Understanding of Data Pre-Processing for given dataset 1 using Spyder - ML

import numpy as np

import matplotlib.pyplot as plt

import pandas as pd

dataset = pd.read_csv('D:\SEM 7\ML\dataset_p1.csv')

X = dataset.iloc[:, :-1].values

y = dataset.iloc[:, 3].values

from sklearn.preprocessing import Imputer

imputer = Imputer(missing_values = 'NaN', strategy = 'most_frequent', axis = 0)

imputer = imputer.fit(X[:, 1:3])

X[:, 1:3] = imputer.transform(X[:, 1:3])

from sklearn.preprocessing import Imputer

from sklearn.impute import SimpleImputer

imputer = Imputer(missing_values = 'NaN', strategy = 'most_frequent', axis = 0)

imputer = SimpleImputer(missing_values=np.nan,strategy='mean',verbose=0)

imputer = imputer.fit(X[:, 1:3])

X[:, 1:3] = imputer.transform(X[:, 1:3])

Variable Explorer:-

Dataset:-

Output:-

Code :-

import numpy as np

import matplotlib.pyplot as plt

import pandas as pd

dataset = pd.read_csv('D:\SEM 7\ML\dataset2.csv')

X = dataset.iloc[:, :].values

from sklearn.preprocessing import LabelEncoder, OneHotEncoder

labelencoder_X = LabelEncoder()

X[:, 0] = labelencoder_X.fit_transform(X[:, 0])

#onehotencoder = OneHotEncoder(categorical_features = [0])

#X = onehotencoder.fit_transform(X).toarray()

X[:, 1] = labelencoder_X.fit_transform(X[:, 2])

#onehotencoder = OneHotEncoder(categorical_features = [1])

#X = onehotencoder.fit_transform(X).toarray()

X[:, 2] = labelencoder_X.fit_transform(X[:, 2])

onehotencoder = OneHotEncoder(categorical_features = [0])

X = onehotencoder.fit_transform(X).toarray()

onehotencoder = OneHotEncoder(categorical_features = [4])

X = onehotencoder.fit_transform(X).toarray()

onehotencoder = OneHotEncoder(categorical_features = [6])

X = onehotencoder.fit_transform(X).toarray()

Variable Explorer:-

Dataset:-

Output:-