Dr. Elena Vasquez

import spacy
from spacy.matcher import Matcher

nlp = spacy.load('en_core_web_sm')
matcher = Matcher(nlp.vocab)
matcher.add('INCIDENT_ID', [[{'TEXT': {'REGEX': '^INC-[0-9]{6}$'}}]])

from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler

X_scaled = StandardScaler().fit_transform(X)

import numpy as np
from sklearn.metrics import confusion_matrix

probabilities = model.predict_proba(X_valid)[:, 1]
thresholds = np.linspace(0.1, 0.9, 9)

from sklearn.metrics import (
    average_precision_score,
    classification_report,
    precision_recall_curve,
    roc_auc_score,
)

import optuna
from sklearn.ensemble import HistGradientBoostingClassifier
from sklearn.model_selection import cross_val_score

def objective(trial):
    model = HistGradientBoostingClassifier(

from sklearn.model_selection import GridSearchCV, RandomizedSearchCV
from sklearn.ensemble import RandomForestClassifier

grid_search = GridSearchCV(
    estimator=RandomForestClassifier(random_state=42, n_jobs=-1),
    param_grid={

from sklearn.compose import ColumnTransformer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.ensemble import RandomForestClassifier

from sklearn.cluster import KMeans, DBSCAN, AgglomerativeClustering
from sklearn.metrics import silhouette_score
from sklearn.preprocessing import StandardScaler

X_scaled = StandardScaler().fit_transform(X)

from sklearn.linear_model import LinearRegression, Ridge, Lasso, ElasticNet
from sklearn.metrics import mean_absolute_error, root_mean_squared_error

models = {
    'linear': LinearRegression(),
    'ridge': Ridge(alpha=1.0),

from sklearn.ensemble import RandomForestClassifier, HistGradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_auc_score
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer

from sklearn.model_selection import StratifiedKFold, train_test_split, cross_validate
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler
from sklearn.linear_model import LogisticRegression

standard_pipeline = Pipeline([
    ('scaler', StandardScaler()),