krishnaths / language_detect Goto Github PK

•	Required -		
  o	Python 3.6
  o	Scikitlearn
  o	Numpy
  o	pandas
• install the required libraries using
  o	pip install -r requirements.txt
•	Place the main.py file in any folder of your choice:
•	Create a new folder called “collected” in the same folder as main.py.
•	Download the zip file from the public URL.
  o	https://drive.google.com/open?id=1JkA84vAwP4kR1P48sIvRboBKGjWT9wj6
•	Unzip the file and put the contents into “collected” folder so they look like this in structure.
•	main.py and collected folder should be the same level.
•	Modify the parameters in the main.py program if you like.
  o	dataFolder='./collected' -  location of the datafiles
  o	constNum_of_lines_selected = 5000 – sets the number of lines of each language used
  o	floatSplitRatio=0.8 - train test data split
•	Execute with “python main.py” from the terminal.