def main():
#read in the training file
train = csv_io.read_csv("input_data/train.csv")
train = train.values
#set the training responses
target = [x[0] for x in train]
#set the training features
train = [x[1:] for x in train]
#read in the test file
realtest = csv_io.read_csv("input_data/test.csv")
realtest = realtest.values
# random forest code
rf = RandomForestClassifier(n_estimators=150, min_samples_split=2, n_jobs=-1)
# fit the training data
print('fitting the model')
rf.fit(train, target)
print("Fitting complete!!!")
# run model against test data
predicted_probs = rf.predict_proba(realtest)
predicted_probs = ["%d" % x[1] for x in predicted_probs]
total_len = len(predicted_probs)
result_df = pd.DataFrame({"ImageId" : range(1, total_len + 1), "Label" : predicted_probs[:]})
csv_io.write_csv("random_forest_solution.csv", result_df)
print ('Random Forest Complete! You Rock! Submit random_forest_solution.csv to Kaggle')
def main():
#read in the training file
header, csv = csv_io.read_csv("transactions.csv")
header = np.array(header[2:])
weight = np.array([x[0] for x in csv])
target = [x[1] for x in csv]
days_ago = [x[2] for x in csv]
#balance = [x[9] for x in csv]
train = [x[2:] for x in csv]
print('fitting the model')
rf = RandomForestRegressor(oob_score=True, n_estimators=100, max_features="auto")
#rf = RandomForestRegressor(n_estimators=100)
scores = cross_validation.cross_val_score(rf, train, target, cv=3)
print scores
print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))
#rf = AdaBoostRegressor()
#scores = cross_validation.cross_val_score(rf, train, target, cv=3)
#print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))
#rf = GradientBoostingRegressor()
#scores = cross_validation.cross_val_score(rf, train, target, cv=3)
#print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))
#rf = BaggingRegressor()
#scores = cross_validation.cross_val_score(rf, train, target, cv=3)
#print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))
#return
#rf.fit(train, target, weight)
rf.fit(train, target)
print "oob_score: %f" % rf.oob_score_
#print target
#print list(rf.oob_prediction_)
order = np.argsort(rf.feature_importances_)[::-1]
print order[0:19]
print header[order[0:19]]
print rf.feature_importances_[order[0:19]]
print np.sum(rf.feature_importances_[order[0:19]])
print np.sum(rf.feature_importances_)
return
print np.array(np.array(range(len(train))),rf.feature_importances_)
print list(np.sort(rf.feature_importances_))
#x = np.array([target, list(rf.oob_prediction_)]).T
#print x
print rf.oob_score_
#plt.plot(days_ago, balance, 'g-')
#plt.show()
plt.plot(days_ago, target, 'g-', days_ago, list(rf.oob_prediction_), 'r-')
plt.show()
def main():
#read in the training and test data
train = csv_io.read_csv("data/train.csv")
#the first column of the training set will be the target for the random forest classifier
target = [x[0] for x in train]
train = [x[1:] for x in train]
test = csv.read_csv("data/test.csv")
#create and train the random forest
print(train.data)
def to_json(input_file):
csv_data = csv_io.read_csv(input_file)
relation = {}
for row in csv_data:
relation[row[0]] = {}
for i in range(1, len(row)):
relation[row[0]][row[i]] = {'know': 1}
json_io.write_json('output/social_graph.json', relation)
def main():
#Auth
storage = Storage('prediction.dat')
credentials = storage.get()
if credentials is None or credentials.invalid: credentials = run(FLOW, storage)
http = httplib2.Http()
http = credentials.authorize(http)
service = build("prediction", "v1.4", http=http)
testset = csv_io.read_csv("test.csv", False)
submit = []
count = 1
for i in range(len(testset)):
try:
body = {"input":{"csvInstance":parseInput(testset[i])}}
prediction = service.trainedmodels().predict(id="br2", body=body).execute()
predval = prediction['outputValue']
#Google Predict isn't smart enough to figure out that we want a probability
#Instead it fits a regression, which can go outside the range 0-1
if predval >=1.0: predval = 0.99999
if predval <=0.0: predval = 0.00001
submit.append(predval)
print str(count) + ": " + str(predval)
except AccessTokenRefreshError:
print ("The credentials have been revoked or expired, please re-run the application to re-authorize")
except:
etype, value, tb = sys.exc_info()
msg = ''.join(traceback.format_exception(etype, value, tb))
csv_io.write_csv("g_submit_err.csv", [["%f" % x] for x in submit])
print "error on: " + str(i) + " exception: " + msg
if count % 50 == 0:
csv_io.write_csv("g_submit.csv", [["%f" % x] for x in submit])
print "wrote to disk"
count = count + 1
#uncomment below if hitting throttling limites from Google
#time.sleep(0.5)
csv_io.write_csv("g_submit.csv", [["%f" % x] for x in submit])
import numpy as np from sklearn import svm from csv_io import read_csv if __name__ == '__main__': data = read_csv(r'data/training.csv') data_points, n_features = data.shape n_features = n_features - 1 X = data[:,2:5] y = data[:,n_features] clf = svm.SVC() clf.fit(X,y) data = read_csv(r'data/test.csv') X = data[:,2:5] y = clf.predict(X)
