python 23 lines · 1 tab

Train test split and stratified cross validation done properly

Dr. Elena Vasquez Apr 2026

1 tab

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

X_train, X_test, y_train, y_test = train_test_split(
    X,
    y,
    test_size=0.2,
    stratify=y,
    random_state=42,
)

pipeline = Pipeline([
    ('imputer', SimpleImputer(strategy='median')),
    ('scaler', StandardScaler()),
    ('model', LogisticRegression(max_iter=1000)),
])

cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
scores = cross_validate(pipeline, X_train, y_train, cv=cv, scoring=['roc_auc', 'f1', 'precision', 'recall'])
print(scores)

1 file · python Explain with highlit

Evaluation goes wrong when data splitting is treated like boilerplate. I stratify imbalanced targets, guard time order when necessary, and make sure preprocessing lives inside cross-validation. This is the difference between a model that looks good in a notebook and one that behaves predictably in production.

Related snips

python

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),

Regression workflows with linear, ridge, lasso, and elastic net

scikit-learn regression ridge

by Dr. Elena Vasquez 1 tab

python

import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler

Encoding categorical variables without creating leakage

categorical-encoding preprocessing scikit-learn

by Dr. Elena Vasquez 1 tab

python

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)

Confusion matrix diagnostics for threshold selection

confusion-matrix thresholding evaluation

by Dr. Elena Vasquez 1 tab

python

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={

Hyperparameter tuning with GridSearchCV and randomized search

hyperparameter-tuning gridsearch scikit-learn

by Dr. Elena Vasquez 1 tab

python

import joblib
import pandas as pd
from fastapi import FastAPI
from pydantic import BaseModel

app = FastAPI(title='Churn Prediction API')

Serving scikit-learn models behind a FastAPI prediction API

fastapi scikit-learn model-serving

by Dr. Elena Vasquez 1 tab

python

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

Classification metrics beyond accuracy for imbalanced problems

classification-metrics imbalanced-data evaluation

by Dr. Elena Vasquez 1 tab

Share this code

Here's the card — post it anywhere.

Train test split and stratified cross validation done properly — share card

Link copied