source1

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

np.set_printoptions(threshold=np.nan)

# Importing the dataset
dataset = pd.read_csv("Data.csv")
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 3].values

# Taking care of missing data
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values='NaN', strategy='mean', axis=0)
imputer = imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])

# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
le = LabelEncoder()
X[:, 0] = le.fit_transform(X[:, 0])

# Add One Hot Encoder(ohe)
ohe = OneHotEncoder(categorical_features=[0])
X = ohe.fit_transform(X).toarray()

# Encoding categorical data in y
le = LabelEncoder()
y = le.fit_transform(y)