def _fit(self, x, y, z, context=None):
if context is None:
context = np.empty((x.shape[0], 0))
x_dim = x.shape[1]
z_dim = z.shape[1]
context_dim = context.shape[1]
treatment_model = self._treatment_model((context_dim + z_dim, ))
response_model = keras.models.Sequential([
keras.layers.Dense(128,
activation='relu',
input_shape=(context_dim + x_dim, )),
keras.layers.Dropout(0.17),
keras.layers.Dense(64, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(32, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(1)
])
self._model = DeepIVEstimator(
n_components=10,
# Number of gaussians in the mixture density networks)
m=lambda _z, _context: treatment_model(
keras.layers.concatenate([_z, _context])),
# Treatment model
h=lambda _t, _context: response_model(
keras.layers.concatenate([_t, _context])),
# Response model
n_samples=1)
t0 = time.time()
self._model.fit(y, x, context, z)
return time.time() - t0
def test_deepiv(self):
X = TestPandasIntegration.df[TestPandasIntegration.features]
Y = TestPandasIntegration.df[TestPandasIntegration.outcome]
T = TestPandasIntegration.df[TestPandasIntegration.cont_treat]
Z = TestPandasIntegration.df[TestPandasIntegration.instrument]
# Test DeepIV
treatment_model = keras.Sequential([
keras.layers.Dense(128, activation='relu', input_shape=(3, )),
keras.layers.Dropout(0.17),
keras.layers.Dense(64, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(32, activation='relu'),
keras.layers.Dropout(0.17)
])
response_model = keras.Sequential([
keras.layers.Dense(128, activation='relu', input_shape=(3, )),
keras.layers.Dropout(0.17),
keras.layers.Dense(64, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(32, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(1)
])
est = DeepIVEstimator(
n_components=
10, # Number of gaussians in the mixture density networks)
m=lambda z, x: treatment_model(keras.layers.concatenate([z, x])
), # Treatment model
h=lambda t, x: response_model(keras.layers.concatenate([t, x])
), # Response model
n_samples=1 # Number of samples used to estimate the response
)
est.fit(Y, T, X=X, Z=Z)
treatment_effects = est.effect(X)
def test_deepiv_shape(self):
"""Make sure that arbitrary sizes for t, z, x, and y don't break the basic operations."""
for _ in range(5):
d_t = np.random.choice(range(1, 4)) # number of treatments
d_z = np.random.choice(range(1, 4)) # number of instruments
d_x = np.random.choice(range(1, 4)) # number of features
d_y = np.random.choice(range(1, 4)) # number of responses
n = 500
# simple DGP only for illustration
x = np.random.uniform(size=(n, d_x))
z = np.random.uniform(size=(n, d_z))
p_x_t = np.random.uniform(size=(d_x, d_t))
p_z_t = np.random.uniform(size=(d_z, d_t))
t = x @ p_x_t + z @ p_z_t
p_xt_y = np.random.uniform(size=(d_x * d_t, d_y))
y = (x.reshape(n, -1, 1) * t.reshape(n, 1, -1)).reshape(n, -1) @ p_xt_y
# Define the treatment model neural network architecture
# This will take the concatenation of one-dimensional values z and x as input,
# so the input shape is (d_z + d_x,)
# The exact shape of the final layer is not critical because the Deep IV framework will
# add extra layers on top for the mixture density network
treatment_model = keras.Sequential([keras.layers.Dense(128, activation='relu', input_shape=(d_z + d_x,)),
keras.layers.Dropout(0.17),
keras.layers.Dense(64, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(32, activation='relu'),
keras.layers.Dropout(0.17)])
# Define the response model neural network architecture
# This will take the concatenation of one-dimensional values t and x as input,
# so the input shape is (d_t + d_x,)
# The output should match the shape of y, so it must have shape (d_y,) in this case
# NOTE: For the response model, it is important to define the model *outside*
# of the lambda passed to the DeepIvEstimator, as we do here,
# so that the same weights will be reused in each instantiation
response_model = keras.Sequential([keras.layers.Dense(128, activation='relu', input_shape=(d_t + d_x,)),
keras.layers.Dropout(0.17),
keras.layers.Dense(64, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(32, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(d_y)])
deepIv = DeepIVEstimator(n_components=10, # number of gaussians in our mixture density network
m=lambda z, x: treatment_model(
keras.layers.concatenate([z, x])), # treatment model
h=lambda t, x: response_model(keras.layers.concatenate([t, x])), # response model
n_samples=1, # number of samples to use to estimate the response
use_upper_bound_loss=False, # whether to use an approximation to the true loss
# number of samples to use in second estimate of the response
# (to make loss estimate unbiased)
n_gradient_samples=1,
# Keras optimizer to use for training - see https://keras.io/optimizers/
optimizer='adam')
deepIv.fit(Y=y, T=t, X=x, Z=z)
# do something with predictions...
deepIv.predict(T=t, X=x)
deepIv.effect(x, np.zeros_like(t), t)
def test_deepiv_models(self):
n = 2000
s1 = 2
s2 = 2
e = np.random.uniform(low=-0.5, high=0.5, size=(n, 1))
z = np.random.uniform(size=(n, 1))
x = np.random.uniform(size=(n, 1)) + e
p = x + z * e + np.random.uniform(size=(n, 1))
y = p * x + e
losses = []
marg_effs = []
z_fresh = np.random.uniform(size=(n, 1))
e_fresh = np.random.uniform(low=-0.5, high=0.5, size=(n, 1))
x_fresh = np.random.uniform(size=(n, 1)) + e_fresh
p_fresh = x_fresh + z_fresh * e_fresh + np.random.uniform(size=(n, 1))
y_fresh = p_fresh * x_fresh + e_fresh
for (n1, u, n2) in [(2, False, None), (2, True, None), (1, False, 1)]:
treatment_model = keras.Sequential([
keras.layers.Dense(10, activation='relu', input_shape=(2, )),
keras.layers.Dense(10, activation='relu'),
keras.layers.Dense(10, activation='relu')
])
hmodel = keras.Sequential([
keras.layers.Dense(10, activation='relu', input_shape=(2, )),
keras.layers.Dense(10, activation='relu'),
keras.layers.Dense(1)
])
deepIv = DeepIVEstimator(
10,
lambda z, x: treatment_model(keras.layers.concatenate([z, x])),
lambda t, x: hmodel(keras.layers.concatenate([t, x])),
n_samples=n1,
use_upper_bound_loss=u,
n_gradient_samples=n2,
s1=s1,
s2=s2)
deepIv.fit(y, p, x, z)
losses.append(
np.mean(np.square(y_fresh - deepIv.predict(p_fresh, x_fresh))))
marg_effs.append(
deepIv.marginal_effect(np.array([[0.3], [0.5], [0.7]]),
np.array([[0.4], [0.6], [0.2]])))
print("losses: {}".format(losses))
print("marg_effs: {}".format(marg_effs))
def test_deepiv_arbitrary_covariance(self):
d = 5
n = 5000
# to generate a random symmetric positive semidefinite covariance matrix, we can use A*A^T
A1 = np.random.normal(size=(d, d))
cov1 = np.matmul(A1, np.transpose(A1))
# convex combinations of semidefinite covariance matrices are themselves semidefinite
A2 = np.random.normal(size=(d, d))
cov2 = np.matmul(A2, np.transpose(A2))
m1 = np.random.normal(size=(d,))
m2 = np.random.normal(size=(d,))
x = np.random.uniform(size=(n, 1))
z = np.random.uniform(size=(n, 1))
alpha = (x * x + z * z) / 2 # in range [0,1]
t = np.array([np.random.multivariate_normal(m1 + alpha[i] * (m2 - m1),
cov1 + alpha[i] * (cov2 - cov1)) for i in range(n)])
y = np.expand_dims(np.einsum('nx,nx->n', t, t), -1) + x
results = []
s = 6
for (n1, u, n2) in [(2, False, None), (2, True, None), (1, False, 1)]:
treatment_model = keras.Sequential([keras.layers.Dense(90, activation='relu', input_shape=(2,)),
keras.layers.Dropout(0.2),
keras.layers.Dense(60, activation='relu'),
keras.layers.Dropout(0.2),
keras.layers.Dense(30, activation='relu')])
hmodel = keras.Sequential([keras.layers.Dense(90, activation='relu', input_shape=(d + 1,)),
keras.layers.Dropout(0.2),
keras.layers.Dense(60, activation='relu'),
keras.layers.Dropout(0.2),
keras.layers.Dense(30, activation='relu'),
keras.layers.Dropout(0.2),
keras.layers.Dense(1)])
deepIv = DeepIVEstimator(s,
lambda z, x: treatment_model(keras.layers.concatenate([z, x])),
lambda t, x: hmodel(keras.layers.concatenate([t, x])),
n_samples=n1, use_upper_bound_loss=u, n_gradient_samples=n2,
first_stage_options={'epochs': 20}, second_stage_options={'epochs': 20})
deepIv.fit(y[:n // 2], t[:n // 2], x[:n // 2], z[:n // 2])
results.append({'s': s, 'n1': n1, 'u': u, 'n2': n2,
'loss': np.mean(np.square(y[n // 2:] - deepIv.predict(t[n // 2:], x[n // 2:]))),
'marg': deepIv.marginal_effect(np.array([[0.5] * d]), np.array([[1.0]]))})
print(results)
def test_deepiv_models_paper2(self):
def monte_carlo_error(g_hat, data_fn, ntest=5000, has_latent=False, debug=False):
seed = np.random.randint(1e9)
try:
# test = True ensures we draw test set images
x, z, t, y, g_true = data_fn(ntest, seed, test=True)
except ValueError:
warnings.warn("Too few images, reducing test set size")
ntest = int(ntest * 0.7)
# test = True ensures we draw test set images
x, z, t, y, g_true = data_fn(ntest, seed, test=True)
# re-draw to get new independent treatment and implied response
t = np.linspace(np.percentile(t, 2.5), np.percentile(t, 97.5), ntest).reshape(-1, 1)
# we need to make sure z _never_ does anything in these g functions (fitted and true)
# above is necesary so that reduced form doesn't win
if has_latent:
x_latent, _, _, _, _ = data_fn(ntest, seed, images=False)
y = g_true(x_latent, z, t)
else:
y = g_true(x, z, t)
y_true = y.flatten()
y_hat = g_hat(x, z, t).flatten()
return ((y_hat - y_true)**2).mean()
def one_hot(col, **kwargs):
z = col.reshape(-1, 1)
enc = OneHotEncoder(sparse=False, **kwargs)
return enc.fit_transform(z)
def sensf(x):
return 2.0 * ((x - 5)**4 / 600 + np.exp(-((x - 5) / 0.5)**2) + x / 10. - 2)
def emocoef(emo):
emoc = (emo * np.array([1., 2., 3., 4., 5., 6., 7.])[None, :]).sum(axis=1)
return emoc
psd = 3.7
pmu = 17.779
ysd = 158. # 292.
ymu = -292.1
def storeg(x, price):
emoc = emocoef(x[:, 1:])
time = x[:, 0]
g = sensf(time) * emoc * 10. + (6 * emoc * sensf(time) - 2.0) * (psd * price.flatten() + pmu)
y = (g - ymu) / ysd
return y.reshape(-1, 1)
def demand(n, seed=1, ynoise=1., pnoise=1., ypcor=0.8, use_images=False, test=False):
rng = np.random.RandomState(seed)
# covariates: time and emotion
time = rng.rand(n) * 10
emotion_id = rng.randint(0, 7, size=n)
emotion = one_hot(emotion_id, n_values=7)
emotion_feature = emotion
# random instrument
z = rng.randn(n)
# z -> price
v = rng.randn(n) * pnoise
price = sensf(time) * (z + 3) + 25.
price = price + v
price = (price - pmu) / psd
# true observable demand function
x = np.concatenate([time.reshape((-1, 1)), emotion_feature], axis=1)
x_latent = np.concatenate([time.reshape((-1, 1)), emotion], axis=1)
def g(x, z, p):
return storeg(x, p) # doesn't use z
# errors
e = (ypcor * ynoise / pnoise) * v + rng.randn(n) * ynoise * np.sqrt(1 - ypcor**2)
e = e.reshape(-1, 1)
# response
y = g(x_latent, None, price) + e
return (x,
z.reshape((-1, 1)),
price.reshape((-1, 1)),
y.reshape((-1, 1)),
g)
def datafunction(n, s, images=False, test=False):
return demand(n=n, seed=s, ypcor=0.5, use_images=images, test=test)
n = 1000
epochs = 20
x, z, t, y, g_true = datafunction(n, 1)
print("Data shapes:\n\
Features:{x},\n\
Instruments:{z},\n\
Treament:{t},\n\
Response:{y}".format(**{'x': x.shape, 'z': z.shape,
't': t.shape, 'y': y.shape}))
losses = []
for (n1, u, n2) in [(2, False, None), (2, True, None), (1, False, 1)]:
treatment_model = keras.Sequential([keras.layers.Dense(50, activation='relu', input_shape=(9,)),
keras.layers.Dense(25, activation='relu'),
keras.layers.Dense(25, activation='relu')])
hmodel = keras.Sequential([keras.layers.Dense(50, activation='relu', input_shape=(9,)),
keras.layers.Dense(25, activation='relu'),
keras.layers.Dense(25, activation='relu'),
keras.layers.Dense(1)])
deepIv = DeepIVEstimator(10,
lambda z, x: treatment_model(keras.layers.concatenate([z, x])),
lambda t, x: hmodel(keras.layers.concatenate([t, x])),
n_samples=n1, use_upper_bound_loss=u, n_gradient_samples=n2,
first_stage_options={'epochs': epochs}, second_stage_options={'epochs': epochs})
deepIv.fit(y, t, x, z)
losses.append(monte_carlo_error(lambda x, z, t: deepIv.predict(
t, x), datafunction, has_latent=False, debug=False))
print("losses: {}".format(losses))
class DeepIV(AbstractBaseline):
def __init__(self, treatment_model=None):
if treatment_model is None:
print("Using standard treatment model...")
self._treatment_model = lambda input_shape: keras.models.Sequential(
[
keras.layers.Dense(
128, activation='relu', input_shape=input_shape),
keras.layers.Dropout(0.17),
keras.layers.Dense(64, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(32, activation='relu'),
keras.layers.Dropout(0.17)
])
else:
if keras.backend.image_data_format() == "channels_first":
image_shape = (1, 28, 28)
else:
image_shape = (28, 28, 1)
self._treatment_model = lambda input_shape: keras.models.Sequential(
[
keras.layers.Reshape(image_shape, input_shape=input_shape),
keras.layers.Conv2D(
16, kernel_size=(3, 3), activation='relu'),
keras.layers.Conv2D(32, (3, 3), activation='relu'),
keras.layers.MaxPooling2D(pool_size=(2, 2)),
keras.layers.Dropout(0.1),
keras.layers.Flatten(),
keras.layers.Dense(128, activation='relu'),
keras.layers.Dropout(0.1)
])
def _fit(self, x, y, z, context=None):
if context is None:
context = np.empty((x.shape[0], 0))
x_dim = x.shape[1]
z_dim = z.shape[1]
context_dim = context.shape[1]
treatment_model = self._treatment_model((context_dim + z_dim, ))
response_model = keras.models.Sequential([
keras.layers.Dense(128,
activation='relu',
input_shape=(context_dim + x_dim, )),
keras.layers.Dropout(0.17),
keras.layers.Dense(64, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(32, activation='relu'),
keras.layers.Dropout(0.17),
keras.layers.Dense(1)
])
self._model = DeepIVEstimator(
n_components=10,
# Number of gaussians in the mixture density networks)
m=lambda _z, _context: treatment_model(
keras.layers.concatenate([_z, _context])),
# Treatment model
h=lambda _t, _context: response_model(
keras.layers.concatenate([_t, _context])),
# Response model
n_samples=1)
t0 = time.time()
self._model.fit(y, x, context, z)
return time.time() - t0
def _predict(self, x, context):
if context is None:
context = np.empty((x.shape[0], 0))
return self._model.predict(x, context)