def main(fn):
# data= pd.read_csv("../data/kddcup.data_10_percent_corrected", names=cols)
data = pd.read_csv(fn, header=-1)
# data= remove_missing(data)
# data= impute_missing(data)
data = impute_missing2(data)
# Features to be used in classification
features = [x for x in range(1, len(data.columns))]
X = data[features]
y = data[0]
#h= TGaussianNB(X, y)
#h.run()
print("GaussianNB")
h = Test(X, y, GaussianNB())
h.run()
h.report(fn="../Report/results/cancer.gnb.cm.tex")
s = Search(X, y, GaussianNB(), [{}])
s.search()
s.report("../Report/results/cancer.gnb.tex")
print("DTree neu")
parameters = [{
'criterion': ['gini', 'entropy'],
'max_features': ['auto', 'sqrt', 'log2']
}]
s = Search(X, y, DTree(), parameters)
s.search()
s.report("../Report/results/cancer.dt.tex")
h = Test(X, y,
DTree(max_features='log2', criterion='gini', random_state=1234))
h.run()
h.report(fn="../Report/results/cancer.dt.cm.tex")
print("RF")
parameters = [{
'n_estimators': range(1, 15),
'criterion': ['gini', 'entropy'],
'max_features': ['auto', 'sqrt', 'log2']
}]
s = Search(X, y, RandomForestClassifier(), parameters)
s.search()
s.report("../Report/results/cancer.rf.tex", )
h = Test(
X, y,
RandomForestClassifier(n_estimators=6,
criterion='gini',
max_features='sqrt',
random_state=1234))
h.run()
h.report(fn="../Report/results/cancer.rf.cm.tex")
parameters = [{
'kernel': ['linear', 'sigmoid', 'rbf', 'poly'],
'C': [0.1, 1, 10, 11, 20]
}]
print("SVM")
from sklearn import preprocessing
X_scaled = preprocessing.scale(X)
s = Search(X_scaled, y, SVC(), parameters)
s.search()
s.report("../Report/results/cancer.svm.tex")
h = Test(X, y, SVC(C=11, kernel='poly'))
h.run()
h.report(fn="../Report/results/cancer.svm.cm.tex")
print("KNeighborsClassifier")
parameters = [{
'n_neighbors': range(4, 8),
'weights': ['uniform', 'distance'],
'p': [1, 2]
}]
s = Search(X, y, KNeighborsClassifier(), parameters)
s.search()
s.report("../Report/results/cancer.knn.tex")
h = Test(X, y, KNeighborsClassifier(n_neighbors=5, weights='uniform', p=2))
h.run()
h.report(fn="../Report/results/cancer.knn.cm.tex")
# https://www.codewars.com/kata/58acfe4ae0201e1708000075/train/python
from Test import Test
def invite_more_women(arr):
return False if sum(arr) <= 0 else True
# best solution
def invite_more_women_best(arr):
return sum(arr) > 0
# Nice Solurion
def invite_more_women_nice(arr):
return arr.count(1) > arr.count(-1)
testing = Test()
testing.describe("Basic Tests")
testing.assert_equals(invite_more_women([1, -1, 1]), True)
testing.assert_equals(invite_more_women([-1, -1, -1]), False)
testing.assert_equals(invite_more_women([1, -1]), False)
testing.assert_equals(invite_more_women([1, 1, 1]), True)
testing.assert_equals(invite_more_women([]), False)
testing.report()
def warn_the_sheep(queue):
if (queue[-1] == 'wolf'):
return 'Pls go away and stop eating my sheep'
else:
return 'Oi! Sheep number {}! You are about to be eaten by a wolf!'.format(
len(queue) - (queue.index('wolf') + 1))
test = Test()
test.assert_equals(
warn_the_sheep([
'sheep', 'sheep', 'sheep', 'sheep', 'sheep', 'wolf', 'sheep', 'sheep'
]), 'Oi! Sheep number 2! You are about to be eaten by a wolf!')
test.assert_equals(
warn_the_sheep(
['sheep', 'wolf', 'sheep', 'sheep', 'sheep', 'sheep', 'sheep']),
'Oi! Sheep number 5! You are about to be eaten by a wolf!')
test.assert_equals(
warn_the_sheep(
['wolf', 'sheep', 'sheep', 'sheep', 'sheep', 'sheep', 'sheep']),
'Oi! Sheep number 6! You are about to be eaten by a wolf!')
test.assert_equals(warn_the_sheep(['sheep', 'wolf', 'sheep']),
'Oi! Sheep number 1! You are about to be eaten by a wolf!')
test.assert_equals(warn_the_sheep(['sheep', 'sheep', 'wolf']),
'Pls go away and stop eating my sheep')
test.report()
