参考链接:
- https://blog.csdn.net/u013869488/article/details/78244923
- https://blog.csdn.net/CalvinHARRIS/article/details/83588673
- https://cloud.tencent.com/developer/article/1331849
- https://blog.csdn.net/huangxiaoyun1900/article/details/82229708
前言:最近参加了百度的NLP专题,其中往期http://abcxueyuan.cloud.baidu.com/newlab/#/lab_detail/lab_simple_say?id=114是使用百度的paddle
目录
第一步 载入数据
from keras.datasets import boston_housing
# 读取数据
(X_train, y_train), (X_test, y_test) = boston_housing.load_data()
# sklearn
# import pandas as pd
# from sklearn.datasets import load_boston
# from sklearn.model_selection import train_test_split
# boston = load_boston()
# X = boston.data
# y = boston.target
# 转化为dataframe
# X = pd.DataFrame(X, columns=boston.feature_names)
# y = pd.DataFrame(y, columns=['MEDV'])
# 分割数据集
# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=10)
第二步 观测数据
- 数据集特征