Lung-Cancer-Prediction

Predicting Lung Cancer incidences by county. See cancer.ipynb to see the implementation of the supervised learner, and Capstone_MLND_Cancer.pdf to see the report. The noteook is best viewed online using nbviewer, http://nbviewer.jupyter.org/github/rjbergerud/Lung-Cancer-Prediction/blob/master/Cancer.ipynb.

conda create --name lungCancer python=3

To run the .ipynb notebook, make sure you have the dependencies in the requiments.txt.

pip install -r requirements.txt

Dot file can be generated using the package graphviz

sudo apt-get install graphviz dot -Tpng tree.dot -o tree.png

Name		Name	Last commit message	Last commit date
Latest commit History 9 Commits
BP_2007_00A1 fastfood		BP_2007_00A1 fastfood
BP_2007_00A1 rubber and plastics		BP_2007_00A1 rubber and plastics
BP_2007_00A1 steel		BP_2007_00A1 steel
TRI		TRI
BP_2007_00A1 chemical mfg.zip		BP_2007_00A1 chemical mfg.zip
BZN01.csv		BZN01.csv
Cancer.ipynb		Cancer.ipynb
Capstone_MLND_Cancer.pdf		Capstone_MLND_Cancer.pdf
EPA_Toxic_Air_Pollutant_Cancer_Risk_by_County.csv		EPA_Toxic_Air_Pollutant_Cancer_Risk_by_County.csv
HSG02.csv		HSG02.csv
HSG02_H.csv		HSG02_H.csv
MAN01_Sheet1.csv		MAN01_Sheet1.csv
POP01_sheet2.csv		POP01_sheet2.csv
README.md		README.md
bladder_incd.csv		bladder_incd.csv
breast_incd.csv		breast_incd.csv
childhood_incd.csv		childhood_incd.csv
county-fips.csv		county-fips.csv
incd Non-hodgekin lymphioma.csv		incd Non-hodgekin lymphioma.csv
kidney_renal_incd.csv		kidney_renal_incd.csv
leukemia_incd.csv		leukemia_incd.csv
lung_incd.csv		lung_incd.csv
requirements.txt		requirements.txt
smokedatwithfips.csv		smokedatwithfips.csv

rjbergerud/Lung-Cancer-Prediction