pp = pprint.PrettyPrinter(depth=6)
def get_best_k_score_noscale(x, y):
kf = KFold(len(x), n_folds=5, shuffle=True, random_state=42)
result = dict()
for k in range(1,51):
knn = KNeighborsClassifier(n_neighbors=k)
scores = cross_val_score(knn, x, y, cv=kf)
result[k] = mean(scores)
sorted_x = sorted(result.items(), key=operator.itemgetter(1))
return sorted_x[-1]
wine_data = pandas.read_csv('Data/wine.data', header=None)
datay = wine_data[0]
datax = wine_data[wine_data.columns[1:14]]
# questions 1 and 2
k, score = get_best_k_score_noscale(datax, datay)
save_to_file("Submissions/question1.txt", str(k))
save_to_file("Submissions/question2.txt", str(score))
datax_scale = scale(datax)
k, score = get_best_k_score_noscale(datax_scale, datay)
save_to_file("Submissions/question3.txt", str(k))
save_to_file("Submissions/question4.txt", str(score))
from statistics import mean
import sklearn
import sklearn.datasets
from sklearn.cross_validation import KFold, cross_val_score
from sklearn.neighbors import KNeighborsRegressor
from sklearn.preprocessing import scale
import numpy as np
from Common.common_io import save_to_file
pp = pprint.PrettyPrinter(depth=6)
boston = sklearn.datasets.load_boston()
x = scale(boston.data)
y = boston.target
kf = KFold(len(x), n_folds=5, shuffle=True, random_state=42)
result = dict()
for p in np.linspace(1, 10, num=200):
regressor = KNeighborsRegressor(n_neighbors=5, weights='distance', p=p)
scores = cross_val_score(regressor, x, y, cv=kf, scoring='mean_squared_error')
result[p] = mean(scores)
sorted_x = sorted(result.items(), key=operator.itemgetter(1))
pp.pprint(sorted_x)
save_to_file("Submissions/question1.txt", str(sorted_x[-1][0]))
print(len(train_data))
def my_acc_score(test, pred):
true_count = 0
for i, val in enumerate(test):
if test[i] == pred[i]:
true_count += 1
return true_count / len(pred)
def get_accuracy_score(perc, trainx, trainy, testx, testy):
perc.fit(trainx, trainy)
y_pred = perc.predict(testx)
return accuracy_score(testy, y_pred)
perc1 = Perceptron(random_state=241)
# non-normalized
score_nonnorm = get_accuracy_score(perc1, x_train, y_train, x_test, y_test)
# normalized
score_norm = get_accuracy_score(perc1, x_train_scaled, y_train, x_test_scaled, y_test)
# diff
print("Score non-normalized: {0}".format(score_nonnorm))
print("Score normalized: {0}".format(score_norm))
diff = score_norm - score_nonnorm
print("Score advancement: {0}".format(diff))
save_to_file("Submissions/question1.txt", str(diff))
C = 10
for _ in range(10001):
w1_temp = w1 + k * (1.0 / len(y)) * sum([y[i]*X[i][0] * (1 - (1.0 / (1 + exp(-y[i] * (w1 * X[i][0] + w2 * X[i][1]))))) for i in range(len(y))])
w2_temp = w2 + k * (1.0 / len(y)) * sum([y[i]*X[i][1] * (1 - (1.0 / (1 + exp(-y[i] * (w1 * X[i][0] + w2 * X[i][1]))))) for i in range(len(y))])
if reg:
w1_temp -= k*C*w1
w2_temp -= k*C*w2
if sqrt((w1_temp-w1)**2 + (w2_temp-w2)**2) < 0.00001:
break
w1 = w1_temp
w2 = w2_temp
a = [(1 / (1 + exp(-w1*X[i][0] - w2 *X[i][1]))) for i in range(len(y))]
return roc_auc_score(y, a)
train_data = genfromtxt('Data/data-logistic.csv', delimiter=',')
y = train_data[:, 0]
X = train_data[:, [1, 2]]
score_noreg = get_score(X,y,reg=False)
score_reg = get_score(X,y,reg=True)
answer = "{0} {1}".format(round(score_noreg,3), round(score_reg,3))
save_to_file("Submissions/question1.txt", answer)
print(answer)