{ "fetched_at": "2026-10-20T06:22:26Z", "source_url": "https://www.kaggle.com/competitions/gdsc-aiml-member-recruitments/data", "pages": [ { "name": "data-description", "content": "# OVERVIEW\nThis dataset contains environmental data collected from NASA’s data access viewer. It consists of weekly meteorology and solar data collected from a city from January 1982 to December 2022.\n\nThe data is split into two groups:\n\n- Training set (train.csv)\n- Test set (test.csv)\nThe training set should be used to build your machine learning models. For the training set, we provide the values for each feature and the output variables (T2M, QV2M and VACATION_RATE). You are free to perform any kind of data preprocessing, feature selection, and apply relevant algorithms to train and improve your model’s performance.\n\nThe test set should be used to evaluate your model's performance on unseen data. For the test set, we do not provide the values for the target variables. It is your job to forecast these values.\nHowever, you are required to submit only the forecasted values for VACATION_RATE.\nNote:\nPlease note that the column ID is an encoding for week numbers. It starts at week 0 (encoded for the first week of January 1982) and continues.\nThe VACATION_RATE is a floating point value between 1 and 100. The sample submission shows VACATION_RATE as an integer just to act as an easy reference\nIn your submission.csv file you should have 2 columns ID (700 values from 1440 to 2139) and VACATION_RATE only. You can see this clearly in the sample_solution.csv\n\n## Files\n- train.csv - the training set\n- test.csv - the test set\n- sample_solution.csv - a sample submission file in the correct format\n\n# DATA DICTIONARY\n| **Variable** | **Definition** | **Explanation** |\n|---------------|---------------------------------------------------------|-------------------------------------------------------------------------------------------------|\n| T2M | Temperature at 2 Metres (°C) | Target Variable #1 |\n| QV2M | Specific Humidity at 2 Meters (g/kg) | Target Variable #2 |\n| WS10M | Wind Speed at 10 Meters (m/s) | |\n| PS | Surface Pressure (kPa) | |\n| T2M_MAX | Maximum temperature at 2 metres above ground level (°C) | |\n| T2M_MIN | Minimum temperature at 2 metres above ground level (°C) | |\n| T2M_RANGE | Temperature range at 2 metres above ground level (°C) | This is the difference between the maximum and minimum temperatures over a given period of time |\n| RH2M | Relative Humidity at 2 Meters (%) | |\n| VACATION_RATE | VACATION_RATE | Target Variable #3. It is affected by all the other features in the dataset |", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "# Evaluation Metric\nThe evaluation metric that will be used to test the goodness predictions is RMSE or Root Mean Squared Error. It is given by the formula:\n$$RMSE = \\sqrt{\\frac{1}{n}\\sum_{i=1}^n(actual - predicted)^2}$$\n\n## Submission File\nRefer to sample_submission.csv in the Data tab for the format of the submission file.\nFor each ID in the test set, you must predict a probability for the TARGET variable. The file should contain a header and have the following format:\n```\nID,VACATION_RATE\n1440,97\n1441,89\n1442,16\n1443,36\n1444,50\n1445,26\n1446,100\n1447,4\n1448,29\n1449,49\n1450,28\n1451,91\netc.\n```", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "# ENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES.\n\n## TEAMS\nFormation of teams is **prohibited** in this competition as it is an individual assessment.\n\n## Submission Limits\nYou are limited to a maximum of **20** submissions per day. The best submission before the deadline will be considered as the final one and will be evaluated.\n\n## Competition Timeline\nStart Date: August 30, 2023 7:30 PM\nEnd Date: September 1, 2023 7:30 PM\n\n## Data Access & Use\nThe dataset created is by our team and **not open to public use.**\n\n## Submissions\n- The output file has to be named as *submission.csv*. Kaggle **DOES NOT** accept any other format of submission filenames.\n- Please make sure that the metadata of submission file matches that of the sample submission file (cross-check the number of rows, attributes, and their data types) before submitting. Kaggle does not allow submissions that are invalid and you will not be scored.\n- You are allowed to make multiple submissions, the one with the best predictions will be used for scoring.\n- Once the deadline has passed, the competition is automatically closed, and no further submissions will be accepted.\n- All submissions must be done via Kaggle. Emails with notebooks attached will not be accepted.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "abstract", "content": "# Welcome to the first round of AI/ML Recruitments into GDSC!\n**P.S. MAKE SURE TO READ THIS DOCUMENT COMPLETELY**\nWelcome to the Googoda.com, the Travel Booking Company, where we aim to help you plan the perfect vacation. As a data scientist in our team, you are tasked with predicting the vacation rate for popular tourist destinations across the globe.\n\nThe vacation rate is an essential metric for us as it helps us determine which destinations to promote during specific times of the year. We believe that the vacation rate is dependent on various factors, such as temperature, humidity, and surface pressure.\n\nTo help our customers plan their dream vacations, we need to predict the vacation rate accurately. We have collected historical data from a popular tourist destination, and we need your expertise to create a predictive model that can forecast the vacation rate with high accuracy.\n\nYour task is to analyze the provided dataset and use machine learning techniques to predict the vacation rate for the based on temperature, humidity, and surface pressure. You will need to preprocess the data, perform feature engineering, and select an appropriate machine learning algorithm to build a predictive model.\n\nTo test the accuracy of your model, we will provide a test dataset with unseen data. The model's performance will be evaluated based on the Root Mean Squared Error (RMSE) between the predicted and actual vacation rates.\n\nWe believe that your analysis and predictive model can help us provide more accurate and personalized vacation recommendations for our customers. So, get ready to pack your bags and explore the world of data science with us!\n\nThis Kaggle competition challenges participants to use the POWER NASA Temperature Dataset to develop accurate forecasting models. The dataset provides historical Weather readings from various locations around the world, and participants must build models that can predict future temperatures at these locations based on past readings.\n\n# How to join\nTo enter the competition, participants must first accept the Competition Rules and gain access to the dataset. They can then download the data and begin building models locally or on Kaggle Notebooks. Once they have generated a prediction file, they can upload it as a submission along with the notebook on Kaggle and receive an accuracy score with a position on the public leaderboard.\n\n# Scoreboard\nThe public leaderboard is calculated based on the RMSE score of the model created and how well it performs on the given test dataset. This allows participants to see how their models rank against those of other Kagglers.\n\n# Submission format\nParticipants are required to submit the following:\n\nCSV file containing the ID and VACATION_RATE.\nNotebook containing EDA and training with reasonings and additional comments **via a google form that will be shared before the end of the competition**\n**P.S. This section is important because you will be judged based on your reasoning ability for the choice of model, data pre-processing etc. so feel free to add markdown cells explaining your steps!**\n\nPlease note, once submitted, **your model will be tested against new unseen data points** for final evaluation. This will determine your position on the private leaderboard which will be released once the First Round of the Datathon ends!\n\nIf you like working with Python, visualizing and understanding large datasets, you’re in the right place. (Psst… also if you took up the Data Analytics course, then brush up on those skills, and this is your time to shine! )\n\nALL THE BEST AND GOOD LUCK TO ALL PARTICIPANTS :)", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }