Multi-dimensional Data Structures
2D kNN Queries Implementation
2D kNN query implementation using K-D Trees, Quad Trees and 2D Range Trees over a dataset of check-in events with x/y coordinates, accuracy, timestamps and place ids.
Client University of Patras, Greece
01Overview
About the project
The train and test dataset is split based on time, and the public/private leaderboard in the test data are split randomly. There is no concept of a person in this dataset. All the row_id's are events, not people. Some of the columns, such as time and accuracy, are intentionally left vague in their definitions. Please consider them as part of the challenge.
File descriptions
1. train.csv, test.csv (www.kaggle.com/c/facebook-v-predicting-check-ins/data)
row_id: id of the check-in event; x y: coordinates; accuracy: location accuracy; time: timestamp; place_id: id of the business, this is the target you are predicting
2. train_x_y.csv
x y: coordinates (drive.google.com/file/d/151xoFDNtabYaFT6Dxy5D1nXp_-8L1ttq/view?usp=sharing)
02Tech stack
Technologies
Related
More in AI
-
BI in a Box
End-to-end Business Intelligence platform that turns raw data from ERP systems and databases into insights via dashboards, reporting and time-series forecasting.
-
Data Mining
Model evaluation on a 75%-25% training-test split using f1 score, precision and recall, parameter tuning, SVM training and the use of neural networks.
Keep exploring
More projects
Interested in something similar?
Tell me about your idea or project and let's see how we can build it together.