trim_anx

anx_sub

dep_sup

This report analyzes the NOAA Storm Database from 1950 to 2011 to identify which types of severe weather events have the greatest impact on population health and the economy in the United States. The analysis focuses on fatalities and injuries to assess health impact, and property and crop damage to assess economic consequences. Data transformations include cleaning event type labels, grouping similar events, and converting damage exponents to numeric values for consistent calculations. The results highlight tornadoes as the most harmful events to population health, and floods and hurricanes as causing the largest economic losses. These findings can inform resource allocation and emergency preparedness for high-impact weather events.

anx_sub

trim and fill

dep plot

sub_dep

Non-linear dimensionality reduction dengan menggunakan t-SNE (t-distributed Stochastic Neighbor Embedding). t-SNE adalah metode reduksi dimensi non-linear yang digunakan untuk memvisualisasikan data berdimensi tinggi dalam bentuk yang lebih sederhana. t-SNE bekerja dengan cara mengubah jarak antara titik data dalam ruang dimensi tinggi, misalnya dataset yang memiliki fitur yang sangat banyak.