RomeAnalytics458

-- There is no readily apparent unique identifier for the dataset so far, 
-- this appears to have caused duplication issues during importing in DBeaver
-- this will be addressed first. 

-- city_ID could be a unique identifier for all rows. 
SELECT city_ID,
	   scientific_name,
	   COUNT(*) AS row_count
FROM dc_tree
GROUP BY city_ID, scientific_name 

RomeAnalytics458

-- Washington DC Tree Survey, Exploratory Data Analysis 

SELECT *
FROM dc_tree_unique
;

-- How many total trees are there?

SELECT COUNT(*)	
FROM dc_tree_unique

RomeAnalytics458

-- Welcome to my Washington DC Tree Survey Project.

-- Lets first select all and view the data 

SELECT *
FROM dc_tree
;

SELECT *
FROM dc_tree

RomeAnalytics458

SELECT *
FROM dc_tree_final
;

-- Removing any rows that have nulls in both name columns

SELECT *
 FROM dc_tree_final 
WHERE scientific_name = ''
	AND common_name = ''