# Classifying partially labeled data

I have 1D data for binary classification. Data includes about 10000 samples and each sample has the length of 120. Data is only partially labeled (for about 20% of samples, I am sure about the label) and I cannot label samples manually for thoes not labeled. Every ~60 samples come from same recording and therefore belong to the same class. I have tried k-mean clustering and in most cases results matches the labels. What semi-supervised learning algorithm is suitable for this problem?

There are 142 different recordings, each repeated ~60 times. About 20% (28 recording) are labeled. Samples are noisy so I need to average every 5-10 of them. I extracted 10 features based on amplitude of signal for clustering. I expect 60-80% of recordings belong to class I.

Based on that, you might try a $$k$$-nearest neighbor classifier. Basically, you classify each test point by finding the $$k$$ most similar labelled samples, and then using some kind of voting scheme among the corresponding $$k$$ labels. I anticipate this might give quite good results.
Alternatively, another way to use this is to use some kind of active learning algorithm to help you choose a small subset of the 10000 samples to manually label, with the goal of choosing those smartly so those additional labels help improve the performance of your classifier as much as possible. One standard approach is to train a classifier on the labelled instances, apply it to all the remaining instances, pick out the 20 instances that the classifier is least confident on, manually label those 20 instances, add them to the training set, and repeat. In your situation, a possible approach is to train a classifier on the labelled instances, apply it to all the remaining instances, from each cluster randomly sample a few instances whose predicted label disagrees with the majority label for that cluster, manually label all those instances, add them to the training set, and repeat. Or, you could train both a normal classifier and a $$k$$-nearest-neighbor classifier on the labelled samples, apply them to all remaining instances, find ones where the two classifiers disagree on their prediction, randomly sample 20 of them (possibly using a farthest-first heuristic to maximize their diversity), manually label them, and add them to the training set and repeat.