Dave_lzw的博客

from sklearn.datasets import fetch_openmlimport matplotlibimport matplotlib.pyplot as pltimport numpy as npdef sort_by_target(mnist): reorder_train = np.array(sorted([(target, i) for i, target in enumerate(mnist.target[:60000])]))[:, 1] reorder

# 线性回归模型# from sklearn.linear_model import LinearRegression## lin_reg = LinearRegression()# lin_reg.fit(housing_prepared,housing_labels)## some_data = housing.iloc[:5]# some_labels = housing_labels.iloc[:5]# some_data_prepared = full_pipeline.trans

from sklearn.pipeline import Pipelinefrom sklearn.preprocessing import StandardScalerfrom sklearn.base import BaseEstimator , TransformerMixinrooms_ix , bedrooms_ix , population_ix , household_ix = 3 , 4 , 5 , 6# 自定义转换器：添加组合后的属性class CombinedAttri.

########## data_clear ##########import numpy as npimport osimport pandas as pdfrom create_test import split_test_by_category########## 获取训练、测试集 ################HOUSING_PATH = "D:\\data"def load_housing_data(housing_path): csv_path = os.path.j

train：test = 0.2数据集属性：1.load_data.pyimport pandas as pdimport osimport matplotlib.pyplot as pltfrom create_test import split_train_testfrom create_test import split_train_by_idHOUSING_PATH = "D:\\data" # 数据集路径# 加载housing.csv数据集def load_housin

基本逻辑就是保持训练好的模型，然后再load_model()加载，用新数据集训练易错点比如第一次训练得到模型a.model,下次利用load_model()加载该模型，对新数据集进行训练，如果不加处理的话很可能报错：ValueError: Error when checking target: expected input_6 to have shape (13966,) but got array with shape (11640,)我这里是因为 ：模型训练时的数据集中，poi_loc数据.