data_preprocessing_template.py

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.preprocessing import Imputer
from sklearn.preprocessing import LabelEncoder, OneHotEncoder, StandardScaler
from sklearn.cross_validation import train_test_split

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

# Taking care of missing data
# axis 0 is column
imputer = Imputer(missing_values = 'NaN', strategy = 'mean', axis = 0)
imputer = imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3]) # replaced to the imputer value

# Encoding Categorical data
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()
labelencoder_y = LabelEncoder()
y = labelencoder_y.fit_transform(y)

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

# Feature Scaling
# Do we need to scale the dummy variables X[:3], it depends on how much you wanna keep interpretation in your
# model. If we scale it, we will lose knowing which observation belongs to which country. It wouldn't break
# your model if you don't scale it.
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.fit_transform(X_test)