import numpy as np  import pandas as pd  import matplotlib.pyplot as plt  import tensorflow as tf  from tensorflow.keras import models,layers    dftrain_raw = pd.read_csv('./data/titanic/train.csv')  dftest_raw = pd.read_csv('./data/titanic/test.csv')  dftrain_raw.head(10)

%matplotlib inline  %config InlineBackend.figure_format = 'png'  ax = dftrain_raw['Survived'].value_counts().plot(kind = 'bar',       figsize = (12,8),fontsize=15,rot = 0)  ax.set_ylabel('Counts',fontsize = 15)  ax.set_xlabel('Survived',fontsize = 15)  plt.show()

年龄分布情况    %matplotlib inline  %config InlineBackend.figure_format = 'png'  ax = dftrain_raw['Age'].plot(kind = 'hist',bins = 20,color= 'purple',                      figsize = (12,8),fontsize=15)    ax.set_ylabel('Frequency',fontsize = 15)  ax.set_xlabel('Age',fontsize = 15)  plt.show()

%matplotlib inline  %config InlineBackend.figure_format = 'png'  ax = dftrain_raw.query('Survived == 0')['Age'].plot(kind = 'density',                        figsize = (12,8),fontsize=15)  dftrain_raw.query('Survived == 1')['Age'].plot(kind = 'density',                        figsize = (12,8),fontsize=15)  ax.legend(['Survived==0','Survived==1'],fontsize = 12)  ax.set_ylabel('Density',fontsize = 15)  ax.set_xlabel('Age',fontsize = 15)  plt.show()

dfresult=pd.DataFrame()  #将船票类型转换为one-hot编码  dfPclass=pd.get_dummies(dftrain_raw["Pclass"])  #设置列名  dfPclass.columns =['Pclass_'+str(x) for x in dfPclass.columns]  dfresult = pd.concat([dfresult,dfPclass],axis = 1)  dfresult

#Sex  dfSex = pd.get_dummies(dftrain_raw['Sex'])  dfresult = pd.concat([dfresult,dfSex],axis = 1)  dfresult

#将缺失值用0填充  dfresult['Age'] = dftrain_raw['Age'].fillna(0)  #增加一列数据为Age_null，同时将不为0的数据用0，将为0的数据用1表示，也就是标记出现0的位置  dfresult['Age_null'] = pd.isna(dftrain_raw['Age']).astype('int32')  dfresult

dfresult['SibSp'] = dftrain_raw['SibSp']  dfresult['Parch'] = dftrain_raw['Parch']  dfresult['Fare'] = dftrain_raw['Fare']  dfresult

#Carbin  dfresult['Cabin_null'] =  pd.isna(dftrain_raw['Cabin']).astype('int32')  dfresult

#Embarked  #需要注意的参数是dummy_na=True，将缺失值另外标记出来  dfEmbarked = pd.get_dummies(dftrain_raw['Embarked'],dummy_na=True)  dfEmbarked.columns = ['Embarked_' + str(x) for x in dfEmbarked.columns]  dfresult = pd.concat([dfresult,dfEmbarked],axis = 1)  dfresult

def preprocessing(dfdata):        dfresult= pd.DataFrame()        #Pclass      dfPclass = pd.get_dummies(dfdata['Pclass'])      dfPclass.columns = ['Pclass_' +str(x) for x in dfPclass.columns ]      dfresult = pd.concat([dfresult,dfPclass],axis = 1)        #Sex      dfSex = pd.get_dummies(dfdata['Sex'])      dfresult = pd.concat([dfresult,dfSex],axis = 1)        #Age      dfresult['Age'] = dfdata['Age'].fillna(0)      dfresult['Age_null'] = pd.isna(dfdata['Age']).astype('int32')        #SibSp,Parch,Fare      dfresult['SibSp'] = dfdata['SibSp']      dfresult['Parch'] = dfdata['Parch']      dfresult['Fare'] = dfdata['Fare']        #Carbin      dfresult['Cabin_null'] =  pd.isna(dfdata['Cabin']).astype('int32')        #Embarked      dfEmbarked = pd.get_dummies(dfdata['Embarked'],dummy_na=True)      dfEmbarked.columns = ['Embarked_' + str(x) for x in dfEmbarked.columns]      dfresult = pd.concat([dfresult,dfEmbarked],axis = 1)        return(dfresult)

x_train = preprocessing(dftrain_raw)  y_train = dftrain_raw['Survived'].values    x_test = preprocessing(dftest_raw)  y_test = dftest_raw['Survived'].values    print("x_train.shape =", x_train.shape )  print("x_test.shape =", x_test.shape )

tf.keras.backend.clear_session()    model = models.Sequential()  model.add(layers.Dense(20,activation = 'relu',input_shape=(15,)))  model.add(layers.Dense(10,activation = 'relu' ))  model.add(layers.Dense(1,activation = 'sigmoid' ))    model.summary()

# 二分类问题选择二元交叉熵损失函数  model.compile(optimizer='adam',              loss='binary_crossentropy',              metrics=['AUC'])    history = model.fit(x_train,y_train,                      batch_size= 64,                      epochs= 30,                      validation_split=0.2 #分割一部分训练数据用于验证                     )

Epoch 1/30  WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/resource_variable_ops.py:1817: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.  Instructions for updating:  If using Keras pass *_constraint arguments to layers.  9/9 [==============================] - 0s 30ms/step - loss: 4.3524 - auc: 0.4888 - val_loss: 3.0274 - val_auc: 0.5492  Epoch 2/30  9/9 [==============================] - 0s 6ms/step - loss: 2.7962 - auc: 0.4710 - val_loss: 1.8653 - val_auc: 0.4599  Epoch 3/30  9/9 [==============================] - 0s 6ms/step - loss: 1.6765 - auc: 0.4040 - val_loss: 1.2673 - val_auc: 0.4067  Epoch 4/30  9/9 [==============================] - 0s 7ms/step - loss: 1.1195 - auc: 0.3799 - val_loss: 0.9501 - val_auc: 0.4006  Epoch 5/30  9/9 [==============================] - 0s 6ms/step - loss: 0.8156 - auc: 0.4874 - val_loss: 0.7090 - val_auc: 0.5514  Epoch 6/30  9/9 [==============================] - 0s 5ms/step - loss: 0.6355 - auc: 0.6611 - val_loss: 0.6550 - val_auc: 0.6502  Epoch 7/30  9/9 [==============================] - 0s 6ms/step - loss: 0.6308 - auc: 0.7169 - val_loss: 0.6502 - val_auc: 0.6546  Epoch 8/30  9/9 [==============================] - 0s 6ms/step - loss: 0.6088 - auc: 0.7156 - val_loss: 0.6463 - val_auc: 0.6610  Epoch 9/30  9/9 [==============================] - 0s 6ms/step - loss: 0.6066 - auc: 0.7163 - val_loss: 0.6372 - val_auc: 0.6644  Epoch 10/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5964 - auc: 0.7253 - val_loss: 0.6283 - val_auc: 0.6646  Epoch 11/30  9/9 [==============================] - 0s 7ms/step - loss: 0.5876 - auc: 0.7326 - val_loss: 0.6253 - val_auc: 0.6717  Epoch 12/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5827 - auc: 0.7409 - val_loss: 0.6195 - val_auc: 0.6708  Epoch 13/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5769 - auc: 0.7489 - val_loss: 0.6170 - val_auc: 0.6762  Epoch 14/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5719 - auc: 0.7555 - val_loss: 0.6156 - val_auc: 0.6803  Epoch 15/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5662 - auc: 0.7629 - val_loss: 0.6119 - val_auc: 0.6826  Epoch 16/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5627 - auc: 0.7694 - val_loss: 0.6107 - val_auc: 0.6892  Epoch 17/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5586 - auc: 0.7753 - val_loss: 0.6084 - val_auc: 0.6927  Epoch 18/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5539 - auc: 0.7837 - val_loss: 0.6051 - val_auc: 0.6983  Epoch 19/30  9/9 [==============================] - 0s 7ms/step - loss: 0.5479 - auc: 0.7930 - val_loss: 0.6011 - val_auc: 0.7056  Epoch 20/30  9/9 [==============================] - 0s 9ms/step - loss: 0.5451 - auc: 0.7986 - val_loss: 0.5996 - val_auc: 0.7128  Epoch 21/30  9/9 [==============================] - 0s 7ms/step - loss: 0.5406 - auc: 0.8047 - val_loss: 0.5962 - val_auc: 0.7192  Epoch 22/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5357 - auc: 0.8123 - val_loss: 0.5948 - val_auc: 0.7212  Epoch 23/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5295 - auc: 0.8181 - val_loss: 0.5928 - val_auc: 0.7267  Epoch 24/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5275 - auc: 0.8223 - val_loss: 0.5910 - val_auc: 0.7296  Epoch 25/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5263 - auc: 0.8227 - val_loss: 0.5884 - val_auc: 0.7325  Epoch 26/30  9/9 [==============================] - 0s 7ms/step - loss: 0.5199 - auc: 0.8313 - val_loss: 0.5860 - val_auc: 0.7356  Epoch 27/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5145 - auc: 0.8356 - val_loss: 0.5835 - val_auc: 0.7386  Epoch 28/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5138 - auc: 0.8383 - val_loss: 0.5829 - val_auc: 0.7402  Epoch 29/30  9/9 [==============================] - 0s 7ms/step - loss: 0.5092 - auc: 0.8405 - val_loss: 0.5806 - val_auc: 0.7416  Epoch 30/30  9/9 [==============================] - 0s 6ms/step - loss: 0.5082 - auc: 0.8394 - val_loss: 0.5792 - val_auc: 0.7424

%matplotlib inline  %config InlineBackend.figure_format = 'svg'    import matplotlib.pyplot as plt    def plot_metric(history, metric):      train_metrics = history.history[metric]      val_metrics = history.history['val_'+metric]      epochs = range(1, len(train_metrics) + 1)      plt.plot(epochs, train_metrics, 'bo--')      plt.plot(epochs, val_metrics, 'ro-')      plt.title('Training and validation '+ metric)      plt.xlabel("Epochs")      plt.ylabel(metric)      plt.legend(["train_"+metric, 'val_'+metric])      plt.show()  plot_metric(history,"loss")  plot_metric(history,"auc")

model.evaluate(x = x_test,y = y_test)

6/6 [==============================] - 0s 2ms/step - loss: 0.5286 - auc: 0.7869  [0.5286471247673035, 0.786877453327179]

model.predict(x_test[0:10])

array([[0.34822357],         [0.4793241 ],         [0.43986577],         [0.7916608 ],         [0.50268507],         [0.536609  ],         [0.29079646],         [0.6085641 ],         [0.34384924],         [0.17756936]], dtype=float32)

model.predict_classes(x_test[0:10])

WARNING:tensorflow:From <ipython-input-36-a161a0a6b51e>:1: Sequential.predict_classes (from tensorflow.python.keras.engine.sequential) is deprecated and will be removed after 2021-01-01.  Instructions for updating:  Please use instead:* `np.argmax(model.predict(x), axis=-1)`,   if your model does multi-class classification   (e.g. if it uses a `softmax` last-layer activation).* `(model.predict(x) > 0.5).astype("int32")`,   if your model does binary classification   (e.g. if it uses a `sigmoid` last-layer activation).  array([[0],         [0],         [0],         [1],         [1],         [1],         [0],         [1],         [0],         [0]], dtype=int32)

# 保存模型结构及权重  model.save('./data/keras_model.h5')  del model  #删除现有模型

# identical to the previous one  model = models.load_model('./data/keras_model.h5')  model.evaluate(x_test,y_test)

WARNING:tensorflow:Error in loading the saved optimizer state. As a result, your model is starting with a freshly initialized optimizer.  6/6 [==============================] - 0s 2ms/step - loss: 0.5286 - auc_1: 0.7869  [0.5286471247673035, 0.786877453327179]

# 保存模型结构  json_str = model.to_json()  # 恢复模型结构  model_json = models.model_from_json(json_str)

# 保存模型权重  model.save_weights('./data/keras_model_weight.h5')

# 恢复模型结构  model_json = models.model_from_json(json_str)  model_json.compile(          optimizer='adam',          loss='binary_crossentropy',          metrics=['AUC']      )    # 加载权重  model_json.load_weights('./data/keras_model_weight.h5')  model_json.evaluate(x_test,y_test)

6/6 [==============================] - 0s 3ms/step - loss: 0.5217 - auc: 0.8123  [0.521678626537323, 0.8122605681419373]

# 保存权重，该方式仅仅保存权重张量  model.save_weights('./data/tf_model_weights.ckpt',save_format = "tf")  # 保存模型结构与模型参数到文件,该方式保存的模型具有跨平台性便于部署    model.save('./data/tf_model_savedmodel', save_format="tf")  print('export saved model.')    model_loaded = tf.keras.models.load_model('./data/tf_model_savedmodel')  model_loaded.evaluate(x_test,y_test)

INFO:tensorflow:Assets written to: ./data/tf_model_savedmodel/assets  export saved model.  6/6 [==============================] - 0s 2ms/step - loss: 0.5286 - auc_1: 0.7869  [0.5286471247673035, 0.786877453327179]