=data_groups,
)
else:
cv = StratifiedKFold(n_splits=5, shuffle=True)
return cv
def run_all_regression_models(
data_x: pd.DataFrame,
data_y: pd.DataFrame,
data_groups: pd.DataFrame,
cross_validator: BaseCrossValidator,
) -> pd.DataFrame:
metrics = ["r2", "neg_mean_absolute_error", "neg_root_mean_squared_error"]
test_metrics = ["test_" + metric for metric in metrics]
scores = pd.DataFrame(columns=["method", "max", "nanmedian"])
@ -159,10 +177,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
dummy_regr = DummyRegressor(strategy="mean")
dummy_regr_scores = cross_validate(
dummy_regr,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -177,10 +195,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
lin_reg_rapids = linear_model.LinearRegression()
lin_reg_scores = cross_validate(
lin_reg_rapids,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -195,10 +213,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
ridge_reg = linear_model.Ridge(alpha=0.5)
ridge_reg_scores = cross_validate(
ridge_reg,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -212,10 +230,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
lasso_reg = linear_model.Lasso(alpha=0.1)
lasso_reg_score = cross_validate(
lasso_reg,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -229,10 +247,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
bayesian_ridge_reg = linear_model.BayesianRidge()
bayesian_ridge_reg_score = cross_validate(
bayesian_ridge_reg,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -246,10 +264,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
ransac_reg = linear_model.RANSACRegressor()
ransac_reg_score = cross_validate(
ransac_reg,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -263,10 +281,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
svr = svm.SVR()
svr_score = cross_validate(
svr,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -280,10 +298,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
kridge = kernel_ridge.KernelRidge()
kridge_score = cross_validate(
kridge,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -297,10 +315,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
gpr = gaussian_process.GaussianProcessRegressor()
gpr_score = cross_validate(
gpr,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -314,10 +332,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
rfr = ensemble.RandomForestRegressor(max_features=0.3, n_jobs=-1)
rfr_score = cross_validate(
rfr,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -331,10 +349,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
xgb = XGBRegressor()
xgb_score = cross_validate(
xgb,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)
@ -348,10 +366,10 @@ def run_all_regression_models(train_x, data_y, data_groups):
ada = ensemble.AdaBoostRegressor()
ada_score = cross_validate(
ada,
X=train_x,
X=data_x,
y=data_y,
groups=data_groups,
cv=logo,
cv=cross_validator,
n_jobs=-1,
scoring=metrics,
)