Clustering Wikipedia

Hi, in this article i’ll make a simple clustering example using wikipedia.

You can access full code, here: https://drive.google.com/drive/folders/1FKAqwAvaSmEt0jzL3lHu5qQGEcw4FQGS?usp=sharing

# 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 as pd 
from scipy.sparse import csc_matrix
documents = pd.read_csv("wikipedia-vectors.txt")
documents.drop(columns="Unnamed: 0",inplace=True)

titles = documents.columns
articles = csc_matrix(documents.values).T

 

# 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(by="label"))