def load(
file: str,
file_types: list,
data_files: Dict[Any, Any],
data_examples: Dict[Any, Any],
) -> pd.DataFrame:
"""Load custom file into dataframe.
Parameters
----------
file: str
Path to file
file_types: list
Supported file types
data_files: dict
Contains all available data files within the Export folder
data_examples: dict
Contains all available examples from Statsmodels
Returns
-------
pd.DataFrame:
Dataframe with custom data
"""
if file in data_examples:
if file == "wage_panel":
return wage_panel.load()
return eval(f"sm.datasets.{file}.load_pandas().data")
if file in data_files:
file = data_files[file]
if not Path(file).exists():
console.print(f"[red]Can not find the file {file}[/red]\n")
return pd.DataFrame()
file_type = Path(file).suffix
if file_type == ".xlsx":
data = pd.read_excel(file)
elif file_type == ".csv":
data = pd.read_csv(file)
else:
return console.print(
f"The file type {file_type} is not supported. Please choose one of the following: "
f"{', '.join(file_types)}")
return data
import numpy as np
from numpy.testing import assert_allclose
from pandas.testing import assert_series_equal
import pytest
from statsmodels.tools.tools import add_constant
from linearmodels.datasets import wage_panel
from linearmodels.iv.model import IV2SLS
from linearmodels.panel.data import PanelData
from linearmodels.panel.model import PanelOLS, PooledOLS, RandomEffects
from linearmodels.panel.results import compare
from linearmodels.tests.panel._utility import datatypes, generate_data
@pytest.fixture(params=[wage_panel.load()])
def data(request):
return request.param
missing = [0.0, 0.02, 0.20]
has_const = [True, False]
perms = list(product(missing, datatypes, has_const))
ids = list(map(lambda s: "-".join(map(str, s)), perms))
@pytest.fixture(params=perms, ids=ids)
def generated_data(request):
missing, datatype, const = request.param
return generate_data(missing,
datatype,
import numpy as np import linearmodels as lm lm.WARN_ON_MISSING = False from linearmodels import utility utility.missing_warning(np.array([True, True, False])) from linearmodels.panel import PanelOLS, RandomEffects, PooledOLS from linearmodels.datasets import wage_panel import statsmodels.api as sm data = wage_panel.load() data = data.set_index(['nr','year']) dependent = data.lwage exog = sm.add_constant(data[['expersq','married','union']]) mod = PanelOLS(dependent, exog, entity_effects=True, time_effects=True) res = mod.fit(cov_type='unadjusted') res2 = mod.fit(cov_type='robust') exog = sm.add_constant(data[['exper', 'expersq','married','union']]) mod = PanelOLS(dependent, exog, entity_effects=True) res3 = mod.fit(cov_type='clustered',cluster_entity=True) mod = RandomEffects(dependent, exog) res4 = mod.fit(cov_type='robust') from linearmodels.panel.results import compare exog = sm.add_constant(data[['exper', 'expersq','married','union']].copy()) import pandas as pd exog['year'] = pd.Categorical(data.reset_index()['year']) mod = PooledOLS(dependent, exog) res5 = mod.fit(cov_type='robust') print(compare([res,res2, res3, res4, res5])) print(data.columns)