bhargava-shankar/odd2023-datascience-ex-05

Ex:05 Feature Generation

AIM

To read the given data and perform Feature Encoding & Scaling process and save the data to a file.

ALGORITHM

1. Read the given Data.
2. Clean the Data Set using Data Cleaning Process
3. Apply Feature Generation techniques to all the feature of the data set
4. Save the data to the file

CODE

import pandas as pd
df=pd.read_csv("/content/Encoding Data.csv")
df

from sklearn.preprocessing import LabelEncoder,OrdinalEncoder
pn=['Hot','Warm','Cold']
e1=OrdinalEncoder(categories=[pn])
e1.fit_transform(df[['ord_2']])
df['bo2']=e1.fit_transform(df[['ord_2']])
df

le=LabelEncoder()
dfc=df.copy()
dfc['ord_2']=le.fit_transform(dfc['ord_2'])
dfc

from sklearn.preprocessing import OneHotEncoder
ohe=OneHotEncoder()#sparse=False
df2=df.copy()

enc=pd.DataFrame(ohe.fit_transform(df2[['nom_0']]))
df2=pd.concat([df2,enc],axis=1)
df2

pd.get_dummies(df2,columns=["nom_0"])

pip install category_encoders

from category_encoders import BinaryEncoder
be=BinaryEncoder()
dfb=df.copy()
nd=be.fit_transform(df['ord_2'])
dfb=pd.concat([dfb,nd],axis=1)
dfb

df=pd.read_csv("/content/data.csv")
df

from category_encoders import TargetEncoder
te=TargetEncoder()
cc=df.copy()
new=te.fit_transform(X=cc["City"],y=cc["Target"])
cc=pd.concat([cc,new],axis=1)
cc

import pandas as pd
df=pd.read_csv("/content/bmi.csv")
df

import numpy as np
max_vals=np.max(np.abs(df[['Height','Weight']]))
max_vals

min_vals=np.min(np.abs(df[['Height','Weight']]))
min_vals

from sklearn.preprocessing import StandardScaler
sc=StandardScaler()
df1=df.copy()
df1[["Height","Weight"]]=sc.fit_transform(df1[["Height","Weight"]])
df1.head(10)

max_val=np.max(np.abs(df1[['Height','Weight']]))
max_val

min_val=np.min(np.abs(df1[['Height','Weight']]))
min_val

from sklearn.preprocessing import MinMaxScaler
sc=MinMaxScaler()
df2=df.copy()
df2[["Height","Weight"]]=sc.fit_transform(df2[["Height","Weight"]])
df2

from sklearn.preprocessing import Normalizer
sc=Normalizer()
df3=df.copy()
df3[["Height","Weight"]]=sc.fit_transform(df3[["Height","Weight"]])
df3

from sklearn.preprocessing import MaxAbsScaler
sc=MaxAbsScaler()
df4=df.copy()
df4[["Height","Weight"]]=sc.fit_transform(df4[["Height","Weight"]])
df4

from sklearn.preprocessing import RobustScaler
sc=RobustScaler()
df5=df.copy()
df5[["Height","Weight"]]=sc.fit_transform(df5[["Height","Weight"]])
df5

RESULT:

This Program has run successfully.