def predict_autosequence(config, context, predict_index, fit_model=True, update_column=None):
if len(context.train_index & predict_index):
logging.warning("Train and predict indices overlap...")
x, y = None, None
if fit_model:
x, y = fit(config, context)
logging.debug(x.columns)
logging.debug(config.model.coef_)
ctx = context.copy()
ps = []
for i in predict_index:
ctx.data = context.data
x = get_x(config, ctx)
predict_x = x.reindex([i])
# make actual predictions
p = config.model.predict(predict_x.values)
if update_column is not None:
ctx.data[update_column][i] = p[0]
ps.append(p[0])
try:
preds = Series(ps, index=predict_index)
except:
preds = DataFrame(ps, index=predict_index)
# prediction post-processing
if config.prediction is not None:
context.data[config.predictions_name] = preds
preds = build_target_safe(config.prediction, context)
preds = preds.reindex(predict_index)
preds.name = ''
return preds, x, y
def evaluate(config, ctx, predict_index,
predict_method=None, predict_update_column=None):
if predict_method is None:
result = predict(config, ctx, predict_index)
else:
# TODO: hacky!
result = predict_method(config, ctx, predict_index, update_column=predict_update_column)
preds = result['predictions']
y = result['actuals']
try:
if config.actual is not None:
actuals = build_target_safe(config.actual, ctx).reindex(predict_index)
else:
actuals = y.reindex(predict_index)
#TODO: HACK -- there may not be an actual attribute on the config
except AttributeError:
actuals = y.reindex(predict_index)
scores = {}
for metric in config.metrics:
name = get_metric_name(metric)
if hasattr(metric, 'score'):
scores[name] = metric.score(actuals, preds)
else:
scores[name] = metric(actuals, preds)
return scores, result
def predict(config, context, predict_index, fit_model=True, model_name=None):
if len(context.train_index & predict_index):
logging.warning("Train and predict indices overlap...")
x, y = None, None
if model_name:
config.model = context.store.load(model_name)
if not model_name and fit_model:
x, y = fit(config, context)
# TODO: possible to have x loaded without new prediction rows
if x is None:
# rebuild just the necessary x:
ctx = context.copy()
ctx.data = context.data.ix[predict_index]
x = get_x(config, ctx)
try:
# we may or may not have y's in predict context
# we get them if we can for metrics and reporting
y = get_y(config, ctx)
except KeyError:
pass
logging.debug(x.columns)
predict_x = x.reindex(predict_index)
logging.info("Making predictions... ")
# make actual predictions
ps = config.model.predict(predict_x.values)
try:
preds = Series(ps, index=predict_x.index)
except:
preds = DataFrame(ps, index=predict_x.index)
logging.info("...done.")
# prediction post-processing
if config.prediction is not None:
old = context.data
context.data = context.data.reindex(predict_x.index)
context.data[config.predictions_name] = preds
preds = build_target_safe(config.prediction, context)
preds = preds.reindex(predict_x.index)
context.data = old
preds.name = ''
actuals = y.reindex(predict_index)
# TODO: handle multi-variate predictions
predict_x['predictions'] = preds
predict_x['actuals'] = actuals
config.update_reporters_with_predictions(context, predict_x, actuals, preds)
return predict_x
def build_target(self):
y, ff = build_target_safe(self.target, self.data)
self.y = y
self.negatives = y[~y.astype('bool')].index
self.positives = y[y.astype('bool')].index
def get_y(config, context):
return build_target_safe(config.target, context)
