Agrupación de muestra de artículos utilizando kmeans y trncatedsvd
# Perform the necessary imports
from sklearn.decomposition import TruncatedSVD
from sklearn.cluster import KMeans
from sklearn.pipeline import make_pipeline
# Create a TruncatedSVD instance: svd
svd = TruncatedSVD(n_components=50)
# Create a KMeans instance: kmeans
kmeans = KMeans(n_clusters=6)
# Create a pipeline: pipeline
pipeline = make_pipeline(svd, kmeans)
# Import pandas
import pandas as pd
# Fit the pipeline to articles
pipeline.fit(articles)
# Calculate the cluster labels: labels
labels = pipeline.predict(articles)
# Create a DataFrame aligning labels and titles: df
df = pd.DataFrame({'label': labels, 'article': titles})
# Display df sorted by cluster label
print(df.sort_values('label'))
josh.ipynb