In this study, we have used the Tapi Basin Weather dataset of 7 weather stations in Gujarat, India obtained from the India Meteorological Department, Pune. It contains two readings of weather parameters for each day at 08:30 and 17:30, from the year 1999 to 2014. The dataset has 76706 records and contains 15 attributes.
1) The dataset for our project is Weather_dataset.xlsx. It can be downloaded from our git repository mentioned in the Important link tab.
2) We used IQR method to remove outliers and mean values to impute numerical missing values. To deal with missing categorical values we used KNN method with value of K equals to sqrt(number of distinct values) .
3) We have used FinalModifiedData.xslx file as the main dataset for our project.
4) For Station-based, predictions as well as for trend analysis, we have used different files that are derived from the dataset mentioned above, they are all present in our git repository.