Day 1_Data PreProcessing

数据集DATA.CSV

Country,Age,Salary,Purchased
France,44,72000,No
Spain,27,48000,Yes
Germany,30,54000,No
Spain,38,61000,No
Germany,40,,Yes
France,35,58000,Yes
Spain,,52000,No
France,48,79000,Yes
Germany,50,83000,No
France,37,67000,Yes

#Step 1: Importing the libraries

import numpy as np
import pandas as pd

#Step 2: Importing dataset

dataset=pd.read_csv('Data.csv')
X=dataset.iloc[:,:-1].values
Y=dataset.iloc[:,3].values

#Step 3: Handling the 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])

#Step 4: Encoding categorical data

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0])

#Creating a dummy variable
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()
labelencoder_Y = LabelEncoder()
Y =  labelencoder_Y.fit_transform(Y)

#Step 5: Splitting the datasets into training sets and Test sets

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 = 0)

#Step 6: Feature Scaling

from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.fit_transform(X_test)