import pandas;
import matplotlib;
from pandas.tools.plotting import scatter_matrix;
data = pandas.read_csv(
'D:\\PDM\\4.2\\data.csv'
)
font = {
'family' : 'SimHei'
}
matplotlib.rc('font', **font)
scatter_matrix(
data[["店铺的面积", "距离最近的车站", "月营业额"]],
figsize=(10, 10), diagonal='kde'
)
data[["店铺的面积", "距离最近的车站", "月营业额"]].corr()
x = data[["店铺的面积", "距离最近的车站"]]
y = data[["月营业额"]]
from sklearn.linear_model import LinearRegression
#建模
lrModel = LinearRegression()
#训练模型
lrModel.fit(x, y)
#评分
lrModel.score(x, y)
#预测
lrModel.predict([10, 110])
lrModel.predict([[10, 110],[20, 110]])
#查看参数
lrModel.coef_
array([[ 41.51347826, -0.34088269]])
