def pipeline(chip, tx, ty, date, acquired, cfg):
ctx = {
'tx': tx,
'ty': ty,
'cx': first(chip),
'cy': second(chip),
'date': date,
'acquired': acquired
}
return thread_first(
ctx,
partial(segments, cfg=cfg),
segments_filter,
partial(segaux.aux, cfg=cfg),
segaux.aux_filter,
segaux.combine,
segaux.unload_segments,
segaux.unload_aux,
segaux.add_training_dates,
add_average_reflectance,
segaux.training_format,
#segaux.log_chip,
segaux.exit_pipeline)
def segments():
return thread_first(
request.json,
partial(exception_handler,
http_status=500,
name='log_request',
fn=log_request),
partial(exception_handler,
http_status=400,
name='parameters',
fn=parameters),
partial(exception_handler,
http_status=500,
name='timeseries',
fn=partial(timeseries, cfg=cfg)),
partial(exception_handler,
http_status=500,
name='nodata',
fn=partial(nodata, cfg=cfg)),
partial(exception_handler,
http_status=500,
name='detection',
fn=partial(detection, cfg=cfg)),
partial(exception_handler,
http_status=500,
name='delete',
fn=partial(delete, cfg=cfg)),
partial(exception_handler,
http_status=500,
name='save',
fn=partial(save, cfg=cfg)), respond)
def load_data(ctx, cfg):
return assoc(
ctx, 'data',
thread_first(
ctx, partial(segments, cfg=cfg), partial(segaux.aux,
cfg=cfg), segaux.combine,
segaux.unload_segments, segaux.unload_aux, extract_segments,
partial(segaux.prediction_dates,
month=get("month", ctx),
day=get("day",
ctx)), segaux.average_reflectance, reformat))
def review_to_tagged_sents(sents):
cluster_distances = cytoolz.thread_first(sents, clizer.vectorize_sents,
clustering.normalize_vecs,
clizer.clusterer.transform)
clusters_for_sents = np.argmin(cluster_distances, axis=1)
res = []
for i, sent in enumerate(sents):
res.append([topic_tags[c] for c in clusters_for_sents[:i + 1][-4:]] +
sent.lower().split())
return res
def tiles():
return thread_first(request.json,
partial(exception_handler, http_status=500, name='log_request', fn=log_request),
partial(exception_handler, http_status=400, name='parameters', fn=parameters),
partial(exception_handler, http_status=500, name='data', fn=partial(data, cfg=cfg)),
partial(exception_handler, http_status=500, name='statistics', fn=statistics),
partial(exception_handler, http_status=500, name='randomize', fn=partial(randomize, cfg=cfg)),
partial(exception_handler, http_status=500, name='split_data', fn=split_data),
partial(exception_handler, http_status=500, name='sample', fn=partial(sample, cfg=cfg)),
partial(exception_handler, http_status=500, name='train', fn=partial(train, cfg=cfg)),
partial(exception_handler, http_status=500, name='save', fn=partial(save, cfg=cfg)),
respond)
def likelihoods_by_sentence(sents):
sent_cluster_distribs = cytoolz.thread_first(sents, clizer.vectorize_sents,
clustering.normalize_vecs,
clizer.clusterer.transform,
(normal_lik, .5),
clustering.normalize_dists)
hard_assignments = np.argmax(sent_cluster_distribs, axis=1)
# print(hard_assignments)
return [
assignment in np.argsort(
get_topic_distribution(
clizer=clizer,
target_dist=clizer.target_dists['best'],
sent_cluster_distribs=sent_cluster_distribs[:i],
new_dists_opts=np.eye(clizer.n_clusters)))[:3]
for i, assignment in enumerate(hard_assignments)
]
def predictions_route():
return thread_first(
request.json,
partial(exception_handler,
http_status=500,
name='log_request',
fn=log_request),
partial(exception_handler,
http_status=400,
name='parameters',
fn=parameters),
partial(exception_handler,
http_status=500,
name='load_model',
fn=partial(load_model, cfg=cfg)),
partial(exception_handler,
http_status=500,
name='load_data',
fn=partial(load_data, cfg=cfg)),
partial(exception_handler,
http_status=500,
name='group_data',
fn=group_data),
partial(exception_handler, http_status=500, name='matrix', fn=matrix),
partial(exception_handler,
http_status=500,
name='predictions',
fn=partial(predictions, cfg=cfg)),
partial(exception_handler,
http_status=500,
name='default_predictions',
fn=default_predictions),
partial(exception_handler,
http_status=500,
name='delete',
fn=partial(delete, cfg=cfg)),
partial(exception_handler,
http_status=500,
name='save',
fn=partial(save, cfg=cfg)), respond)
def get_topic_seq(sents):
cluster_distances = cytoolz.thread_first(sents, clizer.vectorize_sents,
clustering.normalize_vecs,
clizer.clusterer.transform)
return np.argmin(cluster_distances, axis=1)