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 testLearn():
orig_cols = ["gender", "height"]
s0 = seti.create_seti(1.0, bfs=[("gender", "m")], cfs=[("height", 6.0)])
s1 = seti.create_seti(0.0, bfs=[("gender", "f")], cfs=[("height", 3.0)])
s1.for_holdout = True
setis = [s0, s1]
fs = feature_selector.FeatureSelect()
fs.generate_feature_map(orig_cols, setis)
fvs = [[0, 0, 6.0], [0, 1, 3.0]]
l = learner.Learner(fs)
l.learn(setis)
print l.stats()
def testFVSimple():
orig_cols = ['gender', 'height']
s0 = seti.create_seti(1.0, bfs=[('gender', 'm')], cfs=[('height', 6.0)])
s1 = seti.create_seti(0.0, bfs=[('gender', 'f')], cfs=[('height', 3.0)])
setis = [s0, s1]
fs = feature_selector.FeatureSelect()
fs.generate_feature_map(orig_cols, setis)
assertEquals(['gender_MISSING', 'gender_f', 'height'], fs.all_col_names)
fvs = [[0, 0, 6.0], [0, 1, 3.0]]
for i in xrange(len(setis)):
setie = setis[i]
fv = fvs[i]
assertEquals(fv, seti.float_feature_vector(fs, setie))
def testFeatureSelectorMissingColumn():
orig_cols = ['gender', 'height']
s0 = seti.create_seti(1.0, bfs=[], cfs=[('height', 6.0)])
s1 = seti.create_seti(0.0, bfs=[('gender', 'f')], cfs=[])
s2 = seti.create_seti(0.0, bfs=[('gender', 'm')], cfs=[])
setis = [s0, s1, s2]
fs = feature_selector.FeatureSelector()
fs.build_feature_map(setis)
features = ['height', 'gender:m', 'gender:f', 'gender:metro']
indices = [0, 2, 1, None]
for i in xrange(len(features)):
index, err = fs.get_index(features[i])
assertEquals(indices[i], index)
if index is None:
assert err != ''
else:
assert err == None
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))
def testFVManyCategorical():
s0 = seti.create_seti(1.0, bfs=[('dir', 'north')], cfs=[('dist', 6.0)])
s1 = seti.create_seti(1.0, bfs=[('dir', 'south')], cfs=[('dist', 5.0)])
s2 = seti.create_seti(1.0, bfs=[('dir', 'east')], cfs=[('dist', 4.0)])
s3 = seti.create_seti(1.0, bfs=[('dir', 'west')], cfs=[('dist', 3.0)])
s4 = seti.create_seti(1.0, bfs=[], cfs=[('dist', 2.0)])
setis = [s0, s1, s2, s3, s4]
fvs = [[0, 0, 0, 0, 6.0], [0, 1, 0, 0, 5.0], [0, 0, 1, 0, 4.0],
[0, 0, 0, 1, 3.0], [1, 0, 0, 0, 2.0]]
orig_cols = ['dir', 'dist']
fs = feature_selector.FeatureSelect()
fs.generate_feature_map(orig_cols, setis)
#l = learner.Learner(fs)
assertEquals(
['dir_MISSING', 'dir_south', 'dir_east', 'dir_west', 'dist'],
fs.all_col_names)
for i in xrange(len(setis)):
setie = setis[i]
fv = fvs[i]
assertEquals(fv, seti.float_feature_vector(fs, setie))
def testRun():
# Setup feature selector and such.
orig_cols = ['gender', 'height']
s0 = seti.create_seti(1.0, bfs=[('gender', 'm')], cfs=[('height', 6.0)])
s1 = seti.create_seti(0.0, bfs=[('gender', 'f')], cfs=[('height', 3.0)])
setis = [s0, s1]
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')
run_pipeline.run([model_config], setis)
model = {
'gender_MISSING': 0.0,
'gender_f': -0.099999999999999992,
':': -0.7999999999999996,
'height': 0.29999999999999993
}
# Test model gets created and loaded.
# Test that we can score one example.
ss = seti_server.make_from_config([model_config])
# Test the learned model works.
#print 'Learned model: '
#print ss.model_map['v0'].learned_model
s2 = seti.create_seti(5.0, bfs=[('gender', 'm')], cfs=[('height', 2.0)])
val0 = model[':'] + model['gender_MISSING'] * 0 + model['gender_f'] * 0 + model['height'] * 2.0
assertFloatEquals(val0, ss.score(s2))
# Test the memorized model works. Destroy the learned model.
ss.model_map['v0'].learned_model = {}
val1 = model[':'] + model['gender_MISSING'] * 0 + model['gender_f'] * 1 + model['height'] * 3.0
assertFloatEquals(val1, ss.score(s1))