PUI2016 Extra Credit Project Proposal <yc2839>

Problem Description: Why New York City’s Mental Health Service is Indispensable? The approach to exploring this question is via digging into NYC open data.  There are now 836 mental health facilities located in the 5 Boroughs of NYC, among which, Manhattan has the highest number of 284 and Staten Island has the lowest number of 57. Firstly, the 311 complaint data would be analyzed to figure out whether or not the number of facilities is associated with the total compliant number, with the population density, or with the economic status of each Borough.  In other words, this investigation is to determine what factors would makes people complain the most, and are they potentially related to mental stress at all? For this part, some linear regressions would help to identify the correlations between those factors. Secondly, NYC leading cause of death provides important information about that during 2007 to 2011, mental health problem can be the fourth high risky factor to death in NYC. Finally, if all data set works well and point out the correlation among potential factors, we can confirm that NYC's Mental Health Service is indeed required supported by the data.
Data:  1). Mental Health Service Finder Data
           2). 311 Complaint Data
           3). Population Census Tract Data
           4). New York City Leading Causes of Death Data
All datasets will be downloaded from NYC Open Data website. Then, the procedure would contain wrangling the data (clean, transform, merge the current data if necessary). After that, a new ‘Dataframe’ would be made in order to present the needed information all together. Finally, visualizing the final dataset through plot and prediction lines.