Documentación

• An overview of time-aware cross-validation techniques
  • Overfitting Issues and Optimization Techniques in Neural Network
• Overview Of 4 Model Validation Approaches to Mitigate Overfitting Problem
• 4 ways to Reduce Dimensionality of Data
• How to use K-fold Cross Validation with TensorFlow 2 and Keras?
• Bagging Classifier: Genera conjuntos de entrenamiento cogiendo subconjuntos de las columnas.
• Stop Using All Your Features for Modeling
• Handling Imbalanced Data
• Strategies and Tactics for Regression on Imbalanced Data
• Generate new samples non-linearly using Crucio TKRKNN.
• The Curse of Dimensionality and its Cure: Gráfica interesante de las dimensiones vs precisión
• Cross Validation - What, Why and How | Machine Learning
• Examples of Bias Variance Tradeoff in Deep Learning
• Nominal And Ordinal Encoding In Data Science!
• Overfitting Issues and Optimization Techniques in Neural Network
• Overfitting and Regularization in Machine Learning
• Batch Norm Explained Visually — How it works, and why neural networks need it
• Batch Normalization
• Examples of Bias Variance Tradeoff in Deep Learning: Buena explicación
• Bias
  • Introduction to biasness in AI — part 1
  • Biasness in AI— part 2
  • Biasness in AI- part 3
  • Biasness in AI — part 4

• Why is cross entropy not a common evaluation metric for model performance?
• Confidence intervals for the Log Loss metric for model comparison?

• Aprendizaje automatico y las Metricas de regresión
• Aprendizaje automático de métricas de regresión (MSE)
• Machine Learning: Seleccion Metricas de clasificacion

• Vanilla Neural Network: Ejemplo básico en Python de una red neuronal
• Cost, Activation, Loss Function.Neural Network.Deep Learning. What are these?: Explicación de funciones de coste y de activación
• From Linear Regression to Neural Networks: Why and How: Interesan los dibujos
• Case Study: Is Spurious Correlations the reason why Neural Networks fail on unseen data?: Falla con una vaca en el desierto y una vaca en la nieve. Piensa que es un camello y un oso polar
• Paper Walkthrough — Matrix Calculus for Deep Learning (Part 1 / 2): Explicación del Jacobiano
• Batch:
  • Optimizers for machine learning
  • Effect of Batch Size on Neural Net Training: Muy bueno
  • All you need to know about Gradient Descent
  • Batch, Mini-Batch and Stochastic Gradient Descent for Linear Regression

• A Neural Network Playground: Simuladores de redes neuronales
• NN-SVG: Dibujar redes neuronales
• Neptune AI
• TensorBoard

• Predicción con Series de Tiempo - Una guía inicial
• Transformers Explained Visually — Not just how, but Why they work so well
• Feature Engineering of DateTime Variables for Data Science, Machine Learning, Python

• BERT
• BERT: el inicio de una nueva era en el Natural Language Processing

Word Embedding Castellano:

• https://github.com/aitoralmeida/spanish_word2vec
• https://www.kaggle.com/rtatman/pretrained-word-vectors-for-spanish
• https://github.com/dccuchile/spanish-word-embeddings
• https://crscardellino.ar/SBWCE/

• Kaggle. Credit Card Fraud Detection

• Simplifying the concept of Autoencoders

• Basics of Convolutional Neural Networks — Stride and Pooling: Explica las 2 partes de una reco convolicional: Stride y Pooling
• Variational Autoencoders Simply Explained
• Understanding Convolutions by hand vs TensorFlow
• Isometric Drawing Tool

• A Quickstart Guide to Auto-Sklearn (AutoML) for Machine Learning Practitioners
• Bayesian Hyper-Parameter Optimization: Neural Networks, TensorFlow, Facies Prediction Example
• Hyperparameter Optimization with the Keras Tuner, Part 2
• 10 Hyperparameters to keep an eye on for your LSTM model — and other tips
• Hyperparameter search using Bayesian Optimization and an Evolutionary Algorithm
• How to Use Horovod’s Large Batch Simulation to Optimize Hyperparameter Tuning for (Highly) Distributed Training

• Viendo la Teoría - Inferencia Bayesiana
• ¿Cómo funciona la inferencia bayesiana?
• Exploring Bayesian Optimization: Muy buena explicación de la optimización Bayesiana
• La estadística detrás del rescate de la bomba de Palomares
• Bayes’ Theorem: The Holy Grail of Data Science
• Probability Learning II: How Bayes’ Theorem is applied in Machine Learning
• A Gentle Introduction to Bayesian Analysis.Applications to Development Research
• Pre- and post-test probability

• Doing Bayesian Data Analysis:A Tutorial with R, JAGS,and Stan
  • How much of a Bayesian posterior distribution falls inside a region of practical equivalence (ROPE)
  • Bayesian Estimation Supersedes the t Test (PDF)
    • Bayesian estimation supersedes the t test
    • Bayesian Estimation Supersedes the t-test (BEST): Online tool
    • Bayesian parameter estimation versus model comparison: Critica de "Bayesian estimation supersedes the t test"

• Towards MLOps: Technical capabilities of a Machine Learning platform
• Exponer Modelo de clasificación Mediante Tensorflow y FastAPI
• Write and train your own custom machine learning models using PyCaret
• Monitoring Machine Learning Models
• Easy Benchmarking of Long-Running Programs
• Colab + Vs Code + GitHub + Jupyter (Perfect for Deep Learning)
• Guardando y Serializando Modelos con TensorFlow Keras

• Change Axis Labels, Set Title and Figure Size to Plots with Seaborn
• 7 Open Source Libraries for Deep Learning Graphs
• The Bokeh Visualization Library
• graphext
• Altair: Declarative Visualization in Python

• Neural Networks fail on data with Spurious Correlation
• What is MultiCollinearity and how to resolve it?: Ejemplo de correlación
• Pearson and Spearman Rank Correlation Coefficient — Explained
• Covariance, Correlation and R-Squared Explained with Python
• Correlation in Statistics
• When To Use Spearman Correlation?

• Fundamentals Of Statistics For Data Scientists and Analysts
• Basic Statistics for Data Science
• Probabilidad y Estadística con Python
• To Err is Human: What are Type I and II Errors?: Foto que explica muy facilmente los errores de tipo I y tipo II
• Scatter Plots In Data Analysis: La importancia de los Scatter Plots
• Anomaly Detection Techniques
• Bar Chart or Histogram?
• Situación 179: Prácticas de BIOMEDICINA
• Qué es la Paradoja de Simpson y por qué va a ser muy útil para entender los próximos meses de pandemia
• Regresión lineal
  • Linear Regression Assumptions: Que se asume para que una regresión linear se pueda realizar.
  • Probabilistic interpretation of linear regression clearly explained: Explica que el error sigue una distribución y el ½
• Distribuciones
  • The Benefit's Of Central Limit Theorem: Explicación de la utilidad de la distribución normal
  • Related Probability Distributions: Explicación de 3 distribuciones.
  • Visualizing Continuous distributions from SciPy: Imagen con muchas distribuciones.
  • Distribution Analyser: Información sobre distribuciones y si se ajustan a los datos

• A Beginner’s Guide to Linear Algebra for Deep Learning:Escalares, vectores, matrices y tensores
• Paper Walkthrough — Matrix Calculus for Deep Learning (Part 2 / 2)
• Some Maths Resources to Help You in Your ML Journey

• Let’s Create Tensors like NumPy Arrays
• Linear Algebra with TensorFlow: Ejemplos de cálculos con TensorFlow en vez de usar numpy
• Creating and Training Custom Layers in TensorFlow 2
• Creating custom Loss functions using TensorFlow 2
• Creating Custom Activation Functions with Lambda Layers in TensorFlow 2
• 3 Keras Design Patterns Every ML Engineer Should Know

import tensorflow as tf
tf.config.list_physical_devices()

from tensorflow.python.client import device_lib
device_lib.list_local_devices()

device=device_lib.list_local_devices()[0]
with tf.device(device.name):
    history=model.fit(x, y,epochs=epochs,verbose=False)

• Natural Language Processing (NLP) for Semantic Search

• Imputing Missing Data Using Sklearn SimpleImputer
• Everything You’ve Ever Wanted to Know About Exploratory Data Analysis (EDA) Part — 1
• Exploratory Data Analysis On Haberman’s Cancer Survival Data set
• Making Your First Kaggle Submission
• Rapid-Fire EDA process using Python for ML Implementation
• Data Pre-Processing in Machine Learning with 🐍+Notebook
• How to Estimate Vaccine Efficacy Using a Logistic Regression Model
• How to find the best performing Machine Learning algorithm
• How I solved Kaggle’s April 2021 tabular competition
• Preprocessing data for data science (Part 1)
• Data Pre-Processing in Machine Learning with Python and Jupyter
• Exploratory Data Analysis : Iris DataSet
• Step by Step Guide to Build a Logistic Regression Model in Python
• Beginners guide to stock prediction using LSTM.
• Exploratory Data Analysis on Meteorological Data using Python
• Exploratory Data Analysis(EDA) y Exploratory Data Analysis(Part 2)
• Concrete Strength Modeling with 5 Machine Learning Algorithms
• sweetviz:EDA basada en Pandas que genera el resultado en HTML con solo 2 líneas de código
• Solve Machine Learning Problems
  • Solve Machine Learning Problems: EDA (part-1)
  • Solve Machine Learning Problems: Hypothesis Testing (Part-2)
  • Solve Machine Learning Problems: Data Preprocessing(part-3)
  • Solve Machine Learning problems: Feature Selection (part 4)
  • Solve Machine Learning Problems: Dimensionality Reduction (part-5)
  • Solve Machine Learning Problems: Outlier Detection (part-6)
  • Solve Machine Learning Problems: Regression & Model Selection(Part -7)

• Nine Things I Learned About Machine Learning During UmojaHack Africa 2021
• Basics of Data Cleansing: Las 6 cosas que hay que hacer para limpiar los datos
• Data Cleaning Libraries In Python: A Gentle Introduction
• 10 Deadly Sins of ML Model Training
• Data Analytics- Introduction: Tipos de análisis de datos
• Getting Started with Data Science with Python (Part-1): Que es la ciencia de datos
• Top 7 Feature Selection Techniques in Machine Learning
• The Top 25 Python libraries for Data Science
• Life Cycle Of Data Science Projects!

• Dive into Deep Learning. (2021)
• Mathematics for Machine Learning-Ed. Cambridge University Press (2020)
• The Elements of Statistical Learning Data Mining, Inference, and Prediction-Ed Springer (2017)
• Deep Learning-Ed. MIT Press (2016)
• Neural Networks and Deep Learning-Ed Determination Press (2015)
• Pattern Recognition and Machine Learning-Ed. Microsfot Press (2006)

• 58 Resources To Help Get Started With Deep Learning ( In TF )
• Guía rápida de IArtificial.net
• Distill — Latest articles about machine learning: Papers muy buenos sobre IA. Tienen mucho nivel.
• The Complete Reference to Data Science (ML/AI) and Related Concepts
• Important Links of Articles in Data Science and Deep Learning
• CS 189/289A Introduction to Machine Learning: Curso de IA de la universidad de Berkeley
• Ciencia de datos, teoría y ejemplos prácticos en R y Python

• extrapolar

• Charla: "Python packaging: lo estás haciendo mal"
  • Video de la charla:
  • Diapositivas
• Creating PEP 561 compatible packages
• How to make a Python package
• Installing Anaconda for Windows 10/8/7
• Visual Studio IntelliCode
• Google Colaboratory: Make Google Colaboratory GPU session wait for you.
• Google Colab
• How to Efficiently Load Image Datasets into Colab from Github, Kaggle and Local Machine
• 8 Tips and Tricks for Working with Large Datasets in Machine Learning

• Poetry
  • Are You Still Using Virtualenv for Managing Dependencies in Python Projects?
  • Python projects with Poetry and VSCode. Part 1
  • Python projects with Poetry and VSCode. Part 2

poetry config virtualenvs.in-project true
poetry config --list

#se debe instalar siempre esta dependencia
poetry add ipykernel

#instalar
poetry install

#ejecutar código python
poetry run python my_script.py

from matplotlib.colors import LinearSegmentedColormap, to_rgb

def crear_colomap_continuo(hex_colors):
    all_red = []
    all_green = []
    all_blue = []
    
    for hex_color in hex_colors:
        all_red.append(to_rgb(hex_color)[0])
        all_green.append(to_rgb(hex_color)[1])
        all_blue.append(to_rgb(hex_color)[2])

        
    num_colors = len(hex_colors) - 1
    red = tuple([(1/num_colors*i,v,v) for i,v in enumerate(all_red)])
    green = tuple([(1/num_colors*i,v,v) for i,v in enumerate(all_green)])
    blue = tuple([(1/num_colors*i,v,v) for i,v in enumerate(all_blue)])
    
    color_dictionary = {'red':red,'green':green,'blue':blue}
    new_cmap = LinearSegmentedColormap('new_cmap',segmentdata=color_dictionary)
    return new_cmap



new_cmap = build_custom_continuous_cmap(["#FFFFFF","#DBE6FA","#C3D6F4","#ACC8EF","#96BBE9","#81AFE4","#6DA4DE","#599BD9","#4793D3","#358CCE","#2486C8","#1481C3","#057DBD"])

• Propagación de errores
• Guía práctica para la realización de la medida y el cálculo de errores

• Teoria
  • Creating Confidence Intervals for Machine Learning Classifiers
  • Intervalo de confianza de la proporción binomial
  • Intervalos de confianza para las estimaciones de proporciones y las diferencias entre ellas
  • Capitulo 5.Inferencia Estadística II: Estimación por Intervalo de Confianza
  • Intervalos de confianza e intervalos de credibilidad para una proporción
  • Bioestadistica para no estadisticos. Intervalos de confianza
  • Understanding and interpreting confidence and credible intervals around effect estimates
• Herramientas:
  • Exact Confidence Interval for a Proportion:Herramienta online para calcular intervalos de confianza con el teorema de bayes
  • Límites de confianza para una proporción: Herramienta online para calcular intervalos de confianza.
• Código Python
  • statsmodels.stats.proportion.proportion_confint: Calculo en Pyhton de intervalos de confianza.
  • Confidence Interval for Population Proportion basic understanding in python

• Las pruebas PCR con elevada sensibilidad y especificidad, en condiciones de alta prevalencia o bajo prescripción médica, son fiables
• Pruebas diagnosticas: Explicación desde el punto de vista médico de Bayes con la especificidad y sensibilidad
• Falsos negativos en tests de COVID-19
• Commentary: Sensitivity, Specificity,and Predictive Values: Foundations,Pliabilities, and Pitfalls in Research and Practice
• Comentario: Sensibilidad, especificidad y valores predictivos: fundamentos,flexibilidades y dificultades en la investigación y la práctica: El documento anterior pero traducido al castellano.
• Prevalencia
  • Riesgo de contagio por COVID-19 en función del tipo de contacto y de la renta familiar
  • Prevalencia de infección por coronavirus SARS-CoV-2 en pacientes y profesionales de un hospital de media y larga estancia en España

• Introduction to Uncertainty in Deep Learning
• Calibrar modelos de machine learning
• A guide to model calibration

• Predicting Good Probabilities With Supervised Learning
• Neural Network Prediction Scores are not Probabilities
• How and When to Use a Calibrated Classification Model with scikit-learn
• scikit-learn
  • Probability Calibration curves
  • sklearn.calibration.calibration_curve
  • sklearn.calibration.CalibratedClassifierCV
• Regresión logística isotónica
• Calibración de Platt

• Bayesian Linear Regression in Python: Using Machine Learning to Predict Student Grades Part 2