Semi-supervised Classification on a Text Dataset

In this example, semi-supervised classifiers are trained on the 20 newsgroups dataset (which will be automatically downloaded).

You can adjust the number of categories by giving their names to the dataset loader or setting them to None to get all 20 of them.

Out:

2823 documents
5 categories

Supervised SGDClassifier on 100% of the data:
Number of training samples: 2117
Unlabeled samples in training set: 0
Micro-averaged F1 score on test set: 0.898
----------

Supervised SGDClassifier on 20% of the training data:
Number of training samples: 433
Unlabeled samples in training set: 0
Micro-averaged F1 score on test set: 0.790
----------

SelfTrainingClassifier on 20% of the training data (rest is unlabeled):
Number of training samples: 2117
Unlabeled samples in training set: 1684
End of iteration 1, added 1099 new labels.
End of iteration 2, added 212 new labels.
End of iteration 3, added 62 new labels.
End of iteration 4, added 21 new labels.
End of iteration 5, added 4 new labels.
End of iteration 6, added 3 new labels.
End of iteration 7, added 7 new labels.
End of iteration 8, added 2 new labels.
End of iteration 9, added 5 new labels.
End of iteration 10, added 2 new labels.
Micro-averaged F1 score on test set: 0.851
----------

LabelSpreading on 20% of the data (rest is unlabeled):
Number of training samples: 2117
Unlabeled samples in training set: 1684
/home/circleci/project/sklearn/utils/validation.py:593: FutureWarning: np.matrix usage is deprecated in 1.0 and will raise a TypeError in 1.2. Please convert to a numpy array with np.asarray. For more information see: https://numpy.org/doc/stable/reference/generated/numpy.matrix.html
  warnings.warn(
/home/circleci/project/sklearn/utils/validation.py:593: FutureWarning: np.matrix usage is deprecated in 1.0 and will raise a TypeError in 1.2. Please convert to a numpy array with np.asarray. For more information see: https://numpy.org/doc/stable/reference/generated/numpy.matrix.html
  warnings.warn(
Micro-averaged F1 score on test set: 0.678
----------

import numpy as np

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.preprocessing import FunctionTransformer
from sklearn.linear_model import SGDClassifier
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.semi_supervised import SelfTrainingClassifier
from sklearn.semi_supervised import LabelSpreading
from sklearn.metrics import f1_score

# Loading dataset containing first five categories
data = fetch_20newsgroups(
    subset="train",
    categories=[
        "alt.atheism",
        "comp.graphics",
        "comp.os.ms-windows.misc",
        "comp.sys.ibm.pc.hardware",
        "comp.sys.mac.hardware",
    ],
)
print("%d documents" % len(data.filenames))
print("%d categories" % len(data.target_names))
print()

# Parameters
sdg_params = dict(alpha=1e-5, penalty="l2", loss="log")
vectorizer_params = dict(ngram_range=(1, 2), min_df=5, max_df=0.8)

# Supervised Pipeline
pipeline = Pipeline(
    [
        ("vect", CountVectorizer(**vectorizer_params)),
        ("tfidf", TfidfTransformer()),
        ("clf", SGDClassifier(**sdg_params)),
    ]
)
# SelfTraining Pipeline
st_pipeline = Pipeline(
    [
        ("vect", CountVectorizer(**vectorizer_params)),
        ("tfidf", TfidfTransformer()),
        ("clf", SelfTrainingClassifier(SGDClassifier(**sdg_params), verbose=True)),
    ]
)
# LabelSpreading Pipeline
ls_pipeline = Pipeline(
    [
        ("vect", CountVectorizer(**vectorizer_params)),
        ("tfidf", TfidfTransformer()),
        # LabelSpreading does not support dense matrices
        ("todense", FunctionTransformer(lambda x: x.todense())),
        ("clf", LabelSpreading()),
    ]
)


def eval_and_print_metrics(clf, X_train, y_train, X_test, y_test):
    print("Number of training samples:", len(X_train))
    print("Unlabeled samples in training set:", sum(1 for x in y_train if x == -1))
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_test)
    print(
        "Micro-averaged F1 score on test set: %0.3f"
        % f1_score(y_test, y_pred, average="micro")
    )
    print("-" * 10)
    print()


if __name__ == "__main__":
    X, y = data.data, data.target
    X_train, X_test, y_train, y_test = train_test_split(X, y)

    print("Supervised SGDClassifier on 100% of the data:")
    eval_and_print_metrics(pipeline, X_train, y_train, X_test, y_test)

    # select a mask of 20% of the train dataset
    y_mask = np.random.rand(len(y_train)) < 0.2

    # X_20 and y_20 are the subset of the train dataset indicated by the mask
    X_20, y_20 = map(
        list, zip(*((x, y) for x, y, m in zip(X_train, y_train, y_mask) if m))
    )
    print("Supervised SGDClassifier on 20% of the training data:")
    eval_and_print_metrics(pipeline, X_20, y_20, X_test, y_test)

    # set the non-masked subset to be unlabeled
    y_train[~y_mask] = -1
    print("SelfTrainingClassifier on 20% of the training data (rest is unlabeled):")
    eval_and_print_metrics(st_pipeline, X_train, y_train, X_test, y_test)

    print("LabelSpreading on 20% of the data (rest is unlabeled):")
    eval_and_print_metrics(ls_pipeline, X_train, y_train, X_test, y_test)