10/22/24, 7:17 PM datacleaning.

ipynb - Colab

import pandas as pd

df=pd.read_csv("https://docs.google.com/spreadsheets/d/1okbuAhRRXId5a5LPC85wSE2MBgKpQ-kY4nnABE3gCFc/export?format=csv&usp=sharing")

df

brand model transmission age fuel engine km owner price

0 mahindra thar manual 4 diesel 2184.0 11003 1 1231000

1 hyundai verna manual 6 petrol 1591.0 66936 1 786000

2 tata harrier manual 2 diesel 1956.0 27990 1 1489000

3 honda city automatic 1 petrol 1498.0 5061 1 1227000

4 ford ecosport manual 3 diesel 1498.0 23480 1 887000

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

174 maruti baleno manual 8 petrol 1197.0 33099 1 473000

175 mg hector automatic 4 petrol 1451.0 66590 1 1269000

176 hyundai creta manual 4 petrol 1497.0 80554 2 968000

177 kia seltos automatic 5 diesel 1493.0 51955 1 1266000

178 hyundai creta automatic 8 petrol 1591.0 61059 3 715000

179 rows × 9 columns

Next steps: Generate code with df

import plotly.express as px

px.scatter(x=df['engine'],y=df['km'])

120k

100k

80k

60k
y

40k

20k

800 1000 1200 1400 1600 1800

i=df[df['engine']>1500].index

df=df.drop(index=i)

l=[]
for i in range (0,len(df)):
l.append(i)
df['index']=l

px.scatter(x=df['engine'],y=df['km'])

https://colab.research.google.com/drive/1YpcH_4uz3sVHGwE9Em0GZ4p8Tjq5ZTxR#scrollTo=e9RzZJomeQtH&printMode=true 1/4
10/22/24, 7:17 PM datacleaning.ipynb - Colab

120k

100k

80k

60k
y

40k

20k

800 900 1000 1100 1200 1300

px.scatter(x=df['price'],y=df['km'])

120k

100k

80k

60k
y

40k

20k

0.2M 0.4M 0.6M 0.8M 1M 1.2M

df.isnull().sum()

https://colab.research.google.com/drive/1YpcH_4uz3sVHGwE9Em0GZ4p8Tjq5ZTxR#scrollTo=e9RzZJomeQtH&printMode=true 2/4
10/22/24, 7:17 PM datacleaning.ipynb - Colab

brand 0

model 0

transmission 0

age 0

fuel 0

engine 4

km 0

owner 0

price 0

index 0

dtype: int64

df[df['engine'].isnull()]

brand model transmission age fuel engine km owner price index

7 tata nexon automatic 4 diesel NaN 59866 1 728000 4

13 hyundai creta manual 6 petrol NaN 59085 1 823000 9

74 hyundai new automatic 0 petrol NaN 3295 1 974000 66

130 kia seltos manual 5 petrol NaN 90505 1 980000 117

df['engine'].unique()

array([1498., 1199., nan, 1497., 1197., 998., 1493., 1451., 1194.,

df['engine'].mode()[0]

1197.0

df['engine']=df['engine'].fillna(df['engine'].mode()[0])

df[df['engine'].isnull()]

brand model transmission age fuel engine km owner price index

df.isnull().sum()

brand 0

model 0

transmission 0

age 0

fuel 0

engine 0

km 0

owner 0

price 0

index 0

dtype: int64

df.duplicated().sum()

https://colab.research.google.com/drive/1YpcH_4uz3sVHGwE9Em0GZ4p8Tjq5ZTxR#scrollTo=e9RzZJomeQtH&printMode=true 3/4
10/22/24, 7:17 PM datacleaning.ipynb - Colab
len(df['model'].unique())/len(df)

0.2981366459627329

len(df['model'].unique())

48

len(df)

161

df=df.drop(columns=['model'])

df

brand transmission age fuel engine km owner price index

3 honda automatic 1 petrol 1498.0 5061 1 1227000 0

4 ford manual 3 diesel 1498.0 23480 1 887000 1

5 honda manual 3 petrol 1199.0 44787 1 796000 2

6 tata manual 2 petrol 1199.0 450 1 813000 3

7 tata automatic 4 diesel 1197.0 59866 1 728000 4

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

173 mahindra manual 4 petrol 1197.0 40924 1 681000 156

174 maruti manual 8 petrol 1197.0 33099 1 473000 157

175 mg automatic 4 petrol 1451.0 66590 1 1269000 158

176 hyundai manual 4 petrol 1497.0 80554 2 968000 159

177 kia automatic 5 diesel 1493.0 51955 1 1266000 160

161 rows × 9 columns

Next steps: Generate code with df

Start coding or generate with AI.

https://colab.research.google.com/drive/1YpcH_4uz3sVHGwE9Em0GZ4p8Tjq5ZTxR#scrollTo=e9RzZJomeQtH&printMode=true 4/4