Hawaii Weather Data Analysis

This project was done using Numpy, Pandas, MatPlotLib, and Seaborn for analysis, SQLAlchemy serving to connect to a SQLite database I created from CSVs I cleaned, and Flask to generate a mini-API.

The README on Github comprises the Weather Analysis portion of the project. For other aspects, please see the following files:

  • data_engineering.ipynb: This file contains the code used to clean the provided CSV datasets.
  • database_engineering.ipynb: This file contains the code used to create a SQLite database from the cleaned CSVs.
  • app.py: This file contains code for a Flask API based on the datasets I used.

Datasets were provided by Trilogy Education Services (© 2017).

Precipitation Analysis

Between 8/24/2016 and 8/23/2017, Hawaii appears to have recorded observations of some level of precipitation almost every single day. However, it's unclear if precipitation includes only rain or if it includes precipitation like dew.

Across the 2,015 recorded observations, the maximum amount of precipitation recorded was 6.7 inches, but the mean was 0.18 inches.

Temperature Analysis

Between 8/24/2016 and 8/23/2017, the majority of recorded temperature observations were between 72.5-77.5°F with the average recorded temperature observation somewhere around 75°F.

Weather Station Analysis

In this section, I parse through the weather stations that were available as part of the dataset.

There are a total of 9 weather stations in Hawaii, according to the dataset. Of those, the station with the highest observation count is USC00519281 WAIHEE 837.5 with a total of 2,772 observation across the dataset.

Index Station Number Station Name Count of Observations
0 USC00519281 WAIHEE 837.5 2772
1 USC00513117 KANEOHE 838.1 2696
2 USC00519397 WAIKIKI 717.2 2685
3 USC00519523 WAIMANALO EXPERIMENTAL FARM 2572
4 USC00516128 MANOA LYON ARBO 785.2 2484
5 USC00514830 KUALOA RANCH HEADQUARTERS 886.9 1937
6 USC00511918 HONOLULU OBSERVATORY 702.2 1932
7 USC00517948 PEARL CITY 683
8 USC00518838 UPPER WAHIAWA 874.3 342