pyrhon3+tensorflow+ Titanic Data Set (data preprocessing + prediction)

Import TensorFlow as TF import numpy as NP import pandas as PD #数据预处理 def read_data (): Data=pd.read_csv (' train.csv ') #pandas read Data=data.fillna (0) #NAN fill in 0 datax=data[[' Sex ', ' age ', ' pclass ', ' sibsp ', ' parch ', ' Fare ', ' Emba Rked ']] #pandas选择列 datax=pd.get_dummies (datax) # one-hot encoded data[' deceased '] = data[' survived '].apply (
    Lambda s:1-s) #one-hot encoding Datay = data[[' survived ', ' deceased ']] return datax,datay if __name__== ' __main__ ':
    New_datax,new_datay=read_data () New_dataxx = New_datax.values.astype (np.float32) #把pandas矩阵 converted to a NP matrix no two-dimensional label becomes a deposit matrix New_datayy = New_datay.values.astype (np.float32) # Converts the pandas matrix to a NP matrix without a two-dimensional label becoming a deposit matrix Np.random.shuffle (New_dataxx) # Random scrambling sequence Np.random.shuffle (new_datayy) # random scrambling sequence sep = Int (0.7 * len (new_dataxx)) #拆分数据集 Train_datax = New_da
    TAXX[:SEP] # Training data (70%) train_datay=new_datayy[:sep] Test_datax = new_dataxx[sep:] # test data (30%) test_datay=new_datayy[Sep:] # new_datax.to_csv ("Taitan_onehot.csv", Index=false) #简便方法 an easy way to disrupt + split ' split ' from Sklearn.model
                                                  _selection import Train_test_split X_train, X_val, y_train, Y_val = Train_test_split (dataset_x, Dataset_Y, 
    test_size=0.2, random_state=42)
    "' #全链接神经层 input TF_INPUTX training Data's characteristic information tf_inputy training data label Tf_inputx=tf.placeholder (Tf.float32, [None, 11]) Tf_inputy=tf.placeholder (tf.float32,[none,2]) #搭建全链接神经网络 L1 = Tf.layers.dense (TF_INPUTX, 1000, Tf.nn.relu, NA Me= "L1") L2 = Tf.layers.dense (L1, 900, Tf.nn.relu, name= "L2") out = Tf.layers.dense (L2, 2, name= "L3") #计算 The probability is added to 1 Prediction=tf.nn.softmax (out, name= "pred") #计算误差 cost function loss = Tf.reduce_mean (tf.nn.softmax_cro Ss_entropy_with_logits (Labels=tf_inputy, logits=out)) #优化器 reduce error Train_step = Tf.train.AdamOptimizer (0.001). Minimi
    Ze (loss) #初始化变量init = Tf.global_variables_initializer () ' ' correct_prediction = tf.equal (Tf.argmax (tf_inputy, 1), Tf.argmax (pred Iction, 1) accuracy = Tf.reduce_mean (Tf.cast (correct_prediction, Tf.float32)) ' #创建会话 with TF.   Session () as Sess:sess.run (init) #初始化变量 to I in range: #控制迭代次数 # starts to optimize its  
           
            Reduce error start training Sess.run (Train_step, Feed_dict={tf_inputx:train_datax, Tf_inputy:train_datay}) # View current Training real-time data feedback print ("Number:" +str (i)) print (Sess.run, Feed_dict={tf_inputx:train_da Tax, Tf_inputy:train_datay})) # acc = sess.run (accuracy, feed_dict={tf_inputx:test_datax, Tf_inputy:test_da Tay}) # print ("Iter" + str (i) + ", testing accuracy" + STR (ACC)) #训练完成后 forecast View forecast results print ("test ") Print (Sess.run (Prediction,feed_dict={tf_inputx:test_datax}))