List

# K-Means Clustering

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

# Importing the dataset
dataset = pd.read_csv(‘Mall_Customers.csv’)
X = dataset.iloc[:, [3, 4]].values
# y = dataset.iloc[:, 3].values

# 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)”””

# Using the elbow method to find the optimal number of clusters
from sklearn.cluster import KMeans
wcss = []
for i in range(1, 11):
kmeans = KMeans(n_clusters = i, init = ‘k-means++’, random_state = 42)
kmeans.fit(X)
wcss.append(kmeans.inertia_)
plt.plot(range(1, 11), wcss)
plt.title(‘The Elbow Method’)
plt.xlabel(‘Number of clusters’)
plt.ylabel(‘WCSS’)
plt.show()

# Fitting K-Means to the dataset
kmeans = KMeans(n_clusters = 5, init = ‘k-means++’, random_state = 42)
y_kmeans = kmeans.fit_predict(X)

# Visualising the clusters
plt.scatter(X[y_kmeans == 0, 0], X[y_kmeans == 0, 1], s = 100, c = ‘red’, label = ‘Cluster 1’)
plt.scatter(X[y_kmeans == 1, 0], X[y_kmeans == 1, 1], s = 100, c = ‘blue’, label = ‘Cluster 2’)
plt.scatter(X[y_kmeans == 2, 0], X[y_kmeans == 2, 1], s = 100, c = ‘green’, label = ‘Cluster 3’)
plt.scatter(X[y_kmeans == 3, 0], X[y_kmeans == 3, 1], s = 100, c = ‘cyan’, label = ‘Cluster 4’)
plt.scatter(X[y_kmeans == 4, 0], X[y_kmeans == 4, 1], s = 100, c = ‘magenta’, label = ‘Cluster 5’)
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s = 300, c = ‘yellow’, label = ‘Centroids’)
plt.title(‘Clusters of customers’)
plt.xlabel(‘Annual Income (k$)’)
plt.ylabel(‘Spending Score (1-100)’)
plt.legend()
plt.show()

Leave a Reply

Your email address will not be published. Required fields are marked *

  Posts

1 2
April 10th, 2018

Data Preprocessing

The process of converting data from initial or raw state to another format. Importing data Import the data: df = […]

April 22nd, 2018

K means

# K-Means Clustering # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd # […]

April 21st, 2018

Random Forest

# Random Forest Classification # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd […]

April 21st, 2018

Decision Tree

# Decision Tree Classification # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd […]

April 21st, 2018

Naive Bayes

# Naive Bayes # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd # […]

April 21st, 2018

Kernal SVM

# Kernel SVM # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd # […]

April 21st, 2018

SVM

# Support Vector Machine (SVM) # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as […]

April 20th, 2018

Logistic Regression

# Logistic Regression # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd # […]

April 19th, 2018

Random Forest Regression

# Random Forest Regression # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd […]

April 19th, 2018

Decision Tree Regression

# Decision Tree Regression # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd […]

April 19th, 2018

SVR

# SVR # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd # Importing […]