In [1]:

import pandas as pd
import numpy as np
import plotly.express as px
import seaborn as sns
import matplotlib.pyplot as plt

Data Exploration¶

In [2]:

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

In [3]:

df.head()

Out[3]:

	id	name	host_id	host_name	neighbourhood_group	neighbourhood	latitude	longitude	room_type	price	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365	number_of_reviews_ltm	license
0	27934	Condo in Samsen Nai · ★4.85 · 1 bedroom · 1 be...	120437	Nuttee	NaN	Ratchathewi	13.75983	100.54134	Entire home/apt	1903.0	3	64	2020-01-06	0.45	2	329	0	NaN
1	27979	Rental unit in Bangkok · 1 bedroom · 2 beds · ...	120541	Emy	NaN	Bang Na	13.66818	100.61674	Private room	1316.0	1	0	NaN	NaN	2	0	0	NaN
2	28745	Rental unit in Bangkok · 1 bedroom · 1 bed · 1...	123784	Familyroom	NaN	Bang Kapi	13.75232	100.62402	Private room	800.0	60	0	NaN	NaN	1	0	0	NaN
3	820395	Guesthouse in Bangkok · ★4.77 · 1 bedroom · 1 ...	822284	Rae And Charlie	NaN	Bang Sue	13.83026	100.52082	Entire home/apt	700.0	7	13	2018-02-14	0.10	8	349	0	NaN
4	35780	Rental unit in Bangkok · ★4.75 · 1 bedroom · 1...	153730	Sirilak	NaN	Din Daeng	13.78823	100.57256	Private room	1286.0	14	4	2023-04-03	0.04	1	327	2	NaN

In [4]:

df.describe()

Out[4]:

	id	host_id	neighbourhood_group	latitude	longitude	price	minimum_nights	number_of_reviews	reviews_per_month	calculated_host_listings_count	availability_365	number_of_reviews_ltm	license
count	2.210400e+04	2.210400e+04	0.0	22104.000000	22104.000000	21582.000000	22104.000000	22104.000000	14162.000000	22104.000000	22104.000000	22104.000000	0.0
mean	4.311415e+17	2.070399e+08	NaN	13.744426	100.562033	3104.512093	13.874186	16.850389	0.973434	23.785016	213.574557	5.638617	NaN
std	4.450022e+17	1.737502e+08	NaN	0.041207	0.049244	17681.953565	45.670650	43.090693	1.434982	41.836205	135.820058	14.936326	NaN
min	2.793400e+04	2.144700e+04	NaN	13.527300	100.329550	22.000000	1.000000	0.000000	0.010000	1.000000	0.000000	0.000000	NaN
25%	2.924233e+07	4.853662e+07	NaN	13.719570	100.532250	999.000000	1.000000	0.000000	0.180000	2.000000	86.000000	0.000000	NaN
50%	5.381190e+07	1.652139e+08	NaN	13.738820	100.563800	1506.000000	1.000000	2.000000	0.540000	6.000000	255.000000	1.000000	NaN
75%	8.897166e+17	3.336703e+08	NaN	13.758170	100.585010	2632.000000	10.000000	13.000000	1.250000	26.000000	350.000000	5.000000	NaN
max	1.053584e+18	5.522846e+08	NaN	13.953540	100.923710	1000000.000000	1115.000000	1809.000000	62.140000	230.000000	365.000000	796.000000	NaN

In [5]:

df.sample(10)

Out[5]:

	id	name	host_id	host_name	neighbourhood_group	neighbourhood	latitude	longitude	room_type	price	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365	number_of_reviews_ltm	license
14703	822827148383064365	Rental unit in Khet Watthana · ★4.86 · 1 bedro...	345168212	Digital Nomad Work	NaN	Vadhana	13.737577	100.564350	Entire home/apt	2905.0	21	7	2023-11-30	0.74	2	338	7	NaN
2954	18011312	Bed and breakfast in Bangkok · ★4.27 · 2 bedro...	123827255	Zee Thai	NaN	Phra Nakhon	13.764350	100.502360	Private room	543.0	1	22	2023-12-11	0.27	20	354	6	NaN
9426	41870897	Serviced apartment in Khet Din Daeng · 1 bedro...	330608179	Mr.Pranon	NaN	Din Daeng	13.764620	100.563930	Private room	1200.0	1	0	NaN	NaN	1	88	0	NaN
13293	765042873480043520	Rental unit in Khet Watthana · ★4.78 · 1 bedro...	4138170	Kevin	NaN	Vadhana	13.722910	100.604680	Entire home/apt	1774.0	1	41	2023-12-09	3.10	12	360	37	NaN
17398	921472489614446222	Rental unit in Khet Phra Khanong · ★4.62 · 1 b...	52161947	Noons	NaN	Phra Khanong	13.689844	100.613614	Entire home/apt	1749.0	1	20	2023-12-15	3.31	131	0	20	NaN
19056	964116073630095296	Rental unit in Watthana · 1 bedroom · 1 bed · ...	274026012	潜	NaN	Vadhana	13.743108	100.559124	Entire home/apt	1643.0	21	0	NaN	NaN	15	148	0	NaN
7731	36512868	Hostel in Don Mueang · ★4.50 · 1 bedroom · 3 beds	176795569	Suporn	NaN	Don Mueang	13.942735	100.612659	Hotel room	774.0	1	4	2019-12-31	0.08	8	287	0	NaN
6091	31211112	Home in Bangkok · ★5.0 · 3 bedrooms · 8 beds ·...	24777734	Paul	NaN	Saphan Sung	13.743820	100.673230	Entire home/apt	6543.0	2	8	2023-12-11	0.14	4	364	5	NaN
13272	762630175838071003	Rental unit in Khet Bang Kapi · ★5.0 · 1 bedro...	43563241	Raxtham	NaN	Bang Kapi	13.767860	100.638780	Private room	390.0	2	3	2023-08-10	0.26	8	344	3	NaN
10913	53370694	Rental unit in Khet Watthana · ★4.17 · 1 bedro...	240343545	Joseph	NaN	Vadhana	13.740160	100.566990	Entire home/apt	3750.0	28	6	2023-08-06	0.24	38	146	1	NaN

In [6]:

df.shape

Out[6]:

(22104, 18)

In [7]:

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 22104 entries, 0 to 22103
Data columns (total 18 columns):
 #   Column                          Non-Null Count  Dtype  
---  ------                          --------------  -----  
 0   id                              22104 non-null  int64  
 1   name                            22104 non-null  object 
 2   host_id                         22104 non-null  int64  
 3   host_name                       22104 non-null  object 
 4   neighbourhood_group             0 non-null      float64
 5   neighbourhood                   22104 non-null  object 
 6   latitude                        22104 non-null  float64
 7   longitude                       22104 non-null  float64
 8   room_type                       22104 non-null  object 
 9   price                           21582 non-null  float64
 10  minimum_nights                  22104 non-null  int64  
 11  number_of_reviews               22104 non-null  int64  
 12  last_review                     14162 non-null  object 
 13  reviews_per_month               14162 non-null  float64
 14  calculated_host_listings_count  22104 non-null  int64  
 15  availability_365                22104 non-null  int64  
 16  number_of_reviews_ltm           22104 non-null  int64  
 17  license                         0 non-null      float64
dtypes: float64(6), int64(7), object(5)
memory usage: 3.0+ MB

In [8]:

df.columns

Out[8]:

Index(['id', 'name', 'host_id', 'host_name', 'neighbourhood_group',
       'neighbourhood', 'latitude', 'longitude', 'room_type', 'price',
       'minimum_nights', 'number_of_reviews', 'last_review',
       'reviews_per_month', 'calculated_host_listings_count',
       'availability_365', 'number_of_reviews_ltm', 'license'],
      dtype='object')

Dropping not needed columns¶

In [9]:

## id, name, host_id, host_name, neighbourhood_group, license columns are not needed
df.drop(columns=['id', 'name', 'host_id', 'host_name', 'neighbourhood_group', 'license'], axis=1, inplace=True)

In [10]:

df.columns

Out[10]:

Index(['neighbourhood', 'latitude', 'longitude', 'room_type', 'price',
       'minimum_nights', 'number_of_reviews', 'last_review',
       'reviews_per_month', 'calculated_host_listings_count',
       'availability_365', 'number_of_reviews_ltm'],
      dtype='object')

In [11]:

df.nunique()

Out[11]:

neighbourhood                        50
latitude                          15580
longitude                         16103
room_type                             4
price                              3938
minimum_nights                       97
number_of_reviews                   333
last_review                        1667
reviews_per_month                   633
calculated_host_listings_count       73
availability_365                    366
number_of_reviews_ltm               122
dtype: int64

In [12]:

df.isnull().sum()

Out[12]:

neighbourhood                        0
latitude                             0
longitude                            0
room_type                            0
price                              522
minimum_nights                       0
number_of_reviews                    0
last_review                       7942
reviews_per_month                 7942
calculated_host_listings_count       0
availability_365                     0
number_of_reviews_ltm                0
dtype: int64

Removing outliers¶

In [13]:

px.histogram(df, x='neighbourhood')

In [14]:

df['neighbourhood'].value_counts()

Out[14]:

Vadhana                 3341
Khlong Toei             3295
Huai Khwang             1899
Ratchathewi             1550
Sathon                  1007
Bang Rak                 972
Phra Nakhon              825
Phra Khanong             824
Chatu Chak               710
Din Daeng                589
Parthum Wan              566
Bang Na                  538
Suanluang                535
Khlong San               498
Phaya Thai               438
Bang Kapi                414
Bang Phlat               383
Bang Sue                 305
Yan na wa                263
Lat Krabang              247
Don Mueang               219
Thon buri                217
Pra Wet                  184
Bangkok Noi              184
Samphanthawong           177
Phasi Charoen            163
Bang Kho laen            159
Pom Prap Sattru Phai     158
Wang Thong Lang          154
Lak Si                   147
Bang Khen                121
Dusit                    116
Bangkok Yai              114
Chom Thong               101
Bang Khae                 87
Khan Na Yao               66
Lat Phrao                 64
Bueng Kum                 64
Saphan Sung               62
Min Buri                  61
Rat Burana                61
Sai Mai                   49
Taling Chan               45
Khlong Sam Wa             33
Thung khru                26
Bang Khun thain           23
Nong Chok                 19
Thawi Watthana            16
Nong Khaem                 8
Bang Bon                   7
Name: neighbourhood, dtype: int64

In [15]:

pr1 = df.groupby('neighbourhood', as_index=False)['price'].mean()
px.bar(pr1, x='neighbourhood', y='price')

In [16]:

## removing all neighbourhoods with less than 200 units, including 'Taling Chan' which is a pricing outlier
df = df.groupby('neighbourhood').filter(lambda x : len(x)>200)

In [17]:

px.histogram(df, x='neighbourhood')

In [18]:

pr1 = df.groupby('neighbourhood', as_index=False)['price'].mean()
px.bar(pr1, x='neighbourhood', y='price')

In [19]:

fig = px.violin(df, x="neighbourhood", y="price")
fig.show()

In [20]:

fig = px.box(df, x="neighbourhood", y="price")
fig.show()

In [21]:

df[["neighbourhood", "price"]].groupby("neighbourhood").describe()

Out[21]:

	price
	count	mean	std	min	25%	50%	75%	max
neighbourhood
Bang Kapi	406.0	2394.110837	6225.740661	320.0	750.00	1179.0	1749.50	102857.0
Bang Na	532.0	2243.793233	5978.382635	350.0	790.00	1028.5	1543.00	90000.0
Bang Phlat	368.0	1388.774457	2452.067802	347.0	583.00	891.0	1223.75	29393.0
Bang Rak	934.0	3226.020343	10160.155746	310.0	1212.25	1969.5	3569.25	300000.0
Bang Sue	299.0	1859.698997	6503.838597	348.0	700.00	905.0	1299.50	100000.0
Chatu Chak	693.0	2324.432900	6482.725291	315.0	800.00	1200.0	1899.00	100000.0
Din Daeng	574.0	2925.024390	14450.833860	277.0	850.00	1232.5	2000.00	300000.0
Don Mueang	217.0	1239.281106	1329.261571	346.0	580.00	800.0	1310.00	10181.0
Huai Khwang	1848.0	4840.334957	46905.197577	350.0	1060.25	1557.0	2600.00	1000000.0
Khlong San	486.0	2838.382716	8114.317901	280.0	990.00	1421.5	2346.25	160000.0
Khlong Toei	3224.0	2932.180211	5841.815554	290.0	1217.00	1700.0	2681.75	160000.0
Lat Krabang	240.0	1491.170833	1217.511441	331.0	812.00	1200.0	1582.50	8956.0
Parthum Wan	557.0	4838.791741	15924.924222	331.0	1504.00	2500.0	4260.00	300000.0
Phaya Thai	427.0	2067.330211	2082.917201	320.0	950.50	1454.0	2464.50	20000.0
Phra Khanong	806.0	1703.207196	3004.609572	305.0	830.00	1150.0	1880.00	71609.0
Phra Nakhon	814.0	1919.684275	2059.442213	250.0	800.00	1355.5	2398.75	33350.0
Ratchathewi	1513.0	3560.150694	16721.269507	329.0	1300.00	1860.0	2757.00	300000.0
Sathon	984.0	2495.058943	4460.016034	318.0	1010.00	1479.5	2389.50	75000.0
Suanluang	519.0	2149.795761	3441.550500	332.0	850.00	1094.0	1811.00	37000.0
Thon buri	210.0	1815.409524	4225.085954	350.0	850.00	1183.5	1800.00	60000.0
Vadhana	3265.0	4248.409801	15357.271301	300.0	1386.00	2128.0	4000.00	692732.0
Yan na wa	258.0	3318.271318	7117.129000	400.0	1090.00	1489.5	3410.50	75000.0

In [22]:

## removing price outliers per neighbourhood
def is_outlier(s):
    lower_limit = s.mean() - (s.std() * 3)
    upper_limit = s.mean() + (s.std() * 3)
    return ~s.between(lower_limit, upper_limit)

In [23]:

df = df[~df.groupby('neighbourhood')['price'].apply(is_outlier)]

In [24]:

fig = px.box(df, x="neighbourhood", y="price")
fig.show()

In [25]:

fig = px.violin(df, x="neighbourhood", y="price")
fig.show()

In [26]:

px.bar(
    data_frame=df.groupby('room_type')['price'].mean().reset_index(), 
    x="room_type", 
    y="price"
)

In [27]:

fig = px.violin(df, x="room_type", y="price")
fig.show()

In [28]:

## applying outliers removal to room tye prices
df = df[~df.groupby('neighbourhood')['price'].apply(is_outlier)]

In [29]:

px.bar(
    data_frame=df.groupby('room_type')['price'].mean().reset_index(), 
    x="room_type", 
    y="price"
)

In [30]:

fig = px.violin(df, x="room_type", y="price")
fig.show()

In [31]:

pr = df.groupby(['neighbourhood','room_type'], as_index=False)['price'].mean()
fig = px.bar(pr, x="neighbourhood", y='price', color="room_type", barmode="group")
fig.show()

In [32]:

pr2 = df.groupby(['neighbourhood'], as_index=False)['availability_365'].mean()
fig = px.bar(pr2, x="neighbourhood", y='availability_365')
fig.show()

In [ ]: