class StargazerTestCase(unittest.TestCase):
def setUp(self):
self.df = pd.DataFrame(list(zip(range(9), range(0, 18, 2))), columns =['a', 'b'])
self.est1 = smf.ols('a ~ 0 + b', self.df).fit()
self.est2 = smf.ols('a ~ 1 + b', self.df).fit()
self.stargazer = Stargazer([self.est1, self.est2])
def test_add_line(self):
# too few arguments
self.assertRaises(AssertionError, self.stargazer.add_line, '', [0])
# wrong location
self.assertRaises(ValueError, self.stargazer.add_line, '', [0, 0], 'wrong')
# correct usage
for loc in LineLocation:
self.stargazer.add_line(f'test {loc.value}', ['N/A', 'N/A'], loc)
latex = self.stargazer.render_latex()
for loc in LineLocation:
self.assertIn(f' test {loc.value} & N/A & N/A \\', latex)
def test_render_latex(self):
# test escaping
self.stargazer.rename_covariates({'b': 'b_'})
self.assertIn(' b_ ', self.stargazer.render_latex())
self.assertIn(r' b\_ ', self.stargazer.render_latex(escape=True))
def create_table(models, out):
"""Creates a table of regression results.
Args:
models: regression results
out: the generated table is saved here
Returns:
None
"""
results = []
model_names = []
covariate_names = {}
for model in models:
with open(model, 'rb') as file:
result = (pickle.load(file))
results.append(result)
model_names.append(result.model_name)
covariate_names.update(result.var_names)
table = Stargazer(results)
table.dependent_variable_name(
covariate_names[results[0].model.endog_names])
table.custom_columns(model_names, [1] * len(model_names))
table.rename_covariates(covariate_names)
latex_table = table.render_latex()
latex_table = re.sub(r"l(c+)\}", r"lc\1}", latex_table)
# ugly hack because stargazer generates an invalid latex table
with open(out, 'w') as file:
file.write(latex_table)
def create_table(models, path):
path = Path(path)
stargazer = Stargazer(models)
if path.suffix == ".tex":
table = stargazer.render_latex()
elif path.suffix == ".html":
table = stargazer.render_html()
else:
raise NotImplementedError
with open(path, "w") as file:
file.write(table)
for name in strategy_name_list:
# to have the same name for all variables
reg_df_tmp = reg_df.rename({name: "ret"}, axis=1)
results_list.append(
smf.ols(formula="ret ~ MKT + SMB + HML + CMA + RMW",
data=reg_df_tmp * 12).fit())
# Outputting short regression results:
stargazer = Stargazer([results_list[0], results_list[3], results_list[6]])
stargazer.custom_columns(['D 30', 'prob 20', 'prob 40'], [1, 1, 1])
stargazer.covariate_order(['Intercept', 'MKT', 'SMB', 'HML', 'RMW', 'CMA'])
stargazer.show_degrees_of_freedom(False)
f = open(
"/Users/rsigalov/Dropbox/2019_Revision/Writing/Predictive Regressions/tables/disaster_sort_reg_on_ff.tex",
"w")
f.write(stargazer.render_latex())
f.close()
# Doing extended regression table where I do regressions of strategy return on
# (1) just the market, (2) FF 3 factors and (3) FF 5 factors.
results_list = []
for name in ["D_30", "p_20_30"]:
# to have the same name for all variables
reg_df_tmp = reg_df.rename({name: "ret"}, axis=1)
results_list.append(
smf.ols(formula="ret ~ MKT", data=reg_df_tmp * 12).fit())
results_list.append(
smf.ols(formula="ret ~ MKT + SMB + HML", data=reg_df_tmp * 12).fit())
results_list.append(
smf.ols(formula="ret ~ MKT + SMB + HML + CMA + RMW",
data=reg_df_tmp * 12).fit())
df = pd.concat([country, df], axis=1)
df.drop(["Thailand", "location"], axis=1, inplace=True)
df.dropna(subset=["new_tests_per_thousand"], inplace=True)
df["date"] = pd.to_datetime(df["date"])
df_my = df[df["Malaysia"] == 1]
df_my = df_my.merge(mob_my, on="date")
df_th = df[df["Malaysia"] == 0]
df_th = df_th.merge(mob_th, on="date")
df = pd.concat([df_my, df_th])
df["post_election"] = df["date"].apply(
lambda x: 0 if x <= pd.to_datetime("2020-09-26") else 1)
mdl_joined_el = ols(
"new_cases_per_million ~ Malaysia * post_election + new_tests_per_thousand + retail + grocery + parks + transit",
data=df)
results_joined_el = mdl_joined_el.fit()
results_joined_el.summary()
stargazer = Stargazer([results_joined_el])
stargazer.render_latex()
model1 = sm.OLS(y, x).fit()
model2 = sm.OLS(y, x_withfemale).fit()
model1.summary()
model2.summary()
# =============================================================================
# STARGAZER MODEL OUTPUTS
# =============================================================================
from stargazer.stargazer import Stargazer
stargazer = Stargazer([model1, model2])
stargazer.custom_columns(['Base Model', 'Spesified Model'], [1, 1])
stargazer.significant_digits(2)
stargazer.covariate_order([
'const', 'propwomen', 'oppospower', 'gdpcap', 'sepowerdist', 'youthunemp'
])
stargazer.rename_covariates({
'const': 'Constant',
'oppospower': 'Opposition Power',
'gdpcap': 'GDP($)',
'sepowerdist': 'Class Political Power',
'youthunemp': 'Unemployed Youth %',
'propwomen': 'Female Property Rights'
})
stargazer.cov_spacing = 3
print(stargazer.render_latex())
def ols_regression_formatted(data,
specifications,
as_latex=False,
covariates_names=None,
covariates_order=None):
"""
Creates formatted tables for different dependent variables and specifications
Input:
data (df): Dataframe containing all necessary variables for OLS regression
specifications (dictionary): dependent variables as keys and list of specifications
as values
as_latex (bool): specify whether Output as table or Latex code
covariate_names (dict): dictionary with covariate names as in "data" as keys and new
covariate names as values
Output:
list_of_tables (list of stargazer tables): list of formatted tables
"""
# Create dictionary which connects dependent variables with formatted tables
dict_regression_tables = {}
# Generate regressions
for depvar in specifications.keys():
regression_list = []
specification_list = specifications[depvar]
list_all_covariates = []
for specification in specification_list:
estimation_equation = depvar + " ~ " + specification
regression = smf.ols(data=data, formula=estimation_equation).fit()
regression_list.append(regression)
# Create set of all variables for this dependent variable
list_all_covariates = list(
set(list_all_covariates +
regression.params.index.values.tolist()))
# Format table with stargazer
formatted_table = Stargazer(regression_list)
# No dimension of freedoms and blank dependent variable
formatted_table.show_degrees_of_freedom(False)
formatted_table.dependent_variable_name("")
# Optional: Change order of covariates
if covariates_order is not None:
covariates_order_depvar = list(
OrderedSet(covariates_order).intersection(list_all_covariates))
list_remaining_covariates = list(
OrderedSet(list_all_covariates).difference(
OrderedSet(covariates_order_depvar)))
covariates_sorted = list(
OrderedSet(covariates_order_depvar).union(
list_remaining_covariates))
covariates_sorted.remove("Intercept")
covariates_sorted = covariates_sorted + ["Intercept"]
formatted_table.covariate_order(covariates_sorted)
# Optional: Change name of covariates
if covariates_names is not None:
formatted_table.rename_covariates(covariates_names)
# Add table or latex code to dictionary
if as_latex is True:
dict_regression_tables[depvar] = formatted_table.render_latex()
# Delete tabular environment around it
dict_regression_tables[depvar] = dict_regression_tables[
depvar].replace("\\begin{table}[!htbp] \\centering\n", "")
dict_regression_tables[depvar] = dict_regression_tables[
depvar].replace("\\end{table}", "")
else:
dict_regression_tables[depvar] = formatted_table
return dict_regression_tables
