return scores
def plotAccuracy(accuracy, pred, title):
fig = plt.figure(figsize=(10, 4), tight_layout=True)
ax = fig.add_subplot(1, 1, 1)
plt.plot(k, accuracy)
ax.set_xlabel("Predictors")
ax.set_ylabel("Accuracy")
ax.set_title(title, fontsize=12)
plt.show()
if __name__ == '__main__':
X, Y = get_training()
num_pred_list = [3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 30]
alpha_list = [0, .125, .25, .375, .5, .625, .75, .875, 1]
subsets = generate_subsets()
ten_scores_subsets = getScores(X, Y, subsets, 10)
loocv_scores_subsets = getScores(X, Y, subsets, len(X))
ten_scores_pca = getScores_pca(X, Y, num_pred_list, 10)
loocv_scores_pca = getScores_pca(X, Y, num_pred_list, len(X))
ten_scores_lasso = getScores_lasso(X, Y, alpha_list, 10)
loocv_scores_lasso = getScores_lasso(X, Y, alpha_list, len(X))
print("_______________________Subsets______________________________")
for i in range(len(subsets)):
"""Helper function that gets full set of results
Returns:
Returns a dictionary of results as follows:
{
'accuracy' : [list of accuracies],
'recall': [list of recall results],
'precision': [list of precision results]
}
"""
return self.results
if __name__ == '__main__':
from data_utils import get_training
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
X, y = get_training()
mdl = LinearDiscriminantAnalysis()
val = Validation(X, y)
pca_comp_to_test = [ 1, 3, 5, 10, 30]
results = []
best_so_far = (0, -1)
# common validation pattern
for d in pca_comp_to_test:
# update hyper params for preprocessing
val.update(pca=d)
# generally change model params
acc = val.cross_val_accuracy(mdl)
results.append(acc)
import matplotlib.pyplot as plt
from data_utils import get_training, get_testing
from sklearn.linear_model import LogisticRegression
from sklearn.decomposition import PCA
from sklearn import preprocessing
from sklearn.model_selection import cross_val_score
from my_pca import my_pca
def best_logistic_regression():
pass
if __name__ == '__main__':
# Load data
X_train, y_train = get_training()
N, D = X_train.shape
# Logistic Regression
models = [('L2, C=1', LogisticRegression()),
('L2, C=10', LogisticRegression(C=10)),
('L2, C=100', LogisticRegression(C=100)),
('L2, C=1000', LogisticRegression(C=1000)),
('L1, C=1', LogisticRegression(penalty='l1')),
('L1, C=10', LogisticRegression(penalty='l1', C=10)),
('L1, C=100', LogisticRegression(penalty='l1', C=100)),
('L1, C=1000', LogisticRegression(penalty='l1', C=1000))]
print 'Without PCA'
for name, model in models:
scores = cross_val_score(model,