from sklearn.

linear_model import LinearRegression

from sklearn.metrics import mean_squared_error,mean_absolute_error,r2_score
from sklearn.model_selection import train_test_split

import pandas as pd
data=pd.read_csv("Housing.csv")
data

price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea

0 13300000 7420 4 2 3 yes no no no yes 2

1 12250000 8960 4 4 4 yes no no no yes 3

2 12250000 9960 3 2 2 yes no yes no no 2

3 12215000 7500 4 2 2 yes no yes no yes 3

4 11410000 7420 4 1 2 yes yes yes no yes 2

... ... ... ... ... ... ... ... ... ... ... ...

540 1820000 3000 2 1 1 yes no yes no no 2

541 1767150 2400 3 1 1 no no no no no 0

542 1750000 3620 2 1 1 yes no no no no 0

543 1750000 2910 3 1 1 no no no no no 0

544 1750000 3850 3 1 2 yes no no no no 0

545 rows × 13 columns

data.head(5) #first 5 rows will be printed.

price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea

0 13300000 7420 4 2 3 yes no no no yes 2 yes

1 12250000 8960 4 4 4 yes no no no yes 3 no

2 12250000 9960 3 2 2 yes no yes no no 2 yes

3 12215000 7500 4 2 2 yes no yes no yes 3 yes

4 11410000 7420 4 1 2 yes yes yes no yes 2 no

data.head(10)

price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea

0 13300000 7420 4 2 3 yes no no no yes 2 yes

1 12250000 8960 4 4 4 yes no no no yes 3

2 12250000 9960 3 2 2 yes no yes no no 2 yes

3 12215000 7500 4 2 2 yes no yes no yes 3 yes

4 11410000 7420 4 1 2 yes yes yes no yes 2

5 10850000 7500 3 3 1 yes no yes no yes 2 yes

6 10150000 8580 4 3 4 yes no no no yes 2 yes

7 10150000 16200 5 3 2 yes no no no no 0

8 9870000 8100 4 1 2 yes yes yes no yes 2 yes

9 9800000 5750 3 2 4 yes yes no no yes 1 yes

data.shape #tells us the number of rows and columns present in the csv file.

(545, 13)

data.info() #this returns not null values,column,datatype,and information about the data.
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 545 entries, 0 to 544
Data columns (total 13 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 price 545 non-null int64
1 area 545 non-null int64
2 bedrooms 545 non-null int64
3 bathrooms 545 non-null int64
4 stories 545 non-null int64
5 mainroad 545 non-null object
6 guestroom 545 non-null object
7 basement 545 non-null object
8 hotwaterheating 545 non-null object
9 airconditioning 545 non-null object
10 parking 545 non-null int64
11 prefarea 545 non-null object
12 furnishingstatus 545 non-null object
dtypes: int64(6), object(7)
memory usage: 55.5+ KB

from sklearn.preprocessing import LabelEncoder, MinMaxScaler #this command will convert object datatype into integer
le=LabelEncoder() #it converts the categorical entries into numerical entries.
data["mainroad"]=le.fit_transform(data["mainroad"])
data
#change raw feature vectors into a representation that is more suitable for the downstream estimators-sklearn.preproc

price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea

0 13300000 7420 4 2 3 1 no no no yes 2

1 12250000 8960 4 4 4 1 no no no yes 3

2 12250000 9960 3 2 2 1 no yes no no 2

3 12215000 7500 4 2 2 1 no yes no yes 3

4 11410000 7420 4 1 2 1 yes yes no yes 2

... ... ... ... ... ... ... ... ... ... ... ...

540 1820000 3000 2 1 1 1 no yes no no 2

541 1767150 2400 3 1 1 0 no no no no 0

542 1750000 3620 2 1 1 1 no no no no 0

543 1750000 2910 3 1 1 0 no no no no 0

544 1750000 3850 3 1 2 1 no no no no 0

545 rows × 13 columns

from sklearn.preprocessing import LabelEncoder,MinMaxScaler

data["guestroom"]=le.fit_transform(data["guestroom"])
data.head(5)

price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea

0 13300000 7420 4 2 3 1 0 no no yes 2 yes

1 12250000 8960 4 4 4 1 0 no no yes 3 no

2 12250000 9960 3 2 2 1 0 yes no no 2 yes

3 12215000 7500 4 2 2 1 0 yes no yes 3 yes

4 11410000 7420 4 1 2 1 1 yes no yes 2 no

from sklearn.preprocessing import LabelEncoder,MinMaxScaler

data["basement"]=le.fit_transform(data["basement"])
data.head(5)

price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea

0 13300000 7420 4 2 3 1 0 0 no yes 2 yes

1 12250000 8960 4 4 4 1 0 0 no yes 3 no

2 12250000 9960 3 2 2 1 0 1 no no 2 yes

3 12215000 7500 4 2 2 1 0 1 no yes 3 yes

4 11410000 7420 4 1 2 1 1 1 no yes 2 no

 from sklearn.preprocessing import LabelEncoder,MinMaxScaler
data["hotwaterheating"]=le.fit_transform(data["hotwaterheating"])
data.head(5)

price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea

0 13300000 7420 4 2 3 1 0 0 0 yes 2 yes

1 12250000 8960 4 4 4 1 0 0 0 yes 3 no

2 12250000 9960 3 2 2 1 0 1 0 no 2 yes

3 12215000 7500 4 2 2 1 0 1 0 yes 3 yes

4 11410000 7420 4 1 2 1 1 1 0 yes 2 no

from sklearn.preprocessing import LabelEncoder,MinMaxScaler

data["prefarea"]=le.fit_transform(data["prefarea"])
data.head(5)

price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea

0 13300000 7420 4 2 3 1 0 0 0 1 2

1 12250000 8960 4 4 4 1 0 0 0 1 3

2 12250000 9960 3 2 2 1 0 1 0 0 2

3 12215000 7500 4 2 2 1 0 1 0 1 3

4 11410000 7420 4 1 2 1 1 1 0 1 2

from sklearn.preprocessing import LabelEncoder,MinMaxScaler

data["furnishingstatus"]=le.fit_transform(data["furnishingstatus"])
data.head(5)

price area bedrooms bathrooms stories mainroad guestroom basement hotwaterheating airconditioning parking prefarea

0 13300000 7420 4 2 3 1 0 0 0 1 2

1 12250000 8960 4 4 4 1 0 0 0 1 3

2 12250000 9960 3 2 2 1 0 1 0 0 2

3 12215000 7500 4 2 2 1 0 1 0 1 3

4 11410000 7420 4 1 2 1 1 1 0 1 2

x=data.drop(columns=["price"])
y=data["price"]
y=y.values.reshape(-1,1)

scaler=MinMaxScaler()
x=scaler.fit_transform(x)
y=scaler.fit_transform(y)

lr=LinearRegression()
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2)
lr.fit(x_train,y_train)
y_predict=lr.predict(x_test)

mae=mean_absolute_error(y_test,y_predict)
mse=mean_squared_error(y_test,y_predict)
r2=r2_score(y_test,y_predict)
print(mae,mse,r2)

0.06995281320799962 0.007960782075320859 0.6594122430015953

Loading [MathJax]/jax/output/CommonHTML/fonts/TeX/fontdata.js