There is only 1 feature dim. But the result is unreasonable. The code and data is below. The purpose of the code is to judge whether the two sentences are the same:
In fact, the final input to the model is: feature is [1] with label 1, and feature is [0] with label 0.
import pandas as pd
import xgboost as xgb
d = pd.read_csv("data_small.tsv",sep=" ")
def my_test(sent1,sent2):
result = [0]
if "我想说" in sent1 and "我想说" in sent2:
result[0] = 1
if "我想听" in sent1 and "我想听" in sent2:
result[0] = 1
return result
fea_ = d.apply(lambda row: my_test(row['sent1'], row['sent2']), axis=1).tolist()
labels = d["label"].tolist()
fea = pd.DataFrame(fea_)
for i in range(len(fea_)):
print(fea_[i],labels[i])
labels = pd.DataFrame(labels)
from sklearn.model_selection import train_test_split
# train_x_pd_split, valid_x_pd, train_y_pd_split, valid_y_pd = train_test_split(fea, labels, test_size=0.2,
# random_state=1234)
train_x_pd_split = fea[0:16]
valid_x_pd = fea[16:20]
train_y_pd_split = labels[0:16]
valid_y_pd = labels[16:20]
train_xgb_split = xgb.DMatrix(train_x_pd_split, label=train_y_pd_split)
valid_xgb = xgb.DMatrix(valid_x_pd, label=valid_y_pd)
watch_list = [(train_xgb_split, 'train'), (valid_xgb, 'valid')]
params3 = {
'seed': 1337,
'colsample_bytree': 0.48,
'silent': 1,
'subsample': 1,
'eta': 0.05,
'objective': 'binary:logistic',
'eval_metric': 'logloss',
'max_depth': 8,
'min_child_weight': 20,
'nthread': 8,
'tree_method': 'hist',
}
xgb_trained_model = xgb.train(params3, train_xgb_split, 1000, watch_list, early_stopping_rounds=50,
verbose_eval=10)
# xgb_trained_model.save_model("predict/model/xgb_model_all")
print("feature importance 0:")
importance = xgb_trained_model.get_fscore()
temp1 = []
temp2 = []
for k in importance:
temp1.append(k)
temp2.append(importance[k])
print("-----")
feature_importance_df = pd.DataFrame({
'column': temp1,
'importance': temp2,
}).sort_values(by='importance')
# print(feature_importance_df)
feature_sort_list = feature_importance_df["column"].tolist()
feature_importance_list = feature_importance_df["importance"].tolist()
print()
for i,item in enumerate(feature_sort_list):
print(item,feature_importance_list[i])
train_x_xgb = xgb.DMatrix(train_x_pd_split)
train_predict = xgb_trained_model.predict(train_x_xgb)
print(train_predict)
train_predict_binary = (train_predict >= 0.5) * 1
print("TRAIN DATA SELF")
from sklearn import metrics
print('LogLoss: %.4f' % metrics.log_loss(train_y_pd_split, train_predict))
print('AUC: %.4f' % metrics.roc_auc_score(train_y_pd_split, train_predict))
print('ACC: %.4f' % metrics.accuracy_score(train_y_pd_split, train_predict_binary))
print('Recall: %.4f' % metrics.recall_score(train_y_pd_split, train_predict_binary))
print('F1-score: %.4f' % metrics.f1_score(train_y_pd_split, train_predict_binary))
print('Precesion: %.4f' % metrics.precision_score(train_y_pd_split, train_predict_binary))
print()
valid_xgb = xgb.DMatrix(valid_x_pd)
valid_predict = xgb_trained_model.predict(valid_xgb)
print(valid_predict)
valid_predict_binary = (valid_predict >= 0.5) * 1
print("TEST DATA PERFORMANCE")
from sklearn import metrics
print('LogLoss: %.4f' % metrics.log_loss(valid_y_pd, valid_predict))
print('AUC: %.4f' % metrics.roc_auc_score(valid_y_pd, valid_predict))
print('ACC: %.4f' % metrics.accuracy_score(valid_y_pd, valid_predict_binary))
print('Recall: %.4f' % metrics.recall_score(valid_y_pd, valid_predict_binary))
print('F1-score: %.4f' % metrics.f1_score(valid_y_pd, valid_predict_binary))
print('Precesion: %.4f' % metrics.precision_score(valid_y_pd, valid_predict_binary))
data:
sent1 sent2 label
我想听 我想听 1
我想听 我想说 0
我想说 我想说 1
我想说 我想听 0
我想听 我想听 1
我想听 我想说 0
我想说 我想说 1
我想说 我想听 0
我想听 我想听 1
我想听 我想说 0
我想说 我想说 1
我想说 我想听 0
我想听 我想听 1
我想听 我想说 0
我想说 我想说 1
我想说 我想听 0
我想听 我想听 1
我想听 我想说 0
我想说 我想说 1
我想说 我想听 0
result:
TRAIN DATA SELF
LogLoss: 0.6931
AUC: 0.5000
ACC: 0.5000
Recall: 1.0000
F1-score: 0.6667
Precesion: 0.5000
TEST DATA PERFORMANCE
LogLoss: 0.6931
AUC: 0.5000
ACC: 0.5000
Recall: 1.0000
F1-score: 0.6667
Precesion: 0.5000