ranked_batch_mode.py

from functools import partial

import numpy as np
from modAL.batch import uncertainty_batch_sampling
from modAL.models import ActiveLearner
from sklearn.datasets import load_iris
from sklearn.decomposition import PCA
from sklearn.neighbors import KNeighborsClassifier

# Set our RNG for reproducibility.
RANDOM_STATE_SEED = 123
np.random.seed(RANDOM_STATE_SEED)

iris = load_iris()
X_raw = iris['data']
y_raw = iris['target']

# Define our PCA transformer and fit it onto our raw dataset.
pca = PCA(n_components=2, random_state=RANDOM_STATE_SEED)
transformed_iris = pca.fit_transform(X=X_raw)

# Isolate the data we'll need for plotting.
x_component, y_component = transformed_iris[:, 0], transformed_iris[:, 1]

# Isolate our examples for our labeled dataset.
n_labeled_examples = X_raw.shape[0]
training_indices = np.random.randint(low=0, high=n_labeled_examples + 1, size=3)

X_train = X_raw[training_indices]
y_train = y_raw[training_indices]

# Isolate the non-training examples we'll be querying.
X_pool = np.delete(X_raw, training_indices, axis=0)
y_pool = np.delete(y_raw, training_indices, axis=0)

# Pre-set our batch sampling to retrieve 3 samples at a time.
BATCH_SIZE = 3
preset_batch = partial(uncertainty_batch_sampling, n_instances=BATCH_SIZE)

# Testing the cold-start
learner = ActiveLearner(
    estimator=KNeighborsClassifier(n_neighbors=3),
    query_strategy=preset_batch
)
cold_start_idx, cold_start_inst = learner.query(X_raw)
learner.teach(X_raw[cold_start_idx], y_raw[cold_start_idx])

# Specify our active learning model.
learner = ActiveLearner(
    estimator=KNeighborsClassifier(n_neighbors=3),
    X_training=X_train,
    y_training=y_train,
    query_strategy=preset_batch
)

predictions = learner.predict(X_raw)

# Record our learner's score on the raw data.
unqueried_score = learner.score(X_raw, y_raw)

# Pool-based sampling
N_RAW_SAMPLES = 20
N_QUERIES = N_RAW_SAMPLES // BATCH_SIZE

for index in range(N_QUERIES):
    query_index, query_instance = learner.query(X_pool)

    # Teach our ActiveLearner model the record it has requested.
    X, y = X_pool[query_index], y_pool[query_index]
    learner.teach(X=X, y=y)

    # Remove the queried instance from the unlabeled pool.
    X_pool = np.delete(X_pool, query_index, axis=0)
    y_pool = np.delete(y_pool, query_index)

    # Calculate and report our model's accuracy.
    model_accuracy = learner.score(X_raw, y_raw)

predictions = learner.predict(X_raw)