Tredence in association with MachineHack present Ode to Code: Predicting Weather Using Alien Fruit Properties –An exclusive MLDS 2022 hackathon for data scientists

MachineHack, in association with data science & AI engineering company Tredence, is all set to launch an exclusive hackathon as part of MLDS 2022. The one-week long hackathon dubbed, ‘Ode to Code: Predicting weather using alien fruit properties’ will run from Jan 14, 2022 to Jan 24, 2022. The winners of the hackathon stand to bag cash prizes worth INR 1 lakh.

Tredence is a data science and AI engineering company solving the last mile problem in analytics. Last mile refers to the gap between insight creation and value realisation. Tredence has over 1,500 employees with offices in Foster City, Chicago, London, Toronto and Bangalore and boasts a high-end clientele in retail, CPG, hi-tech, telecom and travel sectors.

Machine Learning Developers Summit 2022 brings together India’s leading Machine Learning innovators and practitioners to share their ideas and experience about machine learning tools, advanced development in this sphere and gives the attendees a first look at new trends & developer products.

Let the challenge begin! 

The hackathon is open to data scientists, machine learning practitioners, analytics professionals, and tech enthusiasts at all experience levels. Apart from a chance to win cash prizes, the participants also get the opportunity to improve their Global Leaderboard Rankings and become the ultimate MachineHack GrandMaster. What are you waiting for? The holy grail is just one tap away!

Hackathon start date –  January 14, 2021, at 6:00 pm.

Download our Mobile App

Hackathon end date –  January 24, 2021, at 6:00 pm.

Problem statement:

A team of astronauts lands on an Exoplanet brimming with life and favourable weather conditions in 2050 AD. The scientists start collecting data samples of fruits growing in the terrain to learn about how different seasons affect the vegetation over a solar year of the planet.

The winners of the hackathon will get a chance to win cash prizes worth up to INR 1 lakh. 

To solve this problem, MachineHack has created a training dataset of 42,748 rows and 14 columns and a testing dataset of 18,321 rows and 14 columns. The hackathon demands a few pre-requisite skills like multi-class classification, and the ability to optimise “accuracy” to generalise well on unseen data. 

Datasets will go live on January 14, 2021, at 6:00 pm.

Submission guidelines 

• Sklearn models should support the predict() method to generate the predicted values. 
• The participant should submit a .csv file with exactly  18,321 rows with 1 column (season). The submission will return an Invalid Score if you have extra rows or columns.
• The file should have exactly 1 column.

Note: Do not shuffle the sequence of the test series. 

If you are using pandas, use this submission code: submission_df.to_csv(‘my_submission_file.csv’, index=False)

Evaluation criteria 

The submission will be evaluated using the accuracy metric. One can use sklearn.metrics.accuracy to get a valid score.

The evaluation will be done using 

• It will be based on the participants standing on the private leaderboard.
• The public leaderboard uses 30% of the provided test.csv dataset to evaluate.
• The private leaderboard uses 100% of the provided test.csv dataset to evaluate. 

Prizes

“Ode To Code”  will select three (3) winners based on the given evaluation criteria. The cash prizes are as follows: 

First prize: INR 50,000 

Second prize: INR 30,000

Third prize: INR 20,000

Note: 

• Make sure your MachineHack profile is up to date with all the relevant information/details. 
• Make sure you have gone through the ‘Rules’ section before participating. 
• The participants will receive the prize money only if selected by Tredence and MachineHack. 

Hackathon start date –  January 14, 2021, at 6:00 pm.

Hackathon end date –  January 24, 2021, at 6:00 pm.

The team starts beaming the collected weather data back to the Earth. However, the solar radiation corrupts the data. Now, the scientists back at Earth have to figure out the exoplanet’s weather conditions based on the properties of the fruit to solve the puzzle. Your challenge is to help the scientists identify the earth-like season conducive to fruiting of the alien plant based on the available data.

Attribute description:

Columns: [‘edible-poisonous’, ‘cap-diameter’, ‘cap-shape’, ‘cap-color’, ‘does-bruise-or-bleed’, ‘gill-attachment’, ‘gill-color’, ‘stem-height’, ‘stem-width’, ‘stem-color’, ‘has-ring’, ‘ring-type’, ‘habitat’, ‘season’]

 # Train: 42,748 rows x 14 columns

# Test: 18,321 rows x 14 columns

Data dictionary

Independent variables

• edible-poisonous: edible=e, poisonous=p
• cap-diameter: float number in cm
• cap-shape: bell=b, conical=c, convex=x, flat=f, sunken=s, spherical=p, others=o
• cap-color: brown=n, buff=b, gray=g, green=r, pink=p, purple=u, red=e, white=w, yellow=y, blue=l, orange=o, black=k
• does-bruise-bleed: bruises-or-bleeding=t,no=f
• gill-attachment: adnate=a, adnexed=x, decurrent=d, free=e, sinuate=s, pores=p, none=f
• gill-color: see cap-color + none=f
• stem-height: float number in cm
• stem-width: float number in mm
• stem-color: see cap-color + none=f
• has-ring: ring=t, none=f
• ring-type: cobwebby=c, evanescent=e, flaring=r, grooved=g, large=l, pendant=p, sheathing=s, zone=z, scaly=y, movable=m, none=f
• habitat: grasses=g, leaves=l, meadows=m, paths=p, heaths=h, urban=u, waste=w, woods=d

Dependent variable

• season: spring=s, summer=u, autumn=a, winter=w

Skills: 

• Optimising accuracy to generalise well on unseen data
• Multi-class classification

Winners announcement

Final winners will be notified via email based on an aggregate score of their private leaderboard rankings.

Datasets will go live on January 14, 2021, at 6:00 pm.

The hackathon will conclude on January 24, 2021, at 6:00 pm.