基于uplift模型的营销增益

import pandas as pd
import numpy as np
import toad 
from sklearn.model_selection import train_test_split  # 数据分区库
import xgboost as xgb

# 导入自定义模块
import sys
sys.path.append("/Users/heinrich/Desktop/Heinrich-blog/数据分析使用手册")
from keyIndicatorMapping import *

# 读取数据
raw_data=pd.read_csv('data.csv')
raw_data.head()

# 查看数据信息
toad.detector.detect(raw_data)

# 替换字符串
zip_code_dic={
    'Surburban':1,
    'Urban':2,
    'Rural':3
}
channel_dic={
    'Web':1,
    'Phone':2,
    'Multichannel':3
}
offer_dic={
    'Buy One Get One':1,
    'Discount':2,
    'No Offer':0
}

raw_data=raw_data.replace({'zip_code': zip_code_dic,
                          'channel':channel_dic,
                          'offer':offer_dic})

# 计算活动提升情况
def calc_uplift(df):
    # 计算各活动方式的转化率
    base_conv = df[df.offer == 0]['conversion'].mean()
    disc_conv = df[df.offer == 2]['conversion'].mean()
    bogo_conv = df[df.offer == 1]['conversion'].mean()
    
    # 计算两活动转化率的提升效果
    disc_conv_uplift = disc_conv - base_conv
    bogo_conv_uplift = bogo_conv - base_conv
    
    print('Discount Conversion Uplift: {0}%'.format(np.round(disc_conv_uplift*100,2)))
    
    if len(df[df.offer == 1]['conversion']) > 0:
          
        print('-'*60)
        print('BOGO Conversion Uplift: {0}%'.format(np.round(bogo_conv_uplift*100,2)))

# 根据uplift score计算方式进行分类

# 设置对照-实验组
raw_data['campaign_group'] = 1
raw_data.loc[raw_data.offer == 0, 'campaign_group'] = 0
# 分类
raw_data['target_class'] = 0 # CN
raw_data.loc[(raw_data.campaign_group == 0) & (raw_data.conversion == 1),'target_class'] = 1 # CR
raw_data.loc[(raw_data.campaign_group == 1) & (raw_data.conversion == 0),'target_class'] = 2 # TN
raw_data.loc[(raw_data.campaign_group == 1) & (raw_data.conversion == 1),'target_class'] = 3 # TR

# 模型数据
df_model = raw_data.drop(['offer','campaign_group','conversion'],axis=1) 
df_model.head()

# 样本拆分
X = df_model.drop(['target_class'],axis=1)
y = df_model.target_class
X_train, X_test, y_train, y_test = train_test_split(X, 
            y, test_size=0.2, random_state=56)

# XGB分类模型训练
param_dist = {'objective':'multi:softmax', 'eval_metric':'logloss', 'use_label_encoder':False}
model_xgb = xgb.XGBClassifier(**param_dist)
model_xgb.fit(X_train, y_train)

XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, eval_metric='logloss',
              gamma=0, gpu_id=-1, importance_type='gain',
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=8,
              num_parallel_tree=1, objective='multi:softprob', random_state=0,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=None, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=None)

# 计算uplift_score
y_prob = model_xgb.predict_proba(X)
uplift_score=[]
for i in y_prob:
    us=i[0]+i[3]-i[1]-i[2]
    uplift_score.append(us)
raw_data['uplift_score'] = uplift_score
raw_data.head()

# 模型评估
# 记录活动的base
calc_uplift(raw_data)

Discount Conversion Uplift: 7.66%
------------------------------------------------------------
BOGO Conversion Uplift: 4.52%

# 高Uplift分数：客户的uplift分数>3/4分位数
raw_data_lift = raw_data.copy()
uplift_q_75 = raw_data_lift.uplift_score.quantile(0.75)
raw_data_lift = raw_data_lift[raw_data_lift.uplift_score > uplift_q_75].reset_index(drop=True)
# 计算top1/4的用户的提升情况
calc_uplift(raw_data_lift)

Discount Conversion Uplift: 30.29%
------------------------------------------------------------
BOGO Conversion Uplift: 26.18%

# 低Uplift分数：客户的uplift分数<1/2分位数
raw_data_lift = raw_data.copy()
uplift_q_50 = raw_data_lift.uplift_score.quantile(0.5)
raw_data_lift = raw_data_lift[raw_data_lift.uplift_score < uplift_q_50].reset_index(drop=True)
# 计算bottom1/2的用户的提升情况
calc_uplift(raw_data_lift)

Discount Conversion Uplift: -3.87%
------------------------------------------------------------
BOGO Conversion Uplift: -6.03%

# 评分直方图
def plot_score_hist(df, y_col, score_col, cutoff=None):
    """
    df:数据集（含y_col,score列）
    y_col:目标变量的字段名
    score_col:得分的字段名
    cutoff :划分拒绝/通过的点
    
    return :不同类型用户的得分分布图
    """  
    # 预处理
    x1 = df[df[y_col]==0][score_col]
    x2 = df[df[y_col]==1][score_col]
    x3 = df[df[y_col]==2][score_col]
    x4 = df[df[y_col]==3][score_col]
    # 绘图
    plt.title('Uplift Score Hist')
    sns.kdeplot(x1,shade=True,label='CN')
    sns.kdeplot(x2,shade=True,label='CR')
    sns.kdeplot(x3,shade=True,label='TN')
    sns.kdeplot(x4,shade=True,label='TR')
    if cutoff!=None:
        plt.axvline(x=cutoff)
    plt.legend()
    return plt

plot_score_hist(raw_data, 'target_class', 'uplift_score')
plt.show()