def cal_subject(train_vec, test_vec, subject_list):
bdc = Bdc.cal_bdc(train_vec, subject_list, 10)
train_vec_tmp = train_vec.copy()
for i in range(train_vec_tmp.shape[0]):
for j in range(train_vec_tmp.shape[1]):
if train_vec_tmp[i][j] != 0:
train_vec_tmp[i][j] = bdc[j] * train_vec[i][j]
for i in range(test_vec.shape[0]):
for j in range(test_vec.shape[1]):
if test_vec[i][j] != 0:
test_vec[i][j] = bdc[j] * test_vec[i][j]
# clf = svm.LinearSVC()
clf = lgb.LGBMClassifier(boosting_type='gbdt', num_leaves=55, reg_alpha=0.0, reg_lambda=1,
max_depth=15, n_estimators=6000, objective='binary',
subsample=0.8, colsample_bytree=0.8, subsample_freq=1,
learning_rate=0.06, min_child_weight=1, random_state=20, n_jobs=4)
clf.fit(train_vec_tmp, subject_list)
predict_subject = clf.predict(test_vec)
print(predict_subject)
return predict_subject
def get_res(iter, baseline):
train_vec = pd.read_csv('../content_vec_withoutD.csv', header=None)
test_file = pd.read_csv('../data/test_public.csv')
# train_vec_sentiment = pd.read_csv('../content_vec_sentiment.csv', header=None)
train_vec = np.array(train_vec)
# train_vec_sentiment = np.array(train_vec_sentiment)
data = pd.read_csv('../data/train.csv')
subject_vocab = list(
['价格', '配置', '操控', '舒适性', '油耗', '动力', '内饰', '安全性', '空间', '外观'])
subject_list = list()
for i in data['subject']:
for k in range(10):
if subject_vocab[k] == i:
subject_list.append(k)
break
value_list = list()
for i in data['sentiment_value']:
value_list.append(i)
bdc = Bdc.cal_bdc(train_vec, subject_list, 10)
for i in range(train_vec.shape[0]):
for j in range(train_vec.shape[1]):
if train_vec[i][j] > 0:
train_vec[i][j] = bdc[j]
print(train_vec)
test_vec = Doc2Vec.test2vec()
for i in range(test_vec.shape[0]):
for j in range(test_vec.shape[1]):
if test_vec[i][j] > 0:
test_vec[i][j] = bdc[j]
print(test_vec)
test_id = list(test_file['content_id'])
res_id, res_subject, value_list = Lgb.cal_subject_mul(
train_vec, subject_list, test_id, test_vec, iter, baseline)
GetResult.res2doc_mul(res_id, res_subject, value_list)
def cv_test_mul():
train_vec = pd.read_csv(
'/home/hujoe/PycharmProjects/df-2018-NLP/content_vec_withoutD.csv',
header=None)
test_file = pd.read_csv(
'/home/hujoe/PycharmProjects/df-2018-NLP/data/test_public.csv')
# train_vec_sentiment = pd.read_csv('../content_vec_sentiment.csv', header=None)
train_vec = np.array(train_vec)
# train_vec_sentiment = np.array(train_vec_sentiment)
data = pd.read_csv(
'/home/hujoe/PycharmProjects/df-2018-NLP/data/train.csv')
subject_vocab = list(
['价格', '配置', '操控', '舒适性', '油耗', '动力', '内饰', '安全性', '空间', '外观'])
subject_list = list()
for i in data['subject']:
for k in range(10):
if subject_vocab[k] == i:
subject_list.append(k)
break
subject_list = np.array(subject_list)
value_list = list()
for i in data['sentiment_value']:
value_list.append(i)
value_list = np.array(value_list)
bdc = Bdc.cal_bdc(train_vec, subject_list, 10)
for i in range(train_vec.shape[0]):
for j in range(train_vec.shape[1]):
if train_vec[i][j] > 0:
train_vec[i][j] = bdc[j]
print(train_vec)
test_vec = Doc2Vec.test2vec()
for i in range(test_vec.shape[0]):
for j in range(test_vec.shape[1]):
if test_vec[i][j] > 0:
test_vec[i][j] = bdc[j]
test_id = list(test_file['content_id'])
X, test, y, test_id, y1 = train_vec, test_vec, value_list, test_id, subject_list
N = 10
res = open('res2.txt', 'w')
# kf = StratifiedKFold(n_splits=N, random_state=2018).split(X, y)
for i in range(10):
subject_oh = y1.copy()
for l in range(len(subject_oh)):
if subject_oh[l] != i:
subject_oh[l] = 0
else:
subject_oh[l] = 1
params = {
'boosting_type': 'gbdt',
'num_leaves': 55,
'reg_alpha': 0.1,
'reg_lambda': 1,
'max_depth': 15,
'objective': 'binary',
'subsample': 0.8,
'colsample_bytree': 0.8,
'subsample_freq': 1,
'learning_rate': 0.06,
'min_child_weight': 1,
'random_state': 20,
'n_jobs': 4
}
data_train = lgb.Dataset(X, subject_oh)
clf = lgb.cv(params,
data_train,
num_boost_round=10000,
nfold=5,
stratified=False,
shuffle=True,
metrics='rmse',
early_stopping_rounds=50,
verbose_eval=50,
show_stdv=True,
seed=0)
res.write(str(len(clf['rmse-mean'])))
res.write(' ')
res.write(str(clf['rmse-mean'][-1]))
res.write('\n')
def run_base_bdc():
train_vec = pd.read_csv(
'/home/hujoe/PycharmProjects/df-2018-NLP/content_vec_withoutD.csv',
header=None)
test_file = pd.read_csv(
'/home/hujoe/PycharmProjects/df-2018-NLP/data/test_public.csv')
# train_vec_sentiment = pd.read_csv('../content_vec_sentiment.csv', header=None)
train_vec = np.array(train_vec)
# train_vec_sentiment = np.array(train_vec_sentiment)
data = pd.read_csv(
'/home/hujoe/PycharmProjects/df-2018-NLP/data/train.csv')
subject_vocab = list(
['价格', '配置', '操控', '舒适性', '油耗', '动力', '内饰', '安全性', '空间', '外观'])
subject_list = list()
for i in data['subject']:
for k in range(10):
if subject_vocab[k] == i:
subject_list.append(k)
break
subject_list = np.array(subject_list)
value_list = list()
for i in data['sentiment_value']:
value_list.append(i)
value_list = np.array(value_list)
bdc = Bdc.cal_bdc(train_vec, subject_list, 10)
for i in range(train_vec.shape[0]):
for j in range(train_vec.shape[1]):
if train_vec[i][j] > 0:
train_vec[i][j] = bdc[j]
print(train_vec)
test_vec = Doc2Vec.test2vec()
for i in range(test_vec.shape[0]):
for j in range(test_vec.shape[1]):
if test_vec[i][j] > 0:
test_vec[i][j] = bdc[j]
print(test_vec)
test_id = list(test_file['content_id'])
N = 10
kf = StratifiedKFold(n_splits=N,
random_state=2018).split(train_vec, subject_list)
clf = lgb.LGBMClassifier(boosting_type='gbdt',
num_leaves=80,
reg_alpha=0.1,
reg_lambda=1,
max_depth=8,
n_estimators=500,
objective='binary',
subsample=0.8,
colsample_bytree=0.8,
subsample_freq=1,
learning_rate=0.06,
min_child_weight=1,
random_state=20,
n_jobs=4)
clf_1 = lgb.LGBMClassifier(boosting_type='gbdt',
num_leaves=80,
reg_alpha=0.1,
reg_lambda=1,
max_depth=8,
n_estimators=10,
objective='binary',
subsample=0.8,
colsample_bytree=0.8,
subsample_freq=1,
learning_rate=0.06,
min_child_weight=1,
random_state=20,
n_jobs=4)
y_train_oofp = np.zeros_like(subject_list, dtype='float64')
y_train_oofp1 = np.zeros_like(subject_list, dtype='float64')
'''
y_train_oofp:
y_y_train_oofp1:
'''
y_test_oofp = np.zeros((test_vec.shape[0], N))
y_test_oofp_1 = np.zeros((test_vec.shape[0], N))
acc = 0
vcc = 0
l = 0
ll = 0
for i, (train_fold, test_fold) in enumerate(kf):
X_train, X_validate, label_train, label_validate, label_1_train, label_1_validate, = \
train_vec[train_fold, :], train_vec[test_fold,:], value_list[train_fold], value_list[test_fold], subject_list[train_fold], subject_list[test_fold]
clf.fit(X_train, label_train)
val_ = clf.predict(X_validate)
y_train_oofp[test_fold] = val_
if micro_avg_f1(label_validate, val_) > 0.7:
l += 1
print('sentiment_value_f1:%f' % micro_avg_f1(label_validate, val_))
acc += micro_avg_f1(label_validate, val_)
result = clf.predict(test_vec)
y_test_oofp[:, i] = result
# clf = svm.LinearSVC(loss='hinge', tol=1e-4, C=0.6)
clf_1.fit(X_train, label_1_train)
val_1 = clf_1.predict(X_validate)
y_train_oofp1[test_fold] = val_
if micro_avg_f1(label_1_validate, val_1) > 0.6:
ll += 1
vcc += micro_avg_f1(label_1_validate, val_1)
result = clf_1.predict(test_vec)
y_test_oofp_1[:, i] = result
print(acc / l)
print(vcc / ll)
lbl = pk.load(open('../tmp/label_encoder.sav', 'rb'))
res_2 = []
for i in range(y_test_oofp_1.shape[0]):
tmp = []
for j in range(N):
tmp.append(int(y_test_oofp_1[i][j]))
word_counts = Counter(tmp)
yes = word_counts.most_common(1)
res_2.append(lbl.inverse_transform([yes[0][0]])[0])
res = []
for i in range(y_test_oofp.shape[0]):
tmp = []
for j in range(N):
tmp.append(y_test_oofp[i][j])
res.append(max(set(tmp), key=tmp.count))
result = pd.DataFrame()
result['content_id'] = list(test_id)
result['subject'] = list(res_2)
result['subject'] = result['subject']
result['sentiment_value'] = list(res)
result['sentiment_value'] = result['sentiment_value'].astype(int)
result['sentiment_word'] = ''
result.to_csv('../submit_bdc.csv', index=False)
def cal_value(train_vec, test_vec, subject_list, predict_subject, value_list):
predict_value = np.zeros(len(predict_subject))
for i in range(10):
train_i = 0
test_i = 0
for d in subject_list:
if d == i:
train_i += 1
for d in predict_subject:
if d == i:
test_i += 1
train_vec_with_subject = np.zeros([train_i, train_vec.shape[1]])
value_list_with_subject = np.zeros([train_i])
test_vec_with_subject = np.zeros([test_i, test_vec.shape[1]])
k = 0
for d in range(train_vec.shape[0]):
if subject_list[d] == i:
train_vec_with_subject[k] = train_vec[d]
value_list_with_subject[k] = value_list[d]
k += 1
k = 0
for d in range(test_vec.shape[0]):
if predict_subject[d] == i:
test_vec_with_subject[k] = test_vec[d]
k += 1
bdc = Bdc.cal_bdc(train_vec_with_subject, value_list_with_subject, 3)
for k in range(train_vec_with_subject.shape[0]):
for j in range(train_vec_with_subject.shape[1]):
if train_vec_with_subject[k][j] != 0:
train_vec_with_subject[k][j] = bdc[j] * train_vec_with_subject[k][j]
# if j in high_weight_list:
# train_vec_with_subject[k][j] = 3 * train_vec_with_subject[k][j]
for k in range(test_vec_with_subject.shape[0]):
for j in range(test_vec_with_subject.shape[1]):
if test_vec_with_subject[k][j] != 0:
test_vec_with_subject[k][j] = bdc[j] * test_vec_with_subject[k][j]
# if j in high_weight_list:
# test_vec_with_subject[k][j] = 3 * test_vec_with_subject[k][j]
# clf = svm.LinearSVC()
clf = lgb.LGBMClassifier(boosting_type='gbdt', num_leaves=30, reg_alpha=0.0, reg_lambda=1,
max_depth=6, n_estimators=6000, objective='binary',
subsample=0.8, colsample_bytree=0.8, subsample_freq=1,
learning_rate=0.06, min_child_weight=1, random_state=20, n_jobs=4,
min_child_samples=5)
clf.fit(train_vec_with_subject, value_list_with_subject)
print(test_vec_with_subject.shape)
predict_value_i = clf.predict(test_vec_with_subject)
k = 0
for d in range(len(predict_subject)):
if i == predict_subject[d]:
predict_value[d] = predict_value_i[k]
k += 1
return predict_value
test_vec_with_subject = np.zeros([test_i, test_vec.shape[1]])
k = 0
for d in range(train_vec.shape[0]):
if subject_list[d] == i:
train_vec_with_subject[k] = train_vec[d]
value_list_with_subject[k] = value_list[d]
k += 1
k = 0
for d in range(test_vec.shape[0]):
if predict_subject[d] == i:
test_vec_with_subject[k] = test_vec[d]
k += 1
bdc = Bdc.cal_bdc(train_vec_with_subject, value_list_with_subject, 3)
for k in range(train_vec_with_subject.shape[0]):
for j in range(train_vec_with_subject.shape[1]):
if train_vec_with_subject[k][j] != 0:
train_vec_with_subject[k][
j] = bdc[j] * train_vec_with_subject[k][j]
# if j in high_weight_list:
# train_vec_with_subject[k][j] = 3 * train_vec_with_subject[k][j]
for k in range(test_vec_with_subject.shape[0]):
for j in range(test_vec_with_subject.shape[1]):
if test_vec_with_subject[k][j] != 0:
test_vec_with_subject[k][
j] = bdc[j] * test_vec_with_subject[k][j]
# if j in high_weight_list: