BIDI_ML_INFO_EXTRACTION/BiddingKG/dl/money/train.py

'''
Created on 2019年4月11日

@author: User
'''

import os
import sys
import h5py
sys.path.append(os.path.abspath("../../.."))
import pandas as pd
import gensim
import numpy as np
import math
from keras.callbacks import ModelCheckpoint
from BiddingKG.dl.common.Utils import *
from BiddingKG.dl.common.models import getBiLSTMModel
import tensorflow as tf
from keras.models import load_model


def embedding(datas,shape):
    '''
    @summary:查找词汇对应的词向量
    @param:
        datas:词汇的list
        shape:结果的shape
    @return: array,返回对应shape的词嵌入
    '''
    model_w2v = getModel_word()
    embed = np.zeros(shape)
    length = shape[1]
    out_index = 0
    #print(datas)
    for data in datas:
        index = 0
        for item in str(data)[-shape[1]:]:
            if index>=length:
                break
            if item in model_w2v.vocab:
                embed[out_index][index] = model_w2v[item]
                index += 1
            else:
                #embed[out_index][index] = model_w2v['unk']
                index += 1
        out_index += 1
    return embed

def labeling(label,out_len=3):
    out = np.zeros((out_len))
    out[label] = 1
    return out
    
def getTrainData(percent=0.9):
    df = pd.read_excel("批量.xls")
    train_x = []
    train_y = []
    test_x = []
    test_y = []
    
    for before,text,after,label,turn in zip(df["list_before"],df["list_text"],df["list_after"],df["list_label"],df["turn"]):
        before = str(before) if str(before)!="nan" else ""
        text = str(text)
        after = str(after) if str(after)!="nan" else ""
        the_label = None
        if math.isnan(turn):
            the_label = int(label)
        else:
            the_label = int(turn)
        if the_label not in [0,1,2]:
            print(after,text)
            continue
        x = encodeInput([before,text,after], word_len=50, word_flag=True,userFool=False)
        y = labeling(the_label)
        if np.random.random()<percent:
            train_x.append(x)
            train_y.append(y)
        else:
            test_x.append(x)
            test_y.append(y)
    return np.transpose(np.array(train_x),(1,0,2)),np.array(train_y),np.transpose(np.array(test_x),(1,0,2)),np.array(test_y)



def train():
    pk_file = "traindata/all_data.pk"
    if os.path.exists(pk_file):
        train_x,train_y,test_x,test_y = load(pk_file)
    else:
        train_x,train_y,test_x,test_y = getTrainData()
        save([train_x,train_y,test_x,test_y],pk_file)
    
    #model_w = getModel_word()
    #vocab,weights = getVocabAndMatrix(model_w, Embedding_size=60)
    #model = getTextCNNModel(input_shape=(3,50), vocab=vocab, embedding_weights=weights, classes=6)
    '''
    with tf.Session(graph=tf.get_default_graph()) as sess:
        with sess.graph.as_default():
            
            '''
    with tf.Session() as sess:
      dict_key_value = load("dict_key_value.pk")

      vocab,matrix = getVocabAndMatrix(getModel_word())
      model = getBiLSTMModel(input_shape=(3,50,60), vocab=vocab, embedding_weights=matrix, classes=3)
      # model = getBiLSTMModel(input_shape=(3,50,60), vocab=fool_char_to_id.keys(), embedding_weights=dict_key_value["bert/embeddings/word_embeddings:0"], classes=3)
      # for k,v in dict_key_value.items():
      #     if re.search("encoder",k) is not None:
      #         sess.run(tf.assign(sess.graph.get_tensor_by_name(k[13:]),v))
      #         print(k)
      # sess.run(tf.assign(sess.graph.get_tensor_by_name("char_embeding/embeddings:0"),dict_key_value["bert/embeddings/word_embeddings:0"]))
      #model = models.getTextCNNModel()
      print("loading weights")
      # model.load_weights("log/ep378-loss0.178-val_loss0.117-f1_score0.965.h5",by_name=True, skip_mismatch=True)
    
      callback = ModelCheckpoint(filepath="log/"+"ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}-f1_score{val_f1_score:.3f}.h5",monitor="val_loss",save_best_only=True, save_weights_only=True, mode="min")
      model.fit(x=[train_x[0],train_x[1],train_x[2]],y=train_y,batch_size=128,epochs=600,callbacks=[callback],validation_data=[[test_x[0],test_x[1],test_x[2]],test_y])
        
def test():
    _span = ['：预算金额1000000元，中标金额', '1df元', '；']
    input = encodeInput(_span, word_len=50, word_flag=True,userFool=True)
    print(input)
    graph=tf.get_default_graph()
    with graph.as_default():
      sess = tf.Session(graph=graph)
      with sess.as_default():
        dict_key_value = load("dict_key_value.pk")
        model = getBiLSTMModel(input_shape=(3,50,60), vocab=fool_char_to_id.keys(), embedding_weights=None, classes=3)
        for k,v in dict_key_value.items():
          if re.search("encoder",k) is not None:
              sess.run(tf.assign(sess.graph.get_tensor_by_name(k[13:]),v))
              print(k)
        model.load_weights("log/ep019-loss0.177-val_loss0.115-f1_score0.968.h5",by_name=True, skip_mismatch=True)
        print(model.predict([np.array([input[0]]),np.array([input[1]]),np.array([input[2]])]))
      
def get_savedModel():
  sess = tf.Session(graph=tf.Graph())
  with sess.as_default():
    with sess.graph.as_default():
        vocab,matrix = getVocabAndMatrix(getModel_word())
        model = getBiLSTMModel(input_shape=(3,50,60), vocab=vocab, embedding_weights=matrix, classes=3)
        model.load_weights(filepath="log/ep009-loss0.057-val_loss0.076-f1_score0.978.h5")
        tf.saved_model.simple_save(session=sess,
                                   export_dir="money_savedmodel",
                                   inputs={"input0":model.input[0],
                                         "input1":model.input[1],
                                         "input2":model.input[2]},
                                   outputs={"outputs":model.output})

def tensorboard_model():
    with tf.Session(graph=tf.Graph()).as_default() as sess:
        with sess.graph.as_default():
            tf.saved_model.loader.load(sess,tags=["serve"],export_dir="money_savedmodel1")
            tf.summary.FileWriter(graph=sess.graph,logdir="log2")
    
      
if __name__=="__main__":
    train()
    # test()
    # get_savedModel()
    # tensorboard_model()