Data Preprocessing Template

### Data Preprocessing Template  ###

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

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

### MISSING DATA ###
# Replace NaN with means of columns Age and Salary
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values = 'NaN', strategy = 'mean', axis=0)
imputer = imputer.fit(X[:, 1:3]) #all rows, columns 1 and 2.
X[:, 1:3] = imputer.transform(X[:, 1:3])

### CATEGORICAL DATA ###
# Encoding categorical data (Turning Country column [0] into 0, 1, and 2)
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])

### DUMMY ENCODING ###
# Dummy Encoding turns Country column [0] into three columns 
# because Country [0] shouldn't be attributed an order such as 0,1,2 
# but rather three columns with 1 and 0s
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()

# Encoding the dependent variable y (Purchased). Change from Yes/No to 0/1
labelencoder_y = LabelEncoder()
y = labelencoder_y.fit_transform(y)

### Splitting the dataset into the Training set and Test set ###
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)

### Feature Scaling ###
"""
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
sc_y = StandardScaler()
y_train = sc_y.fit_transform(y_train)
"""

Python Fiddle

Python Cloud IDE