首页 > 开发 > Python > 正文

OpenCV python sklearn随机超参数搜索的实现

2024-09-09 19:03:38
字体:
来源:转载
供稿:网友

本文介绍了OpenCV python sklearn随机超参数搜索的实现,分享给大家,具体如下:

"""房价预测数据集 使用sklearn执行超参数搜索"""import matplotlib as mplimport matplotlib.pyplot as pltimport numpy as npimport sklearnimport pandas as pdimport osimport sysimport tensorflow as tffrom tensorflow_core.python.keras.api._v2 import keras # 不能使用 pythonfrom sklearn.preprocessing import StandardScalerfrom sklearn.datasets import fetch_california_housingfrom sklearn.model_selection import train_test_split, RandomizedSearchCVfrom scipy.stats import reciprocalos.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'assert tf.__version__.startswith('2.')# 0.打印导入模块的版本print(tf.__version__)print(sys.version_info)for module in mpl, np, sklearn, pd, tf, keras:  print("%s version:%s" % (module.__name__, module.__version__))# 显示学习曲线def plot_learning_curves(his):  pd.DataFrame(his.history).plot(figsize=(8, 5))  plt.grid(True)  plt.gca().set_ylim(0, 1)  plt.show()# 1.加载数据集 california 房价housing = fetch_california_housing()print(housing.DESCR)print(housing.data.shape)print(housing.target.shape)# 2.拆分数据集 训练集 验证集 测试集x_train_all, x_test, y_train_all, y_test = train_test_split(  housing.data, housing.target, random_state=7)x_train, x_valid, y_train, y_valid = train_test_split(  x_train_all, y_train_all, random_state=11)print(x_train.shape, y_train.shape)print(x_valid.shape, y_valid.shape)print(x_test.shape, y_test.shape)# 3.数据集归一化scaler = StandardScaler()x_train_scaled = scaler.fit_transform(x_train)x_valid_scaled = scaler.fit_transform(x_valid)x_test_scaled = scaler.fit_transform(x_test)# 创建keras模型def build_model(hidden_layers=1, # 中间层的参数        layer_size=30,        learning_rate=3e-3):  # 创建网络层  model = keras.models.Sequential()  model.add(keras.layers.Dense(layer_size, activation="relu",                 input_shape=x_train.shape[1:])) # 隐藏层设置  for _ in range(hidden_layers - 1):    model.add(keras.layers.Dense(layer_size,                   activation="relu"))  model.add(keras.layers.Dense(1))  # 优化器学习率  optimizer = keras.optimizers.SGD(lr=learning_rate)  model.compile(loss="mse", optimizer=optimizer)  return modeldef main():  # RandomizedSearchCV  # 1.转化为sklearn的model  sk_learn_model = keras.wrappers.scikit_learn.KerasRegressor(build_model)  callbacks = [keras.callbacks.EarlyStopping(patience=5, min_delta=1e-2)]  history = sk_learn_model.fit(x_train_scaled, y_train, epochs=100,                 validation_data=(x_valid_scaled, y_valid),                 callbacks=callbacks)  # 2.定义超参数集合  # f(x) = 1/(x*log(b/a)) a <= x <= b  param_distribution = {    "hidden_layers": [1, 2, 3, 4],    "layer_size": np.arange(1, 100),    "learning_rate": reciprocal(1e-4, 1e-2),  }  # 3.执行超搜索参数  # cross_validation:训练集分成n份, n-1训练, 最后一份验证.  random_search_cv = RandomizedSearchCV(sk_learn_model, param_distribution,                     n_iter=10,                     cv=3,                     n_jobs=1)  random_search_cv.fit(x_train_scaled, y_train, epochs=100,             validation_data=(x_valid_scaled, y_valid),             callbacks=callbacks)  # 4.显示超参数  print(random_search_cv.best_params_)  print(random_search_cv.best_score_)  print(random_search_cv.best_estimator_)  model = random_search_cv.best_estimator_.model  print(model.evaluate(x_test_scaled, y_test))  # 5.打印模型训练过程  plot_learning_curves(history)if __name__ == '__main__':  main()
发表评论 共有条评论
用户名: 密码:
验证码: 匿名发表