深度学习_模型调用预测

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

代码

导包

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

data = pd.read_csv('df_04m.csv')

区分稀疏及类别变量

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

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

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

y = data['flag']
X = data.drop(['customer_id', 'flag', 'duartion_is_lm'], axis = 1)

数据处理成模型样式

X_sparse_x = [X[f].values for f in sparse_cols]
X_dense_x = [X[f].values for f in dense_cols]
y_label = [y.values]

X_sparse_x

模型读取

loaded_model = tf.keras.models.load_model('deepfm_model.h5')

模型预测

deepfm_prob = loaded_model.predict(X_sparse_x+X_dense_x, batch_size=4096*4, verbose=1)
deepfm_prob.shape

deepfm_prob

df_submit          = pd.DataFrame()
df_submit          = data
df_submit['prob']  = deepfm_prob
df_submit.head(3)

df_submit.shape

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)

df_submit = df_submit.reset_index()
df_submit.head(1)

df_submit = df_submit.drop('index', axis = 1)
df_submit.head(1)

df_submit.groupby(['flag', 'y_pre'])['customer_id'].count()

根据上述结果打印召回及精准

precision = 
recall  = 

参考资料：自己琢磨将资料整合