def gen_sub():
train = train_data.copy()
train_idx = [i for i in range(train.shape[0])]
test = test_data.copy()
test_idx = [i + train.shape[0] for i in range(test.shape[0])]
y = train["interest_level"].apply(lambda x: target_num_map[x])
del train["interest_level"]
data = pd.concat([train, test]).reset_index()
X_train, X_test, feats = coreProcess(data, y, train_idx, test_idx)
xgb_clf = xgboostClassifier(
objective='multi:softprob',
eval_metric='mlogloss',
num_class=3,
nthread=12,
eta=0.02,
max_depth=6,
subsample=0.8,
colsample_bytree=1.0,
colsample_bylevel=0.8,
min_child_weight=1,
silent=1,
num_rounds=1700,
seed=RS,
)
print("Trainning:...")
xgb_clf.fit(X_train, y)
preds = xgb_clf.predict_proba(X_test)
sub = pd.DataFrame(preds)
# sub.columns = ["high", "medium", "low"]
sub.columns = ["high", "medium", "low"]
sub["listing_id"] = test.listing_id.values
sub.to_csv("submission.csv", index=False)
def validation_score(early_stop=False):
clf = xgboostClassifier(
objective='multi:softprob',
eval_metric='mlogloss',
num_class=3,
nthread=3,
eta=0.04,
max_depth=6,
subsample=0.7,
colsample_bytree=1.0,
colsample_bylevel=0.7,
min_child_weight=1,
silent=1,
num_rounds=700,
seed=RS,
)
print("*** Validation start ***")
data = train_data.copy()
y = data["interest_level"].apply(lambda x: target_num_map[x])
del data["interest_level"]
# skf = StratifiedKFold(n_splits=5, random_state=RS, shuffle=True)
skf = StratifiedKFold(n_splits=3, shuffle=False)
cv_scores = []
i = 0
for train_idx, val_idx in skf.split(data, y):
i += 1
X = data.copy()
y_train, y_val = y.iloc[train_idx], y.iloc[val_idx]
X_train, X_val, feats = coreProcess(X, y_train, train_idx, val_idx)
clf.fit(X_train, y_train)
# clf.fit_CV(X_train, X_val, y_train, y_val)
y_val_pred = clf.predict_proba(X_val)
loss = log_loss(y_val, y_val_pred)
print("Iteration {}'s loss: {}".format(i, loss))
cv_scores.append(loss)
if early_stop:
break
print("*** Validation finished ***\n")
return cv_scores
def search():
param_dict = {
'eta': [0.02],
'max_depth': [6],
'subsample': [0.8],
'colsample_bylevel': [0.7],
'num_rounds': [1400, 1500, 1600, 1650],
}
clf = xgboostClassifier(
objective='multi:softprob',
eval_metric='mlogloss',
num_class=3,
nthread=12,
eta=0.04,
max_depth=6,
subsample=0.7,
colsample_bytree=1.0,
colsample_bylevel=1.0,
min_child_weight=1,
silent=1,
num_rounds=700,
seed=RS,
)
paramSearch(clf, param_dict)
# colsample_bytree = 1.0,
# colsample_bylevel = 0.8,
# min_child_weight=1,
# silent = 1,
# num_rounds = 1700,
# seed = 0,
# ))
clfs.append(
xgboostClassifier(
objective='multi:softprob',
eval_metric='mlogloss',
num_class=3,
nthread=9,
eta=0.02,
max_depth=6,
subsample=0.8,
colsample_bytree=1.0,
colsample_bylevel=0.7,
min_child_weight=1,
silent=1,
num_rounds=1500,
seed=0,
))
clfs.append(
xgboostClassifier(
objective='multi:softprob',
eval_metric='mlogloss',
num_class=3,
nthread=9,
eta=0.02,
max_depth=6,