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 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 learn(self, setis):
# Determine the original columns to use.
feature_cols = self.fs.all_col_names
# Convert SETI inputs into X and y format.
y = []
X = []
for setie in setis:
if setie.for_holdout:
self.holdout_setis.append(setie)
continue
x = seti.float_feature_vector(self.fs, setie)
y.append(setie.label)
X.append(x)
lm = LinearRegression()
lm.fit(X, y)
#print lm.intercept_
col_and_coeffs = zip(feature_cols, lm.coef_)
model = {}
model[':'] = float(lm.intercept_)
for (col, coeff) in col_and_coeffs:
model[col] = coeff
self.model = dict([(k, float(v)) for k, v in model.iteritems()])
return model
