Corporate Employee | Advanced Excel | Python for data Science | Power BI | Operations Manager

Rishabh Goyal  • Peerlist

<h2 class="rich-heading">Mobile Apps Playstore Data Analysis</h2>Why this analysis - This Data Analysis is for getting insights about the mobile apps w.r.t its future business approaches and development of mobile apps. This study has been summarised from the historical data available from the Google Play store from June 2012 till February 2019. It also helps to know the trend involved in the categories of mobile app availability, usability, and users' expectations.Some Basic Questions asked to the DataSet:Q1: - Which is the most used Android version?Q2: - Which all categories of mob apps are existing from this dataset?Q3: - Which is the most installed category of mob app from this dataset?Q4: - Which apps have got 5-star ratings?Q5: - Which are the top 10 mob apps based on ratings?

Mobile Apps Play Store Data Analysis

<h2 class="rich-heading">Analyzing E-Commerce Trends (Flipkart)</h2>●&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; What is the problem?The aim is to analyze the Flipkart sales dataset to understand customer preferences, product performance, and sales trends. The analysis will focus on identifying the most popular categories, brands, pricing strategies, and customer ratings.●&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Why is it important to solve it?Solving this problem will help Flipkart make data-driven decisions to improve product listings, pricing strategies, and customer satisfaction. The insights gained from this analysis could lead to increased sales, better customer retention, and improved overall business performance.Basic Questions asked to the DataSet:Q1. Which are the top 5 product categories based on the number of listings?Q2. Which are the top 5 brands with the most product listings?Q3. What is the average discount offered by Flipkart across all products?Q4. How many products have customer ratings?Q5. What percentage of products are part of the Flipkart Advantage program?Q6. Which are the top 3 most expensive products listed on Flipkart?Q7. Which brands have the highest average product rating?Q8. Which product category has the highest average retail price?Q9. Which products have the longest and shortest descriptions?Q10. In which month was the data mostly crawled?

Analyzing E-Commerce Trends (Flipkart)

<h3 class="rich-heading">Indian General Elections Data Analysis</h3>This project focuses on conducting Exploratory Data Analysis (EDA) using any analytical tool for the 2019 Indian General Elections dataset.The dataset encompasses comprehensive details about candidates who participated in the elections across different constituencies. It encompasses both personal attributes like assets, education, and criminal records, and electoral attributes like the constituency they contested from their affiliated political party, the total count of received votes, and more.Throughout the project, I leveraged a variety of analytical tools to cleanse the data and create insightful visualizations. The objective is to uncover patterns, trends, and relationships within the dataset to extract meaningful insights about the 2019 Indian General Elections.Some basic questions I tried asking my dataset:<ol><li>Which States/UTs and Constituencies had the highest and the lowest Voter Turnout?</li><li>How many elected MPs have a criminal record and what is their party-wise distribution?</li><li>What is the distribution of assets, liabilities, and net worth of the elected MPs?</li><li>What is the region-wise distribution of seats across the country?</li></ol>India = {'NORTH INDIA': ['Jammu &amp; Kashmir', 'Himachal Pradesh', 'Punjab', 'Haryana', 'Uttarakhand', 'NCT OF Delhi', 'Chandigarh'],&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'CENTRAL INDIA': ['Uttar Pradesh', 'Madhya Pradesh', 'Chhattisgarh'],&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'WEST INDIA': ["Gujarat", "Rajasthan", "Maharashtra", "Goa", "Dadra &amp; Nagar Haveli", "Daman &amp; Diu"],&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'SOUTH INDIA': ['Karnataka', 'Andhra Pradesh', 'Telangana', 'Kerala', 'Tamil Nadu', 'Puducherry', 'Lakshadweep'],&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'EAST INDIA': ["Bihar", "Jharkhand", "West Bengal", "Odisha", "Andaman &amp; Nicobar Islands"],&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'NORTH-EAST INDIA': ['Assam', 'Arunachal Pradesh', 'Manipur', 'Meghalaya', 'Mizoram', 'Nagaland', 'Sikkim', 'Tripura']}#These are the zone based divisions for the different states present in the dataset.

2019 Indian General Elections Data Analysis

<h2 class="rich-heading">Amazon Product Reviews</h2><ul><li>What is the problem?</li></ul>The online retail market is fiercely competitive. Understanding customer preferences, product performance, and market trends can help a retailer stay ahead. The problem here is to analyze the dataset to extract insights that can help in enhancing product visibility, improving customer satisfaction, and eventually, increasing sales.<ul><li>Why is it important to be solved?</li></ul>Solving this problem will not only help in increasing sales but will also enhance the customer's shopping experience. It can aid in personalized marketing, improving product placements, and optimizing the product portfolio, thereby leading to increased customer loyalty and higher profits.<ul><li>Data Dictionary</li></ul><ol><li>product_id: The unique identifier for each product.</li><li>product_name: The name of the product.</li><li>category: The category under which the product is listed, further divided into sub-categories separated by "|".</li><li>discounted_price: The price of the product after applying the discount.</li><li>actual_price: The original price of the product without any discount.</li><li>discount_percentage: The percentage of discount offered on the product.</li><li>rating: The average rating given to the product by the customers.</li><li>rating_count: The number of ratings the product received.</li><li>about_product: A brief description of the product.</li><li>user_id: The unique identifiers for users who reviewed the product, separated by commas.</li><li>user_name: The names of users who reviewed the product, separated by commas.</li><li>review_id: The unique identifiers for the reviews, separated by commas.</li><li>review_title: The titles of the reviews, separated by commas.</li><li>review_content: The content of the reviews, separated by commas.</li><li>img_link: The link to the image of the product.</li><li>product_link: The link to the product's page on Amazon.</li></ol>Some basic Analytics I tried performing on the dataset:Discount Analysis<ol><li>How does the discount percentage affect the rating of a product?</li></ol>Category Analysis<ol><li>Which category has the highest average rating?</li></ol>Price Analysis<ol><li>Is there a correlation between the product's price and its rating?</li></ol>Hint: Convert the price and rating columns to numerical data types and use the corr() function in pandas to find the correlation coefficient.Rating Analysis4. What is the distribution of ratings across all products?Hint: Use Matplotlib or seaborn to create a histogram of the ratings column to visualize the distribution.Product Analysis5. Which product has the highest number of reviews and what is its rating?Hint: Use the groupby function in pandas to group data by product ID and then use the idxmax function to find the product with the maximum number of reviews.User Analysis6. Identify the top 5 users who have given the most reviews?Hint: Use value_counts function in pandas on the user_id column to find the top 5 users with the most reviews.Review Length Analysis7. Is there a correlation between the length of a review and the rating given?Hint: Create a new column representing the length of each review using pandas and then find the correlation between this new column and the rating column using the corr() function.Image Analysis8. Does having an image link affect the product rating?Hint: Create a new column in the pandas dataframe to indicate whether a product has an image link. Then, analyze the average ratings for products with and without image links.Product Description Analysis9. Can the length of the product description be correlated to the product's rating?Hint: Create a new column for the length of the product description using pandas and then find its correlation with the rating column using the corr() function.

Amazon Product Reviews

<ul><li>What is the problem?</li></ul>Identifying the characteristics of successful Netflix original movies based on different attributes such as genre, runtime, IMDB score, and language.<ul><li>Why is it important to be solved?</li></ul>Understanding the features of successful movies can help Netflix in planning and producing more popular and well-received content, thereby attracting a larger audience and increasing its market share in the OTT platform industry.<ul><li>Data Dictionary</li></ul><ol><li>Title: String - The name of the Netflix original movie.</li><li>Genre: String - The category defining the thematic elements of the movie.</li><li>Premiere: Date - The release date of the movie on Netflix.</li><li>Runtime: Integer - The length of the movie in minutes.</li><li>IMDB Score: Float - The rating given to the movie on the IMDB platform.</li><li>Language: String - The language(s) in which the movie is available.</li></ol><h4 class="rich-heading">Some Basic questions I tried asking my dataset: </h4><h4 class="rich-heading">1. What is the average IMDB score for each genre?</h4><ol><li>Which genre has the highest average runtime?</li></ol><ol><li>Are longer movies rated higher on IMDB?</li></ol><ol><li>What is the distribution of movies across different languages?</li></ol><ol><li>What is the trend in the number of releases over the years?</li></ol><ol><li>Which year had the highest average IMDB score?</li></ol><ol><li>Are movies in certain languages rated higher on average?</li></ol><ol><li>What is the distribution of IMDB scores?</li></ol><ol><li>What is the most common genre on Netflix?</li></ol><ol><li>What is the average runtime of movies released in different months?</li></ol>

Success Code of Netflix Original Movies

Introduction: Heart attacks are a leading cause of premature mortality globally, with India witnessing over 3 million deaths annually due to heart attacks and strokes. Numerous factors can impact heart health and efficiency. By gaining valuable insights and taking necessary precautions, we can effectively manage the challenges and complications associated with cardiac health.Project Objective: In this study, I conducted a detailed analysis of medical reports from numerous heart patients. The goal was to perform exploratory analysis, uncover significant findings, and process the dataset for potential use in machine learning models. Ultimately, these models could aid in predicting the likelihood of heart attacks in new patients.By conducting this in-depth analysis, I hope to contribute to the advancement of medical knowledge, enhance patient care, and improve outcomes for individuals at risk of cardiac issues.Some basic questions I tried asking to my dataset:<ol><li>What age group is most vulnerable or has a large number of patients with a higher risk of heart attack?</li></ol><ol><li>Are men mostly prone to heart attacks or women?</li><li>What chest pain types pose a severe risk of a heart attack?</li><li>How fasting blood sugar is related to heart attack?</li><li>What type of thalassemia severely leads to heart attack?</li><li>Due to cholesterol, how many patients are at higher risk?</li></ol>Data Dictionary:1. age (#)2. sex : 1= Male, 0= Female (Binary)3. (cp)chest pain type (4 values -Ordinal):Value 1: typical angina ,Value 2: atypical angina, Value 3: non-anginal pain , Value 4: asymptomatic4. (trestbps) resting blood pressure (#)5. (chol) serum cholesterol in mg/dl (#)6. (fbs)fasting blood sugar &gt; 120 mg/dl(Binary)(1 = true; 0 = false)7. (restecg) resting electrocardiography results(values 0,1,2)8. (thalach) maximum heart rate achieved (#)9. (exang) exercise induced angina (binary) (1 = yes; 0 = no)10. (oldpeak) = ST depression induced by exercise relative to rest (#)11. (slope) of the peak exercise ST segment (Ordinal) (Value 1: up sloping , Value 2: flat , Value 3: down sloping )12. (ca) number of major vessels (0–3, Ordinal) colored by fluoroscopy13. (thal) maximum heart rate achieved — (Ordinal): 3 = normal; 6 = fixed defect; 7 = reversible defect

Cardiac Patients Medical Report Analysis

This project contains the data record of all types of crime against women in India in the span of years 2001-2014. The main aim of working on this project is to reflect on the situation of women in our society and raise concern about this matter.Some basic questions I tried asking to my dataset:<ol><li>Create a Dataset containing the 10 highest reported rape cases in India, in the span of years 2001-2014.</li><li>Create a Dataset containing the 10 highest reported deaths caused by Dowry cases in India, in the span of years 2001-2014.</li><li>Create a dataset containing the 10 highest reported Domestic violence cases in India, in the span of years 2001-2014.</li><li>Create a Dataset containing the 10 highest reported Importation cases in India, in the span of years 2001-2014.</li><li>Find out the total number of cases, in the span of 2001-2014 under each category, state-wise.</li><li>Find out the top 5 states, where the maximum number of cases has been reported in TOTAL in the span of 2001-2014, each category-wise.</li></ol><ul><li>For the "Rape" case&nbsp;</li><li>For Kidnapping and abduction case&nbsp;</li><li>For cases of deaths due to dowry&nbsp;</li><li>For Domestic Violence case&nbsp;</li><li>For the Importation of Girls case</li></ul><ol><li>Which state has featured in both the lists of "Maximum number of rape cases" and "Maximum number of Importation cases".</li><li>Which state has featured in both the lists of "Maximum number of rape cases" and "Maximum number of Deaths due to Dowry cases".</li></ol>

Crime Against Women 2001-2014 (India)

The dataset used contains a list of video games with sales greater than 100,000 copies globally.Some basic insights generated from the analysis:<ol><li>A total of 16598 games were launched between the years 1980 to 2020 (counting launch on each platform separately).If we ignore the platform of the game, the total number of games launched in the same year are 11493.</li><li>These games were launched on a total of 31 platforms.The platforms with most launched games comprises of DS, PS2/3,Wii,X360 etc.</li></ol>In the years 2007-9, DS was the platform with most launched games, increasing each year, 377,405,492 for respective years.<ol><li>The year 2009 had the highest number of game launches. (1431 games)Wii Sports Resort was the highest selling game globally at 33 units.</li><li>Electronic Arts had published most number of games, followed by Activision &amp; Namco Bandai Games (1351,975,932 game launches respectively)Platform wise, Sony Computer Entertainment had most published games, followed by Electronic Arts and Ubisoft on PS2/PS, PS2, DS respectively.</li><li>Talking about Genre, Action genre games were most launched in this duration, followed by Sports &amp; Misc (3316,2346,1739 launches respectively).It can be seen that Strategy &amp; Puzzle genre games were least launched ones being 681 &amp; 582 respectively.</li><li>Talking about the most sold ones,Wii Sports is the most sold game in the regions NA,EU and Globally. Grand Theft Auto: San Andreas is most sold game in other different regions. Pokemon Red/Pokemon Blue is the most sold game in JP region.</li></ol>

Video Game Sales

DailyUber provides the 2016 data. By using this data find out the demand and supply Analysis gap of the cab. The main objective of this project is to analyze the data on Uber Request data.Some basic questions I tried asking my dataset: <ol><li>Which date had the most completed trips during the two weeks?</li></ol><ol><li>What was the highest number of completed trips within a 24-hour period?</li></ol><ol><li>Which hour of the day had the most requests during the two-week period?</li><li>What percentages of all zeroes during the two week period occurred on weekends (Friday at 5 pm to Sunday at 3 am)?&nbsp;</li></ol><ol><li>What is the weighted average ratio of completed trips per driver during the two week period?</li></ol><ol><li>In drafting a driver schedule in terms of 8 hour shifts, when are the busiest 8 consecutive hours over the two week period in terms of unique requests? A new shift starts every 8 hours. Assume that a driver will work the same shift each day.</li><li>True or False: Driver supply always increases when demand increases during the two week period.&nbsp;</li></ol><ol><li>In which 72 hour period is the ratio of Zeroes to Eyeballs the highest?</li><li>If you could add 5 drivers to any single hour of every day during the two week period, which hour should you add them to?</li></ol><ol><li>True or False: There is exactly two weeks of data in this analysis.</li></ol>Some Dataset Terminology: <ul><li>App Openings (Eyeballs) = Customers who launch the app looking for riders. It is a good measure of demand</li><li>Zeroes = Customers who open the app and see no cars in the area.&nbsp;</li><li>Request = Customers who make requests for a car.&nbsp;</li></ul>

Uber - City Insights

A year's worth of sales from a fictitious pizza place, including the date and time of each order and the pizzas, served, with additional details on the type, size, quantity, price, and ingredients.Below are some basic questions I tried asking to my dataset:<ol><li>How many customers do we have each day? Are there any peak hours?</li><li>How many pizzas are typically in order? Do we have any bestsellers?</li><li>How much money did we make this year? Can we identify any seasonality in the sales?</li><li>Are there any pizzas we should take off the menu, or any promotions we could leverage?</li></ol>

Pizza Place Sales

Crowdsourced parental leave data from 1,601 companies across different industries, including paid/unpaid maternity and paternity leave weeks.Some basic questions I tried asking to my dataset:<ol><li>Which companies offer the most paid parental leave weeks?</li><li>Is maternity leave typically longer than paternity leave?</li><li>What is the distribution of parental leave weeks offered?</li><li>Are there noticeable differences between industries?</li></ol>

Parental Leave Policies

Marketing campaign data of 2,240 customers of Maven Marketing, including customer profiles, product preferences, campaign successes/failures, and channel performance.Some basic questions I tried asking my dataset:<ol><li>Are there any null values or outliers? How will you handle them?</li><li>What factors are significantly related to the number of web purchases?</li><li>Which marketing campaign was the most successful?</li><li>What does the average customer look like?</li><li>Which products are performing best?</li><li>Which channels are underperforming?</li></ol>

Marketing Campaign Results

The dataset taken comprises of Daily weather conditions in Madrid from 1997-2015, including max/min/mean temperature, dew point, humidity, visibility, and wind speed, along with precipitation events, cloud cover, and wind direction.Some Analysis questions on behalf of which I've played around with the dataset:<ol><li>During the period in this sample, what % of days had some sort of precipitation event? What % were clear?&nbsp;</li><li>Suppose you're planning a vacation to Madrid and hoping for the warmest temperature. Which month might you plan to travel?</li><li>On which date in the sample did Madrid see the fastest wind gust? What was the weather like on that day?</li><li>How does the average visibility (Km) compare for clear days vs. foggy days?</li></ol>

Madrid Daily Weather 1997-2015

The dataset taken contains information about each company on the INC 5000 list in 2019. Fields include the company name, industry, founding year, website, and location, as well as 2019 revenue, % growth, number of workers (year-over-year), and the number of years on the list.Some basic questions I tried asking my dataset:<ol><li>What's the average revenue among companies on the list? Broken down by industry?</li><li>Which industries are most and least represented in the list?</li><li>Do you notice any interesting geographic trends?</li></ol><ol><li>Which industries saw the largest average growth rate?</li><li>Which companies had the largest increase in staff/new hires? (Top/Bottom 5)</li></ol><ol><li>Did any companies increase revenue while reducing staff?</li><li>Top 1000 - Winner State&nbsp;(Mostly occuring in Top 1000 Companies List)</li></ol><ol><li>Do we have any company which was founded last year and Ranked under Top 100?</li></ol>