# (5 HARD) Which team is highest scoring (per game or total)?

import pandas

df = pandas.read_csv("http://euclid.nmu.edu/~rappleto/Classes/CS295.Python/ncaa.csv")
team_score = df['team_score']
opponent_score = df['opponent_score']
team_name = df['team_name']
opponent_name = df['opponent_name']
totals = {}
count = {}

for i in range(len(df)):
    if team_name[i] in totals:
        totals[team_name[i]] += team_score[i]
        count[team_name[i]]+=1
    else:
        totals[team_name[i]] = team_score[i]
        count[team_name[i]] =1
avg = {}
for team, score in totals.items():
    avg[team] = totals[team]/count[team]
ordered_scores = sorted(avg.items(), key=lambda x: x[1])
ordered_scores[-1]






# (2 HARD) Which companies have more revenue per employee, "Aerospace and Defense" or "Technology"?
import pandas
import matplotlib.pyplot as plt

df = pandas.read_csv("http://euclid.nmu.edu/~rappleto/Classes/CS295.Python/fortune500-small.csv")
sector = df['Sector']
rev = df['Revenues']
revBySector = {}
emp = df['Employees']
empBySector = {}
for i in range(len(sector)):
    if sector[i] in revBySector:
        revBySector[sector[i]] += rev[i]
        empBySector[sector[i]] += emp[i]
    else:
        revBySector[sector[i]] = rev[i]
        empBySector[sector[i]] = emp[i]

for s, r in revBySector.items():
    ans[s] = round(revBySector[s] / empBySector[s] * 1000000,0)
print(ans)
sorted(ans.items(), key=lambda x:  -x[1])
plt.barh(list(ans.keys()), list(ans.values()))


set((df['Sector']))



df.groupby("Sector").sum()



s1 = { 1,2,3}
s2 = {2, 3, 4}
s1.union(s2)
s1 - s2
s1 * 3
s1 + s2
s1[2]