linear regression of area and price

import pandas as pd
import numpy as np
from sklearn import linear_model
import matplotlib.pyplot as plt

In [31]:

df = pd.read_csv("areadata.csv")
df

Out[31]:

	area	price
0	2600	550000
1	3000	565000
2	3200	610000
3	3600	680000
4	4000	725000

In [34]:

%matplotlib inline 
plt.xlabel("area")
plt.ylabel("price")
plt.scatter(df.area,df.price,color="red",marker="+")

Out[34]:

<matplotlib.collections.PathCollection at 0x18712b13c88>

In [37]:

newdf = df.drop("price",axis="columns")
newdf

Out[37]:

	area
0	2600
1	3000
2	3200
3	3600
4	4000

In [39]:

model = linear_model.LinearRegression()
model.fit(newdf,df.price)

Out[39]:

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)

In [43]:

model.predict([[5000]])

Out[43]:

array([859554.79452055])

In [44]:

model.intercept_

Out[44]:

180616.43835616432