!

pip install panda

Requirement already satisfied: panda in c:\users\divya\anaconda3\lib\

site-packages (0.3.1)
Requirement already satisfied: setuptools in c:\users\divya\anaconda3\
lib\site-packages (from panda) (69.5.1)
Requirement already satisfied: requests in c:\users\divya\anaconda3\
lib\site-packages (from panda) (2.32.2)
Requirement already satisfied: charset-normalizer<4,>=2 in c:\users\
divya\anaconda3\lib\site-packages (from requests->panda) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in c:\users\divya\
anaconda3\lib\site-packages (from requests->panda) (3.7)
Requirement already satisfied: urllib3<3,>=1.21.1 in c:\users\divya\
anaconda3\lib\site-packages (from requests->panda) (2.2.2)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\divya\
anaconda3\lib\site-packages (from requests->panda) (2025.1.31)

import pandas as pd

df = pd.read_csv('Housing.csv')
df

price area bedrooms bathrooms stories mainroad guestroom

basement \
0 13300000 7420 4 2 3 yes no
no
1 12250000 8960 4 4 4 yes no
no
2 12250000 9960 3 2 2 yes no
yes
3 12215000 7500 4 2 2 yes no
yes
4 11410000 7420 4 1 2 yes yes
yes
.. ... ... ... ... ... ... ...
...
540 1820000 3000 2 1 1 yes no
yes
541 1767150 2400 3 1 1 no no
no
542 1750000 3620 2 1 1 yes no
no
543 1750000 2910 3 1 1 no no
no
544 1750000 3850 3 1 2 yes no
no

hotwaterheating airconditioning parking prefarea furnishingstatus

0 no yes 2 yes furnished

1 no yes 3 no furnished

2 no no 2 yes semi-furnished

3 no yes 3 yes furnished

4 no yes 2 no furnished

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

540 no no 2 no unfurnished

541 no no 0 no semi-furnished

542 no no 0 no unfurnished

543 no no 0 no furnished

544 no no 0 no unfurnished

[545 rows x 13 columns]

df.head()

price area bedrooms bathrooms stories mainroad guestroom

basement \
0 13300000 7420 4 2 3 yes no
no
1 12250000 8960 4 4 4 yes no
no
2 12250000 9960 3 2 2 yes no
yes
3 12215000 7500 4 2 2 yes no
yes
4 11410000 7420 4 1 2 yes yes
yes

hotwaterheating airconditioning parking prefarea furnishingstatus

0 no yes 2 yes furnished
1 no yes 3 no furnished
2 no no 2 yes semi-furnished
3 no yes 3 yes furnished
4 no yes 2 no furnished

df.tail()

price area bedrooms bathrooms stories mainroad guestroom

basement \
540 1820000 3000 2 1 1 yes no
yes
541 1767150 2400 3 1 1 no no
no
542 1750000 3620 2 1 1 yes no
no
543 1750000 2910 3 1 1 no no
no
544 1750000 3850 3 1 2 yes no
no

hotwaterheating airconditioning parking prefarea furnishingstatus

540 no no 2 no unfurnished

541 no no 0 no semi-furnished

542 no no 0 no unfurnished

543 no no 0 no furnished

544 no no 0 no unfurnished

df.shape

(545, 13)

df.info()

<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

df.describe()
 price area bedrooms bathrooms stories
\
count 5.450000e+02 545.000000 545.000000 545.000000 545.000000

mean 4.766729e+06 5150.541284 2.965138 1.286239 1.805505

std 1.870440e+06 2170.141023 0.738064 0.502470 0.867492

min 1.750000e+06 1650.000000 1.000000 1.000000 1.000000

25% 3.430000e+06 3600.000000 2.000000 1.000000 1.000000

50% 4.340000e+06 4600.000000 3.000000 1.000000 2.000000

75% 5.740000e+06 6360.000000 3.000000 2.000000 2.000000

max 1.330000e+07 16200.000000 6.000000 4.000000 4.000000

parking
count 545.000000
mean 0.693578
std 0.861586
min 0.000000
25% 0.000000
50% 0.000000
75% 1.000000
max 3.000000

df.iloc[0:3, 0:4]

price area bedrooms bathrooms

0 13300000 7420 4 2
1 12250000 8960 4 4
2 12250000 9960 3 2

df.iloc[3]

price 12215000
area 7500
bedrooms 4
bathrooms 2
stories 2
mainroad yes
guestroom no
basement yes
hotwaterheating no
airconditioning yes
parking 3
prefarea yes
furnishingstatus furnished
Name: 3, dtype: object

df.loc[10:16, ['area']]

area
10 13200
11 6000
12 6550
13 3500
14 7800
15 6000
16 6600

df.loc[10:16, ['area', 'bedrooms']]

area bedrooms
10 13200 3
11 6000 4
12 6550 4
13 3500 4
14 7800 3
15 6000 4
16 6600 4

df.nunique()

price 219
area 284
bedrooms 6
bathrooms 4
stories 4
mainroad 2
guestroom 2
basement 2
hotwaterheating 2
airconditioning 2
parking 4
prefarea 2
furnishingstatus 3
dtype: int64

df['bathrooms'].unique()

array([2, 4, 1, 3], dtype=int64)

df.isnull().any()

price False
area False
bedrooms False
bathrooms False
stories False
mainroad False
guestroom False
basement False
hotwaterheating False
airconditioning False
parking False
prefarea False
furnishingstatus False
dtype: bool

df.dropna()

price area bedrooms bathrooms stories mainroad guestroom

basement \
0 13300000 7420 4 2 3 yes no
no
1 12250000 8960 4 4 4 yes no
no
2 12250000 9960 3 2 2 yes no
yes
3 12215000 7500 4 2 2 yes no
yes
4 11410000 7420 4 1 2 yes yes
yes
.. ... ... ... ... ... ... ...
...
540 1820000 3000 2 1 1 yes no
yes
541 1767150 2400 3 1 1 no no
no
542 1750000 3620 2 1 1 yes no
no
543 1750000 2910 3 1 1 no no
no
544 1750000 3850 3 1 2 yes no
no

hotwaterheating airconditioning parking prefarea furnishingstatus

0 no yes 2 yes furnished

1 no yes 3 no furnished

2 no no 2 yes semi-furnished

3 no yes 3 yes furnished

4 no yes 2 no furnished
.. ... ... ... ... ...

540 no no 2 no unfurnished

541 no no 0 no semi-furnished

542 no no 0 no unfurnished

543 no no 0 no furnished

544 no no 0 no unfurnished

[545 rows x 13 columns]

df.duplicated().sum()

df.drop(index=[0,1], axis=0)

price area bedrooms bathrooms stories mainroad guestroom

basement \
2 12250000 9960 3 2 2 yes no
yes
3 12215000 7500 4 2 2 yes no
yes
4 11410000 7420 4 1 2 yes yes
yes
5 10850000 7500 3 3 1 yes no
yes
6 10150000 8580 4 3 4 yes no
no
.. ... ... ... ... ... ... ...
...
540 1820000 3000 2 1 1 yes no
yes
541 1767150 2400 3 1 1 no no
no
542 1750000 3620 2 1 1 yes no
no
543 1750000 2910 3 1 1 no no
no
544 1750000 3850 3 1 2 yes no
no

hotwaterheating airconditioning parking prefarea furnishingstatus

2 no no 2 yes semi-furnished
3 no yes 3 yes furnished

4 no yes 2 no furnished

5 no yes 2 yes semi-furnished

6 no yes 2 yes semi-furnished

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

540 no no 2 no unfurnished

541 no no 0 no semi-furnished

542 no no 0 no unfurnished

543 no no 0 no furnished

544 no no 0 no unfurnished

[543 rows x 13 columns]

df.drop(index=[0,1], axis=0, inplace=True)

df

price area bedrooms bathrooms stories mainroad guestroom

basement \
2 12250000 9960 3 2 2 yes no
yes
3 12215000 7500 4 2 2 yes no
yes
4 11410000 7420 4 1 2 yes yes
yes
5 10850000 7500 3 3 1 yes no
yes
6 10150000 8580 4 3 4 yes no
no
.. ... ... ... ... ... ... ...
...
540 1820000 3000 2 1 1 yes no
yes
541 1767150 2400 3 1 1 no no
no
542 1750000 3620 2 1 1 yes no
no
543 1750000 2910 3 1 1 no no
no
544 1750000 3850 3 1 2 yes no
no
 hotwaterheating airconditioning parking prefarea furnishingstatus

2 no no 2 yes semi-furnished

3 no yes 3 yes furnished

4 no yes 2 no furnished

5 no yes 2 yes semi-furnished

6 no yes 2 yes semi-furnished

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

540 no no 2 no unfurnished

541 no no 0 no semi-furnished

542 no no 0 no unfurnished

543 no no 0 no furnished

544 no no 0 no unfurnished

[543 rows x 13 columns]

grp = df.groupby('area')
grp

<pandas.core.groupby.generic.DataFrameGroupBy object at
0x00000166E10AD430>

d = pd.read_csv('Housing.csv')

d['price'].value_counts()

price
3500000 17
4200000 17
4900000 12
3150000 9
5600000 9
..
6580000 1
4319000 1
4375000 1
4382000 1
13300000 1
Name: count, Length: 219, dtype: int64
d['area'].value_counts()

area
6000 24
3000 14
4500 13
4000 11
5500 9
..
6862 1
4815 1
9166 1
6321 1
3620 1
Name: count, Length: 284, dtype: int64

grp.get_group(9960)['furnishingstatus']

2 semi-furnished
Name: furnishingstatus, dtype: object

grp.get_group(6000)['furnishingstatus']

11 semi-furnished
15 semi-furnished
26 semi-furnished
38 unfurnished
39 semi-furnished
43 semi-furnished
44 furnished
45 semi-furnished
46 furnished
52 furnished
54 semi-furnished
55 unfurnished
59 furnished
60 semi-furnished
68 furnished
71 unfurnished
79 furnished
80 semi-furnished
83 semi-furnished
94 semi-furnished
99 unfurnished
135 unfurnished
227 furnished
486 semi-furnished
Name: furnishingstatus, dtype: object

grp.get_group(6000)
 price area bedrooms bathrooms stories mainroad guestroom
basement \
11 9681000 6000 4 3 2 yes yes
yes
15 9100000 6000 4 1 2 yes no
yes
26 8463000 6000 3 2 4 yes yes
yes
38 7962500 6000 3 1 4 yes yes
no
39 7910000 6000 4 2 4 yes no
no
43 7700000 6000 4 2 4 yes no
no
44 7560000 6000 4 2 4 yes no
no
45 7560000 6000 3 2 3 yes no
no
46 7525000 6000 3 2 4 yes no
no
52 7350000 6000 4 2 4 yes yes
no
54 7350000 6000 3 2 2 yes yes
no
55 7350000 6000 3 1 2 yes no
no
59 7210000 6000 3 2 4 yes yes
no
60 7140000 6000 3 2 2 yes yes
no
68 6860000 6000 3 1 1 yes no
no
71 6755000 6000 4 2 4 yes no
no
79 6650000 6000 3 2 3 yes yes
no
80 6629000 6000 3 1 2 yes no
no
83 6580000 6000 3 2 4 yes no
no
94 6300000 6000 4 2 4 yes no
no
99 6265000 6000 4 1 3 yes yes
yes
135 5775000 6000 3 2 4 yes no
no
227 4690000 6000 2 1 1 yes no
yes
486 2870000 6000 2 1 1 yes no
no
 hotwaterheating airconditioning parking prefarea furnishingstatus

11 yes no 2 no semi-furnished

15 no no 2 no semi-furnished

26 no yes 0 yes semi-furnished

38 no yes 2 no unfurnished

39 no yes 1 no semi-furnished

43 no no 2 no semi-furnished

44 no yes 1 no furnished

45 no yes 0 no semi-furnished

46 no yes 1 no furnished

52 no yes 1 no furnished

54 no yes 1 no semi-furnished

55 no yes 1 no unfurnished

59 no yes 1 no furnished

60 no no 1 no semi-furnished

68 no yes 1 no furnished

71 no yes 0 no unfurnished

79 no yes 0 no furnished

80 yes no 1 yes semi-furnished

83 no yes 0 no semi-furnished

94 no no 1 no semi-furnished

99 no no 0 yes unfurnished

135 no yes 0 no unfurnished

227 no yes 1 no furnished

486 no no 0 no semi-furnished
grp.get_group(6000).min()

price 2870000
area 6000
bedrooms 2
bathrooms 1
stories 1
mainroad yes
guestroom no
basement no
hotwaterheating no
airconditioning no
parking 0
prefarea no
furnishingstatus furnished
dtype: object

grp.get_group(6000).max()

price 9681000
area 6000
bedrooms 4
bathrooms 3
stories 4
mainroad yes
guestroom yes
basement yes
hotwaterheating yes
airconditioning yes
parking 2
prefarea yes
furnishingstatus unfurnished
dtype: object

d.set_index('area')

price bedrooms bathrooms stories mainroad guestroom

basement \
area

7420 13300000 4 2 3 yes no

no
8960 12250000 4 4 4 yes no
no
9960 12250000 3 2 2 yes no
yes
7500 12215000 4 2 2 yes no
yes
7420 11410000 4 1 2 yes yes
yes
... ... ... ... ... ... ... .
..
3000 1820000 2 1 1 yes no
yes
2400 1767150 3 1 1 no no
no
3620 1750000 2 1 1 yes no
no
2910 1750000 3 1 1 no no
no
3850 1750000 3 1 2 yes no
no

hotwaterheating airconditioning parking prefarea

furnishingstatus
area

7420 no yes 2 yes

furnished
8960 no yes 3 no
furnished
9960 no no 2 yes semi-
furnished
7500 no yes 3 yes
furnished
7420 no yes 2 no
furnished
... ... ... ... ... ..
.
3000 no no 2 no
unfurnished
2400 no no 0 no semi-
furnished
3620 no no 0 no
unfurnished
2910 no no 0 no
furnished
3850 no no 0 no
unfurnished

[545 rows x 12 columns]

price area bedrooms bathrooms stories mainroad guestroom

basement \
0 13300000 7420 4 2 3 yes no
no
1 12250000 8960 4 4 4 yes no
no
2 12250000 9960 3 2 2 yes no
yes
3 12215000 7500 4 2 2 yes no
yes
4 11410000 7420 4 1 2 yes yes
yes
.. ... ... ... ... ... ... ...
...
540 1820000 3000 2 1 1 yes no
yes
541 1767150 2400 3 1 1 no no
no
542 1750000 3620 2 1 1 yes no
no
543 1750000 2910 3 1 1 no no
no
544 1750000 3850 3 1 2 yes no
no

hotwaterheating airconditioning parking prefarea furnishingstatus

0 no yes 2 yes furnished

1 no yes 3 no furnished

2 no no 2 yes semi-furnished

3 no yes 3 yes furnished

4 no yes 2 no furnished

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

540 no no 2 no unfurnished

541 no no 0 no semi-furnished

542 no no 0 no unfurnished

543 no no 0 no furnished

544 no no 0 no unfurnished

[545 rows x 13 columns]

d.set_index('furnishingstatus', inplace=True)

d
 price area bedrooms bathrooms stories
mainroad \
furnishingstatus

furnished 13300000 7420 4 2 3

yes
furnished 12250000 8960 4 4 4
yes
semi-furnished 12250000 9960 3 2 2
yes
furnished 12215000 7500 4 2 2
yes
furnished 11410000 7420 4 1 2
yes
... ... ... ... ... ... ..
.
unfurnished 1820000 3000 2 1 1
yes
semi-furnished 1767150 2400 3 1 1
no
unfurnished 1750000 3620 2 1 1
yes
furnished 1750000 2910 3 1 1
no
unfurnished 1750000 3850 3 1 2
yes

guestroom basement hotwaterheating airconditioning

parking \
furnishingstatus

furnished no no no yes
2
furnished no no no yes
3
semi-furnished no yes no no
2
furnished no yes no yes
3
furnished yes yes no yes
2
... ... ... ... ...
...
unfurnished no yes no no
2
semi-furnished no no no no
0
unfurnished no no no no
0
furnished no no no no
0
unfurnished no no no no
0

prefarea
furnishingstatus
furnished yes
furnished no
semi-furnished yes
furnished yes
furnished no
... ...
unfurnished no
semi-furnished no
unfurnished no
furnished no
unfurnished no

[545 rows x 12 columns]

d.reset_index()

furnishingstatus price area bedrooms bathrooms stories

mainroad \
0 furnished 13300000 7420 4 2 3
yes
1 furnished 12250000 8960 4 4 4
yes
2 semi-furnished 12250000 9960 3 2 2
yes
3 furnished 12215000 7500 4 2 2
yes
4 furnished 11410000 7420 4 1 2
yes
.. ... ... ... ... ... ...
...
540 unfurnished 1820000 3000 2 1 1
yes
541 semi-furnished 1767150 2400 3 1 1
no
542 unfurnished 1750000 3620 2 1 1
yes
543 furnished 1750000 2910 3 1 1
no
544 unfurnished 1750000 3850 3 1 2
yes

guestroom basement hotwaterheating airconditioning parking

prefarea
0 no no no yes 2
yes
1 no no no yes 3
no
2 no yes no no 2
yes
3 no yes no yes 3
yes
4 yes yes no yes 2
no
.. ... ... ... ... ... .
..
540 no yes no no 2
no
541 no no no no 0
no
542 no no no no 0
no
543 no no no no 0
no
544 no no no no 0
no

[545 rows x 13 columns]

d['area'].sort_values()

furnishingstatus
unfurnished 1650
unfurnished 1700
semi-furnished 1836
semi-furnished 1905
unfurnished 1950
...
unfurnished 12944
furnished 13200
furnished 13200
semi-furnished 15600
unfurnished 16200
Name: area, Length: 545, dtype: int64

!pip install matplotlib

Requirement already satisfied: matplotlib in c:\users\divya\anaconda3\

lib\site-packages (3.8.4)
Requirement already satisfied: contourpy>=1.0.1 in c:\users\divya\
anaconda3\lib\site-packages (from matplotlib) (1.2.0)
Requirement already satisfied: cycler>=0.10 in c:\users\divya\
anaconda3\lib\site-packages (from matplotlib) (0.11.0)
Requirement already satisfied: fonttools>=4.22.0 in c:\users\divya\
anaconda3\lib\site-packages (from matplotlib) (4.51.0)
Requirement already satisfied: kiwisolver>=1.3.1 in c:\users\divya\
anaconda3\lib\site-packages (from matplotlib) (1.4.4)
Requirement already satisfied: numpy>=1.21 in c:\users\divya\
anaconda3\lib\site-packages (from matplotlib) (1.26.4)
Requirement already satisfied: packaging>=20.0 in c:\users\divya\
anaconda3\lib\site-packages (from matplotlib) (23.2)
Requirement already satisfied: pillow>=8 in c:\users\divya\anaconda3\
lib\site-packages (from matplotlib) (10.3.0)
Requirement already satisfied: pyparsing>=2.3.1 in c:\users\divya\
anaconda3\lib\site-packages (from matplotlib) (3.0.9)
Requirement already satisfied: python-dateutil>=2.7 in c:\users\divya\
anaconda3\lib\site-packages (from matplotlib) (2.9.0.post0)
Requirement already satisfied: six>=1.5 in c:\users\divya\anaconda3\
lib\site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)

import numpy as np
import matplotlib.pyplot as plt

price area bedrooms bathrooms stories

mainroad \
furnishingstatus

furnished 13300000 7420 4 2 3

yes
furnished 12250000 8960 4 4 4
yes
semi-furnished 12250000 9960 3 2 2
yes
furnished 12215000 7500 4 2 2
yes
furnished 11410000 7420 4 1 2
yes
... ... ... ... ... ... ..
.
unfurnished 1820000 3000 2 1 1
yes
semi-furnished 1767150 2400 3 1 1
no
unfurnished 1750000 3620 2 1 1
yes
furnished 1750000 2910 3 1 1
no
unfurnished 1750000 3850 3 1 2
yes

guestroom basement hotwaterheating airconditioning

parking \
furnishingstatus
furnished no no no yes
2
furnished no no no yes
3
semi-furnished no yes no no
2
furnished no yes no yes
3
furnished yes yes no yes
2
... ... ... ... ...
...
unfurnished no yes no no
2
semi-furnished no no no no
0
unfurnished no no no no
0
furnished no no no no
0
unfurnished no no no no
0

prefarea
furnishingstatus
furnished yes
furnished no
semi-furnished yes
furnished yes
furnished no
... ...
unfurnished no
semi-furnished no
unfurnished no
furnished no
unfurnished no

[545 rows x 12 columns]

prices = d['price'].values

prices

array([13300000, 12250000, 12250000, 12215000, 11410000, 10850000,

10150000, 10150000, 9870000, 9800000, 9800000, 9681000,
9310000, 9240000, 9240000, 9100000, 9100000, 8960000,
8890000, 8855000, 8750000, 8680000, 8645000, 8645000,
8575000, 8540000, 8463000, 8400000, 8400000, 8400000,
8400000, 8400000, 8295000, 8190000, 8120000, 8080940,
8043000, 7980000, 7962500, 7910000, 7875000, 7840000,
7700000, 7700000, 7560000, 7560000, 7525000, 7490000,
7455000, 7420000, 7420000, 7420000, 7350000, 7350000,
7350000, 7350000, 7343000, 7245000, 7210000, 7210000,
7140000, 7070000, 7070000, 7035000, 7000000, 6930000,
6930000, 6895000, 6860000, 6790000, 6790000, 6755000,
6720000, 6685000, 6650000, 6650000, 6650000, 6650000,
6650000, 6650000, 6629000, 6615000, 6615000, 6580000,
6510000, 6510000, 6510000, 6475000, 6475000, 6440000,
6440000, 6419000, 6405000, 6300000, 6300000, 6300000,
6300000, 6300000, 6293000, 6265000, 6230000, 6230000,
6195000, 6195000, 6195000, 6160000, 6160000, 6125000,
6107500, 6090000, 6090000, 6090000, 6083000, 6083000,
6020000, 6020000, 6020000, 5950000, 5950000, 5950000,
5950000, 5950000, 5950000, 5950000, 5950000, 5943000,
5880000, 5880000, 5873000, 5873000, 5866000, 5810000,
5810000, 5810000, 5803000, 5775000, 5740000, 5740000,
5740000, 5740000, 5740000, 5652500, 5600000, 5600000,
5600000, 5600000, 5600000, 5600000, 5600000, 5600000,
5600000, 5565000, 5565000, 5530000, 5530000, 5530000,
5523000, 5495000, 5495000, 5460000, 5460000, 5460000,
5460000, 5425000, 5390000, 5383000, 5320000, 5285000,
5250000, 5250000, 5250000, 5250000, 5250000, 5250000,
5250000, 5250000, 5250000, 5243000, 5229000, 5215000,
5215000, 5215000, 5145000, 5145000, 5110000, 5110000,
5110000, 5110000, 5075000, 5040000, 5040000, 5040000,
5040000, 5033000, 5005000, 4970000, 4970000, 4956000,
4935000, 4907000, 4900000, 4900000, 4900000, 4900000,
4900000, 4900000, 4900000, 4900000, 4900000, 4900000,
4900000, 4900000, 4893000, 4893000, 4865000, 4830000,
4830000, 4830000, 4830000, 4795000, 4795000, 4767000,
4760000, 4760000, 4760000, 4753000, 4690000, 4690000,
4690000, 4690000, 4690000, 4690000, 4655000, 4620000,
4620000, 4620000, 4620000, 4620000, 4613000, 4585000,
4585000, 4550000, 4550000, 4550000, 4550000, 4550000,
4550000, 4550000, 4543000, 4543000, 4515000, 4515000,
4515000, 4515000, 4480000, 4480000, 4480000, 4480000,
4480000, 4473000, 4473000, 4473000, 4445000, 4410000,
4410000, 4403000, 4403000, 4403000, 4382000, 4375000,
4340000, 4340000, 4340000, 4340000, 4340000, 4319000,
4305000, 4305000, 4277000, 4270000, 4270000, 4270000,
4270000, 4270000, 4270000, 4235000, 4235000, 4200000,
4200000, 4200000, 4200000, 4200000, 4200000, 4200000,
4200000, 4200000, 4200000, 4200000, 4200000, 4200000,
4200000, 4200000, 4200000, 4200000, 4193000, 4193000,
4165000, 4165000, 4165000, 4130000, 4130000, 4123000,
4098500, 4095000, 4095000, 4095000, 4060000, 4060000,
4060000, 4060000, 4060000, 4025000, 4025000, 4025000,
4007500, 4007500, 3990000, 3990000, 3990000, 3990000,
 3990000, 3920000, 3920000, 3920000, 3920000, 3920000,
3920000, 3920000, 3885000, 3885000, 3850000, 3850000,
3850000, 3850000, 3850000, 3850000, 3850000, 3836000,
3815000, 3780000, 3780000, 3780000, 3780000, 3780000,
3780000, 3773000, 3773000, 3773000, 3745000, 3710000,
3710000, 3710000, 3710000, 3710000, 3703000, 3703000,
3675000, 3675000, 3675000, 3675000, 3640000, 3640000,
3640000, 3640000, 3640000, 3640000, 3640000, 3640000,
3640000, 3633000, 3605000, 3605000, 3570000, 3570000,
3570000, 3570000, 3535000, 3500000, 3500000, 3500000,
3500000, 3500000, 3500000, 3500000, 3500000, 3500000,
3500000, 3500000, 3500000, 3500000, 3500000, 3500000,
3500000, 3500000, 3493000, 3465000, 3465000, 3465000,
3430000, 3430000, 3430000, 3430000, 3430000, 3430000,
3423000, 3395000, 3395000, 3395000, 3360000, 3360000,
3360000, 3360000, 3360000, 3360000, 3360000, 3360000,
3353000, 3332000, 3325000, 3325000, 3290000, 3290000,
3290000, 3290000, 3290000, 3290000, 3290000, 3290000,
3255000, 3255000, 3234000, 3220000, 3220000, 3220000,
3220000, 3150000, 3150000, 3150000, 3150000, 3150000,
3150000, 3150000, 3150000, 3150000, 3143000, 3129000,
3118850, 3115000, 3115000, 3115000, 3087000, 3080000,
3080000, 3080000, 3080000, 3045000, 3010000, 3010000,
3010000, 3010000, 3010000, 3010000, 3010000, 3003000,
2975000, 2961000, 2940000, 2940000, 2940000, 2940000,
2940000, 2940000, 2940000, 2940000, 2870000, 2870000,
2870000, 2870000, 2852500, 2835000, 2835000, 2835000,
2800000, 2800000, 2730000, 2730000, 2695000, 2660000,
2660000, 2660000, 2660000, 2660000, 2660000, 2660000,
2653000, 2653000, 2604000, 2590000, 2590000, 2590000,
2520000, 2520000, 2520000, 2485000, 2485000, 2450000,
2450000, 2450000, 2450000, 2450000, 2450000, 2408000,
2380000, 2380000, 2380000, 2345000, 2310000, 2275000,
2275000, 2275000, 2240000, 2233000, 2135000, 2100000,
2100000, 2100000, 1960000, 1890000, 1890000, 1855000,
1820000, 1767150, 1750000, 1750000, 1750000], dtype=int64)

mean= np.mean(prices)
mean

4766729.247706422

max= np.max(prices)
max

13300000

np.std(prices)

1868722.8281312082
np.min(prices)

1750000

np.percentile(d['price'], 25)

3430000.0

np.sort(d['price'])

array([ 1750000, 1750000, 1750000, 1767150, 1820000, 1855000,

1890000, 1890000, 1960000, 2100000, 2100000, 2100000,
2135000, 2233000, 2240000, 2275000, 2275000, 2275000,
2310000, 2345000, 2380000, 2380000, 2380000, 2408000,
2450000, 2450000, 2450000, 2450000, 2450000, 2450000,
2485000, 2485000, 2520000, 2520000, 2520000, 2590000,
2590000, 2590000, 2604000, 2653000, 2653000, 2660000,
2660000, 2660000, 2660000, 2660000, 2660000, 2660000,
2695000, 2730000, 2730000, 2800000, 2800000, 2835000,
2835000, 2835000, 2852500, 2870000, 2870000, 2870000,
2870000, 2940000, 2940000, 2940000, 2940000, 2940000,
2940000, 2940000, 2940000, 2961000, 2975000, 3003000,
3010000, 3010000, 3010000, 3010000, 3010000, 3010000,
3010000, 3045000, 3080000, 3080000, 3080000, 3080000,
3087000, 3115000, 3115000, 3115000, 3118850, 3129000,
3143000, 3150000, 3150000, 3150000, 3150000, 3150000,
3150000, 3150000, 3150000, 3150000, 3220000, 3220000,
3220000, 3220000, 3234000, 3255000, 3255000, 3290000,
3290000, 3290000, 3290000, 3290000, 3290000, 3290000,
3290000, 3325000, 3325000, 3332000, 3353000, 3360000,
3360000, 3360000, 3360000, 3360000, 3360000, 3360000,
3360000, 3395000, 3395000, 3395000, 3423000, 3430000,
3430000, 3430000, 3430000, 3430000, 3430000, 3465000,
3465000, 3465000, 3493000, 3500000, 3500000, 3500000,
3500000, 3500000, 3500000, 3500000, 3500000, 3500000,
3500000, 3500000, 3500000, 3500000, 3500000, 3500000,
3500000, 3500000, 3535000, 3570000, 3570000, 3570000,
3570000, 3605000, 3605000, 3633000, 3640000, 3640000,
3640000, 3640000, 3640000, 3640000, 3640000, 3640000,
3640000, 3675000, 3675000, 3675000, 3675000, 3703000,
3703000, 3710000, 3710000, 3710000, 3710000, 3710000,
3745000, 3773000, 3773000, 3773000, 3780000, 3780000,
3780000, 3780000, 3780000, 3780000, 3815000, 3836000,
3850000, 3850000, 3850000, 3850000, 3850000, 3850000,
3850000, 3885000, 3885000, 3920000, 3920000, 3920000,
3920000, 3920000, 3920000, 3920000, 3990000, 3990000,
3990000, 3990000, 3990000, 4007500, 4007500, 4025000,
4025000, 4025000, 4060000, 4060000, 4060000, 4060000,
4060000, 4095000, 4095000, 4095000, 4098500, 4123000,
4130000, 4130000, 4165000, 4165000, 4165000, 4193000,
4193000, 4200000, 4200000, 4200000, 4200000, 4200000,
4200000, 4200000, 4200000, 4200000, 4200000, 4200000,
4200000, 4200000, 4200000, 4200000, 4200000, 4200000,
4235000, 4235000, 4270000, 4270000, 4270000, 4270000,
4270000, 4270000, 4277000, 4305000, 4305000, 4319000,
4340000, 4340000, 4340000, 4340000, 4340000, 4375000,
4382000, 4403000, 4403000, 4403000, 4410000, 4410000,
4445000, 4473000, 4473000, 4473000, 4480000, 4480000,
4480000, 4480000, 4480000, 4515000, 4515000, 4515000,
4515000, 4543000, 4543000, 4550000, 4550000, 4550000,
4550000, 4550000, 4550000, 4550000, 4585000, 4585000,
4613000, 4620000, 4620000, 4620000, 4620000, 4620000,
4655000, 4690000, 4690000, 4690000, 4690000, 4690000,
4690000, 4753000, 4760000, 4760000, 4760000, 4767000,
4795000, 4795000, 4830000, 4830000, 4830000, 4830000,
4865000, 4893000, 4893000, 4900000, 4900000, 4900000,
4900000, 4900000, 4900000, 4900000, 4900000, 4900000,
4900000, 4900000, 4900000, 4907000, 4935000, 4956000,
4970000, 4970000, 5005000, 5033000, 5040000, 5040000,
5040000, 5040000, 5075000, 5110000, 5110000, 5110000,
5110000, 5145000, 5145000, 5215000, 5215000, 5215000,
5229000, 5243000, 5250000, 5250000, 5250000, 5250000,
5250000, 5250000, 5250000, 5250000, 5250000, 5285000,
5320000, 5383000, 5390000, 5425000, 5460000, 5460000,
5460000, 5460000, 5495000, 5495000, 5523000, 5530000,
5530000, 5530000, 5565000, 5565000, 5600000, 5600000,
5600000, 5600000, 5600000, 5600000, 5600000, 5600000,
5600000, 5652500, 5740000, 5740000, 5740000, 5740000,
5740000, 5775000, 5803000, 5810000, 5810000, 5810000,
5866000, 5873000, 5873000, 5880000, 5880000, 5943000,
5950000, 5950000, 5950000, 5950000, 5950000, 5950000,
5950000, 5950000, 6020000, 6020000, 6020000, 6083000,
6083000, 6090000, 6090000, 6090000, 6107500, 6125000,
6160000, 6160000, 6195000, 6195000, 6195000, 6230000,
6230000, 6265000, 6293000, 6300000, 6300000, 6300000,
6300000, 6300000, 6405000, 6419000, 6440000, 6440000,
6475000, 6475000, 6510000, 6510000, 6510000, 6580000,
6615000, 6615000, 6629000, 6650000, 6650000, 6650000,
6650000, 6650000, 6650000, 6685000, 6720000, 6755000,
6790000, 6790000, 6860000, 6895000, 6930000, 6930000,
7000000, 7035000, 7070000, 7070000, 7140000, 7210000,
7210000, 7245000, 7343000, 7350000, 7350000, 7350000,
7350000, 7420000, 7420000, 7420000, 7455000, 7490000,
7525000, 7560000, 7560000, 7700000, 7700000, 7840000,
7875000, 7910000, 7962500, 7980000, 8043000, 8080940,
8120000, 8190000, 8295000, 8400000, 8400000, 8400000,
8400000, 8400000, 8463000, 8540000, 8575000, 8645000,
8645000, 8680000, 8750000, 8855000, 8890000, 8960000,
9100000, 9100000, 9240000, 9240000, 9310000, 9681000,
 9800000, 9800000, 9870000, 10150000, 10150000, 10850000,
11410000, 12215000, 12250000, 12250000, 13300000], dtype=int64)

np.var(d['price'])

3492125008378.707

plt.figure(figsize=(8,5))
plt.hist(d['area'], bins=30, color='skyblue', edgecolor='black')
plt.title('Distribution of Area')
plt.xlabel('Area')
plt.ylabel('Frequency')
plt.grid()
plt.show()

sorted_data = d.sort_values('area')
plt.figure(figsize=(40,10))
plt.plot(sorted_data['area'], sorted_data['price'], marker='o', ms =
8, mec = 'k', mfc='w', ls = '-', color='green')
plt.title('Line Plot: Area vs Price')
plt.xlabel('Area')
plt.ylabel('Price')
plt.grid()
plt.show()
bedroom_counts = d['bedrooms'].value_counts()
explode = [0.05] * len(bedroom_counts)
plt.figure(figsize=(10,8))
plt.pie(bedroom_counts, labels=bedroom_counts.index, autopct=lambda
p:f'{p:.1f}%'if p>5 else'', explode=explode, startangle=140,
pctdistance=0.8,labeldistance=1.1,
)
plt.title('Distribution of Houses by Bedrooms', fontsize=16)
plt.tight_layout()
plt.show()
plt.figure(figsize=(10,7))
scatter = plt.scatter(d['area'],d['parking'],c=d['bedrooms'],
cmap='viridis',alpha=0.7,edgecolors='w',s=80 )
plt.colorbar(scatter, label='Number of Bedrooms')
plt.title('Area vs Price Colored by Bedrooms', fontsize=16)
plt.xlabel('Area')
plt.ylabel('Price')
plt.grid()
plt.show()
fig = plt.figure(figsize=(12,8))
ax = fig.add_subplot(111, projection='3d')
x = d['area']
y = d['bedrooms']
z = d['parking']
sorted_idx = np.argsort(x)
x = x.iloc[sorted_idx]
y = y.iloc[sorted_idx]
z = z.iloc[sorted_idx]
ax.plot(x, y, z, color='c', marker='o', ms = 4, mec = 'k', mfc='w', ls
= ':', lw = 2)
ax.set_xlabel('Area')
ax.set_ylabel('Bedrooms')
ax.set_zlabel('parking')
ax.set_title('3D Line Plot: Area, Bedrooms vs Price')

plt.show()
import seaborn as sns
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore')

plt.figure(figsize=(8,5))
sns.boxplot(x='bedrooms', y='price', data=d, palette='Pastel1')
plt.title('Price Distribution Across Bedroom Counts')
plt.xlabel('Number of Bedrooms')
plt.ylabel('Price')
plt.show()
plt.figure(figsize=(8,5))
sns.histplot(d['price'], bins=30, kde=True, color='skyblue',
edgecolor='black')
plt.title('Histogram of Price')
plt.xlabel('Price')
plt.ylabel('Count')
plt.grid()
plt.show()
plt.figure(figsize=(8,5))
sns.kdeplot(d['price'], shade=True, color='purple', linewidth=2)
plt.title('KDE Plot of Price')
plt.xlabel('Price')
plt.ylabel('Density')
plt.grid()
plt.show()
plt.figure(figsize=(8,5))
sns.histplot(d['price'], bins=30, color='orange', edgecolor='black')
plt.title('Distribution Plot of Price with Histogram ')
plt.xlabel('Price')
plt.ylabel('Density')
plt.grid()
plt.show()
import statistics as stats

stats.mean(d['price'])

4766729.247706422

stats.median(d['price'])

4340000

stats.mode(d['bedrooms'])

stats.variance(d['price'])

3498544355820.5728

stats.stdev(d['price'])

1870439.6156573922

stats.harmonic_mean(d['area'])

4398.311914424032

stats.geometric_mean(d['price'])
4443650.939099614

q1 = d['price'].quantile(0.25)
q2 = d['price'].quantile(0.5)
q3 = d['price'].quantile(0.75)
print(f"25% Quantile (Q1): {q1}")
print(f"50% Quantile (Median, Q2): {q2}")
print(f"75% Quantile (Q3): {q3}")
median_grouped_price = stats.median_grouped(d['price'])
print(f"Median Grouped (Price): {median_grouped_price}")

25% Quantile (Q1): 3430000.0

50% Quantile (Median, Q2): 4340000.0
75% Quantile (Q3): 5740000.0
Median Grouped (Price): 4340000.0