k-medoids
February 29, 2024
[1]: import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore')
[9]: df = pd.read_csv("kc_house_data.csv")
df.head()
[9]: id date price bedrooms bathrooms sqft_living \
0 7129300520 20141013T000000 221900.0 3 1.00 1180
1 6414100192 20141209T000000 538000.0 3 2.25 2570
2 5631500400 20150225T000000 180000.0 2 1.00 770
3 2487200875 20141209T000000 604000.0 4 3.00 1960
4 1954400510 20150218T000000 510000.0 3 2.00 1680
sqft_lot floors waterfront view … grade sqft_above sqft_basement \
0 5650 1.0 0 0 … 7 1180 0
1 7242 2.0 0 0 … 7 2170 400
2 10000 1.0 0 0 … 6 770 0
3 5000 1.0 0 0 … 7 1050 910
4 8080 1.0 0 0 … 8 1680 0
yr_built yr_renovated zipcode lat long sqft_living15 \
0 1955 0 98178 47.5112 -122.257 1340
1 1951 1991 98125 47.7210 -122.319 1690
2 1933 0 98028 47.7379 -122.233 2720
3 1965 0 98136 47.5208 -122.393 1360
4 1987 0 98074 47.6168 -122.045 1800
sqft_lot15
0 5650
1 7639
2 8062
3 5000
4 7503
1
[5 rows x 21 columns]
[10]: df.describe()
[10]: id price bedrooms bathrooms sqft_living \
count 2.161300e+04 2.161300e+04 21613.000000 21613.000000 21613.000000
mean 4.580302e+09 5.400881e+05 3.370842 2.114757 2079.899736
std 2.876566e+09 3.671272e+05 0.930062 0.770163 918.440897
min 1.000102e+06 7.500000e+04 0.000000 0.000000 290.000000
25% 2.123049e+09 3.219500e+05 3.000000 1.750000 1427.000000
50% 3.904930e+09 4.500000e+05 3.000000 2.250000 1910.000000
75% 7.308900e+09 6.450000e+05 4.000000 2.500000 2550.000000
max 9.900000e+09 7.700000e+06 33.000000 8.000000 13540.000000
sqft_lot floors waterfront view condition \
count 2.161300e+04 21613.000000 21613.000000 21613.000000 21613.000000
mean 1.510697e+04 1.494309 0.007542 0.234303 3.409430
std 4.142051e+04 0.539989 0.086517 0.766318 0.650743
min 5.200000e+02 1.000000 0.000000 0.000000 1.000000
25% 5.040000e+03 1.000000 0.000000 0.000000 3.000000
50% 7.618000e+03 1.500000 0.000000 0.000000 3.000000
75% 1.068800e+04 2.000000 0.000000 0.000000 4.000000
max 1.651359e+06 3.500000 1.000000 4.000000 5.000000
grade sqft_above sqft_basement yr_built yr_renovated \
count 21613.000000 21613.000000 21613.000000 21613.000000 21613.000000
mean 7.656873 1788.390691 291.509045 1971.005136 84.402258
std 1.175459 828.090978 442.575043 29.373411 401.679240
min 1.000000 290.000000 0.000000 1900.000000 0.000000
25% 7.000000 1190.000000 0.000000 1951.000000 0.000000
50% 7.000000 1560.000000 0.000000 1975.000000 0.000000
75% 8.000000 2210.000000 560.000000 1997.000000 0.000000
max 13.000000 9410.000000 4820.000000 2015.000000 2015.000000
zipcode lat long sqft_living15 sqft_lot15
count 21613.000000 21613.000000 21613.000000 21613.000000 21613.000000
mean 98077.939805 47.560053 -122.213896 1986.552492 12768.455652
std 53.505026 0.138564 0.140828 685.391304 27304.179631
min 98001.000000 47.155900 -122.519000 399.000000 651.000000
25% 98033.000000 47.471000 -122.328000 1490.000000 5100.000000
50% 98065.000000 47.571800 -122.230000 1840.000000 7620.000000
75% 98118.000000 47.678000 -122.125000 2360.000000 10083.000000
max 98199.000000 47.777600 -121.315000 6210.000000 871200.000000
[11]: df.drop(15870, axis = 0, inplace = True)
df.reset_index(drop=True, inplace = True)
2
df.shape
[11]: (21612, 21)
[12]: df[df.columns[df.isnull().sum()>0]].isnull().sum()
[12]: Series([], dtype: float64)
[13]: pip install scikit-learn-extra
Collecting scikit-learn-extra
Downloading scikit_learn_extra-0.3.0-cp311-cp311-win_amd64.whl.metadata (3.7
kB)
Requirement already satisfied: numpy>=1.13.3 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
scikit-learn-extra) (1.26.0)
Requirement already satisfied: scipy>=0.19.1 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
scikit-learn-extra) (1.11.4)
Requirement already satisfied: scikit-learn>=0.23.0 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
scikit-learn-extra) (1.3.2)
Requirement already satisfied: joblib>=1.1.1 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
scikit-learn>=0.23.0->scikit-learn-extra) (1.3.2)
Requirement already satisfied: threadpoolctl>=2.0.0 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
scikit-learn>=0.23.0->scikit-learn-extra) (3.2.0)
Downloading scikit_learn_extra-0.3.0-cp311-cp311-win_amd64.whl (340 kB)
---------------------------------------- 0.0/340.5 kB ? eta -:--:--
- -------------------------------------- 10.2/340.5 kB ? eta -:--:--
- -------------------------------------- 10.2/340.5 kB ? eta -:--:--
--- ----------------------------------- 30.7/340.5 kB 325.1 kB/s eta 0:00:01
------------- ------------------------ 122.9/340.5 kB 798.9 kB/s eta 0:00:01
---------------------------------------- 340.5/340.5 kB 1.8 MB/s eta 0:00:00
Installing collected packages: scikit-learn-extra
Successfully installed scikit-learn-extra-0.3.0
Note: you may need to restart the kernel to use updated packages.
[14]: df.drop(['date', 'id'], axis = 1, inplace = True)
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
Clus_dataSet = scaler.fit_transform(df)
Clus_dataSet
[14]: array([[-0.86668617, -0.40692359, -1.44745951, …, -0.30611525,
-0.94339773, -0.26072358],
3
[-0.00567521, -0.40692359, 0.17558163, …, -0.74637458,
-0.43272969, -0.18787744],
[-0.98081575, -1.50829275, -1.44745951, …, -0.13569228,
1.07009338, -0.17238527],
…,
[-0.37584455, -1.50829275, -1.77206774, …, -0.60435544,
-1.41029422, -0.39414664],
[-0.38156737, -0.40692359, 0.50018986, …, 1.02886466,
-0.84126412, -0.42051628],
[-0.58585659, -1.50829275, -1.77206774, …, -0.60435544,
-1.41029422, -0.41795257]])
[15]: from sklearn_extra.cluster import KMedoids
kmedoids = KMedoids(n_clusters=3).fit(Clus_dataSet)
[16]: df.insert(0, 'kmedoids Cluster Labels', kmedoids.labels_)
df.head()
[16]: kmedoids Cluster Labels price bedrooms bathrooms sqft_living \
0 1 221900.0 3 1.00 1180
1 0 538000.0 3 2.25 2570
2 2 180000.0 2 1.00 770
3 0 604000.0 4 3.00 1960
4 2 510000.0 3 2.00 1680
sqft_lot floors waterfront view condition grade sqft_above \
0 5650 1.0 0 0 3 7 1180
1 7242 2.0 0 0 3 7 2170
2 10000 1.0 0 0 3 6 770
3 5000 1.0 0 0 5 7 1050
4 8080 1.0 0 0 3 8 1680
sqft_basement yr_built yr_renovated zipcode lat long \
0 0 1955 0 98178 47.5112 -122.257
1 400 1951 1991 98125 47.7210 -122.319
2 0 1933 0 98028 47.7379 -122.233
3 910 1965 0 98136 47.5208 -122.393
4 0 1987 0 98074 47.6168 -122.045
sqft_living15 sqft_lot15
0 1340 5650
1 1690 7639
2 2720 8062
3 1360 5000
4 1800 7503
4
[17]: X = df.loc[:, df.columns != 'kmedoids Cluster Labels']
X.head()
[17]: price bedrooms bathrooms sqft_living sqft_lot floors waterfront \
0 221900.0 3 1.00 1180 5650 1.0 0
1 538000.0 3 2.25 2570 7242 2.0 0
2 180000.0 2 1.00 770 10000 1.0 0
3 604000.0 4 3.00 1960 5000 1.0 0
4 510000.0 3 2.00 1680 8080 1.0 0
view condition grade sqft_above sqft_basement yr_built yr_renovated \
0 0 3 7 1180 0 1955 0
1 0 3 7 2170 400 1951 1991
2 0 3 6 770 0 1933 0
3 0 5 7 1050 910 1965 0
4 0 3 8 1680 0 1987 0
zipcode lat long sqft_living15 sqft_lot15
0 98178 47.5112 -122.257 1340 5650
1 98125 47.7210 -122.319 1690 7639
2 98028 47.7379 -122.233 2720 8062
3 98136 47.5208 -122.393 1360 5000
4 98074 47.6168 -122.045 1800 7503
[18]: from sklearn import preprocessing
X= preprocessing.StandardScaler().fit(X).transform(X)
X[0:5]
[18]: array([[-0.86668617, -0.40692359, -1.44745951, -0.97984121, -0.22832648,
-0.91546593, -0.08717466, -0.3057672 , -0.62914619, -0.55885272,
-0.73474634, -0.65864212, -0.5449314 , -0.21013346, 1.87013949,
-0.35252787, -0.30611525, -0.94339773, -0.26072358],
[-0.00567521, -0.40692359, 0.17558163, 0.53360192, -0.18989137,
0.93645991, -0.08717466, -0.3057672 , -0.62914619, -0.55885272,
0.46079706, 0.2451683 , -0.68111108, 4.74656291, 0.87957332,
1.16160686, -0.74637458, -0.43272969, -0.18787744],
[-0.98081575, -1.50829275, -1.44745951, -1.42625249, -0.12330593,
-0.91546593, -0.08717466, -0.3057672 , -0.62914619, -1.40959054,
-1.22987038, -0.65864212, -1.29391966, -0.21013346, -0.93334967,
1.28357482, -0.13569228, 1.07009338, -0.17238527],
[ 0.17409931, 0.69444556, 1.14940631, -0.13057096, -0.2440192 ,
-0.91546593, -0.08717466, -0.3057672 , 2.44468843, -0.55885272,
-0.89173689, 1.39752658, -0.20448219, -0.21013346, 1.08516253,
-0.28324429, -1.2718454 , -0.9142167 , -0.2845295 ],
[-0.08194318, -0.40692359, -0.1490266 , -0.4354372 , -0.16965983,
-0.91546593, -0.08717466, -0.3057672 , -0.62914619, 0.29188511,
-0.13093654, -0.65864212, 0.54450607, -0.21013346, -0.07361299,
5
0.40959143, 1.19928763, -0.27223402, -0.19285837]])
[19]: y = df["kmedoids Cluster Labels"]
y.head()
[19]: 0 1
1 0
2 2
3 0
4 2
Name: kmedoids Cluster Labels, dtype: int64
[20]: pip install pywaffle
Collecting pywaffleNote: you may need to restart the kernel to use updated
packages.
Downloading pywaffle-1.1.0-py2.py3-none-any.whl.metadata (2.6 kB)
Collecting fontawesomefree (from pywaffle)
Downloading fontawesomefree-6.5.1-py3-none-any.whl.metadata (824 bytes)
Requirement already satisfied: matplotlib in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
pywaffle) (3.8.0)
Requirement already satisfied: contourpy>=1.0.1 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
matplotlib->pywaffle) (1.1.1)
Requirement already satisfied: cycler>=0.10 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
matplotlib->pywaffle) (0.12.1)
Requirement already satisfied: fonttools>=4.22.0 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
matplotlib->pywaffle) (4.43.1)
Requirement already satisfied: kiwisolver>=1.0.1 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
matplotlib->pywaffle) (1.4.5)
Requirement already satisfied: numpy<2,>=1.21 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
matplotlib->pywaffle) (1.26.0)
Requirement already satisfied: packaging>=20.0 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
matplotlib->pywaffle) (23.2)
Requirement already satisfied: pillow>=6.2.0 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
matplotlib->pywaffle) (10.1.0)
Requirement already satisfied: pyparsing>=2.3.1 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
matplotlib->pywaffle) (3.1.1)
6
Requirement already satisfied: python-dateutil>=2.7 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
matplotlib->pywaffle) (2.8.2)
Requirement already satisfied: six>=1.5 in
c:\users\lenovo\appdata\local\programs\python\python311\lib\site-packages (from
python-dateutil>=2.7->matplotlib->pywaffle) (1.16.0)
Downloading pywaffle-1.1.0-py2.py3-none-any.whl (30 kB)
Downloading fontawesomefree-6.5.1-py3-none-any.whl (25.6 MB)
---------------------------------------- 0.0/25.6 MB ? eta -:--:--
---------------------------------------- 0.0/25.6 MB 991.0 kB/s eta 0:00:26
--------------------------------------- 0.3/25.6 MB 4.2 MB/s eta 0:00:07
- -------------------------------------- 0.8/25.6 MB 6.5 MB/s eta 0:00:04
-- ------------------------------------- 1.3/25.6 MB 7.7 MB/s eta 0:00:04
--- ------------------------------------ 2.4/25.6 MB 10.9 MB/s eta 0:00:03
---- ----------------------------------- 3.2/25.6 MB 11.9 MB/s eta 0:00:02
----- ---------------------------------- 3.8/25.6 MB 12.1 MB/s eta 0:00:02
------- -------------------------------- 4.6/25.6 MB 12.7 MB/s eta 0:00:02
------- -------------------------------- 5.1/25.6 MB 12.6 MB/s eta 0:00:02
-------- ------------------------------- 5.7/25.6 MB 12.6 MB/s eta 0:00:02
---------- ----------------------------- 6.4/25.6 MB 12.9 MB/s eta 0:00:02
----------- ---------------------------- 7.1/25.6 MB 12.6 MB/s eta 0:00:02
----------- ---------------------------- 7.7/25.6 MB 12.9 MB/s eta 0:00:02
------------- -------------------------- 8.5/25.6 MB 13.0 MB/s eta 0:00:02
-------------- ------------------------- 9.0/25.6 MB 13.1 MB/s eta 0:00:02
-------------- ------------------------- 9.0/25.6 MB 13.1 MB/s eta 0:00:02
-------------- ------------------------- 9.0/25.6 MB 13.1 MB/s eta 0:00:02
---------------- ----------------------- 10.7/25.6 MB 13.9 MB/s eta 0:00:02
----------------- ---------------------- 11.3/25.6 MB 14.2 MB/s eta 0:00:02
------------------ --------------------- 11.8/25.6 MB 13.6 MB/s eta 0:00:02
------------------- -------------------- 12.3/25.6 MB 13.1 MB/s eta 0:00:02
------------------- -------------------- 12.8/25.6 MB 13.1 MB/s eta 0:00:01
--------------------- ------------------ 13.5/25.6 MB 12.8 MB/s eta 0:00:01
--------------------- ------------------ 13.9/25.6 MB 12.9 MB/s eta 0:00:01
---------------------- ----------------- 14.6/25.6 MB 12.6 MB/s eta 0:00:01
----------------------- ---------------- 14.9/25.6 MB 12.6 MB/s eta 0:00:01
------------------------ --------------- 15.8/25.6 MB 12.6 MB/s eta 0:00:01
------------------------- -------------- 16.0/25.6 MB 12.1 MB/s eta 0:00:01
------------------------- -------------- 16.6/25.6 MB 12.4 MB/s eta 0:00:01
--------------------------- ------------ 17.4/25.6 MB 12.1 MB/s eta 0:00:01
--------------------------- ------------ 17.9/25.6 MB 12.1 MB/s eta 0:00:01
---------------------------- ----------- 18.5/25.6 MB 11.9 MB/s eta 0:00:01
----------------------------- ---------- 19.0/25.6 MB 11.7 MB/s eta 0:00:01
------------------------------ --------- 19.7/25.6 MB 13.1 MB/s eta 0:00:01
------------------------------- -------- 20.4/25.6 MB 12.6 MB/s eta 0:00:01
-------------------------------- ------- 21.0/25.6 MB 12.1 MB/s eta 0:00:01
--------------------------------- ------ 21.6/25.6 MB 12.4 MB/s eta 0:00:01
---------------------------------- ----- 22.2/25.6 MB 12.4 MB/s eta 0:00:01
----------------------------------- ---- 22.9/25.6 MB 12.4 MB/s eta 0:00:01
7
------------------------------------ --- 23.6/25.6 MB 12.6 MB/s eta 0:00:01
------------------------------------- -- 24.2/25.6 MB 12.8 MB/s eta 0:00:01
-------------------------------------- - 24.9/25.6 MB 13.1 MB/s eta 0:00:01
--------------------------------------- 25.6/25.6 MB 13.1 MB/s eta 0:00:01
--------------------------------------- 25.6/25.6 MB 13.1 MB/s eta 0:00:01
--------------------------------------- 25.6/25.6 MB 13.1 MB/s eta 0:00:01
--------------------------------------- 25.6/25.6 MB 13.1 MB/s eta 0:00:01
--------------------------------------- 25.6/25.6 MB 13.1 MB/s eta 0:00:01
--------------------------------------- 25.6/25.6 MB 13.1 MB/s eta 0:00:01
---------------------------------------- 25.6/25.6 MB 9.6 MB/s eta 0:00:00
Installing collected packages: fontawesomefree, pywaffle
Successfully installed fontawesomefree-6.5.1 pywaffle-1.1.0
[21]: Count = df.groupby(["kmedoids Cluster Labels"], as_index=False).
↪count()[["kmedoids Cluster Labels", "price"]]
Count.columns = ["kmedoids Cluster Labels", "Count"]
Count
[21]: kmedoids Cluster Labels Count
0 0 6776
1 1 7964
2 2 6872
[23]: from pywaffle import Waffle
fig = plt.figure(
FigureClass=Waffle,
figsize=(6, 8),
rows=5,
values=list(Count.Count/150),
colors=("magenta", "yellow", "cyan"),
legend={'loc': 'upper left', 'bbox_to_anchor': (1, 1)},
icons='sticky-note', icon_size=18,
icon_legend=True,
title={'label': 'Number of Houses in each K-medoids Cluster', 'loc':␣
↪'center'},
labels=list(Count['kmedoids Cluster Labels']))
8
9
[24]: labels = df.groupby(["kmedoids Cluster Labels"], as_index=False).
↪mean()[["kmedoids Cluster Labels", "price"]]
labels
[24]: kmedoids Cluster Labels price
0 0 783367.394923
1 1 327354.355977
2 2 546731.293510
[ ]:
10
