fetch_rcv1_v2

mlquantify.datasets.fetch_rcv1_v2(*, data_home=None, download_if_missing=True, return_X_y=False, as_frame=False, n_retries=3, delay=1.0, protocol=None, n_samples=1000, sample_size=500, random_state=None)

RCV1-v2: Reuters news topics (text, sparse TF-IDF, multilabel).

804414 Reuters news stories represented as 47236-dimensional cosine-normalised TF-IDF vectors, annotated with 103 hierarchical topic labels (multi-label). Uses scikit-learn’s loader when available; otherwise downloads the raw token/label source files.

Quantification: standard high-dimensional text-quant corpus; multilabel – pick a topic column before a protocol.

Documents	804414
Features	47236 (sparse TF-IDF)
Classes	103 topics (multilabel)

Source: https://scikit-learn.org/stable/modules/generated/sklearn.datasets.fetch_rcv1.html

Parameters:

data_homestr or path-like, default=None

Folder used to cache the downloaded file(s); defaults to _data/ next to the package.

download_if_missingbool, default=True

If False, raise instead of downloading when the cache is empty.

return_X_ybool, default=False

Return (X, y) instead of a Bunch.

as_framebool, default=False

Return .data as a DataFrame, .target as a Series, and a combined .frame (features + a "target" column).

n_retriesint, default=3

Number of download attempts before giving up.

delayfloat, default=1.0

Seconds to wait between attempts.

protocol{None, “app”, “npp”, “upp”, “ppp”} or mlquantify protocol, default=None

If set, draw evaluation sample-bags with an mlquantify protocol; the Bunch then also has .samples (index bags into .data), .prevalences and .protocol.

n_samplesint, default=1000

Number of prevalence points (bags) generated by the protocol.

sample_sizeint, default=500

Instances per bag (the protocol batch_size).

random_stateint or None, default=None

Seed forwarded to the protocol.

Returns:

dataBunch

Dictionary-like object. Attributes: data (features), target (labels), feature_names, target_names, DESCR; frame when as_frame=True; and samples / prevalences / protocol when protocol is set.

(X, y)tuple

Returned instead when return_X_y=True.

References

Lewis, D. et al. (2004). RCV1: A new benchmark collection. JMLR 5.

Examples

>>> b = fetch_rcv1_v2(); b.data.shape  
(804414, 47236)  sparse