import sklearn

file = open('train.txt', 'r')
text = file.read()
result = []
for line in text.splitlines():
	result.append(list(line.split()))

X=[]
Y=[]
for value in result:
	X.append(list(map(float, value[:176])))
	Y.append(value[176])

Y = [float(y) for y in Y]

Z=[]
testFile=open('dev_no_label.txt')
text = testFile.read()
result=[]
for line in text.splitlines():
	result.append(list(line.split()))
for value in result:
	Z.append(list(map(float, value)))


def save(predictions):
	outFile = open('predictions.txt', 'w')
	for y in predictions:
		print(int(y), file=outFile)
	outFile.close()


from sklearn import svm, cross_validation, tree, linear_model
X_train,X_test,y_train,y_test=cross_validation.train_test_split(X,Y,test_size=0.4, random_state=0)

from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_moons, make_circles, make_classification
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.lda import LDA
from sklearn.qda import QDA
from sklearn.pipeline import Pipeline
from sklearn.svm import LinearSVC

def tryAll():
	classifiers = [
		KNeighborsClassifier(3),
		DecisionTreeClassifier(max_depth=5),
		RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
		AdaBoostClassifier(),
		GaussianNB(),
		LDA(),
		QDA()]
	for clf in classifiers:
		clf=clf.fit(X_train, y_train)
		print(clf.score(X_test,y_test), clf)

clf=Pipeline([('feature_selection', LinearSVC(penalty='l1', dual=False)),('classification', RandomForestClassifier())])
clf.fit(X_train,y_train)
print(clf.score(X_test,y_test), clf)