import numpy as np

import pandas as pd
import matplotlib.pyplot as plt

var1 = pd.read_csv("D:\\pushpendra\\New folder\\EXCEL\\

cardataset.csv",encoding="latin1")

var1['abtest'].info()

<class 'pandas.core.series.Series'>
RangeIndex: 50000 entries, 0 to 49999
Series name: abtest
Non-Null Count Dtype
-------------- -----
50000 non-null object
dtypes: object(1)
memory usage: 390.8+ KB

var1['price'] = var1['price'].str.replace("$","")

var1['price'] = var1['price'].str.replace(",","")

var1['price'] = pd.to_numeric(var1['price'])

type(var1['price'][0])

numpy.int64

var1.rename(columns = {'price' : 'price_in_usd'},inplace=True)

int(var1['price_in_usd'].mean()) # average

9840

int(var1['price_in_usd'].max()) # min, max

99999999

var1['vehicleType'].value_counts()

vehicleType
limousine 12859
kleinwagen 10822
kombi 9127
bus 4093
cabrio 3061
coupe 2537
suv 1986
andere 420
Name: count, dtype: int64
var1['gearbox'].value_counts()

gearbox
manuell 36993
automatik 10327
Name: count, dtype: int64

var1['gearbox'] = var1['gearbox'].replace("manuell","manual")

var1['gearbox'] = var1['gearbox'].replace("automatik","automatic")

var1['gearbox'].head()

0 manual
1 automatic
2 manual
3 automatic
4 manual
Name: gearbox, dtype: object

var1.rename(columns = {'odometer':'km'},inplace=True)

var1['km'] = var1['km'].str.replace("km","")

var1['km'] = var1['km'].str.replace(",","")

var1['km'].head()

0 150000
1 150000
2 70000
3 70000
4 150000
Name: km, dtype: object

var1['km'] = pd.to_numeric(var1['km'])

var1['km'].dtype

dtype('int64')

var1['fuelType'].value_counts()

fuelType
benzin 30107
diesel 14567
lpg 691
cng 75
hybrid 37
andere 22
elektro 19
Name: count, dtype: int64
var1['gearbox'].head()

0 manual
1 automatic
2 manual
3 automatic
4 manual
Name: gearbox, dtype: object

var1['notRepairedDamage']=
var1['notRepairedDamage'].str.replace('nein','no')

var1['notRepairedDamage']=
var1['notRepairedDamage'].str.replace('ja','yes')

var1['notRepairedDamage']=
var1['notRepairedDamage'].str.replace('NO','no')
var1.head(0)

Empty DataFrame
Columns: [dateCrawled, name, seller, offerType, price_in_usd, abtest,
vehicleType, yearOfRegistration, gearbox, powerPS, model, km,
monthOfRegistration, fuelType, brand, notRepairedDamage, dateCreated,
nrOfPictures, postalCode, lastSeen]
Index: []

var1.rename(columns= {'postalCode':'taruncode'},inplace = True)

var1.rename(columns= {'nrOfPictures' :'No_of_pictures'},inplace =

True)

var1.head()

dateCrawled
name \
0 2016-03-26 17:47:46
Peugeot_807_160_NAVTECH_ON_BOARD
1 2016-04-04 13:38:56
BMW_740i_4_4_Liter_HAMANN_UMBAU_Mega_Optik
2 2016-03-26 18:57:24
Volkswagen_Golf_1.6_United
3 2016-03-12 16:58:10
Smart_smart_fortwo_coupe_softouch/F1/Klima/Pan...
4 2016-04-01 14:38:50
Ford_Focus_1_6_Benzin_TÜV_neu_ist_sehr_gepfleg...

seller offerType price_in_usd abtest vehicleType

yearOfRegistration \
0 privat Angebot 5000 control bus
2004
1 privat Angebot 8500 control limousine
1997
2 privat Angebot 8990 test limousine
2009
3 privat Angebot 4350 control kleinwagen
2007
4 privat Angebot 1350 test kombi
2003

gearbox powerPS model km monthOfRegistration fuelType \

0 manual 158 andere 150000 3 lpg
1 automatic 286 7er 150000 6 benzin
2 manual 102 golf 70000 7 benzin
3 automatic 71 fortwo 70000 6 benzin
4 manual 0 focus 150000 7 benzin

brand notRepairedDamage dateCreated

No_of_pictures \
0 peugeot no 2016-03-26 00:00:00 0

1 bmw no 2016-04-04 00:00:00 0

2 volkswagen no 2016-03-26 00:00:00 0

3 smart no 2016-03-12 00:00:00 0

4 ford no 2016-04-01 00:00:00 0

taruncode lastSeen
0 79588 2016-04-06 06:45:54
1 71034 2016-04-06 14:45:08
2 35394 2016-04-06 20:15:37
3 33729 2016-03-15 03:16:28
4 39218 2016-04-01 14:38:50

var1['seller'] = var1['seller'].str.replace("privat","Private")

var1.rename(columns= {'dateCrawled' :'Date_Crawled'},inplace = True)

var1.rename(columns= {'nrOfPictures' :'No_of_pictures'},inplace =

True)

var1['yearOfRegistration'].value_counts()

yearOfRegistration
2000 3354
2005 3015
1999 3000
2004 2737
2003 2727
...
2800 1
1500 1
1953 1
4800 1
1001 1
Name: count, Length: 97, dtype: int64

var1.describe(include="all")

Date_Crawled name seller offerType

price_in_usd \
count 50000 50000 50000 50000
5.000000e+04
unique 48213 38754 2 2
NaN
top 2016-03-29 23:42:13 Ford_Fiesta Private Angebot
NaN
freq 3 78 49999 49999
NaN
mean NaN NaN NaN NaN
9.840044e+03
std NaN NaN NaN NaN
4.811044e+05
min NaN NaN NaN NaN
0.000000e+00
25% NaN NaN NaN NaN
1.100000e+03
50% NaN NaN NaN NaN
2.950000e+03
75% NaN NaN NaN NaN
7.200000e+03
max NaN NaN NaN NaN
1.000000e+08

abtest vehicleType yearOfRegistration gearbox powerPS

model \
count 50000 44905 50000.000000 47320 50000.000000
47242
unique 2 8 NaN 2 NaN
245
top test limousine NaN manual NaN
golf
freq 25756 12859 NaN 36993 NaN
4024
mean NaN NaN 2005.073280 NaN 116.355920
NaN
std NaN NaN 105.712813 NaN 209.216627
NaN
min NaN NaN 1000.000000 NaN 0.000000
NaN
25% NaN NaN 1999.000000 NaN 70.000000
NaN
50% NaN NaN 2003.000000 NaN 105.000000
NaN
75% NaN NaN 2008.000000 NaN 150.000000
NaN
max NaN NaN 9999.000000 NaN 17700.000000
NaN

km monthOfRegistration fuelType brand \

count 50000.000000 50000.000000 45518 50000
unique NaN NaN 7 40
top NaN NaN benzin volkswagen
freq NaN NaN 30107 10687
mean 125732.700000 5.723360 NaN NaN
std 40042.211706 3.711984 NaN NaN
min 5000.000000 0.000000 NaN NaN
25% 125000.000000 3.000000 NaN NaN
50% 150000.000000 6.000000 NaN NaN
75% 150000.000000 9.000000 NaN NaN
max 150000.000000 12.000000 NaN NaN

notRepairedDamage dateCreated No_of_pictures

taruncode \
count 40171 50000 50000.0
50000.000000
unique 2 76 NaN
NaN
top no 2016-04-03 00:00:00 NaN
NaN
freq 35232 1946 NaN
NaN
mean NaN NaN 0.0
50813.627300
std NaN NaN 0.0
25779.747957
min NaN NaN 0.0
1067.000000
25% NaN NaN 0.0
30451.000000
50% NaN NaN 0.0
49577.000000
75% NaN NaN 0.0
71540.000000
max NaN NaN 0.0
99998.000000

lastSeen
count 50000
unique 39481
top 2016-04-07 06:17:27
freq 8
mean NaN
std NaN
min NaN
25% NaN
50% NaN
75% NaN
max NaN

var1 = var1.drop("No_of_pictures",axis=1)

var1 = var1.drop("notRepairedDamage",axis=1)

var1.shape

(50000, 18)

var1_null_sum = var1.isnull().sum()
var1_nperc = (var1_null_sum * 100/ len(var1))
print(round(var1_nperc,2).sort_values(ascending = False))

fuelType 7.76
vehicleType 6.52
model 5.12
gearbox 5.04
name 0.00
Date_Crawled 0.00
abtest 0.00
price_in_usd 0.00
seller 0.00
offerType 0.00
powerPS 0.00
yearOfRegistration 0.00
km 0.00
monthOfRegistration 0.00
brand 0.00
dateCreated 0.00
taruncode 0.00
lastSeen 0.00
dtype: float64

var1.head()

Date_Crawled
name \
0 2016-03-26 17:47:46
Peugeot_807_160_NAVTECH_ON_BOARD
1 2016-04-04 13:38:56
BMW_740i_4_4_Liter_HAMANN_UMBAU_Mega_Optik
2 2016-03-26 18:57:24
Volkswagen_Golf_1.6_United
3 2016-03-12 16:58:10
Smart_smart_fortwo_coupe_softouch/F1/Klima/Pan...
4 2016-04-01 14:38:50
Ford_Focus_1_6_Benzin_TÜV_neu_ist_sehr_gepfleg...

seller offerType price_in_usd abtest vehicleType

yearOfRegistration \
0 Private Angebot 5000 control bus
2004
1 Private Angebot 8500 control limousine
1997
2 Private Angebot 8990 test limousine
2009
3 Private Angebot 4350 control kleinwagen
2007
4 Private Angebot 1350 test kombi
2003

gearbox powerPS model km monthOfRegistration fuelType \

0 manual 158 andere 150000 3 lpg
1 automatic 286 7er 150000 6 benzin
2 manual 102 golf 70000 7 benzin
3 automatic 71 fortwo 70000 6 benzin
4 manual 0 focus 150000 7 benzin

brand dateCreated taruncode lastSeen

0 peugeot 2016-03-26 00:00:00 79588 2016-04-06 06:45:54
1 bmw 2016-04-04 00:00:00 71034 2016-04-06 14:45:08
2 volkswagen 2016-03-26 00:00:00 35394 2016-04-06 20:15:37
3 smart 2016-03-12 00:00:00 33729 2016-03-15 03:16:28
4 ford 2016-04-01 00:00:00 39218 2016-04-01 14:38:50

var1['price_in_usd'].describe(include = "all")

count 5.000000e+04
mean 9.840044e+03
std 4.811044e+05
min 0.000000e+00
25% 1.100000e+03
50% 2.950000e+03
75% 7.200000e+03
max 1.000000e+08
Name: price_in_usd, dtype: float64

var1['price_in_usd'].value_counts()

price_in_usd
0 1421
500 781
1500 734
2500 643
1000 639
...
35222 1
34490 1
910 1
3890000 1
48600 1
Name: count, Length: 2357, dtype: int64

print('Number of Rows and Columns before removing outliers: ',

var1.shape)
q1 = 1150
q3 = 7200

iqr = q3-q1
lower_bound = q1-(10*iqr)
upper_bound = q3+(10*iqr)

var1 = var1[var1['price_in_usd'].between(lower_bound, upper_bound)]

print('Number of Rows and Columns after removing outliers: ',
var1.shape)

Number of Rows and Columns before removing outliers: (50000, 18)

Number of Rows and Columns after removing outliers: (49892, 18)

var1['km'].describe(include="all")

count 49892.000000
mean 125883.107512
std 39889.981761
min 5000.000000
25% 125000.000000
50% 150000.000000
75% 150000.000000
max 150000.000000
Name: km, dtype: float64

var1['km'].value_counts()

km
150000 32409
125000 5164
100000 2164
90000 1755
80000 1434
70000 1230
60000 1155
50000 1019
5000 952
40000 809
30000 774
20000 768
10000 259
Name: count, dtype: int64

var1[['yearOfRegistration','monthOfRegistration']].describe()

yearOfRegistration monthOfRegistration
count 49892.000000 49892.000000
mean 2005.076906 5.723403
std 105.824742 3.713133
min 1000.000000 0.000000
25% 1999.000000 3.000000
50% 2003.000000 6.000000
75% 2008.000000 9.000000
max 9999.000000 12.000000

var1[['Date_Crawled','dateCreated','lastSeen']][0:5]

Date_Crawled dateCreated lastSeen

0 2016-03-26 17:47:46 2016-03-26 00:00:00 2016-04-06 06:45:54
1 2016-04-04 13:38:56 2016-04-04 00:00:00 2016-04-06 14:45:08
2 2016-03-26 18:57:24 2016-03-26 00:00:00 2016-04-06 20:15:37
3 2016-03-12 16:58:10 2016-03-12 00:00:00 2016-03-15 03:16:28
4 2016-04-01 14:38:50 2016-04-01 00:00:00 2016-04-01 14:38:50

print(var1['Date_Crawled'].str[0:10].value_counts(normalize =
True,dropna= False).sort_index())

Date_Crawled
2016-03-05 0.025375
2016-03-06 0.013950
2016-03-07 0.035958
2016-03-08 0.033252
2016-03-09 0.033232
2016-03-10 0.032169
2016-03-11 0.032550
2016-03-12 0.036799
2016-03-13 0.015594
2016-03-14 0.036639
2016-03-15 0.033993
2016-03-16 0.029484
2016-03-17 0.031508
2016-03-18 0.013028
2016-03-19 0.034956
2016-03-20 0.037842
2016-03-21 0.037461
2016-03-22 0.032871
2016-03-23 0.032410
2016-03-24 0.029103
2016-03-25 0.031749
2016-03-26 0.032490
2016-03-27 0.030987
2016-03-28 0.034835
2016-03-29 0.034194
2016-03-30 0.033613
2016-03-31 0.031929
2016-04-01 0.033753
2016-04-02 0.035416
2016-04-03 0.038643
2016-04-04 0.036499
2016-04-05 0.013108
2016-04-06 0.003187
2016-04-07 0.001423
Name: proportion, dtype: float64

print(var1['dateCreated'].str[0:10].value_counts(normalize =
True,dropna= False).sort_index())

dateCreated
2015-06-11 0.000020
2015-08-10 0.000020
2015-09-09 0.000020
2015-11-10 0.000020
2015-12-05 0.000020
...
2016-04-03 0.038884
2016-04-04 0.036860
2016-04-05 0.011846
2016-04-06 0.003267
2016-04-07 0.001283
Name: proportion, Length: 76, dtype: float64

var1['name'] = var1['name'].str.replace("_"," ")

C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\1530092152.py:1:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['name'] = var1['name'].str.replace("_"," ")

print(var1['lastSeen'].str[0:10].value_counts(normalize = True,dropna=
False).sort_index())

lastSeen
2016-03-05 0.001082
2016-03-06 0.004430
2016-03-07 0.005352
2016-03-08 0.007596
2016-03-09 0.009821
2016-03-10 0.010783
2016-03-11 0.012547
2016-03-12 0.023852
2016-03-13 0.008999
2016-03-14 0.012828
2016-03-15 0.015894
2016-03-16 0.016456
2016-03-17 0.027980
2016-03-18 0.007416
2016-03-19 0.015774
2016-03-20 0.020725
2016-03-21 0.020745
2016-03-22 0.021607
2016-03-23 0.018580
2016-03-24 0.019542
2016-03-25 0.019242
2016-03-26 0.016937
2016-03-27 0.015995
2016-03-28 0.020845
2016-03-29 0.022368
2016-03-30 0.024874
2016-03-31 0.023831
2016-04-01 0.023130
2016-04-02 0.024894
2016-04-03 0.025335
2016-04-04 0.024673
2016-04-05 0.124068
2016-04-06 0.220997
2016-04-07 0.130803
Name: proportion, dtype: float64

print('Total rows data: ', var1.shape[0])

print('number of rows between 1900 and 2016:
',var1['yearOfRegistration'].between(1900, 2016).sum())

Total rows data: 49892

number of rows between 1900 and 2016: 47922

var1 = var1[var1['yearOfRegistration'].between(1900, 2016)]

var1.head()

Date_Crawled
name \
0 2016-03-26 17:47:46
Peugeot_807_160_NAVTECH_ON_BOARD
1 2016-04-04 13:38:56
BMW_740i_4_4_Liter_HAMANN_UMBAU_Mega_Optik
2 2016-03-26 18:57:24
Volkswagen_Golf_1.6_United
3 2016-03-12 16:58:10
Smart_smart_fortwo_coupe_softouch/F1/Klima/Pan...
4 2016-04-01 14:38:50
Ford_Focus_1_6_Benzin_TÜV_neu_ist_sehr_gepfleg...

seller offerType price_in_usd abtest vehicleType

yearOfRegistration \
0 Private Angebot 5000 control bus
2004
1 Private Angebot 8500 control limousine
1997
2 Private Angebot 8990 test limousine
2009
3 Private Angebot 4350 control kleinwagen
2007
4 Private Angebot 1350 test kombi
2003

gearbox powerPS model km monthOfRegistration fuelType \

0 manual 158 andere 150000 3 lpg
1 automatic 286 7er 150000 6 benzin
2 manual 102 golf 70000 7 benzin
3 automatic 71 fortwo 70000 6 benzin
4 manual 0 focus 150000 7 benzin

brand dateCreated taruncode lastSeen

0 peugeot 2016-03-26 00:00:00 79588 2016-04-06 06:45:54
1 bmw 2016-04-04 00:00:00 71034 2016-04-06 14:45:08
2 volkswagen 2016-03-26 00:00:00 35394 2016-04-06 20:15:37
3 smart 2016-03-12 00:00:00 33729 2016-03-15 03:16:28
4 ford 2016-04-01 00:00:00 39218 2016-04-01 14:38:50

var1['Date_Crawled'] = pd.to_datetime(var1['Date_Crawled']).dt.date
var1['dateCreated'] = pd.to_datetime(var1['dateCreated']).dt.date
var1['lastSeen'] = pd.to_datetime(var1['lastSeen']).dt.date

C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\3435252794.py:1:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['Date_Crawled'] = pd.to_datetime(var1['Date_Crawled']).dt.date
C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\3435252794.py:2:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['dateCreated'] = pd.to_datetime(var1['dateCreated']).dt.date
C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\3435252794.py:3:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['lastSeen'] = pd.to_datetime(var1['lastSeen']).dt.date

print(pd.__version__)

2.2.2

var1['name'] = var1['name'].str.replace("_"," ")

var1.head()

C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\2774122297.py:1:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['name'] = var1['name'].str.replace("_"," ")

Date_Crawled name
seller \
0 2016-03-26 Peugeot 807 160 NAVTECH ON BOARD
Private
1 2016-04-04 BMW 740i 4 4 Liter HAMANN UMBAU Mega Optik
Private
2 2016-03-26 Volkswagen Golf 1.6 United
Private
3 2016-03-12 Smart smart fortwo coupe softouch/F1/Klima/Pan...
Private
4 2016-04-01 Ford Focus 1 6 Benzin TÜV neu ist sehr gepfleg...
Private

offerType price_in_usd abtest vehicleType yearOfRegistration

gearbox \
0 Angebot 5000 control bus 2004
manual
1 Angebot 8500 control limousine 1997
automatic
2 Angebot 8990 test limousine 2009
manual
3 Angebot 4350 control kleinwagen 2007
automatic
4 Angebot 1350 test kombi 2003
manual

powerPS model km monthOfRegistration fuelType

brand \
0 158 andere 150000 3 lpg peugeot

1 286 7er 150000 6 benzin bmw

2 102 golf 70000 7 benzin volkswagen

3 71 fortwo 70000 6 benzin smart

4 0 focus 150000 7 benzin ford

dateCreated taruncode lastSeen

0 2016-03-26 79588 2016-04-06
1 2016-04-04 71034 2016-04-06
2 2016-03-26 35394 2016-04-06
3 2016-03-12 33729 2016-03-15
4 2016-04-01 39218 2016-04-01

var1['Date_Crawled'].dtype

dtype('O')

type(var1['Date_Crawled'][0])

datetime.date

var1['seller'] = var1['seller'].str.replace("gewerblich","commercial")

C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\1842077218.py:1:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['seller'] =
var1['seller'].str.replace("gewerblich","commercial")
var1.head()

Date_Crawled name
seller \
0 2016-03-26 Peugeot 807 160 NAVTECH ON BOARD
Private
1 2016-04-04 BMW 740i 4 4 Liter HAMANN UMBAU Mega Optik
Private
2 2016-03-26 Volkswagen Golf 1.6 United
Private
3 2016-03-12 Smart smart fortwo coupe softouch/F1/Klima/Pan...
Private
4 2016-04-01 Ford Focus 1 6 Benzin TÜV neu ist sehr gepfleg...
Private

offerType price_in_usd abtest vehicleType yearOfRegistration

gearbox \
0 Angebot 5000 control bus 2004
manual
1 Angebot 8500 control limousine 1997
automatic
2 Angebot 8990 test limousine 2009
manual
3 Angebot 4350 control kleinwagen 2007
automatic
4 Angebot 1350 test kombi 2003
manual

powerPS model km monthOfRegistration fuelType

brand \
0 158 andere 150000 3 lpg peugeot

1 286 7er 150000 6 benzin bmw

2 102 golf 70000 7 benzin volkswagen

3 71 fortwo 70000 6 benzin smart

4 0 focus 150000 7 benzin ford

dateCreated taruncode lastSeen

0 2016-03-26 79588 2016-04-06
1 2016-04-04 71034 2016-04-06
2 2016-03-26 35394 2016-04-06
3 2016-03-12 33729 2016-03-15
4 2016-04-01 39218 2016-04-01

var1['seller'].unique()

array(['Private', 'commercial'], dtype=object)

var1['offerType'].unique()

array(['Angebot', 'Gesuch'], dtype=object)

var1['offerType'] = var1['offerType'].str.replace("Angebot","offer")
var1['offerType'] = var1['offerType'].str.replace("Gesuch","request")

C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\3117879292.py:1:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['offerType'] = var1['offerType'].str.replace("Angebot","offer")
C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\3117879292.py:2:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['offerType'] =
var1['offerType'].str.replace("Gesuch","request")

var1.head()

Date_Crawled name
seller \
0 2016-03-26 Peugeot 807 160 NAVTECH ON BOARD
Private
1 2016-04-04 BMW 740i 4 4 Liter HAMANN UMBAU Mega Optik
Private
2 2016-03-26 Volkswagen Golf 1.6 United
Private
3 2016-03-12 Smart smart fortwo coupe softouch/F1/Klima/Pan...
Private
4 2016-04-01 Ford Focus 1 6 Benzin TÜV neu ist sehr gepfleg...
Private

offerType price_in_usd abtest vehicleType yearOfRegistration

gearbox \
0 offer 5000 control bus 2004
manual
1 offer 8500 control limousine 1997
automatic
2 offer 8990 test limousine 2009
manual
3 offer 4350 control kleinwagen 2007
automatic
4 offer 1350 test kombi 2003
manual

powerPS model km monthOfRegistration fuelType

brand \
0 158 andere 150000 3 lpg peugeot

1 286 7er 150000 6 benzin bmw

2 102 golf 70000 7 benzin volkswagen

3 71 fortwo 70000 6 benzin smart

4 0 focus 150000 7 benzin ford

dateCreated taruncode lastSeen

0 2016-03-26 79588 2016-04-06
1 2016-04-04 71034 2016-04-06
2 2016-03-26 35394 2016-04-06
3 2016-03-12 33729 2016-03-15
4 2016-04-01 39218 2016-04-01

var1['gearbox'].unique()

array(['manual', 'automatic', nan], dtype=object)

var1['fuelType'].unique()

array(['lpg', 'benzin', 'diesel', nan, 'cng', 'hybrid', 'elektro',

'andere'], dtype=object)

var1['fuelType'] = var1['fuelType'].str.replace("benzin","petrol")
var1['fuelType'] = var1['fuelType'].str.replace("andere","other")
var1['fuelType'] = var1['fuelType'].str.replace("elektro","electric")

C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\2091247764.py:1:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['fuelType'] = var1['fuelType'].str.replace("benzin","petrol")
C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\2091247764.py:2:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation:
https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['fuelType'] = var1['fuelType'].str.replace("andere","other")
C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\2091247764.py:3:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['fuelType'] =
var1['fuelType'].str.replace("elektro","electric")

var1['vehicleType'].unique()

array(['bus', 'limousine', 'kleinwagen', 'kombi', nan, 'coupe', 'suv',

'cabrio', 'andere'], dtype=object)

var1['vehicleType'] =
var1['vehicleType'].str.replace("kleinwagen","small car")
var1['vehicleType'] =
var1['vehicleType'].str.replace("cabrio","convertible")
var1['vehicleType'] = var1['vehicleType'].str.replace("kombi","station
wagon")
var1['vehicleType'] =
var1['vehicleType'].str.replace("andere","other")

C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\541384445.py:1:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['vehicleType'] =
var1['vehicleType'].str.replace("kleinwagen","small car")
C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\541384445.py:2:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['vehicleType'] =
var1['vehicleType'].str.replace("cabrio","convertible")
C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\541384445.py:3:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['vehicleType'] =
var1['vehicleType'].str.replace("kombi","station wagon")
C:\Users\DELL\AppData\Local\Temp\ipykernel_5072\541384445.py:4:
SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation:

https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#
returning-a-view-versus-a-copy
var1['vehicleType'] =
var1['vehicleType'].str.replace("andere","other")

var1.head()

Date_Crawled name
seller \
0 2016-03-26 Peugeot 807 160 NAVTECH ON BOARD
Private
1 2016-04-04 BMW 740i 4 4 Liter HAMANN UMBAU Mega Optik
Private
2 2016-03-26 Volkswagen Golf 1.6 United
Private
3 2016-03-12 Smart smart fortwo coupe softouch/F1/Klima/Pan...
Private
4 2016-04-01 Ford Focus 1 6 Benzin TÜV neu ist sehr gepfleg...
Private

offerType price_in_usd abtest vehicleType yearOfRegistration

\
0 offer 5000 control bus 2004

1 offer 8500 control limousine 1997

2 offer 8990 test limousine 2009

3 offer 4350 control small car 2007

4 offer 1350 test station wagon 2003

gearbox powerPS model km monthOfRegistration fuelType \

0 manual 158 andere 150000 3 lpg
1 automatic 286 7er 150000 6 petrol
2 manual 102 golf 70000 7 petrol
3 automatic 71 fortwo 70000 6 petrol
4 manual 0 focus 150000 7 petrol

brand dateCreated taruncode lastSeen

0 peugeot 2016-03-26 79588 2016-04-06
1 bmw 2016-04-04 71034 2016-04-06
2 volkswagen 2016-03-26 35394 2016-04-06
3 smart 2016-03-12 33729 2016-03-15
4 ford 2016-04-01 39218 2016-04-01