Shape Your Data Smarter: Dimensionality Reduction in Python and R.

For Dimensionality Reduction 3 main methods are Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Kernel PCA. Usage of Python and R for building these 3 models is described below.

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

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

#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 = 0)

#Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

#Applying PCA
from sklearn.decomposition import PCA
pca = PCA(n_components = 2)
X_train = pca.fit_transform(X_train)
X_test = pca.transform(X_test)

#Training the Logistic Regression model on the Training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state = 0)
classifier.fit(X_train, y_train)

#Making the Confusion Matrix
from sklearn.metrics import confusion_matrix, accuracy_score
y_pred = classifier.predict(X_test)
cm = confusion_matrix(y_test, y_pred)
print(cm)
accuracy_score(y_test, y_pred)

         
# Importing the dataset
dataset = read.csv('my_dataset.csv')

# Splitting the dataset into the Training set and Test set
# install.packages('caTools')
library(caTools)
set.seed(123)
split = sample.split(dataset$Customer_Segment, SplitRatio = 0.8)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

# Feature Scaling
training_set[-14] = scale(training_set[-14])
test_set[-14] = scale(test_set[-14])

# Applying PCA
# install.packages('caret')
library(caret)
# install.packages('e1071')
library(e1071)
pca = preProcess(x = training_set[-14], method = 'pca', pcaComp = 2)
training_set = predict(pca, training_set)
training_set = training_set[c(2, 3, 1)]
test_set = predict(pca, test_set)
test_set = test_set[c(2, 3, 1)]

# Fitting SVM to the Training set
# install.packages('e1071')
library(e1071)
classifier = svm(formula = Customer_Segment ~ .,
                 data = training_set,
                 type = 'C-classification',
                 kernel = 'linear')

# Predicting the Test set results
y_pred = predict(classifier, newdata = test_set[-3])

# Making the Confusion Matrix
cm = table(test_set[, 3], y_pred)

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

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

#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 = 0)

#Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

#Applying LDA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
lda = LDA(n_components = 2)
X_train = lda.fit_transform(X_train, y_train)
X_test = lda.transform(X_test)

#Training the Logistic Regression model on the Training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state = 0)
classifier.fit(X_train, y_train)

#Making the Confusion Matrix
from sklearn.metrics import confusion_matrix, accuracy_score
y_pred = classifier.predict(X_test)
cm = confusion_matrix(y_test, y_pred)
print(cm)
accuracy_score(y_test, y_pred)

          
# Importing the dataset
dataset = read.csv('my_dataset.csv')

# Splitting the dataset into the Training set and Test set
# install.packages('caTools')
library(caTools)
set.seed(123)
split = sample.split(dataset$Customer_Segment, SplitRatio = 0.8)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

# Feature Scaling
training_set[-14] = scale(training_set[-14])
test_set[-14] = scale(test_set[-14])

# Applying LDA
library(MASS)
lda = lda(formula = Customer_Segment ~ ., data = training_set)
training_set = as.data.frame(predict(lda, training_set))
training_set = training_set[c(5, 6, 1)]
test_set = as.data.frame(predict(lda, test_set))
test_set = test_set[c(5, 6, 1)]

# Fitting SVM to the Training set
# install.packages('e1071')
library(e1071)
classifier = svm(formula = class ~ .,
                 data = training_set,
                 type = 'C-classification',
                 kernel = 'linear')

# Predicting the Test set results
y_pred = predict(classifier, newdata = test_set[-3])

# Making the Confusion Matrix
cm = table(test_set[, 3], y_pred)

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

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

#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 = 0)

#Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

#Applying Kernel PCA
from sklearn.decomposition import KernelPCA
kpca = KernelPCA(n_components = 2, kernel = 'rbf')
X_train = kpca.fit_transform(X_train)
X_test = kpca.transform(X_test)

#Training the Logistic Regression model on the Training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state = 0)
classifier.fit(X_train, y_train)

#Making the Confusion Matrix
from sklearn.metrics import confusion_matrix, accuracy_score
y_pred = classifier.predict(X_test)
cm = confusion_matrix(y_test, y_pred)
print(cm)
accuracy_score(y_test, y_pred)

         
# Importing the dataset
dataset = read.csv('my_dataset.csv')
dataset = dataset[, 3:5]

# Splitting the dataset into the Training set and Test set
# install.packages('caTools')
library(caTools)
set.seed(123)
split = sample.split(dataset$Purchased, SplitRatio = 0.8)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

# Feature Scaling
training_set[, 1:2] = scale(training_set[, 1:2])
test_set[, 1:2] = scale(test_set[, 1:2])

# Applying Kernel PCA
# install.packages('kernlab')
library(kernlab)
kpca = kpca(~., data = training_set[-3], kernel = 'rbfdot', features = 2)
training_set_pca = as.data.frame(predict(kpca, training_set))
training_set_pca$Purchased = training_set$Purchased
test_set_pca = as.data.frame(predict(kpca, test_set))
test_set_pca$Purchased = test_set$Purchased

# Fitting Logistic Regression to the Training set
classifier = glm(formula = Purchased ~ .,
                 family = binomial,
                 data = training_set_pca)

# Predicting the Test set results
prob_pred = predict(classifier, type = 'response', newdata = test_set_pca[-3])
y_pred = ifelse(prob_pred > 0.5, 1, 0)

# Making the Confusion Matrix
cm = table(test_set_pca[, 3], y_pred)