def _bnb(t, min_freq, save=False):
if save:
clf = bnb().fit(records, labels)
save_classifier(clf, t, 'bnb', min_freq)
return ('bnb', clf)
else:
clf = load_classifier(t, 'bnb', min_freq)
return ('bnb', clf)
def naive_bayes_bnb(x_train, y_train, x_test, y_test):
model = bnb()
model.fit(x_train, y_train)
expected = y_test
predicted = model.predict(x_test)
return expected, predicted
for qid in loadData.questions:
if not loadData.questions[qid].userId in nbuserDict:
nbuserDict[loadData.questions[qid].userId] = nbuserId
nbuserId += 1
for aid in loadData.questions[qid].answers:
if not loadData.answers[aid].userId in nbuserDict:
nbuserDict[loadData.answers[aid].userId] = nbuserId
nbuserId += 1
X = np.zeros((numQuestions/5, nbuserId))
y = np.zeros(numQuestions/5)
yvalues = np.array([0, 1])
for t in range(0,10):
tag = sortedTags[t][0]
print loadData.tags[tag].tag
clf = bnb(alpha=0.001)
i = 0
for qid in loadData.questions:
i = i % (numQuestions/5)
X[i][nbuserDict[loadData.questions[qid].userId]] = 1
for aid in loadData.questions[qid].answers:
X[i][nbuserDict[loadData.answers[aid].userId]] = 1
if tag in loadData.questions[qid].tags:
y[i] = 1
else:
y[i] = 0
if i == numQuestions/5 - 1:
clf.partial_fit(X,y, classes=yvalues)
i += 1
clf.fit(X,y)
from sklearn.naive_bayes import GaussianNB as gnb, BernoulliNB as bnb
with open('train.json') as data:
train = json.load(data)
cuisine = []
ingredients = []
for i in train:
cuisine.append(i["cuisine"])
ingredients.extend(i["ingredients"])
singredients = list(set(ingredients))
traind = []
d = {singredients[i]: i for i in range(len(singredients))}
for i in train:
row = [0] * len(singredients)
for j in i["ingredients"]:
row[d[j]] = 1
traind.append(row)
k_fold = kf(n_splits=3)
ga = cvs(gnb(), traind, cuisine, cv=k_fold, n_jobs=-1)
ba = cvs(bnb(), traind, cuisine, cv=k_fold, n_jobs=-1)
f = open('2d', 'wb')
s = "Gaussian accuracy is: " + str(np.mean(ga))
print s
f.write(s)
s = "Bernoulli accuracy is: " + str(np.mean(ba))
print s
f.write(s)
def predictByBNB(features, classes, test):
clf = bnb(binarize=2)
clf.fit(features, classes)
return clf.predict(test)
