def test_hard_vote():
X,y,test_X,test_Y =get_test_data()
print("bag of words")
bow = BagOfWordsClassifier()
bow_probs = bow.get_proba(X,y,test_X,prefix="t")
print("direct attribute")
da = DirectAttributeClassifier()
da_probs = da.get_proba(X,y,test_X,prefix="t")
probs = zip(*[item for p in [bow_probs,da_probs] for item in p])
#train_probs = probs[0]
test_probs = probs[1]
print(len(test_probs))
preds = [x.idxmax(1) for x in test_probs]
pred = np.zeros(len(preds[0]),dtype=np.int8)
print(len(pred))
for i in range(len(preds[0])):
votes = [p[i] for p in preds]
print(votes)
pred[i]= max(set(votes),key=votes.count)
print(pred[i])
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
le.fit(y)
pred = le.inverse_transform(pred)
print(metrics.accuracy_score(test_Y,pred))
"""
def predict():
X,y,test_X,ids =get_predict_data()
print("bag of words")
bow = BagOfWordsClassifier()
bow_probs = bow.get_proba(X,y,test_X,prefix="p_")
print("direct attribute")
da = DirectAttributeClassifier()
da_probs = da.get_proba(X,y,test_X,prefix="p_")
probs = zip(*[item for p in [bow_probs,da_probs] for item in p])
train_probs = probs[0]
test_probs = probs[1]
print(len(train_probs))
for prob in train_probs:
print(prob.shape)
print(type(prob))
train_attr = pd.concat(train_probs,axis=1)
print(train_attr.shape)
print(type(train_attr))
test_attr = pd.concat(test_probs,axis=1)
print(test_attr.shape)
print(type(test_attr))
clf = LogisticRegression()
clf.fit(train_attr,y)
pred=clf.predict(test_attr)
result = pd.DataFrame({'id':ids,'cuisine':pred})
result[['id','cuisine']].to_csv("av_submission.csv",index=False,cols=["id","cuisine"],engine='python')
def test_vote_soft():
X,y,test_X,test_Y =get_test_data()
print("bag of words")
bow = BagOfWordsClassifier()
bow_probs = bow.get_proba(X,y,test_X,prefix="t")
print("direct attribute")
da = DirectAttributeClassifier()
da_probs = da.get_proba(X,y,test_X,prefix="t")
probs = zip(*[item for p in [bow_probs,da_probs] for item in p])
train_probs = probs[0]
test_probs = probs[1]
print(len(train_probs))
for prob in train_probs:
print(prob.shape)
print(type(prob))
#train_attr = reduce(lambda a,b:a+b,train_probs)
test_attr = reduce(lambda a,b:a+b,test_probs)
pred = test_attr.idxmax(1)
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
le.fit(y)
pred = le.inverse_transform(pred)
print(metrics.accuracy_score(test_Y,pred))
def test():
X,y,test_X,test_Y =get_test_data()
print("bag of words")
bow = BagOfWordsClassifier()
bow_probs = bow.get_proba(X,y,test_X,prefix="t")
print("direct attribute")
da = DirectAttributeClassifier()
da_probs = da.get_proba(X,y,test_X,prefix="t")
probs = zip(*[item for p in [bow_probs,da_probs] for item in p])
train_probs = probs[0]
test_probs = probs[1]
print(len(train_probs))
for prob in train_probs:
print(prob.shape)
print(type(prob))
train_attr = pd.concat(train_probs,axis=1)
print(train_attr.shape)
print(type(train_attr))
test_attr = pd.concat(test_probs,axis=1)
print(test_attr.shape)
print(type(test_attr))
#clf = LogisticRegression()
#clf = svm.SVC()
"""
params={'kernel':('rbf','linear','poly','sigmoid'),'C':[1,10]}
clf = grid_search.GridSearchCV(svm.SVC(),params,cv=5)
params={'penalty':('l1','l2'),'C':[1,10]}
clf = grid_search.GridSearchCV(LogisticRegression(),params,cv=5)
"""
#clf = SGDClassifier(loss="log")
"""
params = {'loss':['hinge','log','modified_huber','squared_hinge','perceptron'],
'penalty':['l1','l2','elasticnet'],
'alpha':[0.0001,0.001,0.01,0.1]}
clf = grid_search.GridSearchCV(SGDClassifier(),params,cv=5)
"""
"""
clf.fit(train_attr,y)
#print(clf.best_params_)
pred = clf.predict(test_attr)
print(clf)
print(metrics.accuracy_score(test_Y,pred))
"""
"""
clf = RandomForestClassifier(n_estimators=50)
benchmark(clf,train_attr,y,test_attr,test_Y)
"""
"""
clf = GradientBoostingClassifier(n_estimators=50)
benchmark(clf,train_attr,y,test_attr,test_Y)
clf=DecisionTreeClassifier()
benchmark(clf,train_attr,y,test_attr,test_Y)
"""
"""
clf = AdaBoostClassifier(base_estimator=SGDClassifier(loss="log"))
benchmark(clf,train_attr,y,test_attr,test_Y)
clf = BaggingClassifier(LogisticRegression())
benchmark(clf,train_attr,y,test_attr,test_Y)
clf = LogisticRegression()
benchmark(clf,train_attr,y,test_attr,test_Y)
clf = SGDClassifier(loss="log")
benchmark(clf,train_attr,y,test_attr,test_Y)
clf=Perceptron()
benchmark(clf,train_attr,y,test_attr,test_Y)
clf =GaussianNB()
benchmark(clf,train_attr,y,test_attr,test_Y)
"""
"""
