HUAWEI赛事CTR广告点击率预测

import pandas as pd

# ----------------数据探索----------------
# 只使用目标域用户行为数据
train_ads = pd.read_csv('train_data_ads.csv',
                        usecols=['log_id', 'label', 'user_id', 'age', 'gender', 'residence', 'device_name',
                                 'device_size', 'net_type', 'task_id', 'adv_id', 'creat_type_cd'])

test_ads = pd.read_csv('test_data_ads.csv',
                       usecols=['log_id', 'user_id', 'age', 'gender', 'residence', 'device_name',
                                'device_size', 'net_type', 'task_id', 'adv_id', 'creat_type_cd'])

# 数据集采样
train_ads = pd.concat([
    train_ads[train_ads['label'] == 0].sample(70000),   #随机取样70000，并与label = 1横向连接
    train_ads[train_ads['label'] == 1].sample(10000),
])

# ----------------模型训练----------------
# 加载训练逻辑回归模型
from sklearn.linear_model import LogisticRegression

clf = LogisticRegression()
clf.fit(
    train_ads.drop(['log_id', 'label', 'user_id'], axis=1),
    train_ads['label']
)
print(clf.classes_)
# ----------------结果输出----------------
# 模型预测与生成结果文件
test_ads['pctr'] = clf.predict_proba(
    test_ads.drop(['log_id', 'user_id'], axis=1),
)[:, 1]   #[:,1]是为了取1的概率,即选取label=1
print(test_ads['pctr'])
# test_ads[['log_id', 'pctr']].to_csv('submission.csv', index=None)