machinelearning_customer_prediction_data_preprocessing.py

# -*- coding: utf-8 -*-
"""MachineLearning_customer_prediction_data_preprocessing.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1aHCBPlJC9ObpEYYBi3ZRXlXV3YkewW7-

# Data Preprocessing Tools

## Importing the libraries
"""

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

"""## Importing the dataset"""

DataSet = pd.read_csv('Data.csv')
x = DataSet.iloc[:, :-1].values
y = DataSet.iloc[:, -1].values

print(x)

print(y)

"""## Taking care of missing data"""

from sklearn.impute import SimpleImputer
sc = SimpleImputer(missing_values = np.nan, strategy = 'mean')
x[:, 1:] = sc.fit_transform(x[:,1:])

print(x)

"""## Encoding categorical data

### Encoding the Independent Variable (country column)
"""

from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers = [('encoder', OneHotEncoder(), [0])], remainder = 'passthrough')
x = np.array(ct.fit_transform(x))

print(x)

"""### Encoding the Dependent Variable (purchase column)"""

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
y = le.fit_transform(y)

print(y)

"""## Splitting the dataset into the Training set and Test set"""

from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 1)

print(x_train)

print(y_train)

print(x_test)

print(y_test)

"""## Feature Scaling (leave the dummy variables)"""

from sklearn.preprocessing import StandardScaler
ss = StandardScaler()
x_train[:, 3:] = ss.fit_transform(x_train[:,3:])
x_test[:, 3:] = ss.transform(x_test[:,3:])

print(x_train)

print(x_test)