第七组

Signed-off-by: 田熠 <13190684+tyvw@user.noreply.gitee.com>

大众点评数据集分析/第七组/第七组实践代码/Boston.py

@@ -0,0 +1,86 @@
+import tensorflow as tf
+dataset_path = keras.utils.get_file("housing.data",
+"https://archive.ics.uci.edu/ml/machine-learning-databases/housing/housing.data")
+column_names = ['CRIM','ZN','INDUS','CHAS','NOX',
+'RM', 'AGE', 'DIS','RAD','TAX','PTRATION', 'B', 'LSTAT', 'MEDV']
+raw_dataset = pd.read_csv(dataset_path, names=column_names,
+na_values = "?", comment='\t',
+sep=" ", skipinitialspace=True)
+dataset = raw_dataset.copy()
+#下面的函数用以返回最后n行。
+#dataset.tail(n=10)
+# 将数据集分为训练集和测试集
+# p 为训练集所占数据比例
+p=0.8
+trainDataset = dataset.sample(frac=p,random_state=0)
+testDataset = dataset.drop(trainDataset.index)
+
+import matplotlib.pyplot as plt
+fig, ax = plt.subplots()
+x = trainDataset['RM']
+y = trainDataset['MEDV']
+ax.scatter(x, y, edgecolors=(0, 0, 0))
+ax.set_xlabel('RM')
+ax.set_ylabel('MEDV')
+plt.show()
+trainInput = trainDataset['RM']
+trainTarget = trainDataset['MEDV']
+testInput = testDataset['RM']
+testTarget = testDataset['MEDV']
+
+model = keras.Sequential([
+layers.Dense(1, use_bias=True, input_shape=(1,))
+])
+
+optimizer = tf.keras.optimizers.Adam(
+learning_rate=0.01, beta_1=0.9, beta_2=0.99, epsilon=1e-05, amsgrad=False,
+name='Adam')
+model.compile(loss='mse', optimizer=optimizer, metrics=['mae','mse'])
+
+
+n_idle_epochs = 100
+earlyStopping = tf.keras.callbacks.EarlyStopping(monitor='val_loss',
+patience=n_idle_epochs, min_delta=0.01)
+class NEPOCHLogger(tf.keras.callbacks.Callback):
+def __init__(self,per_epoch=100):
+'''3 实例 4
+display: Number of batches to wait before outputting loss
+'''
+self.seen = 0
+self.per_epoch = per_epoch
+def on_epoch_end(self, epoch, logs=None):
+if epoch % self.per_epoch == 0:
+print('Epoch {}, loss {:.2f}, val_loss {:.2f},
+mae {:.2f}, val_mae {:.2f}, mse {:.2f}, val_mse {:.2f}'\
+.format(epoch, logs['loss'], logs['val_loss'],logs['mae'],
+logs['val_mae'],logs['mse'], logs['val_mse']))
+log_display = NEPOCHLogger(per_epoch=100)
+n_epochs = 2000
+history = model.fit(
+trainDataOne, trainLabelOne, batch_size=256,
+epochs=n_epochs, validation_split = 0.1, verbose=0,
+callbacks=[earlyStopping,log_display])
+#打印训练集和验证集MAE
+import numpy as np
+import pandas as pd
+import seaborn as sns
+mae = np.asarray(history.history['mae'])
+val_mae = np.asarray(history.history['val_mae'])
+num_values = (len(mae))
+values = np.zeros((num_values,2), dtype=float)
+values[:,0] = mae
+values[:,1] = val_mae
+steps = pd.RangeIndex(start=0,stop=num_values)
+data = pd.DataFrame(values, steps, columns=["mae", "va-mae"])
+sns.set(style="whitegrid")
+sns.lineplot(data=data, palette="tab10", linewidth=2.5)
+
+predictions = model.predict(testInput).flatten()
+a = plt.axes(aspect='equal')
+plt.scatter(predictions, testTarget, edgecolors=(0, 0, 0))
+plt.xlabel('True Values')
+plt.ylabel('Predictions')
+lims = [0, 50]
+plt.xlim(lims)
+plt.ylim(lims)
+_ = plt.plot(lims, lims)