![](\"../images/headers/nb_3.svg\")
"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "abc572dd",
"metadata": {
"papermill": {
"duration": 0.01003,
"end_time": "2024-06-14T14:10:30.780697",
"exception": false,
"start_time": "2024-06-14T14:10:30.770667",
"status": "completed"
},
"tags": []
},
"source": [
"# Import Section"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "0acbc825",
"metadata": {
"execution": {
"iopub.execute_input": "2024-06-14T14:10:30.804669Z",
"iopub.status.busy": "2024-06-14T14:10:30.803667Z",
"iopub.status.idle": "2024-06-14T14:10:37.537562Z",
"shell.execute_reply": "2024-06-14T14:10:37.535561Z"
},
"papermill": {
"duration": 6.749896,
"end_time": "2024-06-14T14:10:37.541554",
"exception": false,
"start_time": "2024-06-14T14:10:30.791658",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"import multiprocessing\n",
"\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"import pandas as pd\n",
"import seaborn as sns\n",
"from imblearn.under_sampling import RandomUnderSampler\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.inspection import permutation_importance\n",
"from sklearn.metrics import classification_report\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.utils.random import sample_without_replacement\n",
"from skopt import BayesSearchCV\n",
"from xgboost import XGBClassifier, plot_importance\n",
"\n",
"from roaf import visualization"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "e3beb31e",
"metadata": {
"execution": {
"iopub.execute_input": "2024-06-14T14:10:37.563093Z",
"iopub.status.busy": "2024-06-14T14:10:37.563093Z",
"iopub.status.idle": "2024-06-14T14:10:37.613093Z",
"shell.execute_reply": "2024-06-14T14:10:37.611086Z"
},
"papermill": {
"duration": 0.064501,
"end_time": "2024-06-14T14:10:37.616090",
"exception": false,
"start_time": "2024-06-14T14:10:37.551589",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"| Parameter \n", " | Description \n", " |
|---|---|
| fast_execution | \n", "Should be set to True if the focus is on testing and not on prediction\n", " quality | \n", "
| plot_dir | \n", "The output directory for the plots | \n", "
| max_sample_size | \n", " The number of data points used for machine learning and validation. \n", " If set to None, all the data (after undersampling) will be used | \n",
"
| n_plot | \n", "The number of data points to plot in certain figures | \n", "
| n_cv | \n", "Parameter for k-fold cross-validation used in parameter optimization | \n", "
| n_permutation_repetitions | \n", "The number of permutations to be performed to find the importance of\n", " features in trained models | \n", "
| n_random_forest_estimators | \n", "The number of estimators in the random forest model | \n", "
BayesSearchCV(cv=5,\n",
" estimator=XGBClassifier(base_score=None, booster=None,\n",
" callbacks=None, colsample_bylevel=None,\n",
" colsample_bynode=None,\n",
" colsample_bytree=None,\n",
" early_stopping_rounds=None,\n",
" enable_categorical=False,\n",
" eval_metric=None, feature_types=None,\n",
" gamma=None, gpu_id=None, grow_policy=None,\n",
" importance_type=None,\n",
" interaction_constraints=None,\n",
" learning_rate=None...\n",
" max_cat_threshold=None,\n",
" max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=None,\n",
" max_leaves=None, min_child_weight=None,\n",
" missing=nan, monotone_constraints=None,\n",
" n_estimators=100, n_jobs=4,\n",
" num_parallel_tree=None, predictor=None,\n",
" random_state=None, ...),\n",
" n_iter=4, n_jobs=2,\n",
" search_spaces={'learning_rate': [0.05, 0.1],\n",
" 'max_depth': [2, 4, 6],\n",
" 'n_estimators': [100, 200]})In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. BayesSearchCV(cv=5,\n",
" estimator=XGBClassifier(base_score=None, booster=None,\n",
" callbacks=None, colsample_bylevel=None,\n",
" colsample_bynode=None,\n",
" colsample_bytree=None,\n",
" early_stopping_rounds=None,\n",
" enable_categorical=False,\n",
" eval_metric=None, feature_types=None,\n",
" gamma=None, gpu_id=None, grow_policy=None,\n",
" importance_type=None,\n",
" interaction_constraints=None,\n",
" learning_rate=None...\n",
" max_cat_threshold=None,\n",
" max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=None,\n",
" max_leaves=None, min_child_weight=None,\n",
" missing=nan, monotone_constraints=None,\n",
" n_estimators=100, n_jobs=4,\n",
" num_parallel_tree=None, predictor=None,\n",
" random_state=None, ...),\n",
" n_iter=4, n_jobs=2,\n",
" search_spaces={'learning_rate': [0.05, 0.1],\n",
" 'max_depth': [2, 4, 6],\n",
" 'n_estimators': [100, 200]})XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, early_stopping_rounds=None,\n",
" enable_categorical=False, eval_metric=None, feature_types=None,\n",
" gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" n_estimators=100, n_jobs=4, num_parallel_tree=None,\n",
" predictor=None, random_state=None, ...)XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, early_stopping_rounds=None,\n",
" enable_categorical=False, eval_metric=None, feature_types=None,\n",
" gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" n_estimators=100, n_jobs=4, num_parallel_tree=None,\n",
" predictor=None, random_state=None, ...)RandomForestClassifier()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
RandomForestClassifier()