diff --git a/docs/.buildinfo.bak b/docs/.buildinfo.bak index 22c685b..f27aa16 100644 --- a/docs/.buildinfo.bak +++ b/docs/.buildinfo.bak @@ -1,4 +1,4 @@ # Sphinx build info version 1 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done. -config: 30c16f527d03e2f32b3ab00067a9aa8f +config: 4d115e8219837f5e7663068621637d0a tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/docs/.doctrees/environment.pickle b/docs/.doctrees/environment.pickle index be8be83..f0465a1 100644 Binary files a/docs/.doctrees/environment.pickle and b/docs/.doctrees/environment.pickle differ diff --git a/docs/.doctrees/usage_guide.doctree b/docs/.doctrees/usage_guide.doctree index 0724b11..179bcfd 100644 Binary files a/docs/.doctrees/usage_guide.doctree and b/docs/.doctrees/usage_guide.doctree differ diff --git a/docs/_sources/usage_guide.rst.txt b/docs/_sources/usage_guide.rst.txt index bf5662d..bf55a68 100644 --- a/docs/_sources/usage_guide.rst.txt +++ b/docs/_sources/usage_guide.rst.txt @@ -32,7 +32,7 @@ Binary Classification Examples - .. raw:: html - Binary Classification + KFold Example: Titanic Dataset - Categorical Data + Binary Classification + KFold Example: Titanic Dataset - Categorical Data - .. raw:: html diff --git a/docs/searchindex.js b/docs/searchindex.js index 6b0fb4d..c5a3ad5 100644 --- a/docs/searchindex.js +++ b/docs/searchindex.js @@ -1 +1 @@ -Search.setIndex({"alltitles": {"1. Accurate Calculation of Scaling Parameters": [[1, "accurate-calculation-of-scaling-parameters"]], "2. Consistency in Data Transformation": [[1, "consistency-in-data-transformation"]], "3. Prevention of Distortion in Scaling": [[1, "prevention-of-distortion-in-scaling"]], "AIDS Clinical Trials Group Study": [[6, "aids-clinical-trials-group-study"]], "About Model Tuner": [[4, null]], "Acknowledgements": [[0, "acknowledgements"]], "Binary Classification": [[6, "binary-classification"]], "Binary Classification Examples": [[6, "binary-classification-examples"]], "Brier Score": [[1, "brier-score"]], "Calibration Curve": [[1, "calibration-curve"]], "California Housing with XGBoost": [[6, "california-housing-with-xgboost"]], "Caveats": [[4, null]], "Changelog": [[2, null]], "Citing Model Tuner": [[0, "citing-model-tuner"]], "Classification Report (Optional)": [[6, "classification-report-optional"]], "Column Stratification with Cross-Validation": [[1, "column-stratification-with-cross-validation"]], "Cross-Validation and Stratification": [[1, "cross-validation-and-stratification"]], "Dependent Variable": [[1, "dependent-variable"]], "Effects on Model Training": [[1, "effects-on-model-training"]], "Example: Calibration in Logistic Regression": [[1, "example-calibration-in-logistic-regression"]], "Getting Started": [[4, null]], "GitHub Repository": [[0, null]], "Goal of Calibration": [[1, "goal-of-calibration"]], "Helper Functions": [[6, "helper-functions"]], "Imputation Before Scaling": [[1, "imputation-before-scaling"]], "Input Parameters": [[6, "input-parameters"]], "Installation": [[3, "installation"]], "Isotonic Regression": [[1, "isotonic-regression"]], "Key Methods and Functionalities": [[6, "key-methods-and-functionalities"]], "Model Calibration": [[1, "model-calibration"]], "Model Tuner Documentation": [[4, null]], "Platt Scaling": [[1, "platt-scaling"]], "Prerequisites": [[3, "prerequisites"]], "References": [[5, null]], "Regression": [[6, "regression"]], "Regression Example": [[6, "regression-example"]], "Solution": [[1, "solution"]], "Step 10: Calibrate the Model (if needed)": [[6, "step-10-calibrate-the-model-if-needed"]], "Step 1: Import Necessary Libraries": [[6, "step-1-import-necessary-libraries"], [6, "id1"]], "Step 2: Load the Dataset": [[6, "step-2-load-the-dataset"]], "Step 2: Load the dataset, define X, y": [[6, "step-2-load-the-dataset-define-x-y"]], "Step 3: Check for zero-variance columns and drop accordingly": [[6, "step-3-check-for-zero-variance-columns-and-drop-accordingly"]], "Step 3: Create an Instance of the XGBClassifier": [[6, "step-3-create-an-instance-of-the-xgbclassifier"]], "Step 4: Create an Instance of the XGBClassifier": [[6, "step-4-create-an-instance-of-the-xgbclassifier"]], "Step 4: Define Hyperparameters for XGBoost": [[6, "step-4-define-hyperparameters-for-xgboost"]], "Step 5: Define Hyperparameters for XGBoost": [[6, "step-5-define-hyperparameters-for-xgboost"]], "Step 5: Initialize and Configure the Model": [[6, "step-5-initialize-and-configure-the-model"]], "Step 6: Fit the Model": [[6, "step-6-fit-the-model"]], "Step 6: Initialize and Configure the Model": [[6, "step-6-initialize-and-configure-the-model"]], "Step 7: Perform Grid Search Parameter Tuning": [[6, "step-7-perform-grid-search-parameter-tuning"]], "Step 8: Fit the Model": [[6, "step-8-fit-the-model"]], "Step 9: Return Metrics (Optional)": [[6, "step-9-return-metrics-optional"]], "Summary": [[1, "summary"]], "Target Variable Shape and Its Effects": [[1, "target-variable-shape-and-its-effects"]], "Usage Guide": [[4, null]], "Version 0.0.010a": [[2, "version-0-0-010a"]], "Version 0.0.011a": [[2, "version-0-0-011a"]], "Version 0.0.012a": [[2, "version-0-0-012a"]], "Version 0.0.013a": [[2, "version-0-0-013a"]], "Version 0.0.014a": [[2, "version-0-0-014a"]], "Version 0.0.02a": [[2, "version-0-0-02a"]], "Version 0.0.05a": [[2, "version-0-0-05a"]], "Version 0.0.06a": [[2, "version-0-0-06a"]], "Version 0.0.07a": [[2, "version-0-0-07a"]], "Version 0.0.08a": [[2, "version-0-0-08a"]], "Version 0.0.09a": [[2, "version-0-0-09a"]], "Version 0.0.15a": [[2, "version-0-0-15a"]], "Version 0.0.16a": [[2, "version-0-0-16a"]], "Welcome to Model Tuner\u2019s Documentation!": [[3, null]], "What Does Model Tuner Offer?": [[3, "what-does-model-tuner-offer"]], "Zero Variance Columns": [[1, null]], "iPython Notebooks": [[6, null]]}, "docnames": ["about", "caveats", "changelog", "getting_started", "index", "references", "usage_guide"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.todo": 2, "sphinx.ext.viewcode": 1}, "filenames": ["about.rst", "caveats.rst", "changelog.rst", "getting_started.rst", "index.rst", "references.rst", "usage_guide.rst"], "indexentries": {"model (built-in class)": [[6, "Model", false]]}, "objects": {"": [[6, 0, 1, "", "Model"]]}, "objnames": {"0": ["py", "class", "Python class"]}, "objtypes": {"0": "py:class"}, "terms": {"": [1, 2, 4, 6], "0": [0, 1, 3, 4, 6], "00": 6, "0001": 6, "01": 6, "010a": 4, "011a": 4, "012a": 4, "013a": 4, "014a": 4, "015a": [], "017a": 3, "02a": 4, "05": 6, "05a": 4, "06a": 4, "07a": 4, "08a": 4, "09a": 4, "1": [2, 3, 4], "10": [0, 3, 4, 5], "100": 6, "1000": 6, "104": 6, "105": 6, "11": [3, 6], "114": [], "11a": 2, "12": 3, "12727322": 0, "14": 3, "15": [], "15a": 4, "16665653153377272": 6, "16737745981389285": 6, "16a": [0, 4], "172": 6, "175": 5, "19": [3, 6], "1998": 5, "1d": 1, "1e": 6, "1ujll2mrtiwwgamnpwkio2f271_q103t": 6, "2": [3, 4], "20": 6, "200": 6, "2024": 0, "21": 3, "22": [], "222": 6, "23": 3, "24": 3, "241": 6, "24205514192581173": 6, "24432": 5, "248": 6, "26": 3, "2633964855111536": 6, "292": [], "3": [3, 4], "30": 6, "300": 6, "303": [], "304": 6, "30it": 6, "314": [], "32": [], "323": 6, "324": 6, "34": [], "35007797000749163": 6, "4": [1, 3, 4], "428": 6, "42it": [], "5": [1, 3, 4], "500": [2, 6], "5132216728774747": 6, "5281": 0, "5469613259668509": 6, "55": 6, "5502958579881657": 6, "58": 1, "6": [3, 4], "66": 3, "68": 6, "69": 6, "7": [3, 4], "71": 6, "72": [], "74": 6, "7461300309597523": 6, "75": 6, "76": 6, "7654320987654321": 6, "77": 6, "79": 6, "7979050719771986": 6, "7979060590722392": 6, "7979488661159093": 6, "798": 6, "8": [3, 4], "80": 6, "8025676192819657": 6, "8090909090909091": [], "81": 6, "8169018952192892": 6, "81it": 6, "82": 6, "83": 6, "8317757009345793": [], "84": 6, "85": 6, "8557692307692307": [], "86": 6, "87": 6, "88": 6, "8809605488850771": [], "8878504672897196": [], "89": 6, "890": 6, "8942307692307693": 6, "895477207977208": [], "9": [1, 4], "90": [], "91": 6, "9158878504672897": [], "9166739453227356": [], "9179028870970327": [], "92": 6, "926": 6, "9260891500474834": 6, "93": 6, "9343063541205956": 6, "9351851851851852": [], "9364035087719298": [], "94": 6, "9428571428571428": 6, "9439252336448598": [], "946877967711301": [], "947": [], "95": 6, "9528301886792453": [], "96": 6, "98": 6, "99": 6, "999": [1, 6], "A": [1, 6], "AND": 6, "By": 1, "For": [1, 3], "If": [1, 6], "In": [1, 2, 6], "It": [1, 3, 6], "Its": 4, "On": 1, "One": [1, 6], "The": [1, 3, 6], "There": 2, "These": 1, "To": 1, "_": 1, "__early_stopping_round": 6, "__eval_metr": 6, "__init__": 6, "__learning_r": 6, "__max_depth": 6, "__n_estim": 6, "__param_nam": 6, "__verbos": 6, "_blank": 6, "_confusion_matrix_print": 6, "_confusion_matrix_print_ml": [], "_i": 1, "_j": 1, "abil": 6, "about": 1, "abram": 5, "absolut": 6, "access": [0, 6], "accordingli": 4, "accur": 4, "accuraci": [1, 6], "achiev": [1, 2], "acknowledg": 4, "across": [1, 2, 3, 6], "actual": [1, 6], "ad": 2, "adasyn": [2, 3], "addit": [1, 6], "addition": [1, 6], "adjust": 1, "advanc": 6, "aforement": 1, "after": 6, "ag": [], "aid": [4, 5], "aids_clinical_": 6, "aids_clinical_trials_group_study_175": 6, "alex": 0, "algorithm": [1, 6], "align": 1, "all": [1, 2, 3, 6], "allow": [2, 3, 6], "also": [1, 6], "alwai": 2, "an": 4, "analysi": 1, "angel": 6, "ani": 1, "anoth": 1, "anova": 1, "apach": 2, "appli": [1, 3, 6], "applic": [1, 6], "approach": 1, "approx": 1, "ar": [0, 1, 2, 3, 6], "arrai": 1, "arthur": [0, 2], "artifici": 1, "ascii": 6, "assert": 2, "assess": [1, 3, 6], "assign": 2, "assum": 1, "attempt": 1, "attributeerror": 6, "auc": 6, "author": 0, "autokera": 2, "autokerasclassifi": 2, "automat": [1, 3], "avail": [1, 2, 6], "averag": 6, "avg": 6, "avoid": [1, 2], "axi": 2, "b": 1, "back": 6, "balanc": [2, 3, 6], "bar": 1, "base": [1, 3, 6], "bayesian": 6, "bayessearchcv": 6, "becaus": [1, 2], "becom": 1, "been": [1, 2], "befor": [2, 3, 4, 6], "begin": 1, "behavior": 1, "being": 2, "below": 3, "best": 6, "best_param": 2, "best_params_per_scor": 6, "beta": 6, "better": 1, "between": [1, 3, 6], "bin": [1, 6], "binari": 4, "bool": 6, "boost": [2, 6], "boost_earli": 6, "bootstrap": 3, "bootstrapp": [2, 6], "both": [1, 2, 6], "breast": 6, "brier": [4, 6], "bug": 2, "bui": 0, "build": 6, "c": 1, "c5g896": 5, "calcul": 4, "calibr": [2, 3, 4], "calibrate_report": 6, "calibratemodel": 6, "calibration_curv": 6, "calibration_method": 6, "california": 4, "california_h": 6, "call": 6, "can": [0, 1, 3, 6], "cancer": 6, "cannot": 1, "captur": 1, "care": 6, "case": [1, 2], "catboost": [2, 3], "categor": 6, "categori": 6, "caus": 1, "caveat": [], "cd40": [], "cd420": [], "cd80": [], "chang": [1, 2, 6], "changelog": 4, "char": 2, "check": [1, 4], "chunk": 2, "cite": 4, "clariti": 6, "class": [1, 2, 3, 6], "class_label": 6, "class_report_test": 6, "class_report_v": 6, "classif": [1, 3, 4], "classifi": 6, "classification_report": 6, "clc": 6, "clean": 2, "click": 0, "clinic": [0, 4, 5], "close": 1, "cm_test": 6, "cm_val": 6, "code": [1, 2], "codebas": 0, "colab": 6, "column": [2, 4], "com": 6, "combin": 6, "command": 6, "comment": 2, "common": 1, "commonli": 6, "compat": 3, "complet": [1, 2], "comput": [1, 6], "concat": 2, "condit": 1, "conduct": 3, "conf_mat_class_kfold": 6, "conf_matrix": 6, "configur": 4, "conflict": 1, "confus": 6, "consid": [1, 2], "consist": 4, "constant": 1, "constraint": [1, 2], "construct": 1, "contain": 2, "context": 1, "contrast": 1, "contribut": [0, 1], "contributor": 0, "convers": 1, "convert": [1, 6], "correct": [1, 2], "correctli": 1, "count": 2, "cpu": 6, "creat": 4, "creation": 3, "critic": 1, "cross": [3, 4, 6], "crucial": 1, "ctsi": 0, "current": [1, 3], "curv": [4, 6], "custom": [2, 3, 6], "custom_scor": 6, "d": [1, 5], "d_1": 1, "d_2": 1, "d_j": 1, "d_k": 1, "data": [2, 3, 4, 6], "dataconversionwarn": 1, "datafram": [1, 6], "dataset": [1, 3, 4], "decis": 6, "decreas": 1, "deep": [], "default": 6, "defin": [1, 4], "denot": 1, "depend": [2, 3, 4, 6], "deploi": 6, "deprec": 2, "depth": 6, "design": [1, 3, 6], "detect": 6, "determin": 1, "dev": 2, "develop": 3, "deviat": 1, "diagnosi": [1, 6], "dict": 6, "dictionari": 6, "differ": [1, 2, 3], "dimens": 1, "dimension": 1, "directli": 3, "discrep": 1, "diseas": 6, "displai": 6, "disrupt": 1, "distinct": 6, "distinguish": 6, "distort": 4, "distribut": [1, 3], "divid": 1, "divis": 1, "do": [2, 6], "doe": 4, "doi": [0, 5], "dot": 1, "dr": 0, "drive": 6, "drop": [1, 4], "drop_strat_feat": [], "drug": [], "due": 1, "dure": [1, 2, 6], "e": [1, 6], "each": [1, 6], "earli": [2, 3, 6], "early_stop": 6, "easier": 6, "easili": 6, "effect": [3, 4, 6], "either": [2, 6], "el": 5, "elimin": 3, "empir": 1, "empti": [1, 6], "enabl": [3, 6], "encount": 1, "end": 1, "enhanc": 2, "ensur": [1, 2, 3, 6], "entir": 1, "equal": 1, "equat": 1, "equival": 6, "error": [1, 2, 6], "essenc": 6, "essenti": [1, 6], "estat": 6, "estim": [1, 2, 3, 6], "estimator_nam": 6, "estimator_name_xgb": 6, "eta": 6, "etc": 2, "eval_set": 6, "evalu": [1, 3, 6], "evaluate_bootstrap_metr": 2, "even": 1, "examin": 6, "exampl": 4, "exceed": 2, "except": 6, "exp": 1, "expect": [1, 6], "explain": 6, "explan": 1, "express": 1, "extend": 6, "extract": 2, "extrem": 1, "f": [1, 6], "f1": 6, "f1_beta_tun": 6, "f_i": 1, "facilit": 3, "failur": 1, "fals": 6, "far": 1, "favor": 2, "feat_num": 1, "featur": [1, 3, 6], "feature_nam": 6, "feature_select": 6, "fetch": 6, "fetch_california_h": 6, "fetch_ucirepo": 6, "figsiz": 6, "figur": 6, "file": [2, 6], "filter": 2, "find": 1, "fine": [3, 6], "first": 1, "fit": [1, 2, 4], "fix": 2, "flexibl": [3, 6], "float": 6, "float64": 6, "fn": 6, "focu": 1, "fold": [1, 3, 6], "follow": [1, 2, 3, 6], "form": 1, "format": 6, "formul": 1, "forthcom": 2, "found": 6, "fp": 6, "frac": 1, "fraction": 1, "fraud": 6, "free": 1, "frequenc": 1, "from": [1, 2, 3, 6], "full": 1, "function": [1, 2, 3, 4], "funnel": 0, "funnell_2024_12727322": 0, "g": [1, 6], "gb": 6, "gender": 6, "gener": [1, 3, 6], "get": 6, "get_best_score_param": 6, "get_cross_valid": 6, "get_test_data": 6, "get_train_data": 6, "get_valid_data": 6, "github": 4, "given": 1, "goal": 4, "googl": 6, "grid": 4, "grid_search_param_tun": 6, "gridsearchcv": 6, "group": [4, 5], "guidanc": 0, "ha": [1, 2], "had": 1, "hand": 1, "handl": [1, 3, 6], "happen": 2, "hat": 1, "have": 2, "haven": 6, "heavili": 1, "help": 6, "helper": 4, "hemo": [], "here": [2, 3, 6], "hi": 0, "higher": 3, "histori": 2, "homo": [], "hous": 4, "howev": 1, "href": 6, "html": 6, "http": [0, 5, 6], "hyperparamet": [2, 3, 4], "i": [1, 2, 3, 6], "id": 6, "ident": 1, "identifi": [], "ij": 1, "imbal": 6, "imbalanc": [2, 3, 6], "imbalance_sampl": 6, "imblearn": 6, "implement": [2, 3], "import": [1, 2, 4], "importerror": 6, "improp": 1, "improperli": 6, "improv": [3, 6], "imput": [2, 3, 4, 6], "inaccur": 1, "includ": [1, 3, 6], "incomplet": 1, "inconsist": 1, "incorrect": [1, 6], "increas": 1, "index": 6, "indexerror": 6, "indic": [1, 6], "infinit": 1, "inflat": 1, "influenc": 1, "inform": 1, "informat": 0, "inher": 1, "initi": 4, "initialis": 2, "input": [1, 4], "insid": 2, "instal": [4, 6], "instanc": [1, 4], "instead": [2, 6], "institut": 0, "int": 6, "integr": [1, 3], "interpret": 1, "interv": 1, "introduc": 2, "invalid": [1, 6], "invalu": 0, "involv": [1, 2], "ipython": 4, "isinst": 1, "isoton": [3, 4, 6], "issu": [1, 2, 6], "iter": 6, "itself": 2, "j": 1, "job": 6, "joblib": 3, "jul": 0, "just": 1, "k": [1, 3, 6], "karnof": [], "kei": [0, 2, 3, 4], "keyerror": 6, "kf": 6, "kfold": [2, 6], "kfold_split": 6, "known": 6, "label": [1, 3, 6], "larg": 1, "later": 1, "layer": 2, "lead": 1, "learn": [1, 2, 3, 5, 6], "legend": 6, "length": 2, "leon": 2, "leonid": 0, "leq": 1, "let": 1, "librari": [3, 4], "licens": 2, "like": [1, 3, 6], "likelihood": 1, "limit": 2, "line": 2, "linestyl": 6, "link": 0, "list": [2, 6], "lo": 6, "load": 4, "log": [2, 6], "logic": 2, "logist": [4, 6], "logloss": 6, "logo": 2, "loop": 2, "low": 2, "lower": 1, "machin": [1, 3, 5, 6], "macro": 6, "maintain": 1, "make": 6, "marker": 6, "match": 1, "mathemat": 1, "matplotlib": 6, "matric": 6, "matrix": 6, "max": 1, "maximum": [1, 6], "mean": [1, 6], "measur": 1, "median": [1, 6], "medic": [0, 1], "meet": 3, "messag": 6, "method": [1, 2, 3, 4], "metric": [1, 2, 3, 4], "mid": 1, "might": 1, "mii": 0, "min": 1, "min_": 1, "minimum": 1, "minmax": 3, "misinterpret": 1, "mismatch": [2, 6], "miss": [1, 6], "mlflow": 2, "model": 2, "model_tun": [3, 6], "model_typ": 6, "model_xgb": 6, "modifi": 2, "modul": 6, "monoton": 1, "month": 0, "more": 1, "move": 2, "msb": 1, "msw": 1, "mu": 1, "multi": [3, 6], "multi_label": 6, "multipl": 2, "n": 1, "n_bin": 6, "n_estim": 6, "n_iter": 6, "n_j": 1, "n_job": 6, "n_sampl": 1, "n_split": 6, "name": [2, 6], "named_step": [], "nan": 1, "necessari": [2, 4], "need": [1, 4], "neg": [1, 6], "non": [1, 2], "none": 6, "nonetyp": [], "note": 1, "notebook": [2, 4], "now": [1, 2], "np": [2, 6], "number": [1, 2, 6], "numer": 6, "numpi": [3, 6], "o": 6, "object": [2, 6], "observ": 1, "occur": 2, "offer": 4, "offtrt": [], "often": 1, "older": 2, "onc": 6, "one": [1, 6], "onli": [1, 2], "onto": 2, "oper": 1, "oprior": [], "optim": [3, 6], "optimal_threshold": 6, "option": 4, "order": [1, 2], "org": [0, 5], "origin": [0, 1], "other": [1, 2, 3, 6], "our": [2, 6], "out": 2, "outcom": [1, 6], "output": [1, 6], "outsid": 2, "over": 1, "overal": 1, "overfit": 3, "oversampl": 3, "p": 1, "p_1": 1, "p_2": 1, "p_i": 1, "p_n": 1, "packag": 6, "panayioti": 0, "panda": [3, 6], "parallel": 6, "param": 6, "paramet": [2, 3, 4], "parametr": 1, "part": 6, "particularli": [1, 3, 6], "pass": [1, 6], "pd": [1, 2, 6], "penal": 1, "per": 2, "perfectli": [1, 6], "perform": [1, 3, 4], "petousi": 0, "pickl": 2, "piecewis": 1, "pip": [3, 6], "pip25": 2, "pipelin": [1, 2, 3, 6], "pipeline_step": [1, 2, 6], "pipelineclass": [], "placehold": 1, "platt": 4, "pleas": 1, "plot": 6, "plt": 6, "pmatrix": 1, "po": 6, "point": 1, "posit": [1, 6], "possibl": [1, 6], "power": [1, 3], "ppv": 6, "pr_auc": [], "practic": [1, 6], "preanti": [], "precis": 6, "predict": [1, 6], "predict_proba": 6, "prefix": 6, "preprocess": [1, 6], "preprocess_imputer_imput": 6, "preprocess_scaler_standardscalar": 6, "preprocessor": [1, 6], "prerequisit": 4, "present": 1, "preserv": 1, "pretti": 2, "prevent": [3, 4], "previou": 2, "previous": 1, "primari": 1, "print": [2, 6], "print_k_best_featur": [], "print_pipelin": 6, "print_result": 6, "print_selected_best_featur": 6, "prior": 1, "prob_pred_calibr": 6, "prob_pred_uncalibr": 6, "prob_true_calibr": 6, "prob_true_uncalibr": 6, "probabilist": 1, "probabl": [1, 3, 6], "problem": [1, 6], "proceed": 1, "process": [1, 2, 6], "process_imbalance_sampl": 6, "produc": [1, 6], "properli": 6, "properti": 1, "proport": [1, 6], "provid": [1, 3, 6], "publish": 0, "py": 2, "pypi": [2, 3], "pyplot": 6, "pyproject": 2, "python": 3, "quad": 1, "quickli": 6, "r": 6, "r2": 6, "race": 6, "rais": [1, 6], "rand_grid": 6, "random": 6, "random_st": 6, "randomized_grid": 6, "randomoversampl": 6, "randomundersampl": 6, "rang": [1, 6], "rate": 6, "rather": 1, "ratio": [1, 6], "raw": 1, "re": 2, "readili": 6, "readm": 2, "real": 6, "recal": 6, "recommend": 1, "recurs": 3, "redfin": 6, "redfin_model_xgb": 6, "ref": 2, "refactor": 2, "refer": [1, 4], "reflect": 1, "regard": 2, "regress": 4, "regression_report": 6, "regression_report_kfold": 6, "regular": 6, "relat": 2, "relationship": 1, "releas": 2, "reli": 1, "reliabl": 6, "remov": [1, 2], "renam": 2, "repeatedli": 1, "replac": 1, "report": [2, 4], "report_model_metr": 6, "repositori": [4, 5, 6], "repres": [1, 2], "represent": 6, "reproduc": 6, "requir": [2, 3, 6], "resampl": [2, 6], "research": 6, "reset": [2, 6], "reset_estim": 6, "resolut": 2, "resourc": 6, "result": 1, "retriev": 6, "return": 4, "return_metr": 6, "rfe": 3, "rightarrow": 1, "risk": 1, "rmse": 6, "robust": [3, 6], "roc": 6, "roc_auc": 6, "root": 6, "routin": 1, "run": 6, "runtim": 1, "runtimeerror": 6, "runtimewarn": 1, "sadr": 5, "same": [1, 2], "sampl": [1, 2], "sampler": 6, "save": 2, "scale": [2, 3, 4], "scenario": 6, "scienc": 0, "scikit": 3, "scipi": 3, "score": [4, 6], "scorer": [], "scrollto": 6, "seamlessli": 6, "search": 4, "seed": 6, "segment": 2, "select": [3, 6], "selectkbest": [2, 3], "selectkbest__k": [], "self": [2, 6], "sensit": 6, "sequenc": 1, "seri": [1, 6], "set": [1, 6], "setup": 2, "sever": 1, "shape": [4, 6], "share": 6, "should": [1, 2, 6], "show": 6, "shpaner": 0, "sigma": 1, "sigmoid": [3, 6], "similar": [1, 6], "simpl": 6, "simpleimput": [1, 3, 6], "simplifi": 2, "simultan": 2, "sinc": 1, "singl": [1, 6], "skew": 1, "sklearn": 6, "smote": [2, 3], "so": [1, 6], "softwar": [0, 2], "solut": 4, "some": 1, "spam": 6, "special": 0, "specif": [1, 2, 6], "specifi": [1, 2, 6], "split": [1, 2, 3, 6], "sqrt": 1, "squar": [1, 6], "squeez": [1, 6], "stage": 6, "standard": 1, "standardscal": [1, 6], "standardscalar": 6, "state": 1, "statist": 1, "step": [2, 4], "stop": [2, 3, 6], "store": 2, "str": 6, "str2": [], "strat": [], "strat_key_val_test": 2, "strategi": 3, "stratif": [2, 4, 6], "stratifi": [1, 2, 3, 6], "stratify_col": [1, 2, 6], "stratify_i": [1, 2, 6], "stratify_kei": 2, "string": 2, "studi": [4, 5], "subsampl": 6, "subsequ": 1, "subset": 1, "suit": 6, "sum_": 1, "summari": 4, "summarize_auto_keras_param": [], "supervis": 6, "support": [0, 2, 3, 6], "symptom": [], "system": 3, "t": 6, "take": [1, 6], "taken": 2, "target": [2, 3, 4, 6], "task": [3, 6], "techniqu": [1, 3, 6], "temporarili": 2, "test": [2, 6], "test_model": 6, "test_siz": 6, "text": 1, "th": 1, "than": 1, "thank": 0, "thei": 1, "them": [1, 6], "therefor": 1, "thi": [0, 1, 2, 3, 6], "thoroughli": 6, "threshold": [2, 3, 6], "through": 6, "time": 2, "titan": 6, "titl": [0, 6], "tn": 6, "toml": 2, "tool": [3, 6], "top": [1, 6], "tp": 6, "tqdm": 3, "track": 6, "train": [3, 4, 6], "train_siz": 6, "train_val_test": 2, "train_val_test_split": [2, 6], "transform": [4, 6], "translat": 0, "treat": 1, "tree": 6, "trial": [4, 5], "trigger": 1, "trt": [], "true": [1, 6], "trust": 1, "tune": [2, 3, 4], "tune_threshold_fbeta": [2, 6], "tuned_paramet": 6, "tuned_parameters_xgb": 6, "tuner": 6, "two": [1, 6], "txt": 2, "type": 6, "typeerror": 6, "typic": 6, "uci": [5, 6], "ucimlrepo": 6, "ucla": 0, "umxyy0yvd2xq": 6, "uncalibr": 6, "undefin": 1, "under": 3, "unexpect": 6, "uniqu": 6, "unlik": 1, "unnecessari": [1, 2], "unpredict": 1, "unreli": 1, "unus": 2, "up": 2, "updat": 2, "url": 0, "us": [1, 2, 3, 6], "usag": 2, "user": 6, "userwarn": 1, "usp": 6, "util": 2, "valid": [3, 4, 6], "validation_data": 6, "validation_s": 6, "valu": 1, "valueerror": 6, "var": [1, 6], "variabl": [2, 3, 4, 6], "varianc": 4, "varieti": 6, "variou": [3, 6], "vdot": 1, "vector": 1, "verbos": 2, "versatil": 3, "version": [0, 3, 4], "visual": 6, "w": [1, 5], "wa": [0, 1, 2], "wai": 1, "warn": 1, "we": 1, "weight": [1, 6], "welcom": 4, "well": [1, 6], "were": 2, "what": 4, "when": [1, 2, 3, 6], "where": [1, 2, 6], "whether": 6, "which": [1, 3, 6], "while": 1, "wide": 6, "wish": 6, "within": 1, "without": 1, "work": [0, 2], "workflow": 3, "world": 6, "would": 1, "wrong": 2, "x": [1, 2, 4], "x_": 1, "x_i": 1, "x_j": 1, "x_test": 6, "x_train": 6, "x_valid": 6, "x_valid_test": 2, "xgb": 6, "xgb__colsample_bytre": 6, "xgb__early_stopping_round": 6, "xgb__eval_metr": 6, "xgb__learning_r": 6, "xgb__max_depth": 6, "xgb__n_estim": 6, "xgb__subsampl": 6, "xgb__verbos": 6, "xgb_colsample_bytre": 6, "xgb_definit": 6, "xgb_early_bootstrap_test": 2, "xgb_early_stopping_round": 6, "xgb_eval_metr": 6, "xgb_learning_r": 6, "xgb_max_depth": 6, "xgb_model": 6, "xgb_n_estim": 6, "xgb_name": 6, "xgb_paramet": 6, "xgb_subsampl": 6, "xgb_verbos": 6, "xgbclassifi": 4, "xgbearli": 6, "xgboost": [2, 3, 4], "xgboost_aid": [], "xgboost_earli": 6, "xgbregressor": 6, "xlabel": 6, "y": [1, 2, 4], "y_1": 1, "y_2": 1, "y_i": 1, "y_n": 1, "y_pred": 6, "y_prob_calibr": 6, "y_prob_uncalibr": 6, "y_test": 6, "y_test_pr": 6, "y_train": 6, "y_true": 6, "y_valid": 6, "y_valid_proba": 6, "y_valid_test": 2, "year": 0, "yet": 6, "ylabel": 6, "you": [0, 1, 3, 6], "your": [1, 3, 6], "z": 1, "z30": [], "z_": 1, "zenodo": [0, 2], "zero": 4, "zero_variance_column": [1, 6]}, "titles": ["GitHub Repository", "Zero Variance Columns", "Changelog", "Welcome to Model Tuner\u2019s Documentation!", "Model Tuner Documentation", "References", "iPython Notebooks"], "titleterms": {"": 3, "0": 2, "010a": 2, "011a": 2, "012a": 2, "013a": 2, "014a": 2, "02a": 2, "05a": 2, "06a": 2, "07a": 2, "08a": 2, "09a": 2, "1": [1, 6], "10": 6, "15a": 2, "16a": 2, "2": [1, 6], "3": [1, 6], "4": 6, "5": 6, "6": 6, "7": 6, "8": 6, "9": 6, "Its": 1, "about": 4, "accordingli": 6, "accur": 1, "acknowledg": 0, "aid": 6, "an": 6, "befor": 1, "binari": 6, "brier": 1, "calcul": 1, "calibr": [1, 6], "california": 6, "caveat": 4, "changelog": 2, "check": 6, "cite": 0, "classif": 6, "clinic": 6, "column": [1, 6], "configur": 6, "consist": 1, "creat": 6, "cross": 1, "curv": 1, "data": 1, "dataset": 6, "defin": 6, "depend": 1, "distort": 1, "document": [3, 4], "doe": 3, "drop": 6, "effect": 1, "exampl": [1, 6], "fit": 6, "function": 6, "get": 4, "github": 0, "goal": 1, "grid": 6, "group": 6, "guid": 4, "helper": 6, "hous": 6, "hyperparamet": 6, "import": 6, "imput": 1, "initi": 6, "input": 6, "instal": 3, "instanc": 6, "ipython": 6, "isoton": 1, "kei": 6, "librari": 6, "load": 6, "logist": 1, "method": 6, "metric": 6, "model": [0, 1, 3, 4, 6], "necessari": 6, "need": 6, "notebook": 6, "offer": 3, "option": 6, "paramet": [1, 6], "perform": 6, "platt": 1, "prerequisit": 3, "prevent": 1, "refer": 5, "regress": [1, 6], "report": 6, "repositori": 0, "return": 6, "scale": 1, "score": 1, "search": 6, "shape": 1, "solut": 1, "start": 4, "step": 6, "stratif": 1, "studi": 6, "summari": 1, "target": 1, "train": 1, "transform": 1, "trial": 6, "tune": 6, "tuner": [0, 3, 4], "usag": 4, "valid": 1, "variabl": 1, "varianc": [1, 6], "version": 2, "welcom": 3, "what": 3, "x": 6, "xgbclassifi": 6, "xgboost": 6, "y": 6, "zero": [1, 6]}}) \ No newline at end of file +Search.setIndex({"alltitles": {"1. Accurate Calculation of Scaling Parameters": [[1, "accurate-calculation-of-scaling-parameters"]], "2. Consistency in Data Transformation": [[1, "consistency-in-data-transformation"]], "3. Prevention of Distortion in Scaling": [[1, "prevention-of-distortion-in-scaling"]], "AIDS Clinical Trials Group Study": [[6, "aids-clinical-trials-group-study"]], "About Model Tuner": [[4, null]], "Acknowledgements": [[0, "acknowledgements"]], "Binary Classification": [[6, "binary-classification"]], "Binary Classification Examples": [[6, "binary-classification-examples"]], "Brier Score": [[1, "brier-score"]], "Calibration Curve": [[1, "calibration-curve"]], "California Housing with XGBoost": [[6, "california-housing-with-xgboost"]], "Caveats": [[4, null]], "Changelog": [[2, null]], "Citing Model Tuner": [[0, "citing-model-tuner"]], "Classification Report (Optional)": [[6, "classification-report-optional"]], "Column Stratification with Cross-Validation": [[1, "column-stratification-with-cross-validation"]], "Cross-Validation and Stratification": [[1, "cross-validation-and-stratification"]], "Dependent Variable": [[1, "dependent-variable"]], "Effects on Model Training": [[1, "effects-on-model-training"]], "Example: Calibration in Logistic Regression": [[1, "example-calibration-in-logistic-regression"]], "Getting Started": [[4, null]], "GitHub Repository": [[0, null]], "Goal of Calibration": [[1, "goal-of-calibration"]], "Helper Functions": [[6, "helper-functions"]], "Imputation Before Scaling": [[1, "imputation-before-scaling"]], "Input Parameters": [[6, "input-parameters"]], "Installation": [[3, "installation"]], "Isotonic Regression": [[1, "isotonic-regression"]], "Key Methods and Functionalities": [[6, "key-methods-and-functionalities"]], "Model Calibration": [[1, "model-calibration"]], "Model Tuner Documentation": [[4, null]], "Platt Scaling": [[1, "platt-scaling"]], "Prerequisites": [[3, "prerequisites"]], "References": [[5, null]], "Regression": [[6, "regression"]], "Regression Example": [[6, "regression-example"]], "Solution": [[1, "solution"]], "Step 10: Calibrate the Model (if needed)": [[6, "step-10-calibrate-the-model-if-needed"]], "Step 1: Import Necessary Libraries": [[6, "step-1-import-necessary-libraries"], [6, "id1"]], "Step 2: Load the Dataset": [[6, "step-2-load-the-dataset"]], "Step 2: Load the dataset, define X, y": [[6, "step-2-load-the-dataset-define-x-y"]], "Step 3: Check for zero-variance columns and drop accordingly": [[6, "step-3-check-for-zero-variance-columns-and-drop-accordingly"]], "Step 3: Create an Instance of the XGBClassifier": [[6, "step-3-create-an-instance-of-the-xgbclassifier"]], "Step 4: Create an Instance of the XGBClassifier": [[6, "step-4-create-an-instance-of-the-xgbclassifier"]], "Step 4: Define Hyperparameters for XGBoost": [[6, "step-4-define-hyperparameters-for-xgboost"]], "Step 5: Define Hyperparameters for XGBoost": [[6, "step-5-define-hyperparameters-for-xgboost"]], "Step 5: Initialize and Configure the Model": [[6, "step-5-initialize-and-configure-the-model"]], "Step 6: Fit the Model": [[6, "step-6-fit-the-model"]], "Step 6: Initialize and Configure the Model": [[6, "step-6-initialize-and-configure-the-model"]], "Step 7: Perform Grid Search Parameter Tuning": [[6, "step-7-perform-grid-search-parameter-tuning"]], "Step 8: Fit the Model": [[6, "step-8-fit-the-model"]], "Step 9: Return Metrics (Optional)": [[6, "step-9-return-metrics-optional"]], "Summary": [[1, "summary"]], "Target Variable Shape and Its Effects": [[1, "target-variable-shape-and-its-effects"]], "Usage Guide": [[4, null]], "Version 0.0.010a": [[2, "version-0-0-010a"]], "Version 0.0.011a": [[2, "version-0-0-011a"]], "Version 0.0.012a": [[2, "version-0-0-012a"]], "Version 0.0.013a": [[2, "version-0-0-013a"]], "Version 0.0.014a": [[2, "version-0-0-014a"]], "Version 0.0.02a": [[2, "version-0-0-02a"]], "Version 0.0.05a": [[2, "version-0-0-05a"]], "Version 0.0.06a": [[2, "version-0-0-06a"]], "Version 0.0.07a": [[2, "version-0-0-07a"]], "Version 0.0.08a": [[2, "version-0-0-08a"]], "Version 0.0.09a": [[2, "version-0-0-09a"]], "Version 0.0.15a": [[2, "version-0-0-15a"]], "Version 0.0.16a": [[2, "version-0-0-16a"]], "Welcome to Model Tuner\u2019s Documentation!": [[3, null]], "What Does Model Tuner Offer?": [[3, "what-does-model-tuner-offer"]], "Zero Variance Columns": [[1, null]], "iPython Notebooks": [[6, null]]}, "docnames": ["about", "caveats", "changelog", "getting_started", "index", "references", "usage_guide"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.todo": 2, "sphinx.ext.viewcode": 1}, "filenames": ["about.rst", "caveats.rst", "changelog.rst", "getting_started.rst", "index.rst", "references.rst", "usage_guide.rst"], "indexentries": {"model (built-in class)": [[6, "Model", false]]}, "objects": {"": [[6, 0, 1, "", "Model"]]}, "objnames": {"0": ["py", "class", "Python class"]}, "objtypes": {"0": "py:class"}, "terms": {"": [1, 2, 4, 6], "0": [0, 1, 3, 4, 6], "00": 6, "0001": 6, "01": 6, "010a": 4, "011a": 4, "012a": 4, "013a": 4, "014a": 4, "017a": 3, "02a": 4, "05": 6, "05a": 4, "06a": 4, "07a": 4, "08a": 4, "09a": 4, "1": [2, 3, 4], "10": [0, 3, 4, 5], "100": 6, "1000": 6, "104": 6, "105": 6, "11": [3, 6], "11a": 2, "12": 3, "12727322": 0, "14": 3, "15a": 4, "16665653153377272": 6, "16737745981389285": 6, "16a": [0, 4], "172": 6, "175": 5, "19": [3, 6], "1998": 5, "1d": 1, "1e": 6, "2": [3, 4], "20": 6, "200": 6, "2024": 0, "21": 3, "222": 6, "23": 3, "24": 3, "241": 6, "24205514192581173": 6, "24432": 5, "248": 6, "26": 3, "2633964855111536": 6, "3": [3, 4], "30": 6, "300": 6, "304": 6, "30it": 6, "323": 6, "324": 6, "35007797000749163": 6, "4": [1, 3, 4], "428": 6, "5": [1, 3, 4], "500": [2, 6], "5132216728774747": 6, "5281": 0, "5469613259668509": 6, "55": 6, "5502958579881657": 6, "58": 1, "6": [3, 4], "66": 3, "68": 6, "69": 6, "7": [3, 4], "71": 6, "74": 6, "7461300309597523": 6, "75": 6, "76": 6, "7654320987654321": 6, "77": 6, "79": 6, "7979050719771986": 6, "7979060590722392": 6, "7979488661159093": 6, "798": 6, "8": [3, 4], "80": 6, "8025676192819657": 6, "81": 6, "8169018952192892": 6, "81it": 6, "82": 6, "83": 6, "84": 6, "85": 6, "86": 6, "87": 6, "88": 6, "89": 6, "890": 6, "8942307692307693": 6, "9": [1, 4], "91": 6, "92": 6, "926": 6, "9260891500474834": 6, "93": 6, "9343063541205956": 6, "94": 6, "9428571428571428": 6, "95": 6, "96": 6, "98": 6, "99": 6, "999": [1, 6], "A": [1, 6], "AND": 6, "By": 1, "For": [1, 3], "If": [1, 6], "In": [1, 2, 6], "It": [1, 3, 6], "Its": 4, "On": 1, "One": [1, 6], "The": [1, 3, 6], "There": 2, "These": 1, "To": 1, "_": 1, "__early_stopping_round": 6, "__eval_metr": 6, "__init__": 6, "__learning_r": 6, "__max_depth": 6, "__n_estim": 6, "__param_nam": 6, "__verbos": 6, "_confusion_matrix_print": 6, "_i": 1, "_j": 1, "abil": 6, "about": 1, "abram": 5, "absolut": 6, "access": [0, 6], "accordingli": 4, "accur": 4, "accuraci": [1, 6], "achiev": [1, 2], "acknowledg": 4, "across": [1, 2, 3, 6], "actual": [1, 6], "ad": 2, "adasyn": [2, 3], "addit": [1, 6], "addition": [1, 6], "adjust": 1, "advanc": 6, "aforement": 1, "after": 6, "aid": [4, 5], "aids_clinical_": 6, "aids_clinical_trials_group_study_175": 6, "alex": 0, "algorithm": [1, 6], "align": 1, "all": [1, 2, 3, 6], "allow": [2, 3, 6], "also": [1, 6], "alwai": 2, "an": 4, "analysi": 1, "angel": 6, "ani": 1, "anoth": 1, "anova": 1, "apach": 2, "appli": [1, 3, 6], "applic": [1, 6], "approach": 1, "approx": 1, "ar": [0, 1, 2, 3, 6], "arrai": 1, "arthur": [0, 2], "artifici": 1, "ascii": 6, "assert": 2, "assess": [1, 3, 6], "assign": 2, "assum": 1, "attempt": 1, "attributeerror": 6, "auc": 6, "author": 0, "autokera": 2, "autokerasclassifi": 2, "automat": [1, 3], "avail": [1, 2, 6], "averag": 6, "avg": 6, "avoid": [1, 2], "axi": 2, "b": 1, "back": 6, "balanc": [2, 3, 6], "bar": 1, "base": [1, 3, 6], "bayesian": 6, "bayessearchcv": 6, "becaus": [1, 2], "becom": 1, "been": [1, 2], "befor": [2, 3, 4, 6], "begin": 1, "behavior": 1, "being": 2, "below": 3, "best": 6, "best_param": 2, "best_params_per_scor": 6, "beta": 6, "better": 1, "between": [1, 3, 6], "bin": [1, 6], "binari": 4, "bool": 6, "boost": [2, 6], "boost_earli": 6, "bootstrap": 3, "bootstrapp": [2, 6], "both": [1, 2, 6], "breast": 6, "brier": [4, 6], "bug": 2, "bui": 0, "build": 6, "c": 1, "c5g896": 5, "calcul": 4, "calibr": [2, 3, 4], "calibrate_report": 6, "calibratemodel": 6, "calibration_curv": 6, "calibration_method": 6, "california": 4, "california_h": 6, "call": 6, "can": [0, 1, 3, 6], "cancer": 6, "cannot": 1, "captur": 1, "care": 6, "case": [1, 2], "catboost": [2, 3], "categor": 6, "categori": 6, "caus": 1, "chang": [1, 2, 6], "changelog": 4, "char": 2, "check": [1, 4], "chunk": 2, "cite": 4, "clariti": 6, "class": [1, 2, 3, 6], "class_label": 6, "class_report_test": 6, "class_report_v": 6, "classif": [1, 3, 4], "classifi": 6, "classification_report": 6, "clc": 6, "clean": 2, "click": 0, "clinic": [0, 4, 5], "close": 1, "cm_test": 6, "cm_val": 6, "code": [1, 2], "codebas": 0, "colab": 6, "column": [2, 4], "combin": 6, "command": 6, "comment": 2, "common": 1, "commonli": 6, "compat": 3, "complet": [1, 2], "comput": [1, 6], "concat": 2, "condit": 1, "conduct": 3, "conf_mat_class_kfold": 6, "conf_matrix": 6, "configur": 4, "conflict": 1, "confus": 6, "consid": [1, 2], "consist": 4, "constant": 1, "constraint": [1, 2], "construct": 1, "contain": 2, "context": 1, "contrast": 1, "contribut": [0, 1], "contributor": 0, "convers": 1, "convert": [1, 6], "correct": [1, 2], "correctli": 1, "count": 2, "cpu": 6, "creat": 4, "creation": 3, "critic": 1, "cross": [3, 4, 6], "crucial": 1, "ctsi": 0, "current": [1, 3], "curv": [4, 6], "custom": [2, 3, 6], "custom_scor": 6, "d": [1, 5], "d_1": 1, "d_2": 1, "d_j": 1, "d_k": 1, "data": [2, 3, 4, 6], "dataconversionwarn": 1, "datafram": [1, 6], "dataset": [1, 3, 4], "decis": 6, "decreas": 1, "default": 6, "defin": [1, 4], "denot": 1, "depend": [2, 3, 4, 6], "deploi": 6, "deprec": 2, "depth": 6, "design": [1, 3, 6], "detect": 6, "determin": 1, "dev": 2, "develop": 3, "deviat": 1, "diagnosi": [1, 6], "dict": 6, "dictionari": 6, "differ": [1, 2, 3], "dimens": 1, "dimension": 1, "directli": 3, "discrep": 1, "diseas": 6, "displai": 6, "disrupt": 1, "distinct": 6, "distinguish": 6, "distort": 4, "distribut": [1, 3], "divid": 1, "divis": 1, "do": [2, 6], "doe": 4, "doi": [0, 5], "dot": 1, "dr": 0, "drop": [1, 4], "due": 1, "dure": [1, 2, 6], "e": [1, 6], "each": [1, 6], "earli": [2, 3, 6], "early_stop": 6, "easier": 6, "easili": 6, "effect": [3, 4, 6], "either": [2, 6], "el": 5, "elimin": 3, "empir": 1, "empti": [1, 6], "enabl": [3, 6], "encount": 1, "end": 1, "enhanc": 2, "ensur": [1, 2, 3, 6], "entir": 1, "equal": 1, "equat": 1, "equival": 6, "error": [1, 2, 6], "essenc": 6, "essenti": [1, 6], "estat": 6, "estim": [1, 2, 3, 6], "estimator_nam": 6, "estimator_name_xgb": 6, "eta": 6, "etc": 2, "eval_set": 6, "evalu": [1, 3, 6], "evaluate_bootstrap_metr": 2, "even": 1, "examin": 6, "exampl": 4, "exceed": 2, "except": 6, "exp": 1, "expect": [1, 6], "explain": 6, "explan": 1, "express": 1, "extend": 6, "extract": 2, "extrem": 1, "f": [1, 6], "f1": 6, "f1_beta_tun": 6, "f_i": 1, "facilit": 3, "failur": 1, "fals": 6, "far": 1, "favor": 2, "feat_num": 1, "featur": [1, 3, 6], "feature_nam": 6, "feature_select": 6, "fetch": 6, "fetch_california_h": 6, "fetch_ucirepo": 6, "figsiz": 6, "figur": 6, "file": [2, 6], "filter": 2, "find": 1, "fine": [3, 6], "first": 1, "fit": [1, 2, 4], "fix": 2, "flexibl": [3, 6], "float": 6, "float64": 6, "fn": 6, "focu": 1, "fold": [1, 3, 6], "follow": [1, 2, 3, 6], "form": 1, "format": 6, "formul": 1, "forthcom": 2, "found": 6, "fp": 6, "frac": 1, "fraction": 1, "fraud": 6, "free": 1, "frequenc": 1, "from": [1, 2, 3, 6], "full": 1, "function": [1, 2, 3, 4], "funnel": 0, "funnell_2024_12727322": 0, "g": [1, 6], "gb": 6, "gender": 6, "gener": [1, 3, 6], "get": 6, "get_best_score_param": 6, "get_cross_valid": 6, "get_test_data": 6, "get_train_data": 6, "get_valid_data": 6, "github": 4, "given": 1, "goal": 4, "googl": 6, "grid": 4, "grid_search_param_tun": 6, "gridsearchcv": 6, "group": [4, 5], "guidanc": 0, "ha": [1, 2], "had": 1, "hand": 1, "handl": [1, 3, 6], "happen": 2, "hat": 1, "have": 2, "haven": 6, "heavili": 1, "help": 6, "helper": 4, "here": [2, 3, 6], "hi": 0, "higher": 3, "histori": 2, "hous": 4, "howev": 1, "html": 6, "http": [0, 5], "hyperparamet": [2, 3, 4], "i": [1, 2, 3, 6], "id": 6, "ident": 1, "ij": 1, "imbal": 6, "imbalanc": [2, 3, 6], "imbalance_sampl": 6, "imblearn": 6, "implement": [2, 3], "import": [1, 2, 4], "importerror": 6, "improp": 1, "improperli": 6, "improv": [3, 6], "imput": [2, 3, 4, 6], "inaccur": 1, "includ": [1, 3, 6], "incomplet": 1, "inconsist": 1, "incorrect": [1, 6], "increas": 1, "index": 6, "indexerror": 6, "indic": [1, 6], "infinit": 1, "inflat": 1, "influenc": 1, "inform": 1, "informat": 0, "inher": 1, "initi": 4, "initialis": 2, "input": [1, 4], "insid": 2, "instal": [4, 6], "instanc": [1, 4], "instead": [2, 6], "institut": 0, "int": 6, "integr": [1, 3], "interpret": 1, "interv": 1, "introduc": 2, "invalid": [1, 6], "invalu": 0, "involv": [1, 2], "ipython": 4, "isinst": 1, "isoton": [3, 4, 6], "issu": [1, 2, 6], "iter": 6, "itself": 2, "j": 1, "job": 6, "joblib": 3, "jul": 0, "just": 1, "k": [1, 3, 6], "kei": [0, 2, 3, 4], "keyerror": 6, "kf": 6, "kfold": [2, 6], "kfold_split": 6, "known": 6, "label": [1, 3, 6], "larg": 1, "later": 1, "layer": 2, "lead": 1, "learn": [1, 2, 3, 5, 6], "legend": 6, "length": 2, "leon": 2, "leonid": 0, "leq": 1, "let": 1, "librari": [3, 4], "licens": 2, "like": [1, 3, 6], "likelihood": 1, "limit": 2, "line": 2, "linestyl": 6, "link": 0, "list": [2, 6], "lo": 6, "load": 4, "log": [2, 6], "logic": 2, "logist": [4, 6], "logloss": 6, "logo": 2, "loop": 2, "low": 2, "lower": 1, "machin": [1, 3, 5, 6], "macro": 6, "maintain": 1, "make": 6, "marker": 6, "match": 1, "mathemat": 1, "matplotlib": 6, "matric": 6, "matrix": 6, "max": 1, "maximum": [1, 6], "mean": [1, 6], "measur": 1, "median": [1, 6], "medic": [0, 1], "meet": 3, "messag": 6, "method": [1, 2, 3, 4], "metric": [1, 2, 3, 4], "mid": 1, "might": 1, "mii": 0, "min": 1, "min_": 1, "minimum": 1, "minmax": 3, "misinterpret": 1, "mismatch": [2, 6], "miss": [1, 6], "mlflow": 2, "model": 2, "model_tun": [3, 6], "model_typ": 6, "model_xgb": 6, "modifi": 2, "modul": 6, "monoton": 1, "month": 0, "more": 1, "move": 2, "msb": 1, "msw": 1, "mu": 1, "multi": [3, 6], "multi_label": 6, "multipl": 2, "n": 1, "n_bin": 6, "n_estim": 6, "n_iter": 6, "n_j": 1, "n_job": 6, "n_sampl": 1, "n_split": 6, "name": [2, 6], "nan": 1, "necessari": [2, 4], "need": [1, 4], "neg": [1, 6], "non": [1, 2], "none": 6, "note": 1, "notebook": [2, 4], "now": [1, 2], "np": [2, 6], "number": [1, 2, 6], "numer": 6, "numpi": [3, 6], "o": 6, "object": [2, 6], "observ": 1, "occur": 2, "offer": 4, "often": 1, "older": 2, "onc": 6, "one": [1, 6], "onli": [1, 2], "onto": 2, "oper": 1, "optim": [3, 6], "optimal_threshold": 6, "option": 4, "order": [1, 2], "org": [0, 5], "origin": [0, 1], "other": [1, 2, 3, 6], "our": [2, 6], "out": 2, "outcom": [1, 6], "output": [1, 6], "outsid": 2, "over": 1, "overal": 1, "overfit": 3, "oversampl": 3, "p": 1, "p_1": 1, "p_2": 1, "p_i": 1, "p_n": 1, "packag": 6, "panayioti": 0, "panda": [3, 6], "parallel": 6, "param": 6, "paramet": [2, 3, 4], "parametr": 1, "part": 6, "particularli": [1, 3, 6], "pass": [1, 6], "pd": [1, 2, 6], "penal": 1, "per": 2, "perfectli": [1, 6], "perform": [1, 3, 4], "petousi": 0, "pickl": 2, "piecewis": 1, "pip": [3, 6], "pip25": 2, "pipelin": [1, 2, 3, 6], "pipeline_step": [1, 2, 6], "placehold": 1, "platt": 4, "pleas": 1, "plot": 6, "plt": 6, "pmatrix": 1, "po": 6, "point": 1, "posit": [1, 6], "possibl": [1, 6], "power": [1, 3], "ppv": 6, "practic": [1, 6], "precis": 6, "predict": [1, 6], "predict_proba": 6, "prefix": 6, "preprocess": [1, 6], "preprocess_imputer_imput": 6, "preprocess_scaler_standardscalar": 6, "preprocessor": [1, 6], "prerequisit": 4, "present": 1, "preserv": 1, "pretti": 2, "prevent": [3, 4], "previou": 2, "previous": 1, "primari": 1, "print": [2, 6], "print_pipelin": 6, "print_result": 6, "print_selected_best_featur": 6, "prior": 1, "prob_pred_calibr": 6, "prob_pred_uncalibr": 6, "prob_true_calibr": 6, "prob_true_uncalibr": 6, "probabilist": 1, "probabl": [1, 3, 6], "problem": [1, 6], "proceed": 1, "process": [1, 2, 6], "process_imbalance_sampl": 6, "produc": [1, 6], "properli": 6, "properti": 1, "proport": [1, 6], "provid": [1, 3, 6], "publish": 0, "py": 2, "pypi": [2, 3], "pyplot": 6, "pyproject": 2, "python": 3, "quad": 1, "quickli": 6, "r": 6, "r2": 6, "race": 6, "rais": [1, 6], "rand_grid": 6, "random": 6, "random_st": 6, "randomized_grid": 6, "randomoversampl": 6, "randomundersampl": 6, "rang": [1, 6], "rate": 6, "rather": 1, "ratio": [1, 6], "raw": 1, "re": 2, "readili": 6, "readm": 2, "real": 6, "recal": 6, "recommend": 1, "recurs": 3, "redfin": 6, "redfin_model_xgb": 6, "ref": 2, "refactor": 2, "refer": [1, 4], "reflect": 1, "regard": 2, "regress": 4, "regression_report": 6, "regression_report_kfold": 6, "regular": 6, "relat": 2, "relationship": 1, "releas": 2, "reli": 1, "reliabl": 6, "remov": [1, 2], "renam": 2, "repeatedli": 1, "replac": 1, "report": [2, 4], "report_model_metr": 6, "repositori": [4, 5, 6], "repres": [1, 2], "represent": 6, "reproduc": 6, "requir": [2, 3, 6], "resampl": [2, 6], "research": 6, "reset": [2, 6], "reset_estim": 6, "resolut": 2, "resourc": 6, "result": 1, "retriev": 6, "return": 4, "return_metr": 6, "rfe": 3, "rightarrow": 1, "risk": 1, "rmse": 6, "robust": [3, 6], "roc": 6, "roc_auc": 6, "root": 6, "routin": 1, "run": 6, "runtim": 1, "runtimeerror": 6, "runtimewarn": 1, "sadr": 5, "same": [1, 2], "sampl": [1, 2], "sampler": 6, "save": 2, "scale": [2, 3, 4], "scenario": 6, "scienc": 0, "scikit": 3, "scipi": 3, "score": [4, 6], "seamlessli": 6, "search": 4, "seed": 6, "segment": 2, "select": [3, 6], "selectkbest": [2, 3], "self": [2, 6], "sensit": 6, "sequenc": 1, "seri": [1, 6], "set": [1, 6], "setup": 2, "sever": 1, "shape": [4, 6], "should": [1, 2, 6], "show": 6, "shpaner": 0, "sigma": 1, "sigmoid": [3, 6], "similar": [1, 6], "simpl": 6, "simpleimput": [1, 3, 6], "simplifi": 2, "simultan": 2, "sinc": 1, "singl": [1, 6], "skew": 1, "sklearn": 6, "smote": [2, 3], "so": [1, 6], "softwar": [0, 2], "solut": 4, "some": 1, "spam": 6, "special": 0, "specif": [1, 2, 6], "specifi": [1, 2, 6], "split": [1, 2, 3, 6], "sqrt": 1, "squar": [1, 6], "squeez": [1, 6], "stage": 6, "standard": 1, "standardscal": [1, 6], "standardscalar": 6, "state": 1, "statist": 1, "step": [2, 4], "stop": [2, 3, 6], "store": 2, "str": 6, "strat_key_val_test": 2, "strategi": 3, "stratif": [2, 4, 6], "stratifi": [1, 2, 3, 6], "stratify_col": [1, 2, 6], "stratify_i": [1, 2, 6], "stratify_kei": 2, "string": 2, "studi": [4, 5], "subsampl": 6, "subsequ": 1, "subset": 1, "suit": 6, "sum_": 1, "summari": 4, "supervis": 6, "support": [0, 2, 3, 6], "system": 3, "t": 6, "take": [1, 6], "taken": 2, "target": [2, 3, 4, 6], "task": [3, 6], "techniqu": [1, 3, 6], "temporarili": 2, "test": [2, 6], "test_model": 6, "test_siz": 6, "text": 1, "th": 1, "than": 1, "thank": 0, "thei": 1, "them": [1, 6], "therefor": 1, "thi": [0, 1, 2, 3, 6], "thoroughli": 6, "threshold": [2, 3, 6], "through": 6, "time": 2, "titan": 6, "titl": [0, 6], "tn": 6, "toml": 2, "tool": [3, 6], "top": [1, 6], "tp": 6, "tqdm": 3, "track": 6, "train": [3, 4, 6], "train_siz": 6, "train_val_test": 2, "train_val_test_split": [2, 6], "transform": [4, 6], "translat": 0, "treat": 1, "tree": 6, "trial": [4, 5], "trigger": 1, "true": [1, 6], "trust": 1, "tune": [2, 3, 4], "tune_threshold_fbeta": [2, 6], "tuned_paramet": 6, "tuned_parameters_xgb": 6, "tuner": 6, "two": [1, 6], "txt": 2, "type": 6, "typeerror": 6, "typic": 6, "uci": [5, 6], "ucimlrepo": 6, "ucla": 0, "uncalibr": 6, "undefin": 1, "under": 3, "unexpect": 6, "uniqu": 6, "unlik": 1, "unnecessari": [1, 2], "unpredict": 1, "unreli": 1, "unus": 2, "up": 2, "updat": 2, "url": 0, "us": [1, 2, 3, 6], "usag": 2, "user": 6, "userwarn": 1, "util": 2, "valid": [3, 4, 6], "validation_data": 6, "validation_s": 6, "valu": 1, "valueerror": 6, "var": [1, 6], "variabl": [2, 3, 4, 6], "varianc": 4, "varieti": 6, "variou": [3, 6], "vdot": 1, "vector": 1, "verbos": 2, "versatil": 3, "version": [0, 3, 4], "visual": 6, "w": [1, 5], "wa": [0, 1, 2], "wai": 1, "warn": 1, "we": 1, "weight": [1, 6], "welcom": 4, "well": [1, 6], "were": 2, "what": 4, "when": [1, 2, 3, 6], "where": [1, 2, 6], "whether": 6, "which": [1, 3, 6], "while": 1, "wide": 6, "wish": 6, "within": 1, "without": 1, "work": [0, 2], "workflow": 3, "world": 6, "would": 1, "wrong": 2, "x": [1, 2, 4], "x_": 1, "x_i": 1, "x_j": 1, "x_test": 6, "x_train": 6, "x_valid": 6, "x_valid_test": 2, "xgb": 6, "xgb__colsample_bytre": 6, "xgb__early_stopping_round": 6, "xgb__eval_metr": 6, "xgb__learning_r": 6, "xgb__max_depth": 6, "xgb__n_estim": 6, "xgb__subsampl": 6, "xgb__verbos": 6, "xgb_colsample_bytre": 6, "xgb_definit": 6, "xgb_early_bootstrap_test": 2, "xgb_early_stopping_round": 6, "xgb_eval_metr": 6, "xgb_learning_r": 6, "xgb_max_depth": 6, "xgb_model": 6, "xgb_n_estim": 6, "xgb_name": 6, "xgb_paramet": 6, "xgb_subsampl": 6, "xgb_verbos": 6, "xgbclassifi": 4, "xgbearli": 6, "xgboost": [2, 3, 4], "xgboost_earli": 6, "xgbregressor": 6, "xlabel": 6, "y": [1, 2, 4], "y_1": 1, "y_2": 1, "y_i": 1, "y_n": 1, "y_pred": 6, "y_prob_calibr": 6, "y_prob_uncalibr": 6, "y_test": 6, "y_test_pr": 6, "y_train": 6, "y_true": 6, "y_valid": 6, "y_valid_proba": 6, "y_valid_test": 2, "year": 0, "yet": 6, "ylabel": 6, "you": [0, 1, 3, 6], "your": [1, 3, 6], "z": 1, "z_": 1, "zenodo": [0, 2], "zero": 4, "zero_variance_column": [1, 6]}, "titles": ["GitHub Repository", "Zero Variance Columns", "Changelog", "Welcome to Model Tuner\u2019s Documentation!", "Model Tuner Documentation", "References", "iPython Notebooks"], "titleterms": {"": 3, "0": 2, "010a": 2, "011a": 2, "012a": 2, "013a": 2, "014a": 2, "02a": 2, "05a": 2, "06a": 2, "07a": 2, "08a": 2, "09a": 2, "1": [1, 6], "10": 6, "15a": 2, "16a": 2, "2": [1, 6], "3": [1, 6], "4": 6, "5": 6, "6": 6, "7": 6, "8": 6, "9": 6, "Its": 1, "about": 4, "accordingli": 6, "accur": 1, "acknowledg": 0, "aid": 6, "an": 6, "befor": 1, "binari": 6, "brier": 1, "calcul": 1, "calibr": [1, 6], "california": 6, "caveat": 4, "changelog": 2, "check": 6, "cite": 0, "classif": 6, "clinic": 6, "column": [1, 6], "configur": 6, "consist": 1, "creat": 6, "cross": 1, "curv": 1, "data": 1, "dataset": 6, "defin": 6, "depend": 1, "distort": 1, "document": [3, 4], "doe": 3, "drop": 6, "effect": 1, "exampl": [1, 6], "fit": 6, "function": 6, "get": 4, "github": 0, "goal": 1, "grid": 6, "group": 6, "guid": 4, "helper": 6, "hous": 6, "hyperparamet": 6, "import": 6, "imput": 1, "initi": 6, "input": 6, "instal": 3, "instanc": 6, "ipython": 6, "isoton": 1, "kei": 6, "librari": 6, "load": 6, "logist": 1, "method": 6, "metric": 6, "model": [0, 1, 3, 4, 6], "necessari": 6, "need": 6, "notebook": 6, "offer": 3, "option": 6, "paramet": [1, 6], "perform": 6, "platt": 1, "prerequisit": 3, "prevent": 1, "refer": 5, "regress": [1, 6], "report": 6, "repositori": 0, "return": 6, "scale": 1, "score": 1, "search": 6, "shape": 1, "solut": 1, "start": 4, "step": 6, "stratif": 1, "studi": 6, "summari": 1, "target": 1, "train": 1, "transform": 1, "trial": 6, "tune": 6, "tuner": [0, 3, 4], "usag": 4, "valid": 1, "variabl": 1, "varianc": [1, 6], "version": 2, "welcom": 3, "what": 3, "x": 6, "xgbclassifi": 6, "xgboost": 6, "y": 6, "zero": [1, 6]}}) \ No newline at end of file diff --git a/docs/usage_guide.html b/docs/usage_guide.html index c15234b..3859d77 100644 --- a/docs/usage_guide.html +++ b/docs/usage_guide.html @@ -145,11 +145,8 @@

iPython Notebooks

Google Colab Notebooks

- -

<a href=”https://colab.research.google.com/drive/1ujLL2mRtIWwGamnpWKIo2f271_Q103t-?usp=sharing#scrollTo=uMxyy0yvd2xQ” target=”_blank”>Binary Classification + KFold Example: Titanic Dataset - Categorical Data</a>

diff --git a/source/usage_guide.rst b/source/usage_guide.rst index bf5662d..bf55a68 100644 --- a/source/usage_guide.rst +++ b/source/usage_guide.rst @@ -32,7 +32,7 @@ Binary Classification Examples - .. raw:: html - Binary Classification + KFold Example: Titanic Dataset - Categorical Data + Binary Classification + KFold Example: Titanic Dataset - Categorical Data - .. raw:: html