def test():
test_df = pd.read_csv("test_processed.csv",index_col="PassengerId")
Xtest = test_df[feature_names]
gbdt = common.load_predictor("gbdt.pkl")
predictions = gbdt.predict(Xtest)
common.make_submission(Xtest.index,predictions,"submit_gbdt.csv")
def fit_train_data(allresults,name,needscale):
traindata = Xtrain_scaled if needscale else Xtrain
estimator = common.load_predictor("%s.pkl"%name)
print "[%s] training score: %f"%(name,estimator.score(traindata,ytrain))
predictions = estimator.predict(traindata)
allresults.append(predictions)
def fit_train_data(allresults, name, needscale):
traindata = Xtrain_scaled if needscale else Xtrain
estimator = common.load_predictor("%s.pkl" % name)
print "[%s] training score: %f" % (name, estimator.score(
traindata, ytrain))
predictions = estimator.predict(traindata)
allresults.append(predictions)
def fit_estimator(name, need_scale, y, X, scaledX):
temp = common.load_predictor("%s.pkl" % name)
estimator = skclone(temp)
if need_scale:
estimator.fit(scaledX, y)
else:
estimator.fit(X, y)
return Estimator(estimator, name, need_scale)
def fit_estimator(name,need_scale,y,X,scaledX):
temp = common.load_predictor("%s.pkl"%name)
estimator = skclone(temp)
if need_scale:
estimator.fit(scaledX,y)
else:
estimator.fit(X,y)
return Estimator(estimator,name,need_scale)
def train_whole():
train_df = pd.read_csv("train_processed.csv",index_col="PassengerId")
Xtrain = train_df[feature_names]
ytrain = train_df["Survived"]
# ------------------------------ load
# this estimator is trained on partial dataset, without using the valiation part
prev_estimator = common.load_predictor("gbdt-cv.pkl")
print "cross-validation score: %f"%(prev_estimator.score(Xtrain,ytrain))
# ------------------------------ train
# after we get the paramters, we should train another estimator with all data
gbdt = GradientBoostingClassifier(verbose=1,
loss=prev_estimator.loss,
learning_rate = prev_estimator.learning_rate,
n_estimators = prev_estimator.n_estimators,
max_depth = prev_estimator.max_depth)
print gbdt
gbdt.fit(Xtrain,ytrain)
print "training with all data, get score: ",gbdt.score(Xtrain,ytrain)
# ------------------------------ save
common.dump_predictor("gbdt.pkl",gbdt)
def train_whole():
prev_knn = common.load_predictor("knn-cv.pkl")
()