def make_submission_2012(fn, predictions):
# get 2012 ids
ids = get_pkl("saved_objs/test_2012.pkl")[1:, 0:1]
# If passed 1d array, change to column
if (predictions.ndim == 1):
predictions = predictions.reshape((-1, 1))
np.savetxt(fn,
np.concatenate((ids, predictions), axis=1),
delimiter=',',
header="id,PES1",
comments='',
fmt="%d,%d")
import os.path
import sys
import getopt
import numpy as np
from pkl_help import get_pkl
from pkl_help import read_make_pkl
import preprocess_help as ph
from sklearn.ensemble import AdaBoostClassifier
from submission import make_submission_2008
from submission import make_submission_2012
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
# Get training data
X_train_2008 = get_pkl("saved_objs/X_train_2008.pkl")
Y_train_2008 = get_pkl("saved_objs/Y_train_2008.pkl")
X_test_2008 = get_pkl("saved_objs/X_test_2008.pkl")
X_test_2012 = get_pkl("saved_objs/X_test_2012.pkl")
X_ver = get_pkl("saved_objs/X_ver_2008.pkl")
Y_ver = get_pkl("saved_objs/Y_ver_2008.pkl")
def knearest_modified_predict(model, Y):
preds = model.predict(Y).reshape(-1, 1)
# Debug
print("preds.shape: " + str(preds.shape))
return preds
def optimize_parameters():
score = 0.0
import os.path
import sys
import getopt
import numpy as np
from pkl_help import get_pkl
from pkl_help import read_make_pkl
import preprocess_help as ph
from sklearn.ensemble import VotingClassifier
from submission import make_submission_2008
from submission import make_submission_2012
from round_predictions import round_predictions
X_train_2008 = get_pkl("saved_objs/X_train_2008.pkl")
Y_train_2008 = get_pkl("saved_objs/Y_train_2008.pkl")
X_test_2008 = get_pkl("saved_objs/X_test_2008.pkl")
X_test_2012 = get_pkl("saved_objs/X_test_2012.pkl")
X_ver = get_pkl("saved_objs/X_ver_2008.pkl")
Y_ver = get_pkl("saved_objs/Y_ver_2008.pkl")
def modified_predict(model, Y):
preds = model.predict(Y).reshape(-1, 1)
# Debug
print("preds.shape: " + str(preds.shape))
return preds
xgb_score = 0.77900
adaboost_ran_forest_score = 0.77838
adaboost_score = 0.77525
lasso_score = 0.77225
import os.path
import sys
import getopt
import numpy as np
from pkl_help import get_pkl
from pkl_help import read_make_pkl
import preprocess_help as ph
from sklearn.ensemble import VotingClassifier
from submission import make_submission_2008
from submission import make_submission_2012
from sklearn.linear_model import RidgeClassifierCV
# Get training data
X_train_2008 = get_pkl("saved_objs/X_train_2008.pkl")
Y_train_2008 = get_pkl("saved_objs/Y_train_2008.pkl")
X_test_2008 = get_pkl("saved_objs/X_test_2008.pkl")
X_test_2012 = get_pkl("saved_objs/X_test_2012.pkl")
X_ver = get_pkl("saved_objs/X_ver_2008.pkl")
Y_ver = get_pkl("saved_objs/Y_ver_2008.pkl")
# Grab all models we have.
ridge = RidgeClassifierCV().fit(X_train_2008, Y_train_2008)
# lasso = get_pkl("saved_objs/lasso.pkl")
mlp = get_pkl("saved_objs/mlp.pkl")
rand_forest = get_pkl("saved_objs/rand_forest.pkl")
adaboost = get_pkl("saved_objs/adaboost.pkl")
# knn = get_pkl("saved_objs/knearest.pkl")
def voting_modified_predict(model, Y):
preds = model.predict(Y).reshape(-1, 1)