def data(request):
missing, datatype, const = request.param
return generate_data(missing,
datatype,
const=const,
other_effects=1,
ntk=(25, 200, 5))
def large_data(request):
missing, datatype, const = request.param
return generate_data(missing,
datatype,
const=const,
ntk=(51, 71, 5),
other_effects=2)
def data(request):
missing, datatype, const = request.param
return generate_data(missing,
datatype,
const=const,
ntk=(91, 15, 5),
other_effects=2)
def singleton_data(request):
missing, datatype, const = request.param
return generate_data(missing,
datatype,
const=const,
ntk=(91, 15, 5),
other_effects=2,
num_cats=[5 * 91, 15])
def const_data(request):
missing, datatype = request.param
data = generate_data(missing, datatype, ntk=(91, 7, 1))
y = PanelData(data.y).dataframe
x = y.copy()
x.iloc[:, :] = 1
x.columns = ['Const']
return AttrDict(y=y, x=x, w=PanelData(data.w).dataframe)
def test_limited_redundancy():
data = generate_data(0,
datatype="numpy",
const=False,
other_effects=1,
ntk=(25, 200, 5))
for i in range(0, data.x.shape[1], 7):
data.x[1, i, :] = data.x[0, i, :]
mod = FamaMacBeth(data.y, data.x)
res = mod.fit()
assert np.any(np.isnan(res.all_params))
def absorbed_data(request):
datatype = request.param
rng = np.random.RandomState(12345)
data = generate_data(0, datatype, ntk=(131, 4, 3), rng=rng)
x = data.x
if isinstance(data.x, np.ndarray):
absorbed = np.arange(x.shape[2])
absorbed = np.tile(absorbed, (1, x.shape[1], 1))
data.x = np.concatenate([data.x, absorbed])
elif isinstance(data.x, pd.DataFrame):
codes = get_codes(data.x.index)
absorbed = np.array(codes[0]).astype(np.double)
data.x["x_absorbed"] = absorbed
return data
def absorbed_data(request):
datatype = request.param
rng = np.random.RandomState(12345)
data = generate_data(0, datatype, ntk=(131, 4, 3), rng=rng)
x = data.x
if isinstance(data.x, np.ndarray):
absorbed = np.arange(x.shape[2])
absorbed = np.tile(absorbed, (1, x.shape[1], 1))
data.x = np.concatenate([data.x, absorbed])
else:
try:
codes = data.x.index.codes
except AttributeError:
# pandas < 0.24
codes = data.x.index.labels
absorbed = np.array(codes[0]).astype(np.double)
data.x["x_absorbed"] = absorbed
return data
def data(request):
missing, datatype = request.param
return generate_data(missing, datatype, other_effects=1)
def data(request):
missing, datatype = request.param
rng = np.random.RandomState(12345)
return generate_data(missing, datatype, ntk=(131, 4, 3), rng=rng)
def data(request):
missing, datatype, const = request.param
return generate_data(missing, datatype, ntk=(1000, 3, 5), const=const)
def data_gen(missing, datatype):
missing = 0.20 if missing else 0.0
return generate_data(missing, datatype)
def missing_data(request):
return generate_data(0.20, request.param)
def data(request):
return generate_data(0.0, request.param)
joined = {}
for n in (2000, ):
beta = {}
std_errs = {}
std_errs_no = {}
std_errs_u = {}
std_errs_u_no = {}
std_errs_r = {}
std_errs_r_no = {}
vals = np.zeros((NUM_REPS, 5, 7))
for b in range(NUM_REPS):
if b % 25 == 0:
print(key, n, b)
data = generate_data(0.00,
'pandas',
ntk=(n, 3, 5),
other_effects=1,
const=False,
rng=rs)
mo, fo = options[key]
mod_type, cluster_type = key.split(':')
y = PanelData(data.y)
random_effects = np.random.randint(0,
n // 3,
size=y.dataframe.shape)
other_random = np.random.randint(0, n // 5, size=y.dataframe.shape)
if mod_type == 'random':
effects = y.copy()
effects.dataframe.iloc[:, :] = random_effects
zz.groupby(level=0).sum() zz.groupby(level=0).sum().T o = zz.groupby(level=0).sum().values o o.T @ o (x.T @ z) @ (x.T @ z).T a = x.T @ p @ x b = (x.T @ z) @ (x.T @ z).T a b np.linalg.inv(a) @ b np.trace(np.linalg.inv(a) @ b) 30 30 data = generate_data(0, 'pandas', ntk=(101, 3, 5), other_effects=1, const=False) y = PanelData(data.y) x = PanelData(data.x) w = PanelData(data.w) x.dataframe.iloc[:, 0] = 1 mod = PanelOLS(data.y, data.x, weights=data.w) mod.fit() mod = PanelOLS(y, x, weights=data.w, entity_effects=True) mod.fit() mod = PanelOLS(data.y, data.x, weights=data.w, time_effects=True) mod.fit() mod = PanelOLS(data.y, data.x, weights=data.w, time_effects=True, entity_effects=True) mod.fit()
def data(request):
missing, datatype = request.param
return generate_data(missing, datatype, ntk=(231, 7, 5))
def test_uneuqal_samples():
data = generate_data(False, "pandas")
with pytest.raises(ValueError, match="dependent and exog must have"):
PooledOLS(data.y.iloc[::2], data.x)