2021-09-15 15:14:54 +02:00
|
|
|
from pathlib import Path
|
2022-12-08 10:00:14 +01:00
|
|
|
|
2022-11-16 18:13:30 +01:00
|
|
|
import numpy as np
|
2023-04-21 21:33:06 +02:00
|
|
|
import pandas as pd
|
|
|
|
from sklearn import (
|
|
|
|
ensemble,
|
|
|
|
gaussian_process,
|
|
|
|
kernel_ridge,
|
|
|
|
linear_model,
|
|
|
|
naive_bayes,
|
|
|
|
svm,
|
|
|
|
)
|
|
|
|
from sklearn.dummy import DummyClassifier, DummyRegressor
|
2023-05-10 20:30:51 +02:00
|
|
|
from sklearn.model_selection import (
|
|
|
|
BaseCrossValidator,
|
|
|
|
LeaveOneGroupOut,
|
|
|
|
StratifiedKFold,
|
|
|
|
cross_validate,
|
|
|
|
)
|
2023-04-21 21:33:06 +02:00
|
|
|
from xgboost import XGBClassifier, XGBRegressor
|
2021-09-15 15:14:54 +02:00
|
|
|
|
|
|
|
|
|
|
|
def safe_outer_merge_on_index(left: pd.DataFrame, right: pd.DataFrame) -> pd.DataFrame:
|
|
|
|
if left.empty:
|
|
|
|
return right
|
|
|
|
elif right.empty:
|
|
|
|
return left
|
|
|
|
else:
|
|
|
|
return pd.merge(
|
|
|
|
left,
|
|
|
|
right,
|
|
|
|
how="outer",
|
|
|
|
left_index=True,
|
|
|
|
right_index=True,
|
|
|
|
validate="one_to_one",
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
def to_csv_with_settings(
|
|
|
|
df: pd.DataFrame, folder: Path, filename_prefix: str, data_type: str
|
|
|
|
) -> None:
|
|
|
|
full_path = construct_full_path(folder, filename_prefix, data_type)
|
|
|
|
df.to_csv(
|
|
|
|
path_or_buf=full_path,
|
|
|
|
sep=",",
|
|
|
|
na_rep="NA",
|
|
|
|
header=True,
|
|
|
|
index=True,
|
|
|
|
encoding="utf-8",
|
|
|
|
)
|
|
|
|
print("Exported the dataframe to " + str(full_path))
|
|
|
|
|
|
|
|
|
|
|
|
def read_csv_with_settings(
|
|
|
|
folder: Path, filename_prefix: str, data_type: str, grouping_variable: list
|
|
|
|
) -> pd.DataFrame:
|
|
|
|
full_path = construct_full_path(folder, filename_prefix, data_type)
|
|
|
|
return pd.read_csv(
|
|
|
|
filepath_or_buffer=full_path,
|
|
|
|
sep=",",
|
|
|
|
header=0,
|
|
|
|
na_values="NA",
|
|
|
|
encoding="utf-8",
|
|
|
|
index_col=(["participant_id"] + grouping_variable),
|
|
|
|
parse_dates=True,
|
|
|
|
infer_datetime_format=True,
|
|
|
|
cache_dates=True,
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
def construct_full_path(folder: Path, filename_prefix: str, data_type: str) -> Path:
|
|
|
|
export_filename = filename_prefix + "_" + data_type + ".csv"
|
|
|
|
full_path = folder / export_filename
|
|
|
|
return full_path
|
2022-11-16 18:13:30 +01:00
|
|
|
|
2023-04-21 21:33:06 +02:00
|
|
|
|
2022-11-16 18:13:30 +01:00
|
|
|
def insert_row(df, row):
|
|
|
|
return pd.concat([df, pd.DataFrame([row], columns=df.columns)], ignore_index=True)
|
|
|
|
|
2022-11-16 19:34:18 +01:00
|
|
|
|
2023-05-10 20:30:51 +02:00
|
|
|
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:
|
2023-04-21 21:33:06 +02:00
|
|
|
index_columns = [
|
|
|
|
"local_segment",
|
|
|
|
"local_segment_label",
|
|
|
|
"local_segment_start_datetime",
|
|
|
|
"local_segment_end_datetime",
|
|
|
|
]
|
2022-11-16 18:13:30 +01:00
|
|
|
model_input.set_index(index_columns, inplace=True)
|
|
|
|
|
2023-05-10 15:28:09 +02:00
|
|
|
if cv_method == "half_logo":
|
2023-04-21 21:41:00 +02:00
|
|
|
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"],
|
|
|
|
)
|
2023-05-10 15:28:09 +02:00
|
|
|
else:
|
|
|
|
data_x, data_y, data_groups = (
|
|
|
|
model_input.drop(["target", "pid"], axis=1),
|
|
|
|
model_input["target"],
|
|
|
|
model_input["pid"],
|
|
|
|
)
|
|
|
|
return data_x, data_y, data_groups
|
|
|
|
|
|
|
|
|
2023-05-10 20:30:51 +02:00
|
|
|
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
|
2022-11-16 19:34:18 +01:00
|
|
|
|
|
|
|
|
2023-05-18 18:40:06 +02:00
|
|
|
def aggregate_and_transpose(df: pd.DataFrame, statistics=None) -> pd.DataFrame:
|
|
|
|
if statistics is None:
|
|
|
|
statistics = ["max", "mean"]
|
|
|
|
return (
|
|
|
|
df.agg(statistics)
|
|
|
|
.transpose()
|
|
|
|
.reset_index()
|
|
|
|
.rename(columns={"index": "test_metric"})
|
|
|
|
)
|
|
|
|
|
|
|
|
|
2023-05-10 20:30:51 +02:00
|
|
|
def run_all_regression_models(
|
|
|
|
data_x: pd.DataFrame,
|
|
|
|
data_y: pd.DataFrame,
|
|
|
|
data_groups: pd.DataFrame,
|
|
|
|
cross_validator: BaseCrossValidator,
|
|
|
|
) -> pd.DataFrame:
|
2023-04-21 21:33:06 +02:00
|
|
|
metrics = ["r2", "neg_mean_absolute_error", "neg_root_mean_squared_error"]
|
2022-12-07 21:25:05 +01:00
|
|
|
test_metrics = ["test_" + metric for metric in metrics]
|
2023-05-18 18:47:56 +02:00
|
|
|
scores = pd.DataFrame(columns=["method", "test_metric", "max", "nanmedian"])
|
2022-11-16 18:13:30 +01:00
|
|
|
|
|
|
|
# Validate models
|
2022-12-07 21:25:05 +01:00
|
|
|
dummy_regr = DummyRegressor(strategy="mean")
|
|
|
|
dummy_regr_scores = cross_validate(
|
|
|
|
dummy_regr,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2022-12-07 21:25:05 +01:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2022-12-07 21:25:05 +01:00
|
|
|
n_jobs=-1,
|
2023-04-21 21:33:06 +02:00
|
|
|
scoring=metrics,
|
2022-12-07 21:25:05 +01:00
|
|
|
)
|
|
|
|
print("Dummy model:")
|
2023-04-21 21:33:06 +02:00
|
|
|
print("R^2: ", np.nanmedian(dummy_regr_scores["test_r2"]))
|
|
|
|
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df = pd.DataFrame(dummy_regr_scores)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "dummy"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del dummy_regr
|
|
|
|
del dummy_regr_scores
|
2022-12-07 21:25:05 +01:00
|
|
|
|
2023-05-10 21:44:40 +02:00
|
|
|
lin_reg = linear_model.LinearRegression()
|
2022-12-07 21:25:05 +01:00
|
|
|
lin_reg_scores = cross_validate(
|
2023-05-10 21:44:40 +02:00
|
|
|
lin_reg,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2022-11-16 18:13:30 +01:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2022-11-16 18:13:30 +01:00
|
|
|
n_jobs=-1,
|
2023-04-21 21:33:06 +02:00
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("Linear regression:")
|
2023-04-21 21:33:06 +02:00
|
|
|
print("R^2: ", np.nanmedian(lin_reg_scores["test_r2"]))
|
2022-12-07 21:25:05 +01:00
|
|
|
|
|
|
|
scores_df = pd.DataFrame(lin_reg_scores)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "linear_reg"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del lin_reg
|
|
|
|
del lin_reg_scores
|
2022-11-16 18:13:30 +01:00
|
|
|
|
2023-04-21 21:33:06 +02:00
|
|
|
ridge_reg = linear_model.Ridge(alpha=0.5)
|
2022-12-07 21:25:05 +01:00
|
|
|
ridge_reg_scores = cross_validate(
|
2022-11-16 18:13:30 +01:00
|
|
|
ridge_reg,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2022-11-16 18:13:30 +01:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2022-11-16 18:13:30 +01:00
|
|
|
n_jobs=-1,
|
2023-04-21 21:33:06 +02:00
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("Ridge regression")
|
2022-12-07 21:25:05 +01:00
|
|
|
|
|
|
|
scores_df = pd.DataFrame(ridge_reg_scores)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "ridge_reg"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del ridge_reg
|
|
|
|
del ridge_reg_scores
|
2022-12-07 21:25:05 +01:00
|
|
|
|
2022-11-16 18:13:30 +01:00
|
|
|
lasso_reg = linear_model.Lasso(alpha=0.1)
|
2022-12-07 21:25:05 +01:00
|
|
|
lasso_reg_score = cross_validate(
|
2022-11-16 18:13:30 +01:00
|
|
|
lasso_reg,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2022-11-16 18:13:30 +01:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2022-11-16 18:13:30 +01:00
|
|
|
n_jobs=-1,
|
2023-04-21 21:33:06 +02:00
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("Lasso regression")
|
2022-12-07 21:25:05 +01:00
|
|
|
|
|
|
|
scores_df = pd.DataFrame(lasso_reg_score)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "lasso_reg"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del lasso_reg
|
|
|
|
del lasso_reg_score
|
2022-11-16 18:13:30 +01:00
|
|
|
|
|
|
|
bayesian_ridge_reg = linear_model.BayesianRidge()
|
2022-12-07 21:25:05 +01:00
|
|
|
bayesian_ridge_reg_score = cross_validate(
|
2022-11-16 18:13:30 +01:00
|
|
|
bayesian_ridge_reg,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2022-11-16 18:13:30 +01:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2022-11-16 18:13:30 +01:00
|
|
|
n_jobs=-1,
|
2023-04-21 21:33:06 +02:00
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("Bayesian Ridge")
|
2022-12-07 21:25:05 +01:00
|
|
|
|
|
|
|
scores_df = pd.DataFrame(bayesian_ridge_reg_score)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "bayesian_ridge"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del bayesian_ridge_reg
|
|
|
|
del bayesian_ridge_reg_score
|
2022-11-16 18:13:30 +01:00
|
|
|
|
|
|
|
ransac_reg = linear_model.RANSACRegressor()
|
2022-12-07 21:25:05 +01:00
|
|
|
ransac_reg_score = cross_validate(
|
2022-11-16 18:13:30 +01:00
|
|
|
ransac_reg,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2022-11-16 18:13:30 +01:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2022-11-16 18:13:30 +01:00
|
|
|
n_jobs=-1,
|
2023-04-21 21:33:06 +02:00
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("RANSAC (outlier robust regression)")
|
2022-12-07 21:25:05 +01:00
|
|
|
|
|
|
|
scores_df = pd.DataFrame(ransac_reg_score)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "RANSAC"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del ransac_reg
|
|
|
|
del ransac_reg_score
|
2022-11-16 18:13:30 +01:00
|
|
|
|
|
|
|
svr = svm.SVR()
|
2022-12-07 21:25:05 +01:00
|
|
|
svr_score = cross_validate(
|
2023-05-10 15:20:33 +02:00
|
|
|
svr,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2023-05-10 15:20:33 +02:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2023-05-10 15:20:33 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("Support vector regression")
|
2023-04-21 21:33:06 +02:00
|
|
|
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df = pd.DataFrame(svr_score)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "SVR"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del svr
|
|
|
|
del svr_score
|
2022-11-16 18:13:30 +01:00
|
|
|
|
|
|
|
kridge = kernel_ridge.KernelRidge()
|
2022-12-07 21:25:05 +01:00
|
|
|
kridge_score = cross_validate(
|
2022-11-16 18:13:30 +01:00
|
|
|
kridge,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2022-11-16 18:13:30 +01:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2022-11-16 18:13:30 +01:00
|
|
|
n_jobs=-1,
|
2023-04-21 21:33:06 +02:00
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("Kernel Ridge regression")
|
2023-04-21 21:33:06 +02:00
|
|
|
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df = pd.DataFrame(kridge_score)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "kernel_ridge"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del kridge
|
|
|
|
del kridge_score
|
2022-11-16 18:13:30 +01:00
|
|
|
|
|
|
|
gpr = gaussian_process.GaussianProcessRegressor()
|
2022-12-07 21:25:05 +01:00
|
|
|
gpr_score = cross_validate(
|
2023-05-10 15:20:33 +02:00
|
|
|
gpr,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2023-05-10 15:20:33 +02:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2023-05-10 15:20:33 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("Gaussian Process Regression")
|
2022-12-07 21:25:05 +01:00
|
|
|
|
|
|
|
scores_df = pd.DataFrame(gpr_score)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "gaussian_proc"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del gpr
|
|
|
|
del gpr_score
|
2022-11-16 18:13:30 +01:00
|
|
|
|
|
|
|
rfr = ensemble.RandomForestRegressor(max_features=0.3, n_jobs=-1)
|
2022-12-07 21:25:05 +01:00
|
|
|
rfr_score = cross_validate(
|
2023-05-10 15:20:33 +02:00
|
|
|
rfr,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2023-05-10 15:20:33 +02:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2023-05-10 15:20:33 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("Random Forest Regression")
|
2022-12-07 21:25:05 +01:00
|
|
|
|
|
|
|
scores_df = pd.DataFrame(rfr_score)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "random_forest"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del rfr
|
|
|
|
del rfr_score
|
2022-11-16 18:13:30 +01:00
|
|
|
|
|
|
|
xgb = XGBRegressor()
|
2022-12-07 21:25:05 +01:00
|
|
|
xgb_score = cross_validate(
|
2023-05-10 15:20:33 +02:00
|
|
|
xgb,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2023-05-10 15:20:33 +02:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2023-05-10 15:20:33 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("XGBoost Regressor")
|
2022-12-07 21:25:05 +01:00
|
|
|
|
|
|
|
scores_df = pd.DataFrame(xgb_score)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "XGBoost"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del xgb
|
|
|
|
del xgb_score
|
2022-11-16 18:13:30 +01:00
|
|
|
|
|
|
|
ada = ensemble.AdaBoostRegressor()
|
2022-12-07 21:25:05 +01:00
|
|
|
ada_score = cross_validate(
|
2023-05-10 15:20:33 +02:00
|
|
|
ada,
|
2023-05-10 20:30:51 +02:00
|
|
|
X=data_x,
|
2023-05-10 15:20:33 +02:00
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 20:30:51 +02:00
|
|
|
cv=cross_validator,
|
2023-05-10 15:20:33 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-11-16 18:13:30 +01:00
|
|
|
)
|
|
|
|
print("ADA Boost Regressor")
|
2022-12-07 21:25:05 +01:00
|
|
|
|
|
|
|
scores_df = pd.DataFrame(ada_score)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", np.nanmedian])
|
2022-12-07 21:25:05 +01:00
|
|
|
scores_df["method"] = "ADA_boost"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 21:44:40 +02:00
|
|
|
del ada
|
|
|
|
del ada_score
|
2022-11-16 18:13:30 +01:00
|
|
|
|
|
|
|
return scores
|
2022-12-08 10:00:14 +01:00
|
|
|
|
|
|
|
|
2023-05-10 22:50:00 +02:00
|
|
|
def run_all_classification_models(
|
|
|
|
data_x: pd.DataFrame,
|
|
|
|
data_y: pd.DataFrame,
|
|
|
|
data_groups: pd.DataFrame,
|
|
|
|
cross_validator: BaseCrossValidator,
|
|
|
|
):
|
2023-04-21 21:33:06 +02:00
|
|
|
metrics = ["accuracy", "average_precision", "recall", "f1"]
|
2022-12-08 10:00:14 +01:00
|
|
|
test_metrics = ["test_" + metric for metric in metrics]
|
|
|
|
|
2023-05-18 18:47:56 +02:00
|
|
|
scores = pd.DataFrame(columns=["method", "test_metric", "max", "mean"])
|
2022-12-08 10:00:14 +01:00
|
|
|
|
|
|
|
dummy_class = DummyClassifier(strategy="most_frequent")
|
|
|
|
|
|
|
|
dummy_score = cross_validate(
|
2023-04-21 21:33:06 +02:00
|
|
|
dummy_class,
|
|
|
|
X=data_x,
|
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 22:50:00 +02:00
|
|
|
cv=cross_validator,
|
2023-04-21 21:33:06 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
error_score="raise",
|
|
|
|
scoring=metrics,
|
2022-12-08 10:00:14 +01:00
|
|
|
)
|
|
|
|
print("Dummy")
|
|
|
|
|
|
|
|
scores_df = pd.DataFrame(dummy_score)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", "mean"])
|
2023-05-18 18:55:31 +02:00
|
|
|
scores_df["method"] = "dummy_classifier"
|
2022-12-08 10:00:14 +01:00
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 22:50:00 +02:00
|
|
|
del dummy_class
|
|
|
|
del dummy_score
|
2022-12-08 10:00:14 +01:00
|
|
|
|
|
|
|
logistic_regression = linear_model.LogisticRegression()
|
|
|
|
|
|
|
|
log_reg_scores = cross_validate(
|
2023-04-21 21:33:06 +02:00
|
|
|
logistic_regression,
|
|
|
|
X=data_x,
|
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 22:50:00 +02:00
|
|
|
cv=cross_validator,
|
2023-04-21 21:33:06 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-12-08 10:00:14 +01:00
|
|
|
)
|
|
|
|
print("Logistic regression")
|
|
|
|
|
|
|
|
scores_df = pd.DataFrame(log_reg_scores)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", "mean"])
|
2023-05-18 18:55:31 +02:00
|
|
|
scores_df["method"] = "logistic_regression"
|
2022-12-08 10:00:14 +01:00
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 22:50:00 +02:00
|
|
|
del logistic_regression
|
|
|
|
del log_reg_scores
|
2022-12-08 10:00:14 +01:00
|
|
|
|
|
|
|
svc = svm.SVC()
|
|
|
|
|
|
|
|
svc_scores = cross_validate(
|
2023-04-21 21:33:06 +02:00
|
|
|
svc,
|
|
|
|
X=data_x,
|
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 22:50:00 +02:00
|
|
|
cv=cross_validator,
|
2023-04-21 21:33:06 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-12-08 10:00:14 +01:00
|
|
|
)
|
|
|
|
print("Support Vector Machine")
|
|
|
|
|
|
|
|
scores_df = pd.DataFrame(svc_scores)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", "mean"])
|
2023-05-18 18:55:31 +02:00
|
|
|
scores_df["method"] = "SVC"
|
2022-12-08 10:00:14 +01:00
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 22:50:00 +02:00
|
|
|
del svc
|
|
|
|
del svc_scores
|
2022-12-08 10:00:14 +01:00
|
|
|
|
|
|
|
gaussian_nb = naive_bayes.GaussianNB()
|
2023-04-21 21:33:06 +02:00
|
|
|
|
2022-12-08 10:00:14 +01:00
|
|
|
gaussian_nb_scores = cross_validate(
|
2023-04-21 21:33:06 +02:00
|
|
|
gaussian_nb,
|
|
|
|
X=data_x,
|
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 22:50:00 +02:00
|
|
|
cv=cross_validator,
|
2023-04-21 21:33:06 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-12-08 10:00:14 +01:00
|
|
|
)
|
|
|
|
print("Gaussian Naive Bayes")
|
|
|
|
|
|
|
|
scores_df = pd.DataFrame(gaussian_nb_scores)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", "mean"])
|
2022-12-08 10:00:14 +01:00
|
|
|
scores_df["method"] = "gaussian_naive_bayes"
|
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 22:50:00 +02:00
|
|
|
del gaussian_nb
|
|
|
|
del gaussian_nb_scores
|
2022-12-08 10:00:14 +01:00
|
|
|
|
|
|
|
sgdc = linear_model.SGDClassifier()
|
|
|
|
|
|
|
|
sgdc_scores = cross_validate(
|
2023-04-21 21:33:06 +02:00
|
|
|
sgdc,
|
|
|
|
X=data_x,
|
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 22:50:00 +02:00
|
|
|
cv=cross_validator,
|
2023-04-21 21:33:06 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-12-08 10:00:14 +01:00
|
|
|
)
|
|
|
|
print("Stochastic Gradient Descent")
|
|
|
|
|
|
|
|
scores_df = pd.DataFrame(sgdc_scores)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", "mean"])
|
2023-05-18 18:55:31 +02:00
|
|
|
scores_df["method"] = "stochastic_gradient_descent_classifier"
|
2022-12-08 10:00:14 +01:00
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 22:50:00 +02:00
|
|
|
del sgdc
|
|
|
|
del sgdc_scores
|
2022-12-08 10:00:14 +01:00
|
|
|
|
|
|
|
rfc = ensemble.RandomForestClassifier()
|
|
|
|
|
|
|
|
rfc_scores = cross_validate(
|
2023-04-21 21:33:06 +02:00
|
|
|
rfc,
|
|
|
|
X=data_x,
|
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 22:50:00 +02:00
|
|
|
cv=cross_validator,
|
2023-04-21 21:33:06 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-12-08 10:00:14 +01:00
|
|
|
)
|
|
|
|
print("Random Forest")
|
|
|
|
|
|
|
|
scores_df = pd.DataFrame(rfc_scores)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", "mean"])
|
2023-05-18 18:55:31 +02:00
|
|
|
scores_df["method"] = "random_forest_classifier"
|
2022-12-08 10:00:14 +01:00
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 22:50:00 +02:00
|
|
|
del rfc
|
|
|
|
del rfc_scores
|
2022-12-08 10:00:14 +01:00
|
|
|
|
|
|
|
xgb_classifier = XGBClassifier()
|
|
|
|
|
|
|
|
xgb_scores = cross_validate(
|
2023-04-21 21:33:06 +02:00
|
|
|
xgb_classifier,
|
|
|
|
X=data_x,
|
|
|
|
y=data_y,
|
|
|
|
groups=data_groups,
|
2023-05-10 22:50:00 +02:00
|
|
|
cv=cross_validator,
|
2023-04-21 21:33:06 +02:00
|
|
|
n_jobs=-1,
|
|
|
|
scoring=metrics,
|
2022-12-08 10:00:14 +01:00
|
|
|
)
|
|
|
|
print("XGBoost")
|
|
|
|
|
|
|
|
scores_df = pd.DataFrame(xgb_scores)[test_metrics]
|
2023-05-18 18:40:06 +02:00
|
|
|
scores_df = aggregate_and_transpose(scores_df, statistics=["max", "mean"])
|
2023-05-18 18:55:31 +02:00
|
|
|
scores_df["method"] = "XGBoost_classifier"
|
2022-12-08 10:00:14 +01:00
|
|
|
scores = pd.concat([scores, scores_df])
|
2023-05-10 22:50:00 +02:00
|
|
|
del xgb_classifier
|
|
|
|
del xgb_scores
|
2022-12-08 10:00:14 +01:00
|
|
|
|
|
|
|
return scores
|