def test_scout():
'''(3 points) scout'''
# new players to hire
x = scout()
# current members of the team
y = [
'bradfch01', # OAK 2002
'chaveer01',
'colanmi01',
'dyeje01',
'hernara02',
'hiljuer01',
'holtzmi01',
'hudsoti01',
'kochbi01',
'lidleco01',
'longte01',
'magnami01',
'mecirji01',
'menecfr01',
'muldema01',
'myersgr01',
'penaca01',
'saenzol01',
'tamje01',
'tejadmi01',
'valdema02',
'velarra01',
'venafmi01',
'zitoba01'
]
assert type(x) == list
assert type(x[0]) == str
assert len(x) == 3 # only choose 3 players
# the hires should not be in the team already
assert x[0] not in y
assert x[1] not in y
assert x[2] not in y
# cannot hire the same player twice
assert x[0] != x[1]
assert x[0] != x[2]
assert x[1] != x[2]
# the new team
T = x + y
# check budget
D = load_csv('Batting2001AJS.csv')
S = sum_salaries(T, D)
print('salaries:', S)
assert S <= 40004167 # too expensive, exceed budget
# the expected number of runs by the team should be larger than 700
print('runs:', runs(T, D))
assert runs(T, D) >= 700
def test_join_batting():
'''(3 points) join_batting'''
x= load_csv('Batting2001A.csv')
y= load_csv('People.csv')
z=join_batting(x,y)
assert z.shape == (1220, 43)
assert z.dtypes.H == int
assert z.dtypes.AB == int
assert z[z.playerID=='abreubo01'].iloc[0].G ==162
assert z[z.playerID=='abreubo01'].iloc[0].birthYear ==1974
assert z[z.playerID=='bradlmi01'].iloc[0].G == 77
assert z[z.playerID=='bradlmi01'].iloc[0].birthYear == 1978
assert z[z.playerID=='bradlmi01'].iloc[0].nameLast =='Bradley'
assert z[z.playerID=='bradlmi01'].iloc[0].nameFirst =='Milton'
# Now let's save the result into a CSV file, for further analysis
save_csv(z,'Batting2001AJ.csv')
def test_join_salary():
'''(3 points) join_salary'''
x = load_csv('Batting2001AJ.csv')
y = load_csv('Salaries2002.csv')
z = join_salary(x, y)
assert z.shape == (786, 47)
assert z[z.playerID == 'anderga01'].iloc[0].G == 161
assert z[z.playerID == 'anderga01'].iloc[0].nameLast == 'Anderson'
assert z[z.playerID == 'anderga01'].iloc[0].salary == 5000000
assert z[z.playerID == 'miltoer01'].iloc[0].G == 35
assert z[z.playerID == 'miltoer01'].iloc[0].nameLast == 'Milton'
assert z[z.playerID == 'miltoer01'].iloc[0].salary == 4000000
assert z[z.playerID == 'woodwch01'].iloc[0].G == 37
assert z[z.playerID == 'woodwch01'].iloc[0].nameLast == "Woodward"
assert z[z.playerID == 'woodwch01'].iloc[0].salary == 235000
# Now let's save the result into a CSV file, for further analysis
save_csv(z, 'Batting2001AJS.csv')
def test_runs():
'''(2 points) runs'''
# test with a team of one player
T = ['hernara02']
D = load_csv('Batting2001AJS.csv')
R = runs(T, D)
assert np.allclose(R, 57.3877, atol=0.01)
T = ['hernara02', 'hattesc01']
R = runs(T, D)
assert np.allclose(R, 88.7553, atol=0.01)
def test_rank_OBP():
'''(3 points) rank_OBP'''
D = load_csv('Batting2001AJS.csv')
R = rank_OBP(D)
assert type(R) == list
assert len(R) == 786
assert R[0] == 'berkmla01'
assert R[1] == 'pujolal01'
assert R[2] == 'giambje01' # OAK team hired Jeremy Giambi in 2002
assert R[3] == 'mientdo01'
assert R[4] == 'pierrju01'
def test_rank_BA():
'''(3 points) rank_BA'''
D = load_csv('Batting2001AJS.csv')
R = rank_BA(D)
assert type(R) == list
assert len(R) == 786
assert R[0] == 'berkmla01'
assert R[1] == 'pujolal01'
assert R[2] == 'pierrju01'
assert R[3] == 'loducpa01'
assert R[4] == 'millake01'
def test_sum_salaries():
'''(2 points) sum_salaries'''
# test with a team of one player
T = ['bradfch01']
D = load_csv('Batting2001AJS.csv')
S = sum_salaries(T, D)
assert S == 235000
T = ['bradfch01', 'chaveer01', 'colanmi01']
S = sum_salaries(T, D)
print(S)
assert S == 2660000
def load_batting(filename='Batting.csv'):
'''
load batting data from a CSV file.
Input:
filename: a string indicating the filename of the CSV file.
Output:
X: a pandas dataframe, loaded from the CSV file
Hint: you could solve this problem using one line of code.
'''
#########################################
## INSERT YOUR CODE HERE
X = load_csv(filename)
#########################################
return X
''' TEST: Now you can test the correctness of your code above by typing `nosetests -v test4.py:test_load_batting' in the terminal. '''
def test_search_salary():
'''(2 points) search_salary'''
x= load_csv('Salaries.csv')
y=search_salary(x)
# Now let's save the result into a CSV file, for further analysis
save_csv(y,'Salaries2002.csv')
assert y.shape == (846, 5)
assert y[y.playerID=='anderga01'].iloc[0].yearID == 2002
assert y[y.playerID=='anderga01'].iloc[0].salary == 5000000
assert y[y.playerID=='miltoer01'].iloc[0].yearID == 2002
assert y[y.playerID=='miltoer01'].iloc[0].salary == 4000000
assert y[y.playerID=='woodwch01'].iloc[0].yearID == 2002
assert y[y.playerID=='woodwch01'].iloc[0].salary == 235000
def test_sum_stat():
'''(2 points) sum_stat'''
# test with a team of one player
T = ['hernara02']
D = load_csv('Batting2001AJS.csv')
S = sum_stat(T, D, key='H')
assert S == 115
T = ['hernara02', 'hattesc01']
S = sum_stat(T, D, key='H')
assert S == (115 + 68)
S = sum_stat(T, D, key='G')
assert S == (136 + 94)
def test_aggregate_batting():
'''(3 points) aggregate_batting'''
x= load_csv('Batting2001.csv')
y=aggregate_batting(x)
# after removing the column 'teamID' and 'lgID' (string cannot be added in aggregation), we have 20 columns
assert y.shape == (1220, 20)
assert y.dtypes.H == int
assert y.dtypes.AB == int
assert y.iloc[1,3] == 28 # the 'G' column for player 'abbotje01'
assert y.iloc[1,4] == 42 # the 'AB' column for player 'abbotje01'
assert y.iloc[7,3] == 59 # the 'G' column for player 'aceveju01'
assert y.iloc[7,4] == 3 # the 'AB' column for player 'aceveju01'
assert y.iloc[84,3] == 46 # the 'G' column for player 'bennega01'
assert y.iloc[84,4] == 131 # the 'AB' column for player 'bennega01'
assert y.iloc[84,-1] == 1 # the 'GIDP' column for player 'bennega01'
# Now let's save the result into a CSV file, for further analysis
save_csv(y,'Batting2001A.csv')
def test_search_batting():
'''(2 points) search_batting'''
x=load_batting()
y=search_batting(x, year=1999)
assert y.shape == (1299, 22)
print(y)
assert y.dtypes.H == int
assert y.dtypes.AB == int
assert y.iloc[0,1] == 1999
assert y.iloc[1200,1] == 1999
assert y.iloc[0,6] == 57
assert y.iloc[1,6] == 21
y=search_batting(x)
assert type(y) == pd.DataFrame
assert y.shape == (1339, 22)
assert y.dtypes.H == int
assert y.dtypes.AB == int
assert y.iloc[0,1] == 2001
assert y.iloc[1338,1] == 2001
assert y.iloc[0,6] == 1
assert y.iloc[1,6] == 42
# Now let's save the dataset of year 2001 into a CSV file, for further analysis
save_csv(y,'Batting2001.csv')
# check the correctness of the saved data
z= load_csv('Batting2001.csv')
assert type(z) == pd.DataFrame
assert z.shape == (1339, 22)
assert z.dtypes.H == int
assert z.dtypes.AB == int
assert z.iloc[0,1] == 2001
assert z.iloc[1338,1] == 2001
assert z.iloc[0,6] == 1
assert z.iloc[1,6] == 42
