Greetings , fellow analysts !

(NOTE : This is a random dataset generated using python. It bears no resemblance to any real entity in the corporate world. Any resemblance is a matter of coincidence.)

REC-SSEC Bank is a govt-aided bank operating in the Indian Peninsula. They have regional branches in over 40+ regions of the country. You have been provided with a massive excel sheet containing the transaction details, the total transaction amount and their location and total transaction count.

The dataset is described as follows :

1. Date - The date on which the transaction took place. 2.Domain - Where or which type of Business entity made the transaction. 3.Location - Where the data is collected from 4.Value - Total value of transaction
2. Count of transaction .

For example , in the very first row , the data can be read as : " On the first of January, 2022 , 1932 transactions of summing upto INR 365554 from Bhuj were reported " NOTE : There are about 2750 transactions every single day. All of this has been given to you.

The bank wants you to answer the following questions :

1. What is the average transaction value everyday for each domain over the year.
2. What is the average transaction value for every city/location over the year
3. The bank CEO , Mr: Hariharan , wants to promote the ease of transaction for the highest active domain. If the domains could be sorted into a priority, what would be the priority list ?
4. What's the average transaction count for each city ?

Accident-Detection-Model

Accident Detection Model is made using YOLOv8, Google Collab, Python, Roboflow, Deep Learning, OpenCV, Machine Learning, Artificial Intelligence. It can detect an accident on any accident by live camera, image or video provided. This model is trained on a dataset of 3200+ images, These images were annotated on roboflow.

Problem Statement

• Road accidents are a major problem in India, with thousands of people losing their lives and many more suffering serious injuries every year.
• According to the Ministry of Road Transport and Highways, India witnessed around 4.5 lakh road accidents in 2019, which resulted in the deaths of more than 1.5 lakh people.
• The age range that is most severely hit by road accidents is 18 to 45 years old, which accounts for almost 67 percent of all accidental deaths.

Accidents survey

https://user-images.githubusercontent.com/78155393/233774342-287492bb-26c1-4acf-bc2c-9462e97a03ca.png" alt="Survey">

Literature Survey

• Sreyan Ghosh in Mar-2019, The goal is to develop a system using deep learning convolutional neural network that has been trained to identify video frames as accident or non-accident.
• Deeksha Gour Sep-2019, uses computer vision technology, neural networks, deep learning, and various approaches and algorithms to detect objects.

Research Gap

• Lack of real-world data - We trained model for more then 3200 images.
• Large interpretability time and space needed - Using google collab to reduce interpretability time and space required.
• Outdated Versions of previous works - We aer using Latest version of Yolo v8.

Proposed methodology

• We are using Yolov8 to train our custom dataset which has been 3200+ images, collected from different platforms.
• This model after training with 25 iterations and is ready to detect an accident with a significant probability.

Model Set-up

Preparing Custom dataset

• We have collected 1200+ images from different sources like YouTube, Google images, Kaggle.com etc.
• Then we annotated all of them individually on a tool called roboflow.
• During Annotation we marked the images with no accident as NULL and we drew a box on the site of accident on the images having an accident
• Then we divided the data set into train, val, test in the ratio of 8:1:1
• At the final step we downloaded the dataset in yolov8 format.
  #### Using Google Collab
• We are using google colaboratory to code this model because google collab uses gpu which is faster than local environments.
• You can use Jupyter notebooks, which let you blend code, text, and visualisations in a single document, to write and run Python code using Google Colab.
• Users can run individual code cells in Jupyter Notebooks and quickly view the results, which is helpful for experimenting and debugging. Additionally, they enable the development of visualisations that make use of well-known frameworks like Matplotlib, Seaborn, and Plotly.
• In Google collab, First of all we Changed runtime from TPU to GPU.
• We cross checked it by running command ‘!nvidia-smi’
  #### Coding
• First of all, We installed Yolov8 by the command ‘!pip install ultralytics==8.0.20’
• Further we checked about Yolov8 by the command ‘from ultralytics import YOLO from IPython.display import display, Image’
• Then we connected and mounted our google drive account by the code ‘from google.colab import drive drive.mount('/content/drive')’
• Then we ran our main command to run the training process ‘%cd /content/drive/MyDrive/Accident Detection model !yolo task=detect mode=train model=yolov8s.pt data= data.yaml epochs=1 imgsz=640 plots=True’
• After the training we ran command to test and validate our model ‘!yolo task=detect mode=val model=runs/detect/train/weights/best.pt data=data.yaml’ ‘!yolo task=detect mode=predict model=runs/detect/train/weights/best.pt conf=0.25 source=data/test/images’
• Further to get result from any video or image we ran this command ‘!yolo task=detect mode=predict model=runs/detect/train/weights/best.pt source="/content/drive/MyDrive/Accident-Detection-model/data/testing1.jpg/mp4"’
• The results are stored in the runs/detect/predict folder.
  Hence our model is trained, validated and tested to be able to detect accidents on any video or image.

Challenges I ran into

I majorly ran into 3 problems while making this model

• I got difficulty while saving the results in a folder, as yolov8 is latest version so it is still underdevelopment. so i then read some blogs, referred to stackoverflow then i got to know that we need to writ an extra command in new v8 that ''save=true'' This made me save my results in a folder.
• I was facing problem on cvat website because i was not sure what

India Condom Market Deep Dive

This dataset is a treasure trove of data, packed with 50,000 rows of juicy insights about India’s booming condom market. It includes everything you need to know—trends, market shares, product types, distribution channels, and even which brands are launching exciting campaigns to spice things up. Whether you’re an analyst, a marketer, or just a curious soul wondering how 1.22 lakh condom packs were delivered in a single day (thanks, Blinkit), this dataset has got you covered! 🕺🎉

From late-night New Year’s Eve preparations to strategic corporate moves like Godrej buying Kamasutra (who knew boardroom deals could be so spicy?), this dataset unrolls all the action. Dive in and discover how latex is leading the way or why some people prefer non-latex (allergic? Fancy? Who knows).

Highlights of the Dataset

Yearly Data: Tracks market trends from 2018 to 2030, showing how things are “expanding” year by year.

Market Size: See how India is gearing up to hit USD 1.8 billion in revenue by 2030. That’s a lot of demand!

Material & Product Segmentation: Latex vs. Non-latex. Male vs. Female condoms. The battle of preferences!

Brands & Market Shares: Curious if Manforce or Durex dominates? Check it out here!

Campaign Insights: Who’s running the loudest campaigns and what’s working (hint: it’s not just size but also flavor).

Regional Growth: Which Indian region is "most active"? Find out who’s contributing to all those sales.

Tasks to Explore the Dataset

Find the Party Regions 🎉

Look for regions with the highest growth rates and market penetration. These areas are clearly gearing up for the afterparties. Maybe Blinkit can expand there next New Year’s Eve? Who’s the Real MVP? 🏆

Analyze market shares by brand to figure out if Manforce, Durex, or Kamasutra is taking the crown. Bonus: Check how the New Year condom trend impacted these brands! Latex or Non-Latex? 🤔

Find out if people prefer latex or non-latex condoms. Is it for comfort, allergies, or something mysterious? The data might surprise you.

Track the Trends 📈

How has the market grown since 2018? Use the CAGR column to see which years were particularly productive. Campaigns That Worked 💡

Look at the Event Name and Details columns to identify which campaigns or product launches had the biggest impact. Did “India’s thinnest flavored condom” actually create buzz?

Blinkit Bonanza 🚚

Analyze e-commerce sales and figure out how Blinkit managed to deliver 1.22 lakh condom packs on New Year’s Eve. That’s logistics on fire!

Regional Rivalry 🗺️

Compare regions (North, South, East, West, Central) and find out which is leading the charge. Who’s having the most fun, statistically speaking?

Fun Fact

Blinkit’s CEO Albinder Dhindsa revealed that they delivered 1.22 lakh condom packs on 31st December 2024. That’s a serious level of preparation for New Year’s afterparties! Makes you wonder, is there a "condom marathon" happening somewhere? 🏃‍♂️💨

What Makes This Dataset Fun to Explore?

It’s not just data—it’s a window into India’s modern-day trends, preferences, and behaviors. Whether you're mapping out serious market strategies or giggling over regional rivalries, there’s something for everyone here. So go ahead, dig in, and have some protected fun with the numbers! 😄

Ramayan, also known as Ramanand Sagar's Ramayan, is an iconic Indian Hindi-language epic television series that originally aired on DD National between 1987 and 1988. Created, written, and directed by Ramanand Sagar, the series is based on the ancient Indian Sanskrit epic, the Ramayana. The show was narrated by the legendary Ashok Kumar and Ramanand Sagar himself, with music composed by Ravindra Jain.

During its initial run, Ramayan became the most-watched television series in the world, boasting an incredible 82% viewership. Its success extended far beyond India, with repeat broadcasts aired on 20 different channels across 17 countries on all five continents. According to the BBC, the series has been viewed by over 650 million people globally. Each episode earned DD National a revenue of ₹40 lakh, making it a highly profitable production.

The series primarily draws from Valmiki's Ramayan and Tulsidas' Ramcharitmanas, while also incorporating elements from various regional versions of the Ramayan, including Tamil, Marathi, Bengali, Telugu, Kannada, Malayalam, and Urdu adaptations. With a budget of ₹9 lakhs per episode, it was the most expensive TV show produced in India at the time.

The cultural impact of Ramayan was profound. On Sundays, when the series was aired, streets would empty, shops would close, and people would perform rituals such as bathing and garlanding their television sets in reverence before the show began. The series was re-aired during the 2020 coronavirus lockdown, where it once again captured global attention, setting a new record with 77 million viewers on 16 April 2020, making it the most-watched TV show in the world at that time.

Dataset Summary:

Show Title: Ramayan (Ramanand Sagar's Ramayan)

Language: Hindi

Genre: Epic, Mythological, Television Series

Country: India

Original Air Dates: 1987-1988

Channel: DD National

Creator, Writer, Director: Ramanand Sagar

Narrators: Ashok Kumar, Ramanand Sagar

Music Composer: Ravindra Jain

Viewership:

82% viewership during the original run

Over 650 million viewers globally

Record-breaking 77 million viewers on 16 April 2020 during the re-airing in 2020

Budget: ₹9 lakhs per episode

Revenue per Episode: ₹40 lakh earned by DD National

Global Reach: Aired in 17 countries across 20 channels

Source Material:

Primary Sources: Valmiki's Ramayan, Tulsidas' Ramcharitmanas

Other Sources: Tamil Kamb Ramayan, Marathi Bhavarath Ramayan, Bengali Krutivas Ramayan, Telugu Shri Rangnath Ramayan, Kannada Ramchandra Charit Puranam, Malayalam Adhyatma Ramayan, Urdu Ramayan by Chakbast.

Cultural Impact:

Streets would be deserted and shops closed during airing.

People would bathe and garland their TV sets before watching.

Re-airing Impact: Broke several viewership records during the 2020 lockdown.

Data Statistics:

Total Unique Values: 78 episodes Unique Rating Categories: 10 Total Data Coverage: Episodes aired from January 25, 1987, to July 31, 1988 Percentage of Data Available: 96% of episodes have summaries. Example Summary: "The saga of Ramayan Gods' Prayers to Lord Vishnu King Dashrath's yagna invoking blessings for a son Birth and childhood of Shri Ram."