- 查询数据库数据保存为pandas.dataframe
from sqlalchemy import create_engine
# 初始化数据库连接,使用pymysql模块
engine = create_engine('mysql+pymysql://用户名:host:3306/数据库名')
# 查询语句,选出employee表中的所有数据
sql = '''
SELECT 字段 FROM 表名 WHERE 条件
'''
# read_sql_query的两个参数: sql语句, 数据库连接
dataset = pd.read_sql_query(sql, engine)
# 输出employee表的查询结果
print(dataset.head(10))
- 获取特征值和目标值,拆分特征为测试集合训练集(0.2为例)
from sklearn.model_selection import train_test_split
# Split-out validation dataset
array = dataset.values
# 假设前5列为特征 最后一列为目标值
X = array[:,:5]
y = array[:,5]
print(X)
print(y)
validation_size = 0.20
seed = 7
X_train, X_validation, Y_train, Y_validation = model_selection.train_test_split(X, y, test_size=validation_size, random_state=seed)
- 使用XGBoost进行预测,打印精准率,召回率和f1,混淆矩阵和准确率