最近打各种比赛，在这里分享一些General Model，稍微改改就能用的
XGBoost调参大全： http://blog.csdn.net/han_xiaoyang/article/details/52665396
XGBoost 官方API：
http://xgboost.readthedocs.io/en/latest//python/python_api.html
Preprocess
# 通用的预处理框架
import pandas as pd
import numpy as np
import scipy as sp
# 文件读取
def read_csv_file(f, logging=False):
print("==========读取数据=========")
data = pd.read_csv(f)
if logging:
print(data.head(5))
print(f, "包含以下列")
print(data.columns.values)
print(data.describe())
print(data.info())
return data
Logistic Regression
# 通用的LogisticRegression框架
import pandas as pd
import numpy as np
from scipy import sparse
from sklearn.preprocessing import OneHotEncoder
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
# 1. load data
df_train = pd.DataFrame()
df_test = pd.DataFrame()
y_train = df_train['label'].values
# 2. process data
ss = StandardScaler()
# 3. feature engineering/encoding
# 3.1 For Labeled Feature
enc = OneHotEncoder()
feats = ["creativeID", "adID", "campaignID"]
for i, feat in enumerate(feats):
x_train = enc.fit_transform(df_train[feat].values.reshape(-1, 1))
x_test = enc.fit_transform(df_test[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))
# 3.2 For Numerical Feature
# It must be a 2-D Data for StandardScalar, otherwise reshape(-1, len(feats)) is required
feats = ["price", "age"]
x_train = ss.fit_transform(df_train[feats].values)
x_test = ss.fit_transform(df_test[feats].values)
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]
LightGBM
1. 二分类
import lightgbm as lgb
import pandas as pd
import numpy as np
import pickle
from sklearn.metrics import roc_auc_score
from sklearn.model_selection import train_test_split
print("Loading Data ... ")
# 导入数据
train_x, train_y, test_x = load_data()
# 用sklearn.cross_validation进行训练数据集划分，这里训练集和交叉验证集比例为7：3，可以自己根据需要设置
X, val_X, y, val_y = train_test_split(
train_x,
train_y,
test_size=0.05,
random_state=1,
stratify=train_y ## 这里保证分割后y的比例分布与原数据一致
)
X_train = X
y_train = y
X_test = val_X
y_test = val_y
# create dataset for lightgbm
lgb_train = lgb.Dataset(X_train, y_train)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)
# specify your configurations as a dict
params = {
'boosting_type': 'gbdt',
'objective': 'binary',
'metric': {'binary_logloss', 'auc'},
'num_leaves': 5,
'max_depth': 6,
'min_data_in_leaf': 450,
