Estadística inferencial con Python: ejemplos de uso paso a paso

import pandas as pd import seaborn as sns import matplotlib.pyplot as plt import numpy as np

#Funciones def bootstrap_replicate_1d(data, func): """Generate bootstrap replicate of 1D data.""" bs_sample = np.random.choice(data, len(data)) return func(bs_sample) def draw_bs_reps(data, func, size=1): """Draw bootstrap replicates.""" # Initialize array of replicates: bs_replicates bs_replicates = np.empty(size) # Generate replicates for i in range(size): bs_replicates[i] = bootstrap_replicate_1d(data, func) return bs_replicates

plt.style.use('ggplot')

iris = sns.load_dataset('iris')

print(iris.sample(5))

print(iris.describe())

sns.boxplot(x='species', y='sepal_length', data=iris) plt.show()

versicolor_sepal_length = iris.query('species == "versicolor"')['sepal_length']

versicolor_sepal_length.values

sns.boxplot(data=versicolor_sepal_length, x=versicolor_sepal_length.values) plt.xlabel('Longitud de sépalo, mm') plt.title('Longitud de sépalo de Iris Versicolor') plt.show()

versicolor_sepal_length.describe()

vers_replicates = draw_bs_reps(versicolor_sepal_length.values, np.mean, size=10000)

ci = np.percentile(vers_replicates, [2.5, 97.5]) print(ci)

plt.hist(vers_replicates, bins=20) plt.xlabel('Longitud de sépalo, mm') plt.ylabel('Frecuencias') plt.title('Réplicas bootstrap de las medias') plt.axvline(x=ci[0], color='#395d90') plt.axvline(x=ci[1], color='#395d90') plt.fill_between([ci[0], ci[1]], 1700, color='#395d90', alpha=0.6) plt.show()

iris

sns.boxplot(x='species', y='sepal_length', data=iris) plt.show()

versicolor_sepal_length = iris.query('species == "versicolor"')['sepal_length'] virginica_sepal_length = iris.query('species == "virginica"')['sepal_length']

observed_diffs_means = np.mean(virginica_sepal_length.values - versicolor_sepal_length.values) print(observed_diffs_means)

observed_diffs_means = np.mean(virginica_sepal_length.values) - np.mean(versicolor_sepal_length.values) print(observed_diffs_means)

versicolor_virginica_concatenated = np.concatenate((versicolor_sepal_length.values, virginica_sepal_length.values))

mean_length = np.mean(versicolor_virginica_concatenated)

print(mean_length)

versicolor_shifted = versicolor_sepal_length.values - np.mean(versicolor_sepal_length.values) + mean_length virginica_shifted = virginica_sepal_length.values - np.mean(virginica_sepal_length.values) + mean_length

bs_replicates_versicolor = draw_bs_reps(versicolor_shifted, np.mean, size=100000) bs_replicates_virginica = draw_bs_reps(virginica_shifted, np.mean, size=100000)

bs_replicates = bs_replicates_virginica - bs_replicates_versicolor

plt.hist(bs_replicates) plt.axvline(x=observed_diffs_means, linestyle='--') plt.fill_between([observed_diffs_means, 0.9], 35000, color='#395d90', alpha=0.6) plt.text(0.7, 25000, 'P-value') plt.title('Distribución de diferencia de medias', size=14) plt.ylabel('Frecuencia') plt.xlabel('Diferencia de medias') plt.show()

p = np.sum(bs_replicates >= observed_diffs_means) / 100000

print(p)