Predicting Product Ratings From Reviews
This is a classic NLP problem dealing with data from an e-commerce store focusing on women’s clothing. Each record in the dataset is a customer review which consists of the review title, text description and a rating (ranging from 1 – 5) for a product amongst other features
We convert this into a binary classification problem such that a customer recommends a product (label 1) is the rating is > 3 else they do not recommend the product (label 0)
Main Objective:
Leverage the review text attributes to predict the recommendation rating (classification)
Real Time Insights From Social Media Data
While we might not be Twitter fans, we have to admit that it has a huge influence on the world (who doesn’t know about Trump’s tweets). Twitter data is not only gold in terms of insights, but Twitter-storms are available for analysis in near real-time. This means we can learn about the big waves of thoughts and moods around the world as they arise.
Twitter provides both global and local trends. Let’s load and inspect data for topics that were hot worldwide (WW) and in the United States (US) at the moment of query — snapshot of JSON response from the call to Twitter’s GET trends/place API.
Optimizing Online Sports Retail Revenue
Sports clothing is a booming sector!
The project involves
-
Using SQL skills to analyze product data for an online sports retail company.
-
Working with numeric, string, and timestamp data on pricing and revenue, ratings, reviews, descriptions, and website traffic.
-
Techniques such as aggregation, cleaning, labeling, Common Table Expressions, and correlation to produce recommendations on how the company can maximize revenue!
The Android App Market on Google Play
You work as a Data Analyst for a finance company which is closely eyeing the Android market before it launches its new app into Google Play. You have been asked to present an analysis of Google Play apps so that the team gets a comprehensive overview of different categories of apps, their ratings, and other metrics.
Your three questions are as follows:
-
Read the apps.csv file and clean the Installs column to convert it into integer data type. Save your answer as a DataFrame apps. Going forward, you will do all your analysis on the apps DataFrame.
-
Find the number of apps in each category, the average price, and the average rating. Save your answer as a DataFrame app_category_info. Your should rename the four columns as: Category, Number of apps, Average price, Average rating.
-
Find the top 10 free FINANCE apps having the highest average sentiment score. Save your answer as a DataFrame top_10_user_feedback. Your answer should have exactly 10 rows and two columns named: App and Sentiment Score, where the average Sentiment Score is sorted from highest to lowest.
World Weather Analysis
Plan my trip is a top travel technology company that specializes in internet related services in the hotel and lodging industry. Jack is the head of analysis for the user interface team. We are tasked to export the data, clean it and use the weather data to choose the best cities for a vacation based on certain weather criteria. And then map these cities using jupiter G maps and google places API At the most fundamental level, Jack needs help answering a question: How might we provide real-time suggestions for our client’s ideal hotels? Your first task was to define what you meant by “ideal.” So, over the course of the conversation, you narrowed that to hotels that were
- within a given range of latitude and longitude and that
- provided the right kind of weather for the client.
Surfs Up
While on vacation in Hawaii last year, you discovered a newfound passion for surfing. You’ve been trying to come up with a plan that will let you not just return to hawaii but live there forever. You finally come up with an idea that you think is foolproof
A Surf n’ Shake shop serving surfboards and ice cream to locals, tourists, and of course yourself. You have some savings you’re willing to invest, but we’ll need some real investor backing to get this off the ground. So after putting together a strong business plan, you reach out to an investor W. Avy who is famous for his love for surfing. Your first meeting with him goes extremely well but he has one concern. What about the weather He has tasked you to run some analytics on a weather dataset he has from the very island you like to open your own shop: The beautiful Oahu.
Retail Strategy Analytics
The Category Manager for Chips at Quantium, wants to better understand the types of customers who purchase Chips and their purchasing behaviour within the region. The insights from your analysis will feed into the supermarket’s strategic plan for the chip category in the next half year.
Analyzing Unicorn Companies
Which industries are booming? Where should your next investment be? With the rise of the ‘amateur investor’ and the availability of platforms enabling people to invest and sell stock in public companies, it’s never been a better time to understand the financial performance of companies across the globe!
Using a PostgreSQL database you’ll be able to analyze information about unicorn companies worth over $1 billion! You’ll find out which industries have the highest average valuation and then zoom in on these to determine how many new unicorns have been produced annually between 2019 and 2021!