def test_mean_missing(data):
xpd = PanelData(data.x)
xpd.drop(xpd.isnull)
entity_mean = xpd.mean('entity')
expected = xpd.dataframe.groupby(level=0).mean()
expected = expected.loc[xpd.entities]
expected.columns.name = None
assert_frame_equal(entity_mean, expected)
time_mean = xpd.mean('time')
expected = xpd.dataframe.groupby(level=1).mean()
expected = expected.loc[xpd.time]
expected.columns.name = None
assert_frame_equal(time_mean, expected)
def data(request):
model, vcv, weights, missing = request.param.split('-')
y_vars = ['y']
x_vars = ['x1', 'x2', 'x3', 'x4', 'x5']
vars = y_vars + x_vars
if missing:
for i, v in enumerate(vars):
vars[i] = v + missing
y_vars = vars[:1]
x_vars = vars[1:]
y = sim_data[y_vars]
x = sim_data[['intercept'] + x_vars]
mod = MODELS[model]
mod_options = {}
if model == 'fixed_effect':
mod_options = {'entity_effects': True}
if weights == 'weighted':
mod_options.update({'weights': sim_data['w']})
fit_options = {'debiased': True}
if weights == 'wls':
fit_options.update({'reweight': True})
if vcv == 'robust' and model not in ('fixed_effect', 'random_effect'):
fit_options.update({'cov_type': 'robust'})
elif vcv in ('cluster', 'robust'):
y_data = PanelData(y)
eid = y_data.entity_ids
entities = pd.DataFrame(eid, index=y_data.index, columns=['firm_ids'])
fit_options.update({'cov_type': 'clustered', 'clusters': entities})
else:
fit_options.update({'cov_type': 'unadjusted'})
if vcv == 'cluster' or (
model in ('fixed_effect', 'random_effect') and vcv == 'robust'):
fit_options.update({'group_debias': True})
spec_mod = mod(y, x, **mod_options)
fit = spec_mod.fit(**fit_options)
return AttrDict(fit=fit, model=spec_mod, model_options=mod_options, y=y,
x=x,
stata=STATA_RESULTS[request.param],
fit_options=fit_options,
model_name=model, vcv=vcv, weights=weights,
missing=missing)
def test_general_demean_oneway(mi_df):
y = PanelData(mi_df)
dm1 = y.demean("entity")
g = DataFrame(y.entity_ids, index=y.index)
dm2 = y.general_demean(g)
assert_allclose(dm1.values2d, dm2.values2d)
dm1 = y.demean("time")
g = DataFrame(y.time_ids, index=y.index)
dm2 = y.general_demean(g)
assert_allclose(dm1.values2d, dm2.values2d)
g = DataFrame(np.random.randint(0, 10, g.shape), index=y.index)
dm2 = y.general_demean(g)
g = Categorical(g.iloc[:, 0])
d = get_dummies(g)
dm1 = y.values2d - d @ lstsq(d, y.values2d, rcond=None)[0]
assert_allclose(dm1, dm2.values2d)
def test_general_demean_oneway(panel):
y = PanelData(panel)
dm1 = y.demean('entity')
g = pd.DataFrame(y.entity_ids, index=y.index)
dm2 = y.general_demean(g)
assert_allclose(dm1.values2d, dm2.values2d)
dm1 = y.demean('time')
g = pd.DataFrame(y.time_ids, index=y.index)
dm2 = y.general_demean(g)
assert_allclose(dm1.values2d, dm2.values2d)
g = pd.DataFrame(np.random.randint(0, 10, g.shape), index=y.index)
dm2 = y.general_demean(g)
g = pd.Categorical(g.iloc[:, 0])
d = pd.get_dummies(g)
dm1 = y.values2d - d @ np.linalg.lstsq(d, y.values2d)[0]
assert_allclose(dm1, dm2.values2d)
def test_nested_effects(data):
y = PanelData(data.y)
effects = pd.DataFrame(y.entity_ids // 2, index=y.index)
with pytest.raises(ValueError) as exception:
PanelOLS(data.y, data.x, entity_effects=True, other_effects=effects)
assert 'entity effects' in str(exception.value)
effects = pd.DataFrame(y.time_ids // 2, index=y.index)
with pytest.raises(ValueError) as exception:
PanelOLS(data.y, data.x, time_effects=True, other_effects=effects)
assert 'time effects' in str(exception.value)
effects1 = pd.Series(y.entity_ids.squeeze() // 2, index=y.index)
effects2 = pd.Series(y.entity_ids.squeeze() // 4, index=y.index)
effects = pd.DataFrame({'eff1': effects1, 'eff2': effects2})
with pytest.raises(ValueError) as exception:
PanelOLS(data.y, data.x, other_effects=effects)
assert 'by other effects' in str(exception.value)
assert 'time effects' not in str(exception.value)
assert 'entity effects' not in str(exception.value)
def test_string_conversion():
t, n = 3, 1000
string = np.random.choice(['a', 'b', 'c'], (t, n))
num = np.random.randn(t, n)
p = pd.Panel({'a': string, 'b': num})
p = p[['a', 'b']]
panel = PanelData(p, var_name='OtherEffect')
df = panel.dataframe
assert df.shape == (3000, 3)
s = string.T.ravel()
a_locs = np.where(s == 'a')
b_locs = np.where(s == 'b')
c_locs = np.where(s == 'c')
assert np.all(df.loc[:, 'a.b'].values[a_locs] == 0.0)
assert np.all(df.loc[:, 'a.b'].values[b_locs] == 1.0)
assert np.all(df.loc[:, 'a.b'].values[c_locs] == 0.0)
assert np.all(df.loc[:, 'a.c'].values[a_locs] == 0.0)
assert np.all(df.loc[:, 'a.c'].values[b_locs] == 0.0)
assert np.all(df.loc[:, 'a.c'].values[c_locs] == 1.0)
def test_valid_weight_shape(data):
# Same size
n = np.prod(data.y.shape)
weights = 1 + np.random.random_sample(n)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
missing = PanelData(data.y).isnull | PanelData(data.x).isnull
expected = weights[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
# Per time
n = data.y.shape[0]
weights = 1 + np.random.random_sample(n)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
expected = weights[:, None] @ np.ones((1, data.y.shape[1]))
expected = expected.T.ravel()
expected = expected[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
# Per entity
n = data.y.shape[1]
weights = 1 + np.random.random_sample(n)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
expected = np.ones((data.y.shape[0], 1)) @ weights[None, :]
expected = expected.T.ravel()
expected = expected[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
weights = 1 + np.random.random_sample(data.y.shape)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
expected = weights.T.ravel()
expected = expected[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
def test_numpy_3d():
n, t, k = 11, 7, 3
x = np.random.random((k, t, n))
dh = PanelData(x)
assert_equal(x, dh.values3d)
assert dh.nentity == n
assert dh.nobs == t
assert dh.nvar == k
assert_equal(np.reshape(x.T, (n * t, k)), dh.values2d)
items = ['entity.{0}'.format(i) for i in range(n)]
obs = [i for i in range(t)]
var_names = ['x.{0}'.format(i) for i in range(k)]
expected = pd.Panel(np.reshape(x, (k, t, n)),
items=var_names,
major_axis=obs,
minor_axis=items)
expected_frame = expected.swapaxes(1, 2).to_frame()
expected_frame.index.levels[0].name = 'entity'
expected_frame.index.levels[1].name = 'time'
assert_frame_equal(dh.dataframe, expected_frame)
def test_methods_equivalent(data, lsdv_config):
other_effects = None
if lsdv_config.other_effects == 1:
other_effects = PanelData(data.c).dataframe.iloc[:, [0]]
elif lsdv_config.other_effects == 2:
other_effects = data.c
weights = data.w if lsdv_config.weights else None
mod = PanelOLS(
data.y,
data.x,
weights=weights,
entity_effects=lsdv_config.entity_effects,
time_effects=lsdv_config.time_effects,
other_effects=other_effects,
)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
res3 = mod.fit(use_lsmr=True)
assert_results_equal(res1, res2)
assert_results_equal(res2, res3, strict=False)
def test_demean_missing_alt_types(data):
check = isinstance(data.x, (DataFrame, np.ndarray))
xpd = PanelData(data.x)
xpd.drop(xpd.isnull)
entity_demean = xpd.demean('entity')
expected = xpd.dataframe.groupby(level=0).transform(lambda s: s - s.mean())
assert_frame_equal(entity_demean.dataframe, expected,
check_index_type=check,
check_column_type=check)
time_demean = xpd.demean('time')
expected = xpd.dataframe.groupby(level=1).transform(lambda s: s - s.mean())
assert_frame_equal(time_demean.dataframe, expected,
check_index_type=check,
check_column_type=check)
def test_lsdv_options(data):
mod = PanelOLS(data.y, data.x, weights=data.w)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, weights=data.w, entity_effect=True)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, time_effect=True)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, time_effect=True, entity_effect=True)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
c1 = PanelData(data.c).dataframe.iloc[:, [0]]
mod = PanelOLS(data.y, data.x, entity_effect=True, other_effects=c1)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, time_effect=True, other_effects=c1)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, weights=data.w, time_effect=True, other_effects=c1)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, weights=data.w, other_effects=data.c)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
def test_singleton_removal_mixed(singleton_data, other_effects):
if other_effects == 1:
other_effects = PanelData(singleton_data.c).dataframe.iloc[:, [0]]
elif other_effects == 2:
other_effects = singleton_data.c
mod = PanelOLS(singleton_data.y,
singleton_data.x,
other_effects=other_effects)
res_keep = mod.fit(use_lsmr=True)
mod = PanelOLS(
singleton_data.y,
singleton_data.x,
other_effects=other_effects,
singletons=False,
)
res = mod.fit(cov_type="clustered",
clusters=singleton_data.vc2,
use_lsmr=True)
assert_allclose(res_keep.params, res.params)
assert res.nobs <= res_keep.nobs
def test_string_input(data):
y = PanelData(data.y)
nt = y.values2d.shape[0]
temp = {}
prim = ['a', 'b', 'c', 'd', 'e']
for i in range(2):
name = 'effect.' + str(i)
temp[name] = pd.Series(np.random.choice(prim, size=nt), index=y.index, name=name)
effects = pd.DataFrame(temp, index=y.index)
mod = PanelOLS(data.y, data.x, other_effects=effects)
mod.fit()
clusters = np.random.randint(0, y.shape[2] // 2, size=(nt, 2))
temp = {}
prim = list(map(lambda s: ''.join(s), list(product(ascii_lowercase, ascii_lowercase))))
for i in range(clusters.shape[1]):
name = 'effect.' + str(i)
temp[name] = pd.Series(np.random.choice(prim, size=nt), index=y.index, name=name)
clusters = pd.DataFrame(temp, index=y.index)
mod.fit(cov_type='clustered', clusters=clusters)
def test_numpy_3d():
n, t, k = 11, 7, 3
x = np.random.random((k, t, n))
dh = PanelData(x)
assert_equal(x, dh.values3d)
assert dh.nentity == n
assert dh.nobs == t
assert dh.nvar == k
assert_equal(np.reshape(x.T, (n * t, k)), dh.values2d)
items = ["entity.{0}".format(i) for i in range(n)]
obs = [i for i in range(t)]
var_names = ["x.{0}".format(i) for i in range(k)]
expected_frame = panel_to_frame(
np.reshape(x, (k, t, n)),
items=var_names,
major_axis=obs,
minor_axis=items,
swap=True,
)
expected_frame.index.set_names(["entity", "time"], inplace=True)
assert_frame_equal(dh.dataframe, expected_frame)
def test_random_effects_small_sample(data):
y = PanelData(data.y)
mod = RandomEffects(data.y, data.x)
no_ss = mod.fit()
ss = mod.fit(small_sample=True)
if y.dataframe.shape[0] == mod.dependent.dataframe.shape[0]:
assert (ss.variance_decomposition.Effects ==
no_ss.variance_decomposition.Effects)
else:
assert (ss.variance_decomposition.Effects !=
no_ss.variance_decomposition.Effects)
mod = RandomEffects(data.y, data.x, weights=data.w)
no_ss = mod.fit()
ss = mod.fit(small_sample=True)
if y.dataframe.shape[0] == mod.dependent.dataframe.shape[0]:
assert (ss.variance_decomposition.Effects ==
no_ss.variance_decomposition.Effects)
else:
assert (ss.variance_decomposition.Effects !=
no_ss.variance_decomposition.Effects)
def test_count(data):
xpd = PanelData(data.x)
xpd.drop(xpd.isnull)
entity_mean = xpd.count("entity")
expected = xpd.dataframe.groupby(level=0).count()
expected = expected.loc[xpd.entities]
expected.columns.name = None
expected = expected.astype(np.int64)
assert_frame_equal(entity_mean, expected)
time_mean = xpd.count("time")
expected = xpd.dataframe.groupby(level=1).count()
expected = expected.loc[xpd.time]
expected.columns.name = None
expected = expected.astype(np.int64)
assert_frame_equal(time_mean, expected)
def test_mixed_input(data):
y = PanelData(data.y)
nt = y.values2d.shape[0]
effects = np.random.randint(0, 5, size=nt)
prim = ["a", "b", "c", "d", "e"]
temp = {
"effect.0": pd.Categorical(pd.Series(effects, index=y.index)),
"effect.1": pd.Series(np.random.choice(prim, size=nt), index=y.index),
}
effects = pd.DataFrame(temp, index=y.index)
mod = PanelOLS(data.y, data.x, other_effects=effects)
mod.fit()
clusters = np.random.randint(0, y.shape[2] // 2, size=(nt, 2))
temp = {}
prim = list(
map(lambda s: "".join(s), list(product(ascii_lowercase, ascii_lowercase)))
)
temp["var.cluster.0"] = pd.Series(np.random.choice(prim, size=nt), index=y.index)
temp["var.cluster.1"] = pd.Series(clusters[:, 1], index=y.index)
clusters = pd.DataFrame(temp, index=y.index)
mod.fit(cov_type="clustered", clusters=clusters)
def test_mixed_input(data):
y = PanelData(data.y)
nt = y.values2d.shape[0]
effects = np.random.randint(0, 5, size=nt)
prim = ['a', 'b', 'c', 'd', 'e']
temp = {
'effect.0': pd.Categorical(pd.Series(effects, index=y.index)),
'effect.1': pd.Series(np.random.choice(prim, size=nt), index=y.index)
}
effects = pd.DataFrame(temp, index=y.index)
mod = PanelOLS(data.y, data.x, other_effects=effects)
mod.fit()
clusters = np.random.randint(0, y.shape[2] // 2, size=(nt, 2))
temp = {}
prim = list(
map(lambda s: ''.join(s),
list(product(ascii_lowercase, ascii_lowercase))))
temp['var.cluster.0'] = pd.Series(np.random.choice(prim, size=nt),
index=y.index)
temp['var.cluster.1'] = pd.Series(clusters[:, 1], index=y.index)
clusters = pd.DataFrame(temp, index=y.index)
mod.fit(cov_type='clustered', clusters=clusters)
def test_results_access(data):
mod = PanelOLS(data.y, data.x, entity_effects=True)
res = mod.fit()
access_attributes(res)
mod = PanelOLS(data.y, data.x, other_effects=data.c)
res = mod.fit()
access_attributes(res)
mod = PanelOLS(data.y, data.x, time_effects=True, entity_effects=True)
res = mod.fit()
access_attributes(res)
mod = PanelOLS(data.y, data.x)
res = mod.fit()
access_attributes(res)
const = PanelData(data.y).copy()
const.dataframe.iloc[:, :] = 1
const.dataframe.columns = ["const"]
mod = PanelOLS(data.y, const)
res = mod.fit()
access_attributes(res)
def test_multiple_obs_per_entity(data):
mod = BetweenOLS(data.y, data.x)
res = mod.fit(reweight=True, debiased=False)
dep = mod.dependent.values3d.mean(1).T
exog = pd.DataFrame(mod.exog.values3d.mean(1).T, columns=mod.exog.vars)
ols = IV2SLS(dep, exog, None, None)
ols_res = ols.fit(cov_type="unadjusted")
assert_results_equal(res, ols_res)
res = mod.fit(cov_type="robust", debiased=False)
ols_res = ols.fit(cov_type="robust", debiased=False)
assert_results_equal(res, ols_res)
clusters = mod.dependent.dataframe.copy()
clusters.loc[:, :] = 0
clusters = clusters.astype(np.int32)
for entity in mod.dependent.entities:
clusters.loc[entity] = np.random.randint(9)
ols_clusters = PanelData(clusters).values3d.mean(1).T.astype(np.int32)
res = mod.fit(cov_type="clustered", clusters=clusters, debiased=False)
ols_res = ols.fit(cov_type="clustered", clusters=ols_clusters)
assert_results_equal(res, ols_res)
def test_two_way_clustering(data):
mod = PooledOLS(data.y, data.x)
y = PanelData(data.y)
entity_clusters = pd.DataFrame(y.entity_ids, index=y.index)
vc1 = PanelData(data.vc1)
clusters = vc1.copy()
clusters.dataframe['var.cluster.entity'] = entity_clusters
clusters._frame = clusters._frame.astype(np.int64)
res = mod.fit(cov_type='clustered', clusters=clusters, debiased=False)
y = mod.dependent.dataframe.copy()
x = mod.exog.dataframe.copy()
y.index = np.arange(len(y))
x.index = y.index
clusters = mod.reformat_clusters(clusters)
ols_mod = IV2SLS(y, x, None, None)
ols_res = ols_mod.fit(cov_type='clustered', clusters=clusters.dataframe)
assert_results_equal(res, ols_res)
def test_incorrect_time_axis():
x = np.random.randn(3, 3, 1000)
entities = ['entity.{0}'.format(i) for i in range(1000)]
time = ['time.{0}' for i in range(3)]
vars = ['var.{0}' for i in range(3)]
p = pd.Panel(x, items=vars, major_axis=time, minor_axis=entities)
with pytest.raises(ValueError):
PanelData(p)
df = p.swapaxes(1, 2).swapaxes(0, 1).to_frame()
with pytest.raises(ValueError):
PanelData(df)
da = xr.DataArray(x,
coords={
'entities': entities,
'time': time,
'vars': vars
},
dims=['vars', 'time', 'entities'])
with pytest.raises(ValueError):
PanelData(da)
time = [1, pd.datetime(1960, 1, 1), 'a']
vars = ['var.{0}' for i in range(3)]
p = pd.Panel(x, items=vars, major_axis=time, minor_axis=entities)
with pytest.raises(ValueError):
PanelData(p)
df = p.swapaxes(1, 2).swapaxes(0, 1).to_frame()
with pytest.raises(ValueError):
PanelData(df)
da = xr.DataArray(x,
coords={
'entities': entities,
'time': time,
'vars': vars
},
dims=['vars', 'time', 'entities'])
with pytest.raises(ValueError):
PanelData(da)
def test_general_unit_weighted_demean_twoway(panel):
np.random.seed(12345)
y = PanelData(panel)
weights = pd.DataFrame(np.random.chisquare(10, (y.dataframe.shape[0], 1)) / 10, index=y.index)
w = PanelData(weights)
dm1 = y.demean('both', weights=w)
g = pd.DataFrame(y.entity_ids, index=y.index)
g['column2'] = pd.Series(y.time_ids.squeeze(), index=y.index)
dm2 = y.general_demean(g, weights=w)
assert_allclose(dm1.values2d - dm2.values2d, np.zeros_like(dm2.values2d), atol=1e-7)
g = pd.DataFrame(np.random.randint(0, 10, g.shape), index=y.index)
dm2 = y.general_demean(g, weights=w)
g1 = pd.Categorical(g.iloc[:, 0])
d1 = pd.get_dummies(g1)
g2 = pd.Categorical(g.iloc[:, 1])
d2 = pd.get_dummies(g2, drop_first=True)
d = np.c_[d1, d2]
wd = np.sqrt(w.values2d) * d
wy = np.sqrt(w.values2d) * y.values2d
dm1 = wy - wd @ np.linalg.lstsq(wd, wy)[0]
assert_allclose(dm1 - dm2.values2d, np.zeros_like(dm2.values2d), atol=1e-7)
def test_numpy_1d():
n = 11
x = np.random.random(n)
with pytest.raises(ValueError):
PanelData(x)
def test_general_weighted_demean_oneway(mi_df):
y = PanelData(mi_df)
weights = DataFrame(np.random.chisquare(10,
(y.dataframe.shape[0], 1)) / 10,
index=y.index)
w = PanelData(weights)
dm1 = y.demean("entity", weights=w)
g = PanelData(DataFrame(y.entity_ids, index=y.index))
dm2 = y.general_demean(g, w)
assert_allclose(dm1.values2d, dm2.values2d)
dm1 = y.demean("time", weights=w)
g = PanelData(DataFrame(y.time_ids, index=y.index))
dm2 = y.general_demean(g, w)
assert_allclose(dm1.values2d, dm2.values2d)
g = PanelData(
DataFrame(np.random.randint(0, 10, g.dataframe.shape), index=y.index))
dm2 = y.general_demean(g, w)
g = Categorical(g.dataframe.iloc[:, 0])
d = get_dummies(g)
wd = np.sqrt(w.values2d) * d
wy = np.sqrt(w.values2d) * y.values2d
dm1 = wy - wd @ lstsq(wd, wy, rcond=None)[0]
assert_allclose(dm1, dm2.values2d, atol=1e-14)
def test_general_unit_weighted_demean_oneway(mi_df):
y = PanelData(mi_df)
dm1 = y.demean("entity")
g = PanelData(DataFrame(y.entity_ids, index=y.index))
weights = PanelData(g).copy()
weights.dataframe.iloc[:, :] = 1
dm2 = y.general_demean(g, weights)
assert_allclose(dm1.values2d, dm2.values2d)
dm3 = y.general_demean(g)
assert_allclose(dm3.values2d, dm2.values2d)
dm1 = y.demean("time")
g = PanelData(DataFrame(y.time_ids, index=y.index))
dm2 = y.general_demean(g, weights)
assert_allclose(dm1.values2d, dm2.values2d)
dm3 = y.general_demean(g)
assert_allclose(dm3.values2d, dm2.values2d)
g = PanelData(
DataFrame(np.random.randint(0, 10, g.dataframe.shape), index=y.index))
dm2 = y.general_demean(g, weights)
dm3 = y.general_demean(g)
g = Categorical(g.dataframe.iloc[:, 0])
d = get_dummies(g)
dm1 = y.values2d - d @ lstsq(d, y.values2d, rcond=None)[0]
assert_allclose(dm1, dm2.values2d)
assert_allclose(dm3.values2d, dm2.values2d)
def test_repr_html(mi_df):
data = PanelData(mi_df)
html = data._repr_html_()
assert "<br/>" in html
def test_demean_simple_weighted(data):
x = PanelData(data.x)
w = PanelData(data.w)
missing = x.isnull | w.isnull
x.drop(missing)
w.drop(missing)
w.dataframe.iloc[:, 0] = 1
unweighted_entity_demean = x.demean("entity")
weighted_entity_demean = x.demean("entity", weights=w)
assert_allclose(unweighted_entity_demean.dataframe,
weighted_entity_demean.dataframe)
unweighted_entity_demean = x.demean("time")
weighted_entity_demean = x.demean("time", weights=w)
assert_allclose(unweighted_entity_demean.dataframe,
weighted_entity_demean.dataframe)
def test_first_difference(data):
x = PanelData(data.x)
x.first_difference()
def test_invalid_seires(mi_df):
si = mi_df.reset_index()
with pytest.raises(ValueError):
PanelData(si.iloc[:, 0])