0%

MachineLearning-0x01-Data-Preprocessing

Posted on Edited on In ,

Download data set

Download data set from this [website](https://www.superdatascience.com/%E4%B8%8B%E8%BD%BD%E6%95%B0%E6%8D%AE%E9%9B%86/)

Importing the Libraries

Python data preprocessing

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
# Data Preprocessing

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

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

# 3. Taking care of missing data
from sklearn.impute import SimpleImputer 
imputer = SimpleImputer(missing_values=np.nan, strategy = 'mean')
imputer = imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])

# 4. Encoding categorical data
# Encoding the Independent Variable
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.compose import ColumnTransformer
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])

# Virtual Coding for Country column
columnTransformer = ColumnTransformer([('encoder', OneHotEncoder(), [0])], remainder='passthrough')
X = np.array(columnTransformer.fit_transform(X), dtype=np.str)

# Encoding the Dependent Variable
labelencoder_y = LabelEncoder()
y = labelencoder_y.fit_transform(y)

# 5. Splitting the dataset into training set and testing set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)

# 6. Scaling features
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)