import os, datetime
import pandas as pd
import pickle
import csv
import xlrd
from pandas import Series, DataFrame, Panel
from datetime import datetime, date, timedelta
from os import sys
import numpy as np
import matplotlib.pyplot as plt
import folium

wdf1 = pd.read_csv('sparql')

wdf1.cause.describe()

wdf1.occupation.describe()

wdf1.occupation.value_counts()

wdf1.cause.value_counts()[:10]

wdf1[wdf1['cause'] == 'http://dbpedia.org/resource/Lung_cancer'].occupation.value_counts()[:10]

wdf1[wdf1['cause'] == 'http://dbpedia.org/resource/Murder'].occupation.value_counts()[:10]

wdf1[(wdf1['cause'] == 'http://dbpedia.org/resource/Murder') & (wdf1['occupation'] == 'http://dbpedia.org/resource/Skateboarding')]