A class project in python for computational tools in data science for analysing Boston street names to take gender equitiy to street names, the purpose is to answer the follwing question:
"Is there any good candidates for renaming, Is there any thing about these candidates that makes them sigificantly different than the other streets in a statiacal way like size, frequency, distribution across Boston area, concentration around an area, etc.?"
you need to install docx for parsing the street-book.doc,
$ pip install python-docx
also it's important to change street book document extension from ".doc" to ".docx".
please note that you shoudn't convert it into .docx, chaning the file extenstion is enough for docx to be able to parse it.
For your convienience street-book has been added to project directory.
To use gender predictor api, you first need to install it through pip install git+git://github.com/clintval/gender_predictor.git
then, you can simply run "Gender_Equity.ipynb"
we have added an "ouput" directoy to project directoy. This directoyry contains the csv files for "male street names frequency","renaming inforamtion","data frame created after paring street book" and "street names frequency".
Also, Output cells haven't been cleared.