import pandas as pd
from [Link] import MinMaxScaler, StandardScaler
from [Link] import LabelEncoder, OneHotEncoder
df = pd.read_csv("C:\\Users\\HP\\Downloads\\iris_data (2).csv")
df
sepal_length sepal_width petal_length petal_width species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa
.. ... ... ... ... ...
145 6.7 3.0 5.2 2.3 virginica
146 6.3 2.5 5.0 1.9 virginica
147 6.5 3.0 5.2 2.0 virginica
148 6.2 3.4 5.4 2.3 virginica
149 5.9 3.0 5.1 1.8 virginica
[150 rows x 5 columns]
# Normal df containns both feature and target
df_num = [Link]('species',axis = 1) # axis means row,column to drop
and 0 means row and 1 means column
df_num.head()
sepal_length sepal_width petal_length petal_width
0 5.1 3.5 1.4 0.2
1 4.9 3.0 1.4 0.2
2 4.7 3.2 1.3 0.2
3 4.6 3.1 1.5 0.2
4 5.0 3.6 1.4 0.2
n = MinMaxScaler()
df_normalization = [Link](n.fit_transform(df_num),columns =
df_num.columns)
df_normalization
sepal_length sepal_width petal_length petal_width
0 0.222222 0.625000 0.067797 0.041667
1 0.166667 0.416667 0.067797 0.041667
2 0.111111 0.500000 0.050847 0.041667
3 0.083333 0.458333 0.084746 0.041667
4 0.194444 0.666667 0.067797 0.041667
.. ... ... ... ...
145 0.666667 0.416667 0.711864 0.916667
146 0.555556 0.208333 0.677966 0.750000
147 0.611111 0.416667 0.711864 0.791667
148 0.527778 0.583333 0.745763 0.916667
149 0.444444 0.416667 0.694915 0.708333
[150 rows x 4 columns]
#Standarize the data (Z-Score Scaling)
s = StandardScaler()
df_standardize = [Link](s.fit_transform(df_num),columns =
df_num.columns)
df_standardize.head()
sepal_length sepal_width petal_length petal_width
0 -0.900681 1.032057 -1.341272 -1.312977
1 -1.143017 -0.124958 -1.341272 -1.312977
2 -1.385353 0.337848 -1.398138 -1.312977
3 -1.506521 0.106445 -1.284407 -1.312977
4 -1.021849 1.263460 -1.341272 -1.312977
# LabelEncoder
label_encoder = LabelEncoder()
df['species_encoder'] =label_encoder.fit_transform(df['species'])
print(df['species_encoder'].head())
print('===============================================================
=============================')
df
0 0
1 0
2 0
3 0
4 0
Name: species_encoder, dtype: int32
======================================================================
======================
sepal_length sepal_width petal_length petal_width
species \
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa
.. ... ... ... ... ...
145 6.7 3.0 5.2 2.3 virginica
146 6.3 2.5 5.0 1.9 virginica
147 6.5 3.0 5.2 2.0 virginica
148 6.2 3.4 5.4 2.3 virginica
149 5.9 3.0 5.1 1.8 virginica
species_encoder
0 0
1 0
2 0
3 0
4 0
.. ...
145 2
146 2
147 2
148 2
149 2
[150 rows x 6 columns]
# ===================OneHot Encoding=========================
import pandas as pd
df = pd.read_csv('C:\\Users\\HP\\Downloads\\iris_data (2).csv')
onehot_encoder = OneHotEncoder(sparse_output = False)
encoded_species =
[Link](onehot_encoder.fit_transform(df[['species']]))
encoded_species
merged = [Link]([df, encoded_species], axis=1)
merged
result = [Link]('species',axis = 1)
result
sepal_length sepal_width petal_length petal_width 0 1
2
0 5.1 3.5 1.4 0.2 1.0 0.0
0.0
1 4.9 3.0 1.4 0.2 1.0 0.0
0.0
2 4.7 3.2 1.3 0.2 1.0 0.0
0.0
3 4.6 3.1 1.5 0.2 1.0 0.0
0.0
4 5.0 3.6 1.4 0.2 1.0 0.0
0.0
.. ... ... ... ... ... ... .
..
145 6.7 3.0 5.2 2.3 0.0 0.0
1.0
146 6.3 2.5 5.0 1.9 0.0 0.0
1.0
147 6.5 3.0 5.2 2.0 0.0 0.0
1.0
148 6.2 3.4 5.4 2.3 0.0 0.0
1.0
149 5.9 3.0 5.1 1.8 0.0 0.0
1.0
[150 rows x 7 columns]