def testScoreWithMemorizedModel():
orig_cols = ['gender', 'height']
memorized_cols = ['gender']
model_config = model_cfg.ModelConfig(
'v1', 'tmp/learned_model_v1.csv', 'tmp/memorized_model_v1.csv',
model_cfg.ColsCfg(orig_cols, memorized_cols),
'tmp/feature_map_v1.csv', 'tmp/feature_map2_v1.csv')
s0 = seti.create_seti(5.0, bfs=[('gender', 'm')], cfs=[('height', 6.0)])
s1 = seti.create_seti(7.0, bfs=[('gender', 'f')], cfs=[('height', 6.0)])
setis = [s0, s1]
# Empty learned model.
lm = model_exporter.LearnedModel()
lm.write_model({}, 'tmp/learned_model_v1.csv')
# Set up memorized model.
fs, _ = training_data.write_feature_maps_from_seti(model_config, setis)
mem = model_exporter.Memorizer(fs, model_config)
memorized_model = mem.create_model(setis)
mm = model_exporter.MemorizedModel()
mm.write_features(memorized_model, model_config.memorized_model_loc)
ss = seti_server.make_from_config([model_config])
ss.model_map['v1'].learned_model = {}
s2 = seti.create_seti(7.0, bfs=[('gender', 'f')])
assertFloatEquals(7.0, ss.score(s2))
def run(model_configs, setis):
# Determine which setis are for holdout and which are for training.
for seti in setis:
if random.random() < 0.1:
seti.for_holdout = True
for model_config in model_configs:
# - Look at the occurence of features and their index.
fs, fs2 = training_data.write_feature_maps_from_seti(model_config, setis)
print 'Learning model %s' % (model_config.name)
# - Memorize the examples.
mem = model_exporter.Memorizer(fs, model_config)
memorized_model = mem.create_model(setis)
mm = model_exporter.MemorizedModel()
mm.write_features(memorized_model, model_config.memorized_model_loc)
# - Build a model for unmemorized examples.
l = learner.Learner(fs2)
learned_model = l.learn(setis)
lm = model_exporter.LearnedModel()
lm.write_model(learned_model, model_config.learned_model_loc)
print 'Wrote learned model to: %s' % (model_config.learned_model_loc)
print 'Model performed as: %s' % (str(l.stats()))
#print l.stats()
# Write the model to a file.
print 'Finished model generation for %s' % (model_config.name)
def testScoreWithLearnedModel():
model = {
'gender_MISSING': 0.0,
'gender_f': -0.099999999999999992,
':': -0.7999999999999996,
'height': 0.29999999999999993
}
lm = model_exporter.LearnedModel()
lm.write_model(model, 'tmp/learned_model.csv')
mm = model_exporter.MemorizedModel()
mm.write_features([], 'tmp/memorized_model.csv')
# Setup feature selector and such.
orig_cols = ['gender', 'height']
s0 = seti.create_seti(5.0, bfs=[('gender', 'm')], cfs=[('height', 6.0)])
s1 = seti.create_seti(3.0, bfs=[('gender', 'f')], cfs=[('height', 3.0)])
setis = [s0, s1]
model_types = [model_cfg.LINEAR_REGRESSION, model_cfg.LOGISTIC_REGRESSION]
transforms = [lambda x: x, lambda x: 1 / (1 + math.exp(-x))]
# Test the actual model.
for mIndex in xrange(len(model_types)):
model_config = model_cfg.ModelConfig(
'v0', 'tmp/learned_model.csv', 'tmp/memorized_model.csv',
model_cfg.ColsCfg(orig_cols, orig_cols),
'tmp/feature_map_v0.csv', 'tmp/feature_map2_v0.csv',
model_type=model_types[mIndex])
training_data.write_feature_maps_from_seti(model_config, setis)
ss = seti_server.make_from_config([model_config])
w0 = model[':'] + model['gender_MISSING'] * 0 + model['gender_f'] * 0 + model['height'] * 6.0
w1 = model[':'] + model['gender_MISSING'] * 0 + model['gender_f'] * 1 + model['height'] * 3.0
wants = [w0, w1]
for i in xrange(len(setis)):
setie = setis[i]
want_after_transform = transforms[mIndex](wants[i])
assertEquals(want_after_transform, ss.score(setie))
