8/26/24, 11:46 AM DMLAB-2_4238_01-08-2024.

ipynb - Colab

A) Dealing with categorial Data

1 import pandas as pd
2 data ={'chocolets':["Cadbury","Snickers","KitKack","MilkyBar"]}
3 data
4 df = pd.DataFrame(data)
5 df

chocolets

0 Cadbury

1 Snickers

2 KitKack

3 MilkyBar

1 df_encoded = pd.get_dummies(df)
2 df_encoded.head()

chocolets_Cadbury chocolets_KitKack chocolets_MilkyBar chocolets_Snickers

0 True False False False

1 False False False True

2 False True False False

3 False False True False

1 from sklearn.preprocessing import OneHotEncoder

2 encoder = OneHotEncoder()
3 encoder_result = encoder.fit_transform(df).toarray()
4 encoder_result

array([[1., 0., 0., 0.],

[0., 0., 0., 1.],
[0., 1., 0., 0.],
[0., 0., 1., 0.]])

B)Scaling

1 import pandas as pd
2 from sklearn.preprocessing import StandardScaler
3 scale = StandardScaler()
4 df=pd.read_excel("/content/students.xlsx")
5 df.head()

https://colab.research.google.com/drive/1ghyP3zLjCY_gZhTo4Hrkan3CXFTgtwnn#printMode=true 1/4
8/26/24, 11:46 AM DMLAB-2_4238_01-08-2024.ipynb - Colab

Name ID Branch Marks Percentage

0 Uday 1 CSM 456 91.2

1 Kalyan 2 CSM 434 86.8

2 Ajay 3 CSM 334 66.8

3 Abhi ram 4 CSM 423 84.6

4 Sai Kumar 5 CSM 458 91.6

1 x=df[['Marks','Percentage']]
2 scaledx=scale.fit_transform(x)
3 print(scaledx)

[[ 0.87218389 0.87218389]
[ 0.58557 0.58557 ]
[-0.7172204 -0.7172204 ]
[ 0.44226306 0.44226306]
[ 0.8982397 0.8982397 ]
[ 1.01549084 1.01549084]
[-0.73024831 -0.73024831]
[-0.86052735 -0.86052735]
[-0.54785765 -0.54785765]
[-1.73339692 -1.73339692]
[ 0.71584905 0.71584905]
[ 0.87218389 0.87218389]
[ 1.43238377 1.43238377]
[-0.57391346 -0.57391346]
[-2.02001081 -2.02001081]
[-1.17319705 -1.17319705]
[ 0.12959336 0.12959336]
[ 1.27604892 1.27604892]
[ 0.11656546 0.11656546]]

C) splitting dataset into training & Testing

1 import numpy as np
2 from sklearn.model_selection import train_test_split
3 x=np.arange(1,25).reshape(12,2)
4 y=np.array([0,1,1,0,1,0,0,1,1,0,1,0])
5

1 x

array([[ 1, 2],
[ 3, 4],
[ 5, 6],
[ 7, 8],
[ 9, 10],
[11, 12],
[13, 14],
[15, 16],

https://colab.research.google.com/drive/1ghyP3zLjCY_gZhTo4Hrkan3CXFTgtwnn#printMode=true 2/4
8/26/24, 11:46 AM DMLAB-2_4238_01-08-2024.ipynb - Colab
[17, 18],
[19, 20],
[21, 22],
[23, 24]])

1 y

array([0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 0])

1 x_train,x_test,y_train,y_test = train_test_split(x,y)

1 x_train

array([[21, 22],
[ 9, 10],
[19, 20],
[13, 14],
[ 7, 8],
[15, 16],
[ 1, 2],
[ 3, 4],
[23, 24]])

1 x_test

array([[ 5, 6],
[11, 12],
[17, 18]])

1 y_train

array([1, 1, 0, 0, 0, 1, 0, 1, 0])

1 y_test

array([1, 0, 1])

https://colab.research.google.com/drive/1ghyP3zLjCY_gZhTo4Hrkan3CXFTgtwnn#printMode=true 3/4
8/26/24, 11:46 AM DMLAB-2_4238_01-08-2024.ipynb - Colab

https://colab.research.google.com/drive/1ghyP3zLjCY_gZhTo4Hrkan3CXFTgtwnn#printMode=true 4/4