## 测试数据
测试数据./testing-X.pkl，是一个key为X，value为np.array类型对象的字典。可通过以下代码读取:

```python
import pickle
X_test = pickle.load(open("./testing-X.pkl", "rb"))['X'] # type: numpy array
```

预测结果通过csv的形式提交进行评测。csv文件分为Id列和Category列，其中Id为X_test的行号，Category为预测标签。
可以通过如下代码输出可以提交的预测结果：

```python
import pandas as pd
y_pred = clf.predict(X_test) # get predictition, clf is the classifier
df_dict  = {'Id': np.arange(len(X_test)), 'Category': y_pred}
test_df = pd.DataFrame.from_dict(df_dict, dtype=str) # turn into a DataFrame object
test_df.to_csv("./submission.csv", columns=['Id, 'Category'], index=False) # save as submission.csv under current directory.
```