Python and Deep Learning: Special Topics

Rajeshwari Sai Aishwarya Puppala

Student ID: 16298162

Class ID: 35

In class programming: 6

Objectives:

1.Apply K means clustering in this data set provided below:

https://umkc.box.com/s/a9lzu9qoqfkbhjwk5nz9m6dyybhl1wqy

Remove any null values by the mean. Use the elbow method to find a good number of clusters with the KMeans algorithm

Calculate the silhouette score for the above clustering

Apply PCA on the same dataset.

Clustering

• Import the required libraries like seaborn, pandas, matplotlib, kmeans, pathlib
• Load the data set into a data frame with the help of path lib.
• For better information print the tenure counts
• Now find the null counts in the data set.
• After printing the null counts we will get to know that Minimum_Payments and Credit_limit have the null value.
• Replace it with the mean of the respective feature.
• Divide the data set into train and test.
• Now with the elbow method, we will find the optimal number of cluster
• As you can see the plot, 3 is the optimal number of clusters.
• Now calculate the silhouette_score for 3 clusters by doing KMeans for 3 clusters.
• Apply the Standardization and apply PCA for the results obtained from standardization.
• For the results obtained from PCA, check if the score is improving or not.

Source Code

Output

Elbow Plot

Null counts and Silhouette_score before sandardization

After PCA and Silhouette_score after sandardization