def predict(self, x):
if self.coefficients is None:
raise Exception('Model has not been fitted yet')
x = core.enhance_matrix(x)
reg_eval.regression_data_check(x, width=len(self.coefficients))
return x * self.coefficients
def evaluate(self, x, y_true):
"""
Evaluates the performance of the trained model on a global and variable
level. For global, RSE, R^2 and F-statistic are standard. For variables
the SE and t-statistic is used.
:param x: Matrix of predictors
:param y_true: Vector of true y values
:return:
"""
x = core.enhance_matrix(x)
y_pred = self.predict(x)
global_metrics = [['RSE', reg_eval.residual_standard_error],
['R^2', reg_met.r_squared],
['F-statistic', reg_eval.f_statistic], ['p-value']]
var_metrics = [['SE', reg_eval.standard_error_coefs],
['t-statistic', reg_eval.t_statistic], ['p-value']]
glob_outcomes = {'Metric': [], 'Value': []}
for i in global_metrics:
if len(i) > 1:
glob_outcomes['Metric'].append(i[0])
glob_outcomes['Value'].append(i[1](x=x,
y_true=y_true,
y_pred=y_pred,
num_predictors=x.n_cols))
elif i[0] == 'p-value':
glob_outcomes['Metric'].append(i[0])
glob_outcomes['Value'].append(
f.sf(glob_outcomes['Value'][2],
dfn=len(y_pred),
dfd=x.n_cols - 1))
else:
raise Exception('Single value metric not implemented')
var_outcomes = {
'Column': list(range(x.n_cols)),
'Coefficient': self.coefficients.data
}
for i in var_metrics:
if len(i) > 1:
var_outcomes[i[0]] = i[1](x=x,
y_true=y_true,
y_pred=y_pred,
coefs=var_outcomes['Coefficient'])
elif i[0] == 'p-value':
var_outcomes[i[0]] = [
2 * t.sf(abs(float(score)),
len(y_pred) - x.n_cols)
for score in var_outcomes['t-statistic']
]
print(tabulate(glob_outcomes, headers='keys'))
print(tabulate(var_outcomes, headers='keys'))
return glob_outcomes, var_outcomes
def fit(self, x, y_true):
"""
Fits the parameters of X to predict the value y with model criterion
:param x: Matrix with equal amounts of rows as y
:param y_true: Column Vector with length equal to rows in X
"""
if self.criterion != 'LS':
raise Exception('Only Least Squares is implemented')
reg_eval.regression_data_check(x, y_true)
x = core.enhance_matrix(x)
self.coefficients = (x.transpose() *
x).inverse() * x.transpose() * y_true
def t_statistic(x, y_true, y_pred, coefs, number_type=float, **kwargs):
x = core.enhance_matrix(x)
se_coefs = standard_error_coefs(x, y_true, y_pred, number_type)
return [coefs[i] / se_coefs[i] for i in range(len(coefs))]
def standard_error_coefs(x, y_true, y_pred, number_type=float, **kwargs):
x = core.enhance_matrix(x)
mse = ((y_true - y_pred)**2).sum() / (len(y_true) - x.n_cols)
matrix = (x.transpose() * x).inverse()
return [(mse * matrix.data[i][i])**0.5 for i in range(x.n_cols)]
def score(self, x, y_true, metric=reg_met.r_squared, number_type=float):
x = core.enhance_matrix(x)
if self.coefficients is None:
raise Exception('Model has not been fitted yet')
return metric(y_true, self.predict(x), number_type)