def run():
# read train data.
X, y = cu.get_train_data(encode_non_object=True)
# train model.
lrm = LinearRegressionModel()
tarlist = [
c for c in X.columns if not c in
'fips,hashottuborspa,poolcnt,pooltypeid10,assessmentyear'.split(',')
]
X_trans, propdic = getTransData(X, y, tarlist)
x_train, y_train, x_holdout, y_holdout = cu.get_cv(X_trans, y)
lrm.train(x_train, y_train, None, None)
y_pred = lrm.predict(x_holdout)
score = abs(y_pred - y_holdout).mean()
print(score)
y_trans = [max([min([0.1, v]), -0.1]) for v in y]
lrm.train(X_trans, y_trans, None, None)
# read test data.
T = cu.get_test_data(encode_non_object=True)
T_trans = getTransTest(T, propdic)
# predict result.
print('Predicting.')
y_pred = lrm.predict(T_trans[X_trans.columns].values)
# write result.
cu.write_result(y_pred)
print(max(list(lrm.base_model.coef_)))
print(min(y_pred))
def run():
# read train data.
X, y = cu.get_train_data(encode_non_object=True)
# read test data.
T = cu.get_test_data(encode_non_object=True)
# create base models.
base_models = [
LinearRegressionModel(),
XGBoostModel(),
LightGBMModel()
]
# setup ensemble parameters.
ensemble = Ensemble(
n_folds=10,
stacker=LinearRegressionModel(),
base_models=base_models
)
# ensemble result.
print('Ensembling result.')
y_pred = ensemble.fit_predict(X, y, T[X.columns])
# write result.
cu.write_result(y_pred)
def run():
# read train data.
X, y = cu.get_train_data(encode_non_object=True)
# read test data.
T = cu.get_test_data(encode_non_object=True)
# create base models.
base_models = [
XGBoostModel(),
LightGBMModel(),
LinearRegressionModel(),
RidgeModel(),
LassoModel(),
ElasticNetModel(),
LassoLarsModel(),
BayesianRidgeModel(),
]
# setup ensemble parameters.
ensemble = Ensemble(stacker=LinearRegressionModel(),
base_models=base_models)
# ensemble result.
print('Ensembling result.')
y_pred = ensemble.fit_predict(X, y, T[X.columns])
# write result.
cu.write_result(y_pred)
def run():
# read train data.
X, y = cu.get_train_data(encode_non_object=False)
y_mean, y_std = y.mean(), y.std()
y -= y_mean
y /= y_std
# get CV from train data.
X_train, y_train, X_holdout, y_holdout = cu.get_cv(X, y)
# train model.
xgbm = XGBoostModel()
xgbm.train(X_train, y_train, X_holdout, y_holdout)
# read test data.
T = cu.get_test_data(encode_non_object=False)
# predict result.
print('Predicting.')
y_pred = xgbm.predict(T[X_train.columns])
y_pred *= y_std
y_pred += y_mean
# write result.
cu.write_result(y_pred)
def run():
# read train data.
X, y = cu.get_train_data(encode_non_object=False)
# MeanEncoder
print('Use MeanEncoder.')
mean_encoder = MeanEncoder(categorical_features=[
'regionidcity', 'regionidneighborhood', 'regionidzip'
],
target_type='regression')
X = mean_encoder.fit_transform(X, pd.Series(y))
X = X.drop(mean_encoder.categorical_features, axis=1)
# get CV from train data.
X_train, y_train, X_holdout, y_holdout = cu.get_cv(X, y)
# train model.
xgbm = XGBoostModel()
xgbm.train(X_train, y_train, X_holdout, y_holdout)
# read test data.
T = cu.get_test_data(encode_non_object=False)
T = mean_encoder.transform(T)
# predict result.
print('Predicting.')
y_pred = xgbm.predict(T[X_train.columns])
# write result.
cu.write_result(y_pred)
def run():
# read train data.
X, y = cu.get_train_data(encode_non_object=True)
# train model.
lrm = BayesianRidgeModel()
lrm.train(X, y)
# read test data.
T = cu.get_test_data(encode_non_object=True)
# predict result.
print('Predicting.')
y_pred = lrm.predict(T[X.columns])
# write result.
cu.write_result(y_pred)
def run():
# read train data.
X, y = cu.get_train_data(encode_non_object=True, standard_scaler_flag=True)
X = drop_columns(X)
# train model.
lrm = MLPRegressorModel()
lrm.train(X, y)
# read test data.
T = cu.get_test_data(encode_non_object=True, standard_scaler_flag=True)
# predict result.
print('Predicting.')
y_pred = lrm.predict(T[X.columns])
# write result.
cu.write_result(y_pred)
def run():
def gridSearch():
st,nt,step=5,51,5
for a in range(st,nt,step):
for b in range(st,nt,step):
rlist = []
for c in range(st,nt,step):
bindic = dict(zip(tarlist, [a, b, c]))
X_trans = dt.getTransData(X, tarlist, bindic)
# get CV from train data.
X_train, y_train, X_holdout, y_holdout = cu.get_cv(X_trans, y)
# train model.
xgbm = XGBoostModel()
xgbm.train(X_train, y_train, X_holdout, y_holdout)
rlist.append([a, b, c, xgbm.base_model.best_score])
with open('../../data/param.data','a') as outfile:
for vs in rlist:
outfile.write('\t'.join([str(v) for v in vs]) + '\n')
# read train data.
X, y = cu.get_train_data(encode_non_object=True)
tarlist = X.columns
X_trans, propdic = dt.getTransData(X, y, tarlist)
for c in tarlist:
X_trans[c] = X_trans[c].astype(float)
# get CV from train data.
X_train, y_train, X_holdout, y_holdout = cu.get_cv(X_trans, y)
# train model.
xgbm = XGBoostModel()
xgbm.train(X_train, y_train, X_holdout, y_holdout)
# read test data.
T = cu.get_test_data(encode_non_object=True)
T_trans = dt.getTransTest(T, propdic)
# predict result.
print('Predicting.')
y_pred = xgbm.predict(T_trans[X_train.columns])
# write result.
cu.write_result(y_pred)
def run():
# read train data.
X, y = cu.get_train_data(encode_non_object=False)
# get CV from train data.
X_train, y_train, X_holdout, y_holdout = cu.get_cv(X, y)
# train model.
lgbmm = LightGBMModel()
lgbmm.train(X_train, y_train, X_holdout, y_holdout)
# read test data.
T = cu.get_test_data(encode_non_object=False)
# predict result.
print('Predicting.')
y_pred = lgbmm.predict(T[X_train.columns])
# write result.
cu.write_result(y_pred)
def run():
# read train data.
X, y = cu.get_train_data(encode_non_object=False)
print('Transform, replace feature outliers.')
X['yearbuilt'] = 2016 - X['yearbuilt']
yearbuilt_llimit, yearbuilt_ulimit = get_series_percentile(X['yearbuilt'])
yearbuilt_median = X['yearbuilt'].median()
taxamount_q1, taxamount_q3 = get_series_q1q3(X['taxamount'])
X['yearbuilt'] = replace_with_value(X['yearbuilt'], yearbuilt_llimit,
yearbuilt_ulimit, yearbuilt_median)
X['taxamount'] = replace_with_iqr_boundary(X['taxamount'], taxamount_q1,
taxamount_q3)
# get CV from train data.
X_train, y_train, X_holdout, y_holdout = cu.get_cv(X, y)
# train model.
xgbm = XGBoostModel()
xgbm.train(X_train, y_train, X_holdout, y_holdout)
# read test data.
T = cu.get_test_data(encode_non_object=False)
T['yearbuilt'] = 2016 - T['yearbuilt']
T['yearbuilt'] = replace_with_value(T['yearbuilt'], yearbuilt_llimit,
yearbuilt_ulimit, yearbuilt_median)
T['taxamount'] = replace_with_iqr_boundary(T['taxamount'], taxamount_q1,
taxamount_q3)
# predict result.
print('Predicting.')
y_pred = xgbm.predict(T[X_train.columns])
# write result.
cu.write_result(y_pred)
y_train_trim = [max([min([0.1, v]), -0.1]) for v in y_train]
y_train_trim = np.array(y_train_trim)
model.fit(x_train.values, y_train_trim, epochs=5, batch_size=32)
y_pred = model.predict(x_holdout.values)
y_pred = y_pred[:, 0]
score = abs(y_pred - y_holdout).mean()
print(score)
# read test data.
T = cu.get_test_data(encode_non_object=True)
T_trans = getTransTest(T, propdic)
# predict result.
print('Predicting.')
y_pred = model.predict(T_trans[X_trans.columns].values)
# write result.
cu.write_result(y_pred)
#tmpdf = getTransTest(T.iloc[-100:,:], propdic)
#print(tmpdf.shape)
#for c in tmpdf.columns:
# print(c)
# print(tmpdf[c].value_counts())
#tmpy = model.predict(tmpdf[X_trans.columns].values)
#print(tmpy)
#print(tmpdf[X_trans.columns].values)
#print(tmpdf.latitude)
#print(T.iloc[-100:,:].latitude)
#print(propdic['latitude'])