def coordinate_converter(
vdf: vDataFrame,
x: str,
y: str,
x0: float = 0.0,
earth_radius: float = 6371,
reverse: bool = False,
):
"""
---------------------------------------------------------------------------
Converts between geographic coordinates (latitude and longitude) and
Euclidean coordinates (x,y).
Parameters
----------
vdf: vDataFrame
input vDataFrame.
x: str
vColumn used as the abscissa (longitude).
y: str
vColumn used as the ordinate (latitude).
x0: float, optional
The initial abscissa.
earth_radius: float, optional
Earth radius in km.
reverse: bool, optional
If set to True, the Euclidean coordinates are converted to latitude
and longitude.
Returns
-------
vDataFrame
result of the transformation.
"""
check_types([
("vdf", vdf, [vDataFrame]),
("x", x, [str]),
("y", y, [str]),
("x0", x0, [int, float]),
("earth_radius", earth_radius, [int, float]),
("reverse", reverse, [bool]),
])
vdf.are_namecols_in([x, y])
result = vdf.copy()
if reverse:
result[x] = result[x] / earth_radius * 180 / st.pi + x0
result[y] = ((st.atan(st.exp(result[y] / earth_radius)) - st.pi / 4) /
st.pi * 360)
else:
result[x] = earth_radius * ((result[x] - x0) * st.pi / 180)
result[y] = earth_radius * st.ln(
st.tan(result[y] * st.pi / 360 + st.pi / 4))
return result
def het_breuschpagan(
vdf: vDataFrame, eps: str, X: list,
):
"""
---------------------------------------------------------------------------
Breusch-Pagan test for heteroscedasticity.
Parameters
----------
vdf: vDataFrame
Input vDataFrame.
eps: str
Input residual vcolumn.
X: list
Exogenous Variables to test the heteroscedasticity on.
Returns
-------
tablesample
An object containing the result. For more information, see
utilities.tablesample.
"""
check_types(
[("eps", eps, [str],), ("X", X, [list],), ("vdf", vdf, [vDataFrame, str,],),],
)
columns_check([eps] + X, vdf)
eps = vdf_columns_names([eps], vdf)[0]
X = vdf_columns_names(X, vdf)
from verticapy.learn.linear_model import LinearRegression
schema_writing = vdf._VERTICAPY_VARIABLES_["schema_writing"]
if not (schema_writing):
schema_writing = "public"
name = schema_writing + ".VERTICAPY_TEMP_MODEL_LINEAR_REGRESSION_{}".format(
get_session(vdf._VERTICAPY_VARIABLES_["cursor"])
)
model = LinearRegression(name, cursor=vdf._VERTICAPY_VARIABLES_["cursor"])
vdf_copy = vdf.copy()
vdf_copy["VERTICAPY_TEMP_eps2"] = vdf_copy[eps] ** 2
try:
model.fit(vdf_copy, X, "VERTICAPY_TEMP_eps2")
R2 = model.score("r2")
model.drop()
except:
try:
model.set_params({"solver": "bfgs"})
model.fit(vdf_copy, X, "VERTICAPY_TEMP_eps2")
R2 = model.score("r2")
model.drop()
except:
model.drop()
raise
n = vdf.shape()[0]
k = len(X)
LM = n * R2
lm_pvalue = chi2.sf(LM, k)
F = (n - k - 1) * R2 / (1 - R2) / k
f_pvalue = f.sf(F, k, n - k - 1)
result = tablesample(
{
"index": [
"Lagrange Multiplier Statistic",
"lm_p_value",
"F Value",
"f_p_value",
],
"value": [LM, lm_pvalue, F, f_pvalue],
}
)
return result
