HDP Analyst Data Science Training

The training provides practice of Data science covering machine learning and other natural language processed. Other tools covered are programming and tools languages such as Mathout, Pig, NumPY, Natural Language Toolkit, pandas, Spark MLlib and SciPy.

Contact us to customize this class with your preferred dates, times and location.
You can call us on 1-800-961-0337 or Chat with our representative.

• Identifying the cases for data science.
• Describing about YARN architecture and Hadoop.
• Describing unsupervised and supervised learning differences.
• Utilizing Mahout to execute a ML algorithm on Hadoop.
• Describing the lifecycle of data science.
• Utilizing Pig to prepare and transform data on Hadoop.
• Writing Python script.
• Describing about the options for running Python code.
• Writing Pig User-Defined functionalities in Python.
• Utilizing Pig streaming with Python script on Hadoop.
• Utilizing ML algorithms.
• Describing the utilizing cases for NLP.
• Utilizing the NLTK.
• Writing about Spark application in Python.
• Running ML algorithms by utilizing Spark MLlib.

This training is intended for software developers and architects. However, the primary audience for this training are data scientists and analysts who want to apply machine learning and data science on Hadoop.

It is suggested to have basic knowledge in at least one programming language. However, you must have knowledge in statistics/mathematics and fundamental basic knowledge of Hadoop principles and big data.

• 1. An Introduction to Data Science, Python, Hadoop and Machine Learning
• Define Data Science and Explain What a Data Scientist Does
• Differentiate Between Different Types of Data Roles
• List a Number of Data Science Use Cases
• Present an Overview of Python
• Describe the Components of the Big Data Scientific Stack

LABS

• Using IPython
• Data Analysis with Python
• Using HDFS Commands
• Introduction to Spark REPLs and Zeppelin
• Using Apache Mahout for Machine Learning
View Less    View More   
2. Working with Spark RDDs, DataFrames and SparkSQL, Visualization in Zeppelin
Explain What an RDD Is
Explain How RDDs are Partitioned
Create Manipulate and Restore RDDs
Use Spark SQL to Create Tables
Create an Application and Submit to the Cluster
LABS
Create and Manipulate RDDs
Create and Save DataFrames
Build and Submit Spark Applications
3. Machine Learning Algorithms, Natural Language Processing, and Spark MLlib
Describe Common Machine Learning Applications
List the Pros and Cons of Various Algorithms
Explain what Natural Language Processing is
Explain the Feature Engineering Capabilities of Spark MLlib
LABS
Use the Python Natural Language Toolkit (NLTK)
Classify text using Naïve Bayes
Compute K-nearest neighbors
Creating a Spam Classifier with MLlib
Sentiment Analysis with Spark MLlib
4.