advanced-algorithmic-trading

296
sample_dict["seed_%s" % i] = np.array(
)
sample_dict["seed_%s" % i]
# Create the "average test MSE" series by averaging the
# test MSE for each degree of the linear regression model,
# across all random samples
sample_dict["avg"] = np.zeros(degrees)
for i in range(1, random_seeds+1):
sample_dict["avg"] += sample_dict["seed_%s" % i]
sample_dict["avg"] /= float(random_seeds)
return sample_dict
def k_fold_cross_val_poly(folds, degrees, X, y):
"""
Use the k-fold cross validation method to create
k separate training test splits over linear
regression models of varying flexibility
"""
# Create the KFold object and
# set the initial fold to zero
n = len(X)
kf = KFold(n, n_folds=folds)
kf_dict = dict(
[("fold_%s" % i,[]) for i in range(1, folds+1)]
)
fold = 0
# Loop over the k-folds
for train_index, test_index in kf:
fold += 1
print("Fold: %s" % fold)
X_train, X_test = X.ix[train_index], X.ix[test_index]
y_train, y_test = y.ix[train_index], y.ix[test_index]
# Increase degree of linear regression polynomial order
for d in range(1, degrees+1):
print("Degree: %s" % d)
# Create the model and fit it
polynomial_features = PolynomialFeatures(
degree=d, include_bias=False
)
linear_regression = LinearRegression()