#!/usr/bin/env python
# First prediction, using sklearn's RandomForestClassifier
import lib.loader as ld
import sklearn.ensemble as ens
if __name__ == '__main__':
trainx, trainy = ld.loadtrain('data/trainingdata.txt')
testx = ld.loadtest('data/testingdata.txt')
clf = ens.RandomForestClassifier(criterion='entropy', n_estimators=20)
clf.fit(trainx, trainy)
ld.write('predictions/Prediction1.txt', clf.predict(testx))
# Score: 0.52515
n_jobs=n_jobs))
# 0.0420 + 0.16 - 0.04
elif rand == 5:
numChange = comp.append(
lm.SGDClassifier(loss='hinge',
alpha=0.000631 + 0.01 * r.random()))
# 0.000631 + 0.01
elif rand == 6:
numChange = comp.append(
svm.LinearSVC(dual=False, C=0.01 + 0.1 * r.random()))
# 0.01 + 0.1
elif rand == 7:
numChange = comp.append(
ens.RandomForestClassifier(n_estimators=100,
max_features=0.120 +
0.4 * r.random(),
min_samples_split=7,
n_jobs=n_jobs))
# 0.32 +- 0.2
elif rand == 8:
numChange = comp.append(
svm.LinearSVC(dual=False, C=100 + 900 * r.random()))
# 1000 - 900
if numChange == 0:
num_consec += 1
else:
num_consec = 0
print('Number CV Changes: ' + str(numChange))
if len(comp.clfs) % save_interval == 0: # don't save every time
ld.write('predictions/Prediction7.txt', comp.predict())
# 0.7 +- 0.3
elif rand == 4:
numChange = comp.append(ens.RandomForestClassifier(n_estimators=450,
max_features=0.0020 + 0.2 * r.random(), min_samples_split=7,
n_jobs=n_jobs))
# 0.0420 + 0.16 - 0.04
elif rand == 5:
numChange = comp.append(lm.SGDClassifier(loss='hinge',
alpha=0.000631 + 0.01 * r.random()))
# 0.000631 + 0.01
elif rand == 6:
numChange = comp.append(svm.LinearSVC(dual=False, C=0.01 + 0.1 *
r.random()))
# 0.01 + 0.1
elif rand == 7:
numChange = comp.append(ens.RandomForestClassifier(n_estimators=100,
max_features=0.120 + 0.4 * r.random(), min_samples_split=7,
n_jobs=n_jobs))
# 0.32 +- 0.2
elif rand == 8:
numChange = comp.append(svm.LinearSVC(dual=False, C=100 + 900 *
r.random()))
# 1000 - 900
if numChange == 0:
num_consec += 1
else:
num_consec = 0
print('Number CV Changes: ' + str(numChange))
if len(comp.clfs) % save_interval == 0: # don't save every time
ld.write('predictions/Prediction7.txt', comp.predict())
#!/usr/bin/env python
# prediction 3 with more features. Totally guessing by now
import numpy as np
import lib.loader as ld
import sklearn.ensemble as ens
import sklearn.feature_extraction.text as tfidf
if __name__ == '__main__':
ens.RandomForestClassifier(n_jobs=-1)
trainx, trainy = ld.loadtrain('data/trainingdata.txt')
testx = ld.loadtest('data/testingdata.txt')
trainx2 = tfidf.TfidfTransformer().fit_transform(trainx)
testx2 = tfidf.TfidfTransformer().fit_transform(testx)
clf = ens.RandomForestClassifier(max_features=0.38, criterion='entropy',
n_estimators=5000, min_samples_split=7)
clf.fit(trainx2, trainy)
ld.write('predictions/Prediction5.txt', clf.predict(testx2))
# score=0.51
#!/usr/bin/env python
# prediction 3, with gridsearch'd parameters
import lib.loader as ld
import sklearn.ensemble as ens
import sklearn.feature_extraction.text as tfidf
if __name__ == '__main__':
ens.RandomForestClassifier(n_jobs=-1)
trainx, trainy = ld.loadtrain('data/trainingdata.txt')
testx = ld.loadtest('data/testingdata.txt')
trainx2 = tfidf.TfidfTransformer().fit_transform(trainx)
testx2 = tfidf.TfidfTransformer().fit_transform(testx)
clf = ens.RandomForestClassifier(max_features=0.0420,
criterion='entropy',
n_estimators=5000,
min_samples_split=7)
clf.fit(trainx2, trainy)
ld.write('predictions/Prediction3.txt', clf.predict(testx2))
# score 0.51
