1.Through our data we have found out the countries that have the highest suicide rates and then provided insights on it with the help of various parameters that could be a reason for suicide attempts. 2.After we acquire the dataset from various websites, we did web scraping to add additional values in our dataset and then data preprocessing, manipulation merging and analysis. 3.The goal of the project is to provide insights to Suicide prevention agencies ensuring the target population is taken care of first, which would eventually save more lives.
1.Open the file Suicide_project.ipynb. 2.In order to run the project source code mention the directory where the data sets are present. For instance, if the data sets are present in C:\Users\Mike\Downloads\Data-Project, then the variable must be populated as shown below (add \ before every \ to escape it). Also, do not forgot to add \ at the end of the directory as shown below: C:\Users\Mike\Downloads\Data-Project\ 3.Run every single cell one-by-one. 4.At the end of the execution, file named “Final_merged_dataset.xlsx” with all the preprocessed final data.
1.Government Agencies: Through our data set the government could track the relative suicide rate for counties similar to theirs in terms of size, economy, geography, etc., and then analyze the areas where it needs to improve through our variables to reduce suicides. E.g. Setting up new mental health hospitals, expenditure on mental health, increasing the number of psychologists etc. 2.Social Work Organizations: The social camp organizers can fill in the gap to meet the needs of citizens to have professional mental health practitioners and guides. It could also analyze the uneven split of suicide rates among men and women and target the population that is hit hardest among the entire set in any given country. 3.Paramedics: The paramedics in any country could analyze the need for mental health workers and increase their workforce to meet the needs as per the demand for the country. 4.Suicide Hotline Numbers: Suicide hotline number could set a plan to observe the suicide trend in terms of age group, sex etc. and set us a constructive plan to ensure reduction on suicide among these categories. 5.Business sector: The business sector could co-relate with the happiness index, mental health employee counts, etc. before setting up a business. The ones who already have a business set in a country could set up boot camps regarding suicide prevention for their employees and people in general. Upcoming companies could also come up with suicide prevention and detection products in countries with high suicide rates.
1.Missing Values: While the data is available, some parameters are not as widely reported by many countries. 2.Assumption: When manipulating the data, a couple of variables were created with the column in years considering random values from -3 to 9 in order to ensure standardization. However, in real work scenario this value can be changed to the global trend in each of the parameter. 3.Formatting: While extracting the data, some of the countries were named differently in each of the data set. This created the problem where for example we had two rows one with United States and the other with United States of America. Although both are the same countries the nomenclature caused this kind of issue.
1.All our data set was fetched through websites that are publicly available and can be publicily accessed and distributed. 2.As there are no such restrictions on our data, we can easily make use of the readily available dataset and transform each of the dataset as per our needs. 3.We are distributing our source code along with the data sets on Kaggle and GitHub.
The dataset files were also uploaded in the Kaggle.
1.Through our project we believe to have provided multiple variables to concerned agencies to review the statistics for suicide in any given country. 2.By doing this the government, social workers etc could identify the problem in their system and try to fix the problem. 3.The dataset would help them narrow down on the problem related to the age, sex, location, inadequate policy for mental health, infrastructure etc. and move in the direction to reduce suicides.
1.Abhishek Shetty 2.Anamika Rekha 3.Srinivas Pai 4.Siddharth Dudugu 5.Jibin Joby