22 lines
634 B
Python
22 lines
634 B
Python
# Data preprocessing
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
import pandas as pd
|
|
|
|
# Importing the dataset
|
|
dataset = pd.read_csv('Data.csv')
|
|
# Create the matrix of features (independant variables)
|
|
# [:, = lines -- all of them
|
|
# :-1] = colums -- all of them unless the last one
|
|
# X = (Country, Age, Salary)
|
|
X = dataset.iloc[:, :-1].values
|
|
# Create vector of linked variables
|
|
# [:, 3] = all values of the 3rd column
|
|
# Y = (Purchased)
|
|
X = dataset.iloc[:, 3].values
|
|
|
|
# Taking care of the missing data
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
imputer = Imputer(missing_values = 'NaN', strategy = 'mean', axis = 0)
|