# 65th-Place Simple Solution Without Using Data Leakage

𝙷𝚒
I had 9 submissions with different complexities. Here I'll present the winning one.
The solution is simple. It uses
[tsfresh](https://github.com/blue-yonder/tsfresh)
to extract and select features from our time-series data. tsfresh calculates a
lot
of features with many parameters including the minimum value of the signal, the maximum, standard deviation, approximate entropy, skewness, number of peaks, etc.
After that, LightGBM is used to build the model and generate predictions. The generated predictions are the probabilities of each type of surfaces for each test case. The surface with the highest probability was chosen.
The code used is available in
[this Github repository](https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition)
in
eda.ipynb
and
kernel.ipynb
files.
[https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition](https://github.com/ammar1y/My-Solution-to-Help-Navigate-Robots-Competition)