转化率算法大赛

最近做了一个月的腾讯广告大赛，总结一下，算法程序

 

腾讯给出了两个代码

1、基于平均分组转化的代码

 

# -*- coding: utf-8 -*-
"""
baseline 1: history pCVR of creativeID/adID/camgaignID/advertiserID/appID/appPlatform
"""

import zipfile
import numpy as np
import pandas as pd

# load data
data_root = "."
dfTrain = pd.read_csv("%s/train.csv"%data_root)
dfTest = pd.read_csv("%s/test.csv"%data_root)
dfAd = pd.read_csv("%s/ad.csv"%data_root)

# process data
dfTrain = pd.merge(dfTrain, dfAd, on="creativeID")
dfTest = pd.merge(dfTest, dfAd, on="creativeID")
y_train = dfTrain["label"].values

# model building
key = "appID"
dfCvr = dfTrain.groupby(key).apply(lambda df: np.mean(df["label"])).reset_index()
dfCvr.columns = [key, "avg_cvr"]
dfTest = pd.merge(dfTest, dfCvr, how="left", on=key)
dfTest["avg_cvr"].fillna(np.mean(dfTrain["label"]), inplace=True)
proba_test = dfTest["avg_cvr"].values

# submission
df = pd.DataFrame({"instanceID": dfTest["instanceID"].values, "proba": proba_test})
df.sort_values("instanceID", inplace=True)
df.to_csv("submission.csv", index=False)
with zipfile.ZipFile("submission.zip", "w") as fout:
    fout.write("submission.csv", compress_type=zipfile.ZIP_DEFLATED)

2、基于热编码后进行逻辑回归算法的预测算法

# -*- coding: utf-8 -*-
"""
baseline 2: ad.csv (creativeID/adID/camgaignID/advertiserID/appID/appPlatform) + lr
"""

import zipfile
import pandas as pd
from scipy import sparse
from sklearn.preprocessing import OneHotEncoder
from sklearn.linear_model import LogisticRegression

# load data
data_root = "."
dfTrain = pd.read_csv("%s/train.csv"%data_root)
dfTest = pd.read_csv("%s/test.csv"%data_root)
dfAd = pd.read_csv("%s/ad.csv"%data_root)

# process data
dfTrain = pd.merge(dfTrain, dfAd, on="creativeID")
dfTest = pd.merge(dfTest, dfAd, on="creativeID")
y_train = dfTrain["label"].values

# feature engineering/encoding
enc = OneHotEncoder()
feats = ["creativeID", "adID", "camgaignID", "advertiserID", "appID", "appPlatform"]
for i,feat in enumerate(feats):
    x_train = enc.fit_transform(dfTrain[feat].values.reshape(-1, 1))
    x_test = enc.transform(dfTest[feat].values.reshape(-1, 1))
    if i == 0:
        X_train, X_test = x_train, x_test
    else:
        X_train, X_test = sparse.hstack((X_train, x_train)), sparse.hstack((X_test, x_test))

# model training
lr = LogisticRegression()
lr.fit(X_train, y_train)
proba_test = lr.predict_proba(X_test)[:,1]

# submission
df = pd.DataFrame({"instanceID": dfTest["instanceID"].values, "proba": proba_test})
df.sort_values("instanceID", inplace=True)
df.to_csv("submission.csv", index=False)
with zipfile.ZipFile("submission.zip", "w") as fout:
fout.write("submission.csv", compress_type=zipfile.ZIP_DEFLATED)

然后我基于第二组的代码进行不同的特征选择，最终这个比较好

# -*- coding: utf-8 -*-
"""
baseline 2: ad.csv (creativeID/adID/camgaignID/advertiserID/appID/appPlatform) + lr
"""

import zipfile
import pandas as pd
from scipy import sparse
from sklearn.preprocessing import OneHotEncoder
from sklearn.linear_model import LogisticRegression

# load data
data_root = "."
dfTrain = pd.read_csv("%s/train.csv"%data_root)
dfTest = pd.read_csv("%s/test.csv"%data_root)
dfAd = pd.read_csv("%s/ad.csv"%data_root)
dfapp_categories = pd.read_csv("%s/app_categories.csv"%data_root)
dfuser = pd.read_csv("%s/user.csv"%data_root)
dfposition = pd.read_csv("%s/position.csv"%data_root)

# process data
dfad=pd.merge(dfAd,dfapp_categories,on="appID")
dfTrain = pd.merge(dfTrain, dfad, on="creativeID")
dfTrain = pd.merge(dfTrain, dfposition,how='left',on="positionID")
dfTest = pd.merge(dfTest, dfad, on="creativeID")
dfTest = pd.merge(dfTest, dfposition, how='left', on="positionID")
y_train = dfTrain["label"].values
dfTest.sort_values("instanceID", inplace=True)
dfTrain.to_csv("strain.csv", index=False)
dfTest.to_csv("stest.csv", index=False)
# feature engineering/encoding
enc = OneHotEncoder()
feats = ["creativeID", "adID", "camgaignID", "advertiserID", "appPlatform","appID","appCategory","positionID","sitesetID","positionType","userID","connectionType","telecomsOperator"]
for i,feat in enumerate(feats):
    x_train = enc.fit_transform(dfTrain[feat].values.reshape(-1, 1))
    x_test = enc.transform(dfTest[feat].values.reshape(-1, 1))
    if i == 0:
        X_train, X_test = x_train, x_test
    else:
        X_train, X_test = sparse.hstack((X_train, x_train)), sparse.hstack((X_test, x_test))



# 模型训练
# model training
lr = LogisticRegression()
lr.fit(X_train, y_train)
proba_test = lr.predict_proba(X_test)[:,1]

# submission
df = pd.DataFrame({"instanceID": dfTest["instanceID"].values, "proba": proba_test})
df.sort_values("instanceID", inplace=True)
      
df.to_csv("submission.csv", index=False)
with zipfile.ZipFile("submission.zip", "w") as fout:
    fout.write("submission.csv", compress_type=zipfile.ZIP_DEFLATED)

不同的特征，结果是不同的，所以如果以后做算法大赛的话，需要的还是调参和特征选择

PS：

使用的Python中SK-learn包中的一些机器学习算法，Python的好处就是简洁，另外有很多机器学习的算法都已经集成在包中，使用时

调用即可，不用再去写算法的代码。

PSS:此次成绩不是很理想，最高也仅仅是3百多名而已，以后还要深入学习Python机器学习方面的知识，为以后的工作打下基础。

PSSS:此次大赛的数据集在此

链接：http://pan.baidu.com/s/1nv7cf49 密码：gqz1