def runProgram(youtube_search_query, text_to_find):
dl = Downloader()
celeb_videos = Search.search(youtube_search_query)
links = [Caption.YOUTUBE_LINK + x for x in celeb_videos]
print links
count = 0
for videoid in celeb_videos:
cap = Caption(videoid)
results = cap.find(text_to_find)
for result in results:
dl.download(result, text_to_find + str(count))
count += 1
def tune( dataFilename ):
Nvalues = [8]
Kvalues = [4, 8]
print "Starting"
for n in Nvalues:
print n
for k in Kvalues:
print k
Parameters.N = n
Parameters.K = k
t = int((Parameters.E - Parameters.N)/Parameters.K)
Parameters.T = t
print Parameters.T
from Search import Search
results = Search.search()
f = open( dataFilename , 'a' )
f.write( str( Parameters.N ) + " " + str( Parameters.K ) + " " + str( Parameters.T ) + " " + str( results[ 0 ].get_fitness() ) + "\n" )
f.close()
def tune(dataFilename):
Nvalues = [8]
Kvalues = [4, 8]
print "Starting"
for n in Nvalues:
print n
for k in Kvalues:
print k
Parameters.N = n
Parameters.K = k
t = int((Parameters.E - Parameters.N) / Parameters.K)
Parameters.T = t
print Parameters.T
from Search import Search
results = Search.search()
f = open(dataFilename, 'a')
f.write(
str(Parameters.N) + " " + str(Parameters.K) + " " +
str(Parameters.T) + " " + str(results[0].get_fitness()) + "\n")
f.close()
def search():
query = request.form['query']
s = Search()
results = s.search(query)
return render_template('search.html', query=query, results=results, clippyjs_agent=random_clippyjs_agent())
try:
initial_puzzle = list(map(int, args.puzzle.split()))
except ValueError:
parser.error("Please input a string of numbers as puzzle")
if len(initial_puzzle) % args.columns != 0:
parser.error("Incompatible puzzle and columns value(" + str(args.columns) + ").")
if len(set(initial_puzzle)) != len(initial_puzzle):
parser.error("Please do not have any duplicate values in puzzle.")
if args.b:
start_breadth_first = perf_counter()
initial_node = Node(initial_puzzle, args.columns, None, "0", 0)
breadth_first = Search(initial_node)
breadth_first.search("breadth_first")
end_breadth_first = perf_counter()
start_depth_first = perf_counter()
initial_node = Node(initial_puzzle, args.columns, None, "0", 0)
depth_first = Search(initial_node)
depth_first.search("depth_first", args.max_depth, args.i)
end_depth_first = perf_counter()
start_best_first_linear = perf_counter()
initial_node = Node(initial_puzzle, args.columns, None, "0", 0, "linear_distance")
best_first_linear = Search(initial_node)
best_first_linear.search("best_first")
end_best_first_linear = perf_counter()
start_best_first_wrong = perf_counter()
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")
