基於Keras的FM系列NN

import numpy as np
import pandas as pd
import time
import gc
import sys
from sklearn.preprocessing import OneHotEncoder,LabelEncoder
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split
from keras.layers import *
from keras.models import *
from keras.callbacks import *
from keras.optimizers import *
from keras.applications import *
from keras.regularizers import *
import itertools
from keras import backend  as KK
#from keras.engine.topology import Layer
from keras.metrics import categorical_accuracy
from keras.utils import multi_gpu_model
gpus_num=2
import keras
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0,1"

single_emb=['LBS','age','carrier','consumptionAbility','education','gender','house','os','ct','marriageStatus','advertiserId','campaignId', 'creativeId','adCategoryId', 'productId', 'productType','creativeSize','new_AID']
singel_max=[898,5,3,2,7,3,1,4,64,27,197,479,831,74,83,3,14]

model_col_name=['interest1','interest2','interest3','interest4','interest5','kw1', 'kw2','kw3','topic1', 'topic2', 'topic3','aid_insterest1']
model_col_max_length=[33,33,10,10,33,5,5,5,5,5,5,33]
model_col_max_value=[122,82,10,10,136,796741,121958,58782,9999,9999,9463,95379]
 
super_f_name=['final_sdd_embedding_feature_aid_neg.csv',
'final_sdd_embedding_feature_aid_pos.csv',
'final_sdd_embedding_feature_adCategoryId_adCategoryId_neg.csv',
'final_sdd_embedding_feature_adCategoryId_adCategoryId_pos.csv'
]
super_f_length=[29,51,29,30] 
super_f_max_value=[2230,2230,282,282]
super_fuck_name=['sdd_aid_neg','sdd_aid_pos','sdd_cate_neg','sdd_cate_pos']
def binary_crossentropy_with_ranking(y_true, y_pred):
    """ Trying to combine ranking loss with numeric precision"""
    # first get the log loss like normal
    logloss = KK.mean(KK.binary_crossentropy( y_true,y_pred), axis=-1)
    # next, build a rank loss
    # clip the probabilities to keep stability
    y_pred_clipped = KK.clip(y_pred, KK.epsilon(), 1-KK.epsilon())
    # translate into the raw scores before the logit
    y_pred_score = KK.log(y_pred_clipped / (1 - y_pred_clipped))
    # determine what the maximum score for a zero outcome is
    y_pred_score_zerooutcome_max = KK.max(tf.boolean_mask(y_pred_score ,(y_true < 1)))
    # determine how much each score is above or below it
    rankloss = y_pred_score - y_pred_score_zerooutcome_max
    # only keep losses for positive outcomes
    rankloss = tf.boolean_mask(rankloss,tf.equal(y_true,1))
    # only keep losses where the score is below the max
    rankloss = KK.square(KK.clip(rankloss, -100, 0))
    # average the loss for just the positive outcomes
    #tf.reduce_sum(tf.cast(myOtherTensor, tf.float32))
    rankloss = KK.sum(rankloss, axis=-1) / (KK.sum(KK.cast(y_true > 0,tf.float32) + 1))
    return (rankloss + 1)* logloss #- an alternative to try
    #return logloss

# PFA, prob false alert for binary classifier  
def binary_PFA(y_true, y_pred, threshold=KK.variable(value=0.5)):  
    y_pred = KK.cast(y_pred >= threshold, 'float32')  
    # N = total number of negative labels  
    N = KK.sum(1 - y_true)  
    # FP = total number of false alerts, alerts from the negative class labels  
    FP = KK.sum(y_pred - y_pred * y_true)  
    return FP/N 


# P_TA prob true alerts for binary classifier  
def binary_PTA(y_true, y_pred, threshold=KK.variable(value=0.5)):  
    y_pred = KK.cast(y_pred >= threshold, 'float32')  
    # P = total number of positive labels  
    P = KK.sum(y_true)  
    # TP = total number of correct alerts, alerts from the positive class labels  
    TP = KK.sum(y_pred * y_true)  
    return TP/P

def auc(y_true, y_pred):  
    ptas = tf.stack([binary_PTA(y_true,y_pred,k) for k in np.linspace(0, 1, 1000)],axis=0)  
    pfas = tf.stack([binary_PFA(y_true,y_pred,k) for k in np.linspace(0, 1, 1000)],axis=0)  
    pfas = tf.concat([tf.ones((1,)) ,pfas],axis=0)  
    binSizes = -(pfas[1:]-pfas[:-1])  
    s = ptas*binSizes  
    return KK.sum(s, axis=0)  


def log_loss(y_true, y_pred):
    """ Trying to combine ranking loss with numeric precision"""
    # first get the log loss like normal
    logloss = KK.sum(KK.binary_crossentropy(y_true,y_pred), axis=-1)
    return logloss

def Mean_layer(x):
    return KK.mean(x,axis=1)

def build_model(len_sdd,len_uid_count):
    field_sizes=len(single_emb)+len(model_col_name)
    emb_n=128
    #FFM_layers=[]
    inputs = []
    flatten_layers=[]
    columns = range(len(single_emb))
    ###------second order term-------###
    for c in columns:
        inputs_c = Input(shape=(1,), dtype='int32',name = 'input_%s'%single_emb[c])
        num_c = singel_max[c]+1
        inputs.append(inputs_c)
        print (num_c,c)
        embed_c = Embedding(num_c,emb_n,input_length=1,name = 'embed_%s'%single_emb[c])(inputs_c)
       
        flatten_c = Reshape((emb_n,))(embed_c)
        flatten_layers.append(flatten_c)

        #FFM_temp=[Embedding(num_c,emb_n,input_length=1)(inputs_c) for i_i in range(field_sizes)]
        #FFM_layers.append(FFM_temp)
    #length
    inputs_length=Input(shape=(len_sdd,))
    emb_length=Dense(emb_n, activation='relu')(inputs_length)
    inputs.append(inputs_length)
	
    inputs_uid_count=Input(shape=(len_uid_count,))
    emb_uid_count=Dense(emb_n, activation='relu')(inputs_uid_count)
    inputs.append(inputs_uid_count)
    #flatten_c = Reshape((emb_n,))(emb_length)
    #flatten_layers.append(flatten_c)

    for f in range(len(model_col_name)):
        inputs_f = Input(shape=(model_col_max_length[f],),name = 'input_%s'%model_col_name[f])
        num_f = model_col_max_value[f]+1
        inputs.append(inputs_f)
        #print (num_f,f)
        embed_f = Embedding(num_f,emb_n,input_length=model_col_max_length[f],name = 'embed_%s'%model_col_name[f])(inputs_f)
        embed_f=Lambda(Mean_layer)(embed_f)
        flatten_f = Reshape((emb_n,))(embed_f)
        flatten_layers.append(flatten_f)        
		
    for f in range(len(super_fuck_name)):
        inputs_f = Input(shape=(super_f_length[f],),name = 'input_%s'%super_fuck_name[f])
        num_f = super_f_max_value[f]+1
        inputs.append(inputs_f)
        #print (num_f,f)
        embed_f = Embedding(num_f,emb_n,input_length=super_f_length[f],name = 'embed_%s'%super_fuck_name[f])(inputs_f)
        embed_f=Lambda(Mean_layer)(embed_f)
        flatten_f = Reshape((emb_n,))(embed_f)
        flatten_layers.append(flatten_f)      

        #FFM_temp=[Lambda(Mean_layer)(Embedding(num_f,emb_n,input_length=model_col_max_length[f])(inputs_f)) for i_i in range(field_sizes)]
        #FFM_layers.append(FFM_temp)		
		
	#FFM
    #FFM_product=[]
    #for ff_i in range(field_sizes):
    #    for ff_j in range(ff_i+1,field_sizes):
    #       FFM_product.append(Reshape((emb_n,))(multiply([FFM_layers[ff_i][ff_j],FFM_layers[ff_j][ff_i]])))
    ##FFM_second_order=add(FFM_product)
    #FFM_second_order=concatenate(FFM_product)

    #___________________________________________________________--
    fm_layers=[]
    for em1,em2 in itertools.combinations(flatten_layers,2):
       dot_layer=Reshape((emb_n,))(multiply([em1,em2]))
       fm_layers.append(dot_layer)
    fm_layers=concatenate(fm_layers)

    fm_2layers=[]
    for em1,em2 in itertools.combinations(flatten_layers,2):
       dot_layer=merge([em1,em2],mode='dot',dot_axes=1)
       fm_2layers.append(dot_layer)
    fm_2layers=concatenate(fm_2layers)
    #y_first_order = add(flatten_layers) 
    #y_first_order = BatchNormalization()(y_first_order)
    #y_first_order = Dropout(0.8)(y_first_order)
    #------------------------------------------------------------
    y_deep = concatenate(flatten_layers)  
    #y_deep = Dense(256)(y_deep)  #加入BN會變差  PReLU 優於Relu 0.5 is 7483
    #y_deep = Activation('relu',name='output_1')(y_deep)
    #y_deep = Dropout(0.5)(y_deep)
    #y_deep=  Dense(128)(y_deep)
    #y_deep = Activation('relu',name='output_2')(y_deep)
    #y_deep = Dropout(0.5)(y_deep)

	
    concat_input = concatenate([fm_layers,fm_2layers,y_deep,emb_length,emb_uid_count],axis=1)
    concat_input = Dense(256)(concat_input)  #加入BN會變差  PReLU 優於Relu 0.5 is 7483
    concat_input = Activation('relu',name='output_3')(concat_input)
    concat_input = Dropout(0.5)(concat_input)
    concat_input=  Dense(128)(concat_input)
    concat_input = Activation('relu',name='output_4')(concat_input)
    concat_input = Dropout(0.5)(concat_input)	
	
    #new_input = concatenate([fm_layers,y_deep,FFM_second_order],axis=1)
    outp = Dense(1,activation='sigmoid')(concat_input)

    model = Model(inputs=inputs, outputs=outp,name='model')
    #optimizer_adam = Adam(lr=0.002)
    optimizer_adam = Adam(lr=0.005,decay=0.0005,amsgrad=True)
    parallel_model = keras.utils.training_utils.multi_gpu_model(model,gpus=gpus_num)
    parallel_model.compile(optimizer=optimizer_adam,loss='binary_crossentropy',metrics=[auc,log_loss])
	
	
    #if(loss_flag==0):
    #  model.compile(loss='binary_crossentropy',optimizer=optimizer_adam,metrics=[auc,log_loss])
    #elif(loss_flag==1):
    #  model.compile(loss=binary_crossentropy_with_ranking,optimizer=optimizer_adam,metrics=[auc,log_loss])
   # model.summary()
    return parallel_model

#read data
#------------------------------------------------------------------------------
t1=time.time()
single_onehot=pd.read_csv("./SDD_data/final_sdd_single_onehot_embedding_feature2_mix_test12.csv",dtype='float32')
single_onehot['new_AID']=LabelEncoder().fit_transform(single_onehot['aid'].apply(int))
print("read single_onehot over",time.time()-t1)
tem_max=single_onehot['new_AID'].max()
print("NEWID max",tem_max)
singel_max.append(tem_max)
#-**************************************************************************************
train_set=single_onehot[single_onehot['label']!=-1].values[:,3:] #train data
label_train=single_onehot[single_onehot['label']!=-1].values[:,2:3] #label data
test_set=single_onehot[single_onehot['label']==-1].values[:,3:] #test data
subfile=single_onehot[single_onehot['label']==-1][['aid','uid','label']]
del single_onehot;gc.collect()
print("seg over",time.time()-t1)
#-**************************************************************************************
ramdom_seed=1
spilt_prob=0.05
train_x, evals_x, train_y, evals_y=train_test_split(train_set,label_train,test_size=spilt_prob, random_state=ramdom_seed)
del train_set;gc.collect()
print('split data over!',time.time()-t1)
#-**************************************************************************************

X_train=[]
X_valid=[]
X_test=[]
for i in range(len(single_emb)-1):
   X_train.append(train_x[:,i:i+1])
   X_valid.append(evals_x[:,i:i+1])
   X_test.append(test_set[:,i:i+1])
X_train.append(train_x[:,(len(single_emb)-1):])
X_valid.append(evals_x[:,(len(single_emb)-1):])
X_test.append(test_set[:,(len(single_emb)-1):])##
print('input data over!',time.time()-t1)
#-**************************************************************************************


#*********************READ trans**************************************************************************************************************
temp_file1=pd.read_csv("user_statis_feature_train.csv",dtype='float32')
temp_file2=pd.read_csv("user_statis_feature_test.csv",dtype='float32')
temp_file=pd.concat([temp_file1,temp_file2])
temp_file=temp_file.fillna(temp_file.mean())
del temp_file1,temp_file2;gc.collect()

from  sklearn import preprocessing
len_sdd=0
for i in list(temp_file):
  print(i,len_sdd)
  len_sdd=len_sdd+1
  scaler=preprocessing.StandardScaler().fit(temp_file[i].values.reshape(-1,1))
  temp_file[i]=scaler.transform(temp_file[i].values.reshape(-1,1))

  
temp_train=temp_file.values[:45539700,:] #train data
temp_test=temp_file.values[45539700:,:] #test data
#temp_test=temp_test[11729073:,:]
#temp_test=temp_test[11729073:,:]
print('temp_test',temp_test.shape)
del temp_file;gc.collect()
temp_train_x, temp_evals_x, temp_train_y, temp_evals_y=train_test_split(temp_train,label_train,test_size=spilt_prob, random_state=ramdom_seed)
X_train.append(temp_train_x)
X_valid.append(temp_evals_x)
X_test.append(temp_test)##
del temp_train_x,temp_evals_x;gc.collect()

#-**************************************************************************************


#uid count
#*********************uid count************************************************************************************************************** 
temp_file=pd.read_csv("SDD_data/sdd_uid_count.csv")
temp_file=temp_file.fillna(temp_file.mean())

from  sklearn import preprocessing
len_uid_count=0
for i in list(temp_file):
  print(i,len_uid_count)
  len_uid_count=len_uid_count+1
  scaler=preprocessing.StandardScaler().fit(temp_file[i].values.reshape(-1,1))
  temp_file[i]=scaler.transform(temp_file[i].values.reshape(-1,1))

  
temp_train=temp_file.values[:45539700,:] #train data
temp_test=temp_file.values[45539700:,:] #test data
#temp_test=temp_test[11729073:,:]
#temp_test=temp_test[11729073:,:]
print('temp_test',temp_test.shape)
del temp_file;gc.collect()
temp_train_x, temp_evals_x, temp_train_y, temp_evals_y=train_test_split(temp_train,label_train,test_size=spilt_prob, random_state=ramdom_seed)
X_train.append(temp_train_x)
X_valid.append(temp_evals_x)
X_test.append(temp_test)##
del temp_train_x,temp_evals_x;gc.collect()
  
 
#--------------------------------------------------------------------------------------------------------------------------------------------  

for i in range(len(model_col_name)):
   temp_file=pd.read_csv("./SDD_data/final_sdd_embedding_feature_mix_chusai_%s.csv"%model_col_name[i],dtype='float32')
   print("read %s over"%model_col_name[i],time.time()-t1)
   temp_train=temp_file[temp_file['label']!=-1].values[:,3:] #train data
   temp_test=temp_file[temp_file['label']==-1].values[:,3:] #test data
   del temp_file;gc.collect()
   temp_train_x, temp_evals_x, temp_train_y, temp_evals_y=train_test_split(temp_train,label_train,test_size=spilt_prob, random_state=ramdom_seed)
   del temp_train;gc.collect()
   X_train.append(temp_train_x)
   X_valid.append(temp_evals_x)
   X_test.append(temp_test)##
   del temp_train_x,temp_evals_x;gc.collect()
#-**************************************************************************************

#FFD feature

for _name in super_f_name:
   temp_file=pd.read_csv("./SDD_data/%s"%_name,dtype='float32')
   temp_train=temp_file.values[:45539700,1:] #train data
   temp_test=temp_file.values[45539700:,1:] #test data
   print('temp_test',temp_test.shape)
   del temp_file;gc.collect()
   temp_train_x, temp_evals_x, temp_train_y, temp_evals_y=train_test_split(temp_train,label_train,test_size=spilt_prob, random_state=ramdom_seed)
   X_train.append(temp_train_x)
   X_valid.append(temp_evals_x)
   X_test.append(temp_test)##
   del temp_train_x,temp_evals_x;gc.collect()


model=build_model(len_sdd,len_uid_count)


batch_size=6000
model.fit(X_train,train_y, batch_size=batch_size, validation_data=(X_valid,evals_y),epochs=1, shuffle=True)
print('fit model over!',time.time()-t1)

y_pred_d = model.predict(X_valid,batch_size=6000)  
print('predict over!',time.time()-t1)
from sklearn.metrics import roc_auc_score,log_loss
print ('AUC:',roc_auc_score(evals_y,y_pred_d))
print ('log_loss:',log_loss(evals_y,y_pred_d))
print('compute AUC over!',time.time()-t1)

pre1=model.predict(X_test,batch_size=6000) 
subfile['label']=pre1
subfile.to_csv("./sdd_results/submission_FM_1.csv",header=True,index=False)