Classification of weather time series is beneficial for weather forecasting problem. The classification can assist in identifying weather patterns for certain periods. In addition, extracting patterns from weather time series provides useful insights about the weather conditions to the domain experts. In this paper, we present the classification of weather time series using feature based approach that extracts feature vectors from the time series and performs the classification based on local and global features. The experimental results show that feature-based method with random forest performs well with more number of subsequences and may achieve comparable results with other methods.