Campionare dalla stessa distribuzione di probabilità

Molte organizzazioni, come lo U.S. Census, pubblicano campioni dei dati raccolti sui cittadini. Questi insiemi di dati vengono prima anonimizzati con varie tecniche e poi si rilascia una piccola frazione, dall’1% al 5%, per consentire le analisi. Il campionamento è noto per preservare le caratteristiche statistiche dei dati, permettendo di studiare e comprendere la popolazione sottostante.

In questo esercizio, anonimizzerai la colonna department dell’insieme di dati IBM HR campionando dalle distribuzioni del dataset originale.

Il dataset è stato caricato come hr.

Questo esercizio fa parte del corso

Riservatezza dei dati e anonimizzazione in Python

Visualizza il corso

Istruzioni dell'esercizio

Ottieni le frequenze relative di ciascun valore univoco nella colonna department.
Estrai le probabilità da counts e salvale in una variabile chiamata distributions.
Campiona dalle distribuzioni di probabilità calcolate in precedenza. La dimensione del campione deve essere uguale alla dimensione del dataset hr.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

# Obtain the probability distribution counts 
counts = ____

# Get the probability distribution values 
distributions = ____

# Sample from the calculated probability distributions
hr['department'] = np.random.choice(counts.index, 
                                    p=____, 
                                    size=len(____))

# See the resulting DataFrame
print(hr.head())

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Riservatezza dei dati e anonimizzazione in Python

AvançadoNível de habilidade

4.9+

Inizia il corso gratis

Get ready to apply anonymization techniques such as data suppression, masking, synthetic data generation, and generalization. In this chapter, you’ll learn how to distinguish between sensitive and non-sensitive personally identifiable information (PII), quasi-identifiers, and the basics of the GDPR. You'll also encounter real-life examples of what can go wrong if you don't follow these best practices.

Exercise 1: What's private, and why do we care?Exercise 2: Privacy is power Exercise 3: Is it sensitive or non-sensitive?Exercise 4: Suppression of sensitive attributes Exercise 5: Data masking and data generation with Faker Exercise 6: Masking sensitive PII Exercise 7: Removing names with faker Exercise 8: Anonymizing with data generalization Exercise 9: Reducing identification risk with generalization Exercise 10: Data aggregation and data generalization Exercise 11: Top and bottom coding White House salaries

Discover how to anonymize data by sampling from datasets following the probability distribution of the columns. You’ll then learn how to apply the k-anonymity privacy model to prevent linkage or re-identification attacks and use hierarchies to perform data generalization in categorical variables.

Exercise 1: Anonimizzare i dati categoriali Exercise 2: Esplora la distribuzione dei dati Exercise 3: Campionare dalla stessa distribuzione di probabilità

Esercizio in corso

Exercise 4: Anonimizzare i dati continui Exercise 5: Distribuzioni diverse Exercise 6: Campionare dalla migliore distribuzione continua Exercise 7: Introduzione alla k-anonymity Exercise 8: Attributi di privacy Exercise 9: Generalizzare in intervalli Exercise 10: Generalizzare i dati usando le gerarchie Exercise 11: Usare gerarchie per dati categorici Exercise 12: Applicare la k-anonimizzazione a un insieme di dati

Learn about differential privacy, the model used by major technology companies such as Apple, Google, and Uber. In this chapter, you’ll explore data by generating private histograms and computing private averages in data. You’ll also create differentially private machine learning models that allow businesses to increase the utility of their data.

Exercise 1: Introduction to differential privacy Exercise 2: Epsilon (ϵ): the magic number Exercise 3: Histograms with differential privacy Exercise 4: Privacy budgets Exercise 5: Using privacy budgets Exercise 6: When no budget is left Exercise 7: Exploring data with a privacy budget accountant Exercise 8: Differentially private machine learning models Exercise 9: Build a differentially private classifier Exercise 10: Predicting salaries Exercise 11: Differentially private clustering models Exercise 12: Pre-processing data Exercise 13: Segmenting customers

In this final chapter, you’ll learn how to apply dimensionality reduction methods such as principal component analysis (PCA) to anonymize large multi-column datasets. You’ll then use Faker to generate realistic and consistent datasets, and scikit-learn to create synthetic datasets that follow a normal distribution. Lastly, you’ll tie everything you learned in this course together as you combine multiple techniques to safely release datasets to the public.

Exercise 1: PCA for anonymization Exercise 2: Anonymization of high-dimensional data Exercise 3: Data masking with PCA Exercise 4: Generating realistic datasets with Faker Exercise 5: Consistent synthetic dataset Exercise 6: Datasets with the same probabilistic distribution Exercise 7: Creating synthetic datasets using scikit-learn Exercise 8: Generating datasets for classification Exercise 9: Generating datasets for clustering Exercise 10: Safely release datasets to the public Exercise 11: Exploring and pseudonymizing a dataset Exercise 12: Preparing employee data for safe release Exercise 13: Great work!