def test_suggested_cased_always_qualified_column_names(completer):
text = 'SELECT from users'
position = len('SELECT ')
cols = [column(c) for c in cased_users_col_names]
result = result_set(completer, text, position)
assert result == set(cased_funcs + cols + testdata.builtin_functions() +
testdata.keywords())
def test_columns_before_keywords(completer):
text = 'SELECT * FROM orders WHERE s'
completions = get_result(completer, text)
col = column('status', -1)
kw = keyword('SELECT', -1)
assert completions.index(col) < completions.index(kw)
def test_columns_before_keywords(completer):
text = 'SELECT * FROM orders WHERE s'
completions = get_result(completer, text)
col = column('status', -1)
kw = keyword('SELECT', -1)
assert completions.index(col) < completions.index(kw)
def test_suggested_cased_always_qualified_column_names(
completer
):
text = 'SELECT from users'
position = len('SELECT ')
cols = [column(c) for c in cased_users_col_names]
result = result_set(completer, text, position)
assert result == set(cased_funcs + cols
+ testdata.builtin_functions() + testdata.keywords())
def predict(self, x_data):
y_hat_models = []
for model in self.models:
y_hat_models.append((model.predict(x_data))) # make a predict with every model
y_hat = []
for i in range(len(x_data)): # find the most frequency predict. (can not be equality due to odd number of
# models)
lst = column(y_hat_models, i)
y_hat.append(max(set(lst), key=lst.count))
return y_hat
def adaboost(train, test, headers, fullTestData):
ylabels = ['H', 'A', 'D']#Make predictions for each of the possible labels
results = []
for y in ylabels:
# print "Training for", y
rootNode = Node(train)#Initialize first decision stump
treeRootNode = buildTree(rootNode, y, headers)
results.append(predict(test, rootNode.splits, y))
print "Now making predictions"
prediction = []
for r in xrange(0,len(results[0])):
temp = [zy for zy in column(results, r)]
#Take the label with corresponding max value of alpha as final prediction
prediction.append(ylabels[temp.index(max(temp))])
print "Now checking predictions"
corr = 0
print "Home\tAway\tPrediction\tActual\tBookie"
file = open("resultdata.csv", 'a')
writer = csv.writer(file, quoting=csv.QUOTE_ALL)
for p in xrange(0,len(prediction)):
print '\a'
writer.writerow([column(fullTestData,-2)[p], column(fullTestData,-1)[p], prediction[p], column(test,-2)[p], column(fullTestData,-4)[p]])
print [column(fullTestData,-2)[p], column(fullTestData,-1)[p], prediction[p], column(test,-2)[p], column(fullTestData,-4)[p]]
if prediction[p] == column(test,-2)[p]:
corr+=1
file.close()
try:
print str(float(corr)*100/len(prediction)), len(prediction)
except ZeroDivisionError:
print 0, len(prediction)
print "done"
def test_join_using_suggests_columns_after_first_column(completer, text):
result = result_set(completer, text)
cols = [column(c) for c in metadata['tables']['USERS']]
cols += [column(c) for c in metadata['tables']['ORDERS']]
assert result == set(cols)
def test_suggest_columns_after_three_way_join(completer):
text = '''SELECT * FROM users u1
INNER JOIN users u2 ON u1.id = u2.id
INNER JOIN users u3 ON u2.id = u3.'''
result = result_set(completer, text)
assert (column('id') in result)
def test_no_column_qualification(text, completer):
cols = [column(c) for c in cased_users_col_names]
result = result_set(completer, text)
assert result == set(cols)
cased_func_names = [
'Custom_Fun', '_custom_fun', 'Custom_Func1', 'custom_func2',
'set_returning_func'
]
cased_tbls = ['Users', 'Orders']
cased_views = ['User_Emails', 'Functions']
casing = (['SELECT', 'PUBLIC'] + cased_func_names + cased_tbls + cased_views +
cased_users_col_names + cased_users2_col_names)
# Lists for use in assertions
cased_funcs = [
function(f)
for f in ('Custom_Fun', '_custom_fun', 'Custom_Func1', 'custom_func2')
] + [function('set_returning_func')]
cased_tbls = [table(t) for t in (cased_tbls + ['"Users"', '"select"'])]
cased_rels = [view(t) for t in cased_views] + cased_funcs + cased_tbls
cased_users_cols = [column(c) for c in cased_users_col_names]
aliased_rels = [
table(t) for t in ('users u', '"Users" U', 'orders o', '"select" s')
] + [view('user_emails ue'), view('functions f')] + [
function(f) for f in ('_custom_fun() cf', 'custom_fun() cf',
'custom_func1() cf', 'custom_func2() cf')
] + [
function('set_returning_func(x := , y := ) srf',
display='set_returning_func(x, y) srf')
]
cased_aliased_rels = [
table(t) for t in ('Users U', '"Users" U', 'Orders O', '"select" s')
] + [view('User_Emails UE'), view('Functions F')] + [
function(f) for f in ('_custom_fun() cf', 'Custom_Fun() CF',
'Custom_Func1() CF', 'custom_func2() cf')
] + [
try:#Try and load serialized data with features extracted
traindata = pickle.load( open( "traindata.p", "rb" ) )
headers = pickle.load( open( "headers.p", "rb" ) )
except:#Else now calculate feature data for every match and seralize it
traindata, teamwise, matchwise, headers = trainOnAll(data)
pickle.dump( traindata, open( "traindata.p", "wb" ) )
pickle.dump( teamwise, open( "teamwise.p", "wb" ) )
pickle.dump( matchwise, open( "matchwise.p", "wb" ) )
pickle.dump( headers, open( "headers.p", "wb" ) )
# normalize features in training data
# If any feature has missing values (None) replace it with the average
for x in xrange(len(traindata[0])-5):
tmp = [t for t in column(traindata,x) if t != None]
if len(tmp) == 0:
avg = 0.0
else:
avg = sum(tmp)/len(tmp)
mn = min(tmp)
mx = max(tmp)
#Now normalize the values as (fx-fmin)/fmax
for num, y in enumerate(column(traindata,x)):
if traindata[num][x] == None:
try:
traindata[num][x] = (avg-mn)/(mx-mn)
except ZeroDivisionError:
traindata[num][x] = 0.0
else:
try:
def test_join_using_suggests_columns_after_first_column(completer, text):
result = result_set(completer, text)
cols = [column(c) for c in metadata['tables']['USERS']]
cols += [column(c) for c in metadata['tables']['ORDERS']]
assert result == set(cols)
def test_suggest_columns_after_three_way_join(completer):
text = '''SELECT * FROM users u1
INNER JOIN users u2 ON u1.id = u2.id
INNER JOIN users u3 ON u2.id = u3.'''
result = result_set(completer, text)
assert (column('id') in result)
def test_no_column_qualification(text, completer):
cols = [column(c) for c in cased_users_col_names]
result = result_set(completer, text)
assert result == set(cols)
cased_func_names = [
'Custom_Fun', '_custom_fun', 'Custom_Func1', 'custom_func2', 'set_returning_func'
]
cased_tbls = ['Users', 'Orders']
cased_views = ['User_Emails', 'Functions']
casing = (
['SELECT', 'PUBLIC'] + cased_func_names + cased_tbls + cased_views
+ cased_users_col_names + cased_users2_col_names
)
# Lists for use in assertions
cased_funcs = [
function(f) for f in ('Custom_Fun', '_custom_fun', 'Custom_Func1', 'custom_func2')
] + [function('set_returning_func')]
cased_tbls = [table(t) for t in (cased_tbls + ['"Users"', '"select"'])]
cased_rels = [view(t) for t in cased_views] + cased_funcs + cased_tbls
cased_users_cols = [column(c) for c in cased_users_col_names]
aliased_rels = [
table(t) for t in ('users u', '"Users" U', 'orders o', '"select" s')
] + [view('user_emails ue'), view('functions f')] + [
function(f) for f in (
'_custom_fun() cf', 'custom_fun() cf', 'custom_func1() cf',
'custom_func2() cf'
)
] + [function(
'set_returning_func(x := , y := ) srf',
display='set_returning_func(x, y) srf'
)]
cased_aliased_rels = [
table(t) for t in ('Users U', '"Users" U', 'Orders O', '"select" s')
] + [view('User_Emails UE'), view('Functions F')] + [
function(f) for f in (
app.layout = html.Div(
children=[
row([
html.H2(
'Visualizing common distributions',
style={ 'textAlign': 'center', 'color': colors['text']},
)]),
row([
column([
row([
html.Br(),
html.Label('Set N:'),
dcc.Input(id='set_n', value=10, type='number', min=0, step=1, size=1),
]),
row([
html.Label('Set p:'),
dcc.Input(id='set_p', value=0.5, type='number', min=0.0, max=1.0, step=0.05),
])
], className='two columns'),
column([
dcc.Graph(
id='binomial_graph',
config={
'displaylogo': False, #dont show plotly logo
'modeBarButtonsToRemove': ['pan2d','lasso2d'], #dont show certain options in plotly menu
},
),
], className='eight columns'),
