深度学习_数据读取到model模型存储

概要

应用场景:用户流失

本文将介绍模型调用预测的步骤,这里深度学习模型使用的是自定义的deepfm,并用机器学习lgb做比较

代码

导包

python 复制代码
import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
import seaborn as sns
from collections import defaultdict  
from scipy import stats
from scipy import signal
from tqdm import tqdm
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, f1_score
from scipy.spatial.distance import cosine

import lightgbm as lgb

from sklearn.preprocessing import LabelEncoder, MinMaxScaler, StandardScaler
from tensorflow.keras.layers import *
import tensorflow.keras.backend as K
import tensorflow as tf
from tensorflow.keras.models import Model

import os,gc,re,warnings,sys,math
warnings.filterwarnings("ignore")

pd.set_option("display.max_rows", None)
pd.set_option("display.max_columns", None)

读取数据

python 复制代码
data = pd.read_csv('df_03m.csv')

区分稀疏及类别变量

python 复制代码
sparse_cols = ['shop_id','sex']
dense_cols  = [c for c in data.columns if c not in sparse_cols + ['customer_id', 'flag', 'duartion_is_lm']]

dense特征处理

python 复制代码
def process_dense_feats(data, cols):
    d = data.copy()
    for f in cols:
        d[f] = d[f].fillna(0)
        ss=StandardScaler()
        d[f] = ss.fit_transform(d[[f]])
    return d

data = process_dense_feats(data, dense_cols)

sparse稀疏特征处理

python 复制代码
def process_sparse_feats(data, cols):
    d = data.copy()
    for f in cols:
        d[f] = d[f].fillna('-1').astype(str)
        label_encoder = LabelEncoder()
        d[f] = label_encoder.fit_transform(d[f])
    return d

data = process_sparse_feats(data, sparse_cols)

切分训练及测试集

python 复制代码
X_train, X_test, _, _ = train_test_split(data, data, test_size=0.3, random_state=2024)

y_train = X_train['flag']
y_test = X_test['flag']

X_train1 = X_train.drop(['customer_id', 'flag', 'duartion_is_lm'], axis = 1)
X_test1 = X_test.drop(['customer_id', 'flag', 'duartion_is_lm'], axis = 1)

模型定义

python 复制代码
def deepfm_model(sparse_columns, dense_columns, train, test):
    
    ####### sparse features ##########
    sparse_input = []
    lr_embedding = []
    fm_embedding = []
    for col in sparse_columns:
        ## lr_embedding
        _input = Input(shape=(1,))
        sparse_input.append(_input)
        
        nums = pd.concat((train[col], test[col])).nunique() + 1
        embed = Flatten()(Embedding(nums, 1, embeddings_regularizer=tf.keras.regularizers.l2(0.5))(_input))
        lr_embedding.append(embed)
        
        ## fm_embedding
        embed = Embedding(nums, 10, input_length=1, embeddings_regularizer=tf.keras.regularizers.l2(0.5))(_input)
        reshape = Reshape((10,))(embed)
        fm_embedding.append(reshape)
    
    ####### fm layer ##########
    fm_square = Lambda(lambda x: K.square(x))(Add()(fm_embedding)) # 
    square_fm = Add()([Lambda(lambda x:K.square(x))(embed)
                     for embed in fm_embedding])
    snd_order_sparse_layer = subtract([fm_square, square_fm])
    snd_order_sparse_layer  = Lambda(lambda x: x * 0.5)(snd_order_sparse_layer)
    
    ####### dense features ##########
    dense_input = []
    for col in dense_columns:
        _input = Input(shape=(1,))
        dense_input.append(_input)
    concat_dense_input = concatenate(dense_input)
    fst_order_dense_layer = Dense(4, activation='relu')(concat_dense_input)
    
#     #######  NFM  ##########
#     inner_product = []
#     for i in range(field_cnt):
#         for j in range(i + 1, field_cnt):
#             tmp = dot([fm_embedding[i], fm_embedding[j]], axes=1)
#             # tmp = multiply([fm_embedding[i], fm_embedding[j]])
#             inner_product.append(tmp)
#     add_inner_product = add(inner_product)
    
    
#     #######  PNN  ##########
#     for i in range(field_cnt):
#         for j in range(i+1,field_cnt):
#             tmp = dot([lr_embedding[i],lr_embedding[j]],axes=1)
#             product_list.append(temp)
#     inp = concatenate(lr_embedding+product_list)
    
    ####### linear concat ##########
    fst_order_sparse_layer = concatenate(lr_embedding)
    linear_part = concatenate([fst_order_dense_layer, fst_order_sparse_layer])
    
#     #######  DCN  ##########
#     linear_part = concatenate([fst_order_dense_layer, fst_order_sparse_layer])
#     x0 = linear_part
#     xl = x0
#     for i in range(3):
#         embed_dim = xl.shape[-1]
#         w = tf.Variable(tf.random.truncated_normal(shape=(embed_dim,), stddev=0.01))
#         b = tf.Variable(tf.zeros(shape=(embed_dim,)))
#         x_lw = tf.tensordot(tf.reshape(xl, [-1, 1, embed_dim]), w, axes=1)
#         cross = x0 * x_lw 
#         xl = cross + b + xl
    
    #######dnn layer##########
    concat_fm_embedding = concatenate(fm_embedding, axis=-1) # (None, 10*26)
    fc_layer = Dropout(0.2)(Activation(activation="relu")(BatchNormalization()(Dense(128)(concat_fm_embedding))))
    fc_layer = Dropout(0.2)(Activation(activation="relu")(BatchNormalization()(Dense(64)(fc_layer))))
    fc_layer = Dropout(0.2)(Activation(activation="relu")(BatchNormalization()(Dense(32)(fc_layer))))
    
    ######## output layer ##########
    output_layer = concatenate([linear_part, snd_order_sparse_layer, fc_layer]) # (None, )
    output_layer = Dense(1, activation='sigmoid')(output_layer)
    
    model = Model(inputs=sparse_input+dense_input, outputs=output_layer)
    
    return model
python 复制代码
model = deepfm_model(sparse_cols, dense_cols, X_train1, X_test1)
model.compile(optimizer="adam", 
              loss="binary_crossentropy", 
              metrics=["binary_crossentropy", tf.keras.metrics.AUC(name='auc')])
python 复制代码
train_sparse_x = [X_train1[f].values for f in sparse_cols]
train_dense_x = [X_train1[f].values for f in dense_cols]
train_label = [y_train.values]

test_sparse_x = [X_test1[f].values for f in sparse_cols]
test_dense_x = [X_test1[f].values for f in dense_cols]
test_label = [y_test.values]
python 复制代码
test_sparse_x

训练模型

python 复制代码
from keras.callbacks import *
# 回调函数
file_path = "deepfm_model_data.h5"
earlystopping = EarlyStopping(monitor="val_loss", patience=3)
checkpoint = ModelCheckpoint(
    file_path, save_weights_only=True, verbose=1, save_best_only=True)
callbacks_list = [earlystopping, checkpoint]

hist = model.fit(train_sparse_x+train_dense_x, 
                  train_label,
                  batch_size=4096,
                  epochs=20,
                  validation_data=(test_sparse_x+test_dense_x, test_label),
                  callbacks=callbacks_list,
                  shuffle=False)

模型存储

python 复制代码
model.save('deepfm_model.h5')
loaded_model = tf.keras.models.load_model('deepfm_model.h5')
python 复制代码
print("np.min(hist.history['val_loss']):", np.min(hist.history['val_loss']))
#np.min(hist.history['val_loss']):0.19
python 复制代码
print("np.max(hist.history['val_auc']):", np.max(hist.history['val_auc']))
#np.max(hist.history['val_auc']):0.95

模型预测

python 复制代码
deepfm_prob = model.predict(test_sparse_x+test_dense_x, batch_size=4096*4, verbose=1)
deepfm_prob.shape
python 复制代码
deepfm_prob
python 复制代码
df_submit          = pd.DataFrame()
df_submit          = X_test
df_submit['prob']  = deepfm_prob 
df_submit.head(3)
python 复制代码
df_submit.shape
python 复制代码
df_submit['y_pre'] = ''
df_submit['y_pre'].loc[(df_submit['prob']>=0.5)] = 1
df_submit['y_pre'].loc[(df_submit['prob']<0.5)]  = 0
df_submit.head(3)
python 复制代码
df_submit = df_submit.reset_index()
df_submit.head(1)
python 复制代码
df_submit = df_submit.drop('index', axis = 1)
df_submit.head(1)
python 复制代码
df_submit.groupby(['flag', 'y_pre'])['customer_id'].count()

根据上述结果打印召回及精准

python 复制代码
precision = 
recall  = 

查看lgb结果做比较

python 复制代码
from lightgbm import LGBMClassifier
from sklearn.model_selection import GridSearchCV
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.metrics import f1_score, confusion_matrix, recall_score, precision_score



params = {'n_estimators': 1500, 
            'learning_rate': 0.1,
            'max_depth': 15,
            'metric': 'auc',
            'verbose': -1, 
            'seed: 2023,
            'n_jobs':-1

model=LGBMClarsifier(**params) 
model.fit(X_train, y_train,
            eval_set=[(X_train1, y_train), (X_test1, y_test)], 
            eval_metric = 'auc', 
            verbose=50,
            early_stopping_rounds = 100)
y_pred = model.predict(X_test1, num_iteration = model.best_iteration_)


          
          

y_pred = model.predict(X_test1)
y_pred_proba = model.predict_proba(X_test1)
lgb_acc = model.score(X_test1, y_test) * 100
lgb_recall = recall_score(y_test, y_pred) * 100
lgb_precision = precision_score(y_test, y_pred) * 100 I 
lgb_f1 = f1_score(y_test, y_pred, pos_label=1) * 100
print("1gb 准确率:{:.2f}%".format(lgb_acc))
print("lgb 召回率:{:.2f}%".fornat(lgb_recall))
print("lgb 精准率:{:.2f}%".format(lgb_precision))
print("lgb F1分数:{:.2f}%".format(lgb_f1))


#from sklearn.metrics import classification_report
#printf(classification_report(y_test, y_pred))

# 混淆矩阵
plt.title("混淆矩阵", fontsize=21)
data_confusion_matrix = confusion_matrix(y_test, y_pred)
sns.heatmap(data_confusion_matrix, annot=True, cmap='Blues', fmt='d', cbar='False', annot_kws={'size': 28})
plt.xlabel('Predicted label') 
plt.ylabel('True label')


from sklearn.metrics import roc_curve, auc
probs = model.predict_proba(X_test1)
preds = probs[:, 1]
fpr, tpr, threshold = roc_curve(y_test, preds)
# 绘制ROC曲线
roc_auc = auc(fpr, tpr)
plt.plot(fpr, tpr, 'b', label = 'AUC = %0.2f' % roc_auc)
plt.plot([0, 1], [0, 1], 'r--')
plt.xlim([0, 1])
plt.ylim([0, 1])
plt.ylabel('True Positive(TPR)')
plt.xlabel('False Positive(FPR)')
plt.title('ROC')
plt.legend(loc='lower right')
plt.show()

参考资料:自己琢磨将资料整合

相关推荐
mit6.82426 分钟前
[Meetily后端框架] Whisper转录服务器 | 后端服务管理脚本
c++·人工智能·后端·python
Baihai IDP28 分钟前
AI 系统架构的演进:LLM → RAG → AI Workflow → AI Agent
人工智能·ai·系统架构·llm·agent·rag·白海科技
沫儿笙31 分钟前
弧焊机器人气体全方位节能指南
网络·人工智能·机器人
LONGZETECH32 分钟前
【龙泽科技】新能源汽车维护与动力蓄电池检测仿真教学软件【吉利几何G6】
人工智能·科技·汽车·汽车仿真教学软件·汽车教学软件
看到我,请让我去学习1 小时前
OpenCV 与深度学习:从图像分类到目标检测技术
深度学习·opencv·分类
jndingxin2 小时前
OpenCV 图像哈希类cv::img_hash::AverageHash
人工智能·opencv·哈希算法
加油加油的大力2 小时前
入门基于深度学习(以yolov8和unet为例)的计算机视觉领域的学习路线
深度学习·yolo·计算机视觉
Jamence2 小时前
多模态大语言模型arxiv论文略读(153)
论文阅读·人工智能·语言模型·自然语言处理·论文笔记
晨曦5432102 小时前
量子计算突破:8比特扩散模型实现指数级加速
人工智能
Albert_Lsk2 小时前
【2025/07/11】GitHub 今日热门项目
人工智能·开源·github·开源协议