Principal Component Analysis (PCA) in Python – Step 8.) Visualize the Results of PCA Model

with No Comments

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

# Import Data
dataset = pd.read_csv(‘PCA data.csv’)
X = dataset.iloc[:, 0:13].values
y = dataset.iloc[:, 13].values

# Split into the Training set and Test set
from sklearn.cross_validation import train_test_split
Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, test_size = 0.2)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
Xtrain = sc.fit_transform(Xtrain)
Xtest = sc.transform(Xtest)

# Applying PCA
from sklearn.decomposition import PCA
pca = PCA(n_components = 2)
Xtrain = pca.fit_transform(Xtrain)
Xtest = pca.transform(Xtest)
explained_variance = pca.explained_variance_ratio_

# Train Regression Model with PCA
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state = 0)
classifier.fit(Xtrain, ytrain)

# Predict Results from PCA Model
ypred = classifier.predict(Xtest)

# Create Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(ytest, ypred)

# Visual the Training results
from matplotlib.colors import ListedColormap
Xset, y_set = Xtrain, ytrain
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() – 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() – 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap((‘red’, ‘green’, ‘blue’)))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap((‘red’, ‘green’, ‘blue’))(i), label = j)
plt.title(‘Logistic Regression (Training set)’)
plt.xlabel(‘PC1’)
plt.ylabel(‘PC2’)
plt.legend()
plt.show()

# Visual the Test set results
from matplotlib.colors import ListedColormap
Xset, y_set = Xtest, ytest
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() – 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() – 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap((‘red’, ‘green’, ‘blue’)))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap((‘red’, ‘green’, ‘blue’))(i), label = j)
plt.title(‘Logistic Regression (Test set)’)
plt.xlabel(‘PC1’)
plt.ylabel(‘PC2’)
plt.legend()
plt.show()

Other Topics – Multivariate Analysis : 
Other Topics – Association Rule : 
Other Topics – Artifical Inteligent : 
  • Upper Confidence Bound
  • Thompson Sampling

Leave a Reply