def model(base, winequality_vd):
base.cursor.execute("DROP MODEL IF EXISTS linreg_model_test")
model_class = LinearRegression("linreg_model_test", cursor=base.cursor)
model_class.fit("public.winequality",
["citric_acid", "residual_sugar", "alcohol"], "quality")
yield model_class
model_class.drop()
def model(winequality_vd):
model_class = LinearRegression("linreg_model_test", )
model_class.drop()
model_class.fit("public.winequality",
["citric_acid", "residual_sugar", "alcohol"], "quality")
yield model_class
model_class.drop()
def test_contour(self, winequality_vd):
model_test = LinearRegression("model_contour", )
model_test.drop()
model_test.fit(
winequality_vd,
["citric_acid", "residual_sugar"],
"quality",
)
result = model_test.contour()
assert len(result.get_default_bbox_extra_artists()) == 32
model_test.drop()
def test_model_from_vDF(self, base, winequality_vd):
base.cursor.execute("DROP MODEL IF EXISTS linreg_from_vDF")
model_test = LinearRegression("linreg_from_vDF", cursor=base.cursor)
model_test.fit(winequality_vd, ["alcohol"], "quality")
base.cursor.execute(
"SELECT model_name FROM models WHERE model_name = 'linreg_from_vDF'"
)
assert base.cursor.fetchone()[0] == "linreg_from_vDF"
model_test.drop()
def test_set_cursor(self, base):
model_test = LinearRegression("linear_reg_cursor_test", cursor=base.cursor)
# TODO: creat a new cursor
model_test.set_cursor(base.cursor)
model_test.drop()
model_test.fit("public.winequality", ["alcohol"], "quality")
base.cursor.execute(
"SELECT model_name FROM models WHERE model_name = 'linear_reg_cursor_test'"
)
assert base.cursor.fetchone()[0] == "linear_reg_cursor_test"
model_test.drop()
def test_get_plot(self, winequality_vd):
current_cursor().execute("DROP MODEL IF EXISTS model_test_plot")
model_test = LinearRegression("model_test_plot", )
model_test.fit(winequality_vd, ["alcohol"], "quality")
result = model_test.plot(color="r")
assert len(result.get_default_bbox_extra_artists()) == 9
plt.close("all")
model_test.drop()
model_test.fit(winequality_vd, ["alcohol", "residual_sugar"],
"quality")
result = model_test.plot(color="r")
assert len(result.get_default_bbox_extra_artists()) == 3
plt.close("all")
model_test.drop()
def test_drop(self):
current_cursor().execute("DROP MODEL IF EXISTS linreg_model_test_drop")
model_test = LinearRegression("linreg_model_test_drop", )
model_test.fit("public.winequality", ["alcohol"], "quality")
current_cursor().execute(
"SELECT model_name FROM models WHERE model_name = 'linreg_model_test_drop'"
)
assert current_cursor().fetchone()[0] == "linreg_model_test_drop"
model_test.drop()
current_cursor().execute(
"SELECT model_name FROM models WHERE model_name = 'linreg_model_test_drop'"
)
assert current_cursor().fetchone() is None
def test_drop(self, base):
base.cursor.execute("DROP MODEL IF EXISTS linreg_model_test_drop")
model_test = LinearRegression("linreg_model_test_drop", cursor=base.cursor)
model_test.fit("public.winequality", ["alcohol"], "quality")
base.cursor.execute(
"SELECT model_name FROM models WHERE model_name = 'linreg_model_test_drop'"
)
assert base.cursor.fetchone()[0] == "linreg_model_test_drop"
model_test.drop()
base.cursor.execute(
"SELECT model_name FROM models WHERE model_name = 'linreg_model_test_drop'"
)
assert base.cursor.fetchone() is None
def test_cochrane_orcutt(self, airline_vd):
airline_copy = airline_vd.copy()
airline_copy["passengers_bias"] = (airline_copy["passengers"]**2 -
50 * st.random())
drop("lin_cochrane_orcutt_model_test", method="model")
model = LinearRegression("lin_cochrane_orcutt_model_test")
model.fit(airline_copy, ["passengers_bias"], "passengers")
result = st.cochrane_orcutt(
model,
airline_copy,
ts="date",
prais_winsten=True,
)
assert result.coef_["coefficient"][0] == pytest.approx(
25.8582027191416, 1e-2)
assert result.coef_["coefficient"][1] == pytest.approx(
0.00123563974547625, 1e-2)
model.drop()
def test_cochrane_orcutt(self, airline_vd, base):
airline_copy = airline_vd.copy()
airline_copy["passengers_bias"] = airline_copy[
"passengers"]**2 - 50 * st.random()
from verticapy.learn.linear_model import LinearRegression
base.cursor.execute(
"DROP MODEL IF EXISTS lin_cochrane_orcutt_model_test")
model = LinearRegression("lin_cochrane_orcutt_model_test",
cursor=base.cursor)
model.fit(airline_copy, ["passengers_bias"], "passengers")
result = st.cochrane_orcutt(
model,
airline_copy,
ts="date",
prais_winsten=True,
)
assert result.coef_["coefficient"][0] == pytest.approx(
25.8582027191416, 1e-2)
assert result.coef_["coefficient"][1] == pytest.approx(
0.00123563974547625, 1e-2)
model.drop()
def het_white(
vdf: vDataFrame, eps: str, X: list,
):
"""
---------------------------------------------------------------------------
White’s Lagrange Multiplier Test for heteroscedasticity.
Parameters
----------
vdf: vDataFrame
Input vDataFrame.
eps: str
Input residual vcolumn.
X: str
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)
X_0 = ["1"] + X
variables = []
variables_names = []
for i in range(len(X_0)):
for j in range(i, len(X_0)):
if i != 0 or j != 0:
variables += ["{} * {} AS var_{}_{}".format(X_0[i], X_0[j], i, j)]
variables_names += ["var_{}_{}".format(i, j)]
query = "(SELECT {}, POWER({}, 2) AS VERTICAPY_TEMP_eps2 FROM {}) VERTICAPY_SUBTABLE".format(
", ".join(variables), eps, vdf.__genSQL__()
)
vdf_white = vdf_from_relation(query, cursor=vdf._VERTICAPY_VARIABLES_["cursor"])
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"])
try:
model.fit(vdf_white, variables_names, "VERTICAPY_TEMP_eps2")
R2 = model.score("r2")
model.drop()
except:
try:
model.set_params({"solver": "bfgs"})
model.fit(vdf_white, variables_names, "VERTICAPY_TEMP_eps2")
R2 = model.score("r2")
model.drop()
except:
model.drop()
raise
n = vdf.shape()[0]
if len(X) > 1:
k = 2 * len(X) + math.factorial(len(X)) / 2 / (math.factorial(len(X) - 2))
else:
k = 1
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
def het_goldfeldquandt(
vdf: vDataFrame, y: str, X: list, idx: int = 0, split: float = 0.5
):
"""
---------------------------------------------------------------------------
Goldfeld-Quandt homoscedasticity test.
Parameters
----------
vdf: vDataFrame
Input vDataFrame.
y: str
Response Column.
X: list
Exogenous Variables.
idx: int, optional
Column index of variable according to which observations are sorted
for the split.
split: float, optional
Float to indicate where to split (Example: 0.5 to split on the median).
Returns
-------
tablesample
An object containing the result. For more information, see
utilities.tablesample.
"""
def model_fit(input_relation, X, y, model):
var = []
for vdf_tmp in input_relation:
model.drop()
model.fit(vdf_tmp, X, y)
model.predict(vdf_tmp, name="verticapy_prediction")
vdf_tmp["residual_0"] = vdf_tmp[y] - vdf_tmp["verticapy_prediction"]
var += [vdf_tmp["residual_0"].var()]
model.drop()
return var
check_types(
[
("y", y, [str],),
("X", X, [list],),
("idx", idx, [int, float],),
("split", split, [int, float],),
("vdf", vdf, [vDataFrame, str,],),
],
)
columns_check([y] + X, vdf)
y = vdf_columns_names([y], vdf)[0]
X = vdf_columns_names(X, vdf)
split_value = vdf[X[idx]].quantile(split)
vdf_0_half = vdf.search(vdf[X[idx]] < split_value)
vdf_1_half = vdf.search(vdf[X[idx]] > split_value)
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"])
try:
var0, var1 = model_fit([vdf_0_half, vdf_1_half], X, y, model)
except:
try:
model.set_params({"solver": "bfgs"})
var0, var1 = model_fit([vdf_0_half, vdf_1_half], X, y, model)
except:
model.drop()
raise
n, m = vdf_0_half.shape()[0], vdf_1_half.shape()[0]
F = var0 / var1
f_pvalue = f.sf(F, n, m)
result = tablesample({"index": ["F Value", "f_p_value",], "value": [F, f_pvalue],})
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
def het_arch(
vdf: vDataFrame, eps: str, ts: str, by: list = [], p: int = 1,
):
"""
---------------------------------------------------------------------------
Engle’s Test for Autoregressive Conditional Heteroscedasticity (ARCH).
Parameters
----------
vdf: vDataFrame
Input vDataFrame.
eps: str
Input residual vcolumn.
ts: str
vcolumn used as timeline. It will be to use to order the data. It can be
a numerical or type date like (date, datetime, timestamp...) vcolumn.
by: list, optional
vcolumns used in the partition.
p: int, optional
Number of lags to consider in the test.
Returns
-------
tablesample
An object containing the result. For more information, see
utilities.tablesample.
"""
check_types(
[
("eps", eps, [str],),
("ts", ts, [str],),
("p", p, [int, float],),
("vdf", vdf, [vDataFrame, str,],),
],
)
columns_check([eps, ts] + by, vdf)
eps = vdf_columns_names([eps], vdf)[0]
ts = vdf_columns_names([ts], vdf)[0]
by = vdf_columns_names(by, vdf)
X = []
X_names = []
for i in range(0, p + 1):
X += [
"LAG(POWER({}, 2), {}) OVER({}ORDER BY {}) AS lag_{}".format(
eps, i, ("PARTITION BY " + ", ".join(by)) if (by) else "", ts, i
)
]
X_names += ["lag_{}".format(i)]
query = "(SELECT {} FROM {}) VERTICAPY_SUBTABLE".format(
", ".join(X), vdf.__genSQL__()
)
vdf_lags = vdf_from_relation(query, cursor=vdf._VERTICAPY_VARIABLES_["cursor"])
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"])
try:
model.fit(vdf_lags, X_names[1:], X_names[0])
R2 = model.score("r2")
model.drop()
except:
try:
model.set_params({"solver": "bfgs"})
model.fit(vdf_lags, X_names[1:], X_names[0])
R2 = model.score("r2")
model.drop()
except:
model.drop()
raise
n = vdf.shape()[0]
k = len(X)
LM = (n - p) * R2
lm_pvalue = chi2.sf(LM, p)
F = (n - 2 * p - 1) * R2 / (1 - R2) / p
f_pvalue = f.sf(F, p, n - 2 * p - 1)
result = tablesample(
{
"index": [
"Lagrange Multiplier Statistic",
"lm_p_value",
"F Value",
"f_p_value",
],
"value": [LM, lm_pvalue, F, f_pvalue],
}
)
return result
def variance_inflation_factor(
vdf: vDataFrame, X: list, X_idx: int = None,
):
"""
---------------------------------------------------------------------------
Computes the variance inflation factor (VIF). It can be used to detect
multicollinearity in an OLS Regression Analysis.
Parameters
----------
vdf: vDataFrame
Input vDataFrame.
X: list
Input Variables.
X_idx: int
Index of the exogenous variable in X. If left to None, a tablesample will
be returned with all the variables VIF.
Returns
-------
float
VIF.
"""
check_types(
[
("X_idx", X_idx, [int],),
("X", X, [list],),
("vdf", vdf, [vDataFrame, str,],),
],
)
columns_check(X, vdf)
X = vdf_columns_names(X, vdf)
if isinstance(X_idx, str):
columns_check([X_idx], vdf)
for i in range(len(X)):
if str_column(X[i]) == str_column(X_idx):
X_idx = i
break
if isinstance(X_idx, (int, float)):
X_r = []
for i in range(len(X)):
if i != X_idx:
X_r += [X[i]]
y_r = X[X_idx]
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"])
try:
model.fit(vdf, X_r, y_r)
R2 = model.score("r2")
model.drop()
except:
try:
model.set_params({"solver": "bfgs"})
model.fit(vdf, X_r, y_r)
R2 = model.score("r2")
model.drop()
except:
model.drop()
raise
if 1 - R2 != 0:
return 1 / (1 - R2)
else:
return np.inf
elif X_idx == None:
VIF = []
for i in range(len(X)):
VIF += [variance_inflation_factor(vdf, X, i)]
return tablesample({"X_idx": X, "VIF": VIF})
else:
raise ParameterError(
f"Wrong type for Parameter X_idx.\nExpected integer, found {type(X_idx)}."
)
def seasonal_decompose(
vdf: vDataFrame,
column: str,
ts: str,
by: list = [],
period: int = -1,
polynomial_order: int = 1,
estimate_seasonality: bool = True,
rule: Union[str, datetime.timedelta] = None,
mult: bool = False,
two_sided: bool = False,
):
"""
---------------------------------------------------------------------------
Performs a seasonal time series decomposition.
Parameters
----------
vdf: vDataFrame
Input vDataFrame.
column: str
Input vcolumn to decompose.
ts: str
TS (Time Series) vcolumn to use to order the data. It can be of type date
or a numerical vcolumn.
by: list, optional
vcolumns used in the partition.
period: int, optional
Time Series period. It is used to retrieve the seasonality component.
if period <= 0, the seasonal component will be estimated using ACF. In
this case, polynomial_order must be greater than 0.
polynomial_order: int, optional
If greater than 0, the trend will be estimated using a polynomial of degree
'polynomial_order'. The parameter 'two_sided' will be ignored.
If equal to 0, the trend will be estimated using Moving Averages.
estimate_seasonality: bool, optional
If set to True, the seasonality will be estimated using cosine and sine
functions.
rule: str / time, optional
Interval to use to slice the time. For example, '5 minutes' will create records
separated by '5 minutes' time interval.
mult: bool, optional
If set to True, the decomposition type will be 'multiplicative'. Otherwise,
it is 'additive'.
two_sided: bool, optional
If set to True, a centered moving average is used for the trend isolation.
Otherwise only past values are used.
Returns
-------
vDataFrame
object containing (ts, column, TS seasonal part, TS trend, TS noise).
"""
if isinstance(by, str):
by = [by]
check_types(
[
("ts", ts, [str],),
("column", column, [str],),
("by", by, [list],),
("rule", rule, [str, datetime.timedelta,],),
("vdf", vdf, [vDataFrame,],),
("period", period, [int,],),
("mult", mult, [bool,],),
("two_sided", two_sided, [bool,],),
("polynomial_order", polynomial_order, [int,],),
("estimate_seasonality", estimate_seasonality, [bool,],),
],
)
assert period > 0 or polynomial_order > 0, ParameterError("Parameters 'polynomial_order' and 'period' can not be both null.")
columns_check([column, ts] + by, vdf)
ts, column, by = (
vdf_columns_names([ts], vdf)[0],
vdf_columns_names([column], vdf)[0],
vdf_columns_names(by, vdf),
)
if rule:
vdf_tmp = vdf.asfreq(ts=ts, rule=period, method={column: "linear"}, by=by)
else:
vdf_tmp = vdf[[ts, column]]
trend_name, seasonal_name, epsilon_name = (
"{}_trend".format(column[1:-1]),
"{}_seasonal".format(column[1:-1]),
"{}_epsilon".format(column[1:-1]),
)
by, by_tmp = "" if not (by) else "PARTITION BY " + ", ".join(vdf_columns_names(by, self)) + " ", by
if polynomial_order <= 0:
if two_sided:
if period == 1:
window = (-1, 1)
else:
if period % 2 == 0:
window = (-period / 2 + 1, period / 2)
else:
window = (int(-period / 2), int(period / 2))
else:
if period == 1:
window = (-2, 0)
else:
window = (-period + 1, 0)
vdf_tmp.rolling("avg", window, column, by_tmp, ts, trend_name)
else:
vdf_poly = vdf_tmp.copy()
X = []
for i in range(1, polynomial_order + 1):
vdf_poly[f"t_{i}"] = f"POWER(ROW_NUMBER() OVER ({by}ORDER BY {ts}), {i})"
X += [f"t_{i}"]
schema = vdf_poly._VERTICAPY_VARIABLES_["schema_writing"]
if not (schema):
schema = vdf_poly._VERTICAPY_VARIABLES_["schema"]
if not (schema):
schema = "public"
from verticapy.learn.linear_model import LinearRegression
model = LinearRegression(name="{}.VERTICAPY_TEMP_MODEL_LINEAR_REGRESSION_{}".format(schema, get_session(vdf_poly._VERTICAPY_VARIABLES_["cursor"])),
cursor=vdf_poly._VERTICAPY_VARIABLES_["cursor"],
solver="bfgs",
max_iter=100,
tol=1e-6,)
model.drop()
model.fit(vdf_poly, X, column)
coefficients = model.coef_["coefficient"]
coefficients = [str(coefficients[0])] + [f"{coefficients[i]} * POWER(ROW_NUMBER() OVER({by}ORDER BY {ts}), {i})" if i != 1 else f"{coefficients[1]} * ROW_NUMBER() OVER({by}ORDER BY {ts})" for i in range(1, polynomial_order + 1)]
vdf_tmp[trend_name] = " + ".join(coefficients)
model.drop()
if mult:
vdf_tmp[seasonal_name] = f'{column} / NULLIFZERO("{trend_name}")'
else:
vdf_tmp[seasonal_name] = vdf_tmp[column] - vdf_tmp[trend_name]
if period <= 0:
acf = vdf_tmp.acf(column=seasonal_name, ts=ts, p=23, acf_type="heatmap", show=False)
period = int(acf["index"][1].split("_")[1])
if period == 1:
period = int(acf["index"][2].split("_")[1])
vdf_tmp["row_number_id"] = f"MOD(ROW_NUMBER() OVER ({by} ORDER BY {ts}), {period})"
if mult:
vdf_tmp[
seasonal_name
] = f"AVG({seasonal_name}) OVER (PARTITION BY row_number_id) / NULLIFZERO(AVG({seasonal_name}) OVER ())"
else:
vdf_tmp[
seasonal_name
] = f"AVG({seasonal_name}) OVER (PARTITION BY row_number_id) - AVG({seasonal_name}) OVER ()"
if estimate_seasonality:
vdf_seasonality = vdf_tmp.copy()
vdf_seasonality["t_cos"] = f"COS(2 * PI() * ROW_NUMBER() OVER ({by}ORDER BY {ts}) / {period})"
vdf_seasonality["t_sin"] = f"SIN(2 * PI() * ROW_NUMBER() OVER ({by}ORDER BY {ts}) / {period})"
X = ["t_cos", "t_sin",]
schema = vdf_seasonality._VERTICAPY_VARIABLES_["schema_writing"]
if not (schema):
schema = vdf_seasonality._VERTICAPY_VARIABLES_["schema"]
if not (schema):
schema = "public"
from verticapy.learn.linear_model import LinearRegression
model = LinearRegression(name="{}.VERTICAPY_TEMP_MODEL_LINEAR_REGRESSION_{}".format(schema, get_session(vdf_seasonality._VERTICAPY_VARIABLES_["cursor"])),
cursor=vdf_seasonality._VERTICAPY_VARIABLES_["cursor"],
solver="bfgs",
max_iter=100,
tol=1e-6,)
model.drop()
model.fit(vdf_seasonality, X, seasonal_name)
coefficients = model.coef_["coefficient"]
vdf_tmp[seasonal_name] = f"{coefficients[0]} + {coefficients[1]} * COS(2 * PI() * ROW_NUMBER() OVER ({by}ORDER BY {ts}) / {period}) + {coefficients[2]} * SIN(2 * PI() * ROW_NUMBER() OVER ({by}ORDER BY {ts}) / {period})"
model.drop()
if mult:
vdf_tmp[
epsilon_name
] = f'{column} / NULLIFZERO("{trend_name}") / NULLIFZERO("{seasonal_name}")'
else:
vdf_tmp[epsilon_name] = (
vdf_tmp[column] - vdf_tmp[trend_name] - vdf_tmp[seasonal_name]
)
vdf_tmp["row_number_id"].drop()
return vdf_tmp
def test_repr(self, model):
assert "|coefficient|std_err |t_value |p_value" in model.__repr__()
model_repr = LinearRegression("lin_repr")
model_repr.drop()
assert model_repr.__repr__() == "<LinearRegression>"