Модель DNN показала потери в самом начале

Question

Моя цель - предсказать результат «если мы подадим заявку на этого пользователя». Я использую сущность, чтобы справиться с категориальной функцией и применить ее в нейронной сети. Но это показало потери наночастиц в самом начале. Я опустил несколько функций, которые смешаны с пробелом, str и float. Также я попытался понизить скорость обучения даже до 0 и по-прежнему показывать Nan для потери. Ниже приведен код и данные.

import os 
import matplotlib.pylab as plt
import pandas as pd

import datetime, warnings, scipy 
import pandas as pd
import numpy as np
import seaborn as sns
import keras as ka
from sklearn import metrics, linear_model
from sklearn.model_selection import train_test_split, cross_val_score, cross_val_predict
from sklearn.preprocessing import StandardScaler
from keras import optimizers 
from keras.models import Sequential,Model
from keras.models import Model as KerasModel
from keras.layers import Input, Dense, Activation, Reshape
from keras.layers import Concatenate, Dropout
from keras.layers.embeddings import Embedding
from keras.callbacks import ModelCheckpoint
from keras.utils import plot_model

plt.rcParams["patch.force_edgecolor"] = True
plt.style.use('fivethirtyeight')
from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity = "last_expr"
pd.options.display.max_columns = 50
warnings.filterwarnings("ignore")
%matplotlib inline
data_df = pd.read_csv('training_data.csv')
print('DataFrame size:', data_df.shape)
features = ['pol_coverage','pol_pay_freq','pol_payd','pol_usage','pol_insee_code','drv_drv2','drv_sex1','vh_fuel','vh_make','vh_model','vh_type']
target = ['made_claim']
#data_df=data_df[features + target]
#data_df['pol_insee_code']= data_df['pol_insee_code'].astype('object')
data_df['commune_code']= data_df['commune_code'].astype('object')
data_df['canton_code']= data_df['canton_code'].astype('object')
data_df['regional_department_code']= data_df['regional_department_code'].astype('object')
data_df = data_df.drop(columns = ['id_policy','drv_sex2','regional_department_code','commune_code','canton_code'])
X_train, y_train = data_df.iloc[:50000], data_df.iloc[:50000][target]
X_val, y_val = data_df.iloc[50000:75000], data_df.iloc[50000:75000][target]
X_test = data_df.iloc[75000:]
embed_cols=[i for i in X_train.select_dtypes(include=['object'])] #挑选类型为obj的列，妙！

for i in embed_cols:
    print(i,data_df[i].nunique())
embed_cols=[i for i in X_train.select_dtypes(include=['object'])]
print(embed_cols)


#converting data to list format to match the network structure 这个函数将每一列类别特征手动labelencoder了，然后转成了list
def preproc(X_train, X_val, X_test):

    input_list_train = []
    input_list_val = []
    input_list_test = []

    #the cols to be embedded: rescaling to range [0, # values)
    for c in embed_cols:
        raw_vals = np.unique(X_train[c])
        val_map = {}
        for i in range(len(raw_vals)):
            val_map[raw_vals[i]] = i    #这一步最终把创建了一个，类别特征为键，值为第几个类别特征  

        input_list_train.append(X_train[c].map(val_map).values) 
        input_list_val.append(X_val[c].map(val_map).fillna(0).values)
        input_list_test.append(X_test[c].map(val_map).fillna(0).values)

    #the rest of the columns
    other_cols = [c for c in X_train.columns if (not c in embed_cols)]
    input_list_train.append(X_train[other_cols].values)
    input_list_val.append(X_val[other_cols].values)
    input_list_test.append(X_test[other_cols].values)

    return input_list_train, input_list_val, input_list_test input_models=[]
output_embeddings=[]
numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']

for categorical_var in X_train.select_dtypes(include=['object']):

    #Name of the categorical variable that will be used in the Keras Embedding layer
    cat_emb_name= categorical_var.replace(" ", "")+'_Embedding'

    # Define the embedding_size
    no_of_unique_cat  = X_train[categorical_var].nunique()
    embedding_size = int(min(np.ceil((no_of_unique_cat)/2), 50 ))

    #One Embedding Layer for each categorical variable
    input_model = Input(shape=(1,))
    output_model = Embedding(no_of_unique_cat, embedding_size, name=cat_emb_name)(input_model)
    output_model = Reshape(target_shape=(embedding_size,))(output_model)    

    #Appending all the categorical inputs
    input_models.append(input_model)

    #Appending all the embeddings
    output_embeddings.append(output_model)

#Other non-categorical data columns (numerical). 
#I define single another network for the other columns and add them to our models list.
input_numeric = Input(shape=(len(X_train.select_dtypes(include=numerics).columns.tolist()),))
embedding_numeric = Dense(128)(input_numeric) 
input_models.append(input_numeric)
output_embeddings.append(embedding_numeric)

#At the end we concatenate altogther and add other Dense layers
output = Concatenate()(output_embeddings)
output = Dense(1000, kernel_initializer="uniform")(output)
output = Activation('sigmoid')(output)
output= Dropout(0.4)(output)
output = Dense(512, kernel_initializer="uniform")(output)
output = Activation('sigmoid')(output)
output= Dropout(0.3)(output)
output = Dense(1, activation='sigmoid')(output)

model = Model(inputs=input_models, outputs=output)
model.compile(loss='mean_squared_error', optimizer=ka.optimizers.Adadelta(lr=0.00001),metrics=['mse','mape'])
import pydot_ng as pydot
plot_model(model, show_shapes=True, show_layer_names=True, to_file='model.png')
from IPython.display import Image
Image(retina=True, filename='model.png')
X_train_list,X_val_list,X_test_list = preproc(X_train,X_val, X_test)
history  =  model.fit(X_train_list,y_train,validation_data=(X_val_list,y_val) , epochs =  10000 )

данные находятся по этой ссылке Trainingdata.csv файл IPY находится здесь ipyfile Большое спасибо, если кто-то может дать мне совет. Я знаю, что принятие решения может помочь в решении проблемы, но я хочу попробовать DNN здесь. Спасибо!