def build_tabnet():
model_file_name = 'tabnet_model_{}'.format(current_dataset_name)
df = current_dataset.copy()
cleaning_text(df)
X = df['clean_content']
y = df['emotion']
# tokenize la data
tok = Tokenizer(num_words=1000, oov_token='<UNK>')
# fit le model avec les données de train
# tok.fit_on_texts(X)
# X = tok.texts_to_matrix(X, mode='tfidf')
# split data
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
stratify=y,
random_state=1)
X_test_save = X_test
tok.fit_on_texts(X_test)
X_test = tok.texts_to_matrix(X_test, mode='tfidf')
tok.fit_on_texts(X_train)
X_train = tok.texts_to_matrix(X_train, mode='tfidf')
# X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.3, stratify=y)
# build model, fit and predict
if LOAD_MODEL and pathlib.Path(model_file_name).exists():
model = pickle.load(open(model_file_name, 'rb'))
else:
model = TabNetClassifier()
model.fit(X_train=X_train,
y_train=y_train,
eval_set=[(X_train, y_train), (X_test, y_test)],
eval_name=['train', 'valid'],
eval_metric=['accuracy', 'balanced_accuracy', 'logloss'])
preds_mapper = {
idx: class_name
for idx, class_name in enumerate(model.classes_)
}
preds = model.predict_proba(X_test)
y_pred_proba = np.vectorize(preds_mapper.get)(np.argmax(preds, axis=1))
y_pred = model.predict(X_test)
test_acc = accuracy_score(y_pred=y_pred, y_true=y_test)
pickle.dump(model, open(model_file_name, 'wb'))
# model.save_model(model_file_name)
return model, y_test, y_pred, test_acc
class ModelTabNetClassifier(Model):
def train(self, tr_x, tr_y, va_x=None, va_y=None, te_x=None):
categorical_dims = {}
for col in self.categorical_features:
tr_x[col] = tr_x[col].fillna("unk")
va_x[col] = va_x[col].fillna("unk")
te_x[col] = te_x[col].fillna("unk")
categorical_dims[col] = len(set(tr_x[col].values) | set(va_x[col].values) | set(te_x[col].values))
cat_idxs = [i for i, f in enumerate(tr_x.columns) if f in self.categorical_features]
cat_dims = [categorical_dims[f] for i, f in enumerate(tr_x.columns) if f in self.categorical_features]
cat_emb_dim = [10 for _ in categorical_dims]
for col in tr_x.columns:
tr_x[col] = tr_x[col].fillna(tr_x[col].mean())
va_x[col] = va_x[col].fillna(tr_x[col].mean())
te_x[col] = te_x[col].fillna(tr_x[col].mean())
self.model = TabNetClassifier(cat_dims=cat_dims, cat_emb_dim=cat_emb_dim, cat_idxs=cat_idxs)
self.model.fit(X_train=tr_x.values, y_train=tr_y.values,
X_valid=va_x.values, y_valid=va_y.values,
max_epochs=1000,
patience=50,
batch_size=1024,
virtual_batch_size=128)
def predict(self, te_x):
return self.model.predict_proba(te_x.values)[:, 1].reshape(-1, )
def save_model(self):
model_path = os.path.join('../output/model', f'{self.run_fold_name}.model')
os.makedirs(os.path.dirname(model_path), exist_ok=True)
Data.dump(self.model, model_path)
def load_model(self):
model_path = os.path.join('../output/model', f'{self.run_fold_name}.model')
self.model = Data.load(model_path)
def main():
# Generate Synthetic Data
data, test_data, cat_col_names, num_col_names = data_load()
cat_dims = data[cat_col_names].nunique().to_list()
cat_idxs = [(cat_col_names + num_col_names).index(cat_col)
for cat_col in cat_col_names]
cat_emb_dims = np.ceil(np.log(cat_dims)).astype(np.int).tolist()
cat_emb_dims = np.ceil(np.clip((np.array(cat_dims)) / 2, a_min=1,
a_max=50)).astype(np.int).tolist()
FEATURES = cat_col_names + num_col_names
df_sub = pd.read_csv('Data/sample_submission.csv')
bsize = 2500 * 2
# ##########Define the Configs############
N_D = 16
N_A = 16
N_INDEP = 2
N_SHARED = 2
N_STEPS = 1 # 2
MASK_TYPE = "sparsemax"
GAMMA = 1.5
BS = 512
MAX_EPOCH = 21 # 20
PRETRAIN = True
X = data[FEATURES].values
y = data["target"].values
X_test = test_data[FEATURES].values
if PRETRAIN:
pretrain_params = dict(
n_d=N_D,
n_a=N_A,
n_steps=N_STEPS, # 0.2,
n_independent=N_INDEP,
n_shared=N_SHARED,
cat_idxs=cat_idxs,
cat_dims=cat_dims,
cat_emb_dim=cat_emb_dims,
gamma=GAMMA,
lambda_sparse=0.,
optimizer_fn=torch.optim.Adam,
optimizer_params=dict(lr=2e-2),
mask_type=MASK_TYPE,
scheduler_params=dict(
mode="min",
patience=3,
min_lr=1e-5,
factor=0.5,
),
scheduler_fn=torch.optim.lr_scheduler.ReduceLROnPlateau,
verbose=1,
)
pretrainer = TabNetPretrainer(**pretrain_params)
pretrainer.fit(
X_train=X_test,
eval_set=[X],
max_epochs=MAX_EPOCH,
patience=25,
batch_size=BS,
virtual_batch_size=BS, # 128,
num_workers=0,
drop_last=True,
pretraining_ratio=
0.5 # The bigger your pretraining_ratio the harder it is to reconstruct
)
# Training the Model
# tabular_mode.fit(train=train, validation=val)
# # Evaluating the Model
# # #Loss and Metrics on New Data¶
# result = tabular_mode.evaluate(test)
cv = StratifiedKFold(n_splits=10, shuffle=True, random_state=777)
BS = 2048
MAX_EPOCH = 20
# skf = StratifiedKFold(n_splits=5, random_state=2021, shuffle=True)
data['oof_preds'] = np.nan
for fold_nb, (train_index, valid_index) in enumerate(cv.split(X, y)):
X_train, X_valid = X[train_index], X[valid_index]
y_train, y_valid = y[train_index], y[valid_index]
tabnet_params = dict(
n_d=N_D,
n_a=N_A,
n_steps=N_STEPS,
gamma=GAMMA,
n_independent=N_INDEP,
n_shared=N_SHARED,
lambda_sparse=1e-5,
seed=0,
clip_value=2,
cat_idxs=cat_idxs,
cat_dims=cat_dims,
cat_emb_dim=cat_emb_dims,
mask_type=MASK_TYPE,
device_name='auto',
optimizer_fn=torch.optim.Adam,
optimizer_params=dict(lr=5e-2, weight_decay=1e-5),
scheduler_params=dict(
max_lr=5e-2,
steps_per_epoch=int(X_train.shape[0] / BS),
epochs=MAX_EPOCH,
# final_div_factor=100,
is_batch_level=True),
scheduler_fn=torch.optim.lr_scheduler.OneCycleLR,
# scheduler_params=dict(mode='max',
# factor=0.5,
# patience=5,
# is_batch_level=False,),
# scheduler_fn=torch.optim.lr_scheduler.ReduceLROnPlateau,
verbose=1)
# Defining TabNet model
model = TabNetClassifier(**tabnet_params)
model.fit(
X_train=X_train,
y_train=y_train,
from_unsupervised=pretrainer if PRETRAIN else None,
eval_set=[(X_train, y_train), (X_valid, y_valid)],
eval_name=["train", "valid"],
eval_metric=["auc"],
batch_size=BS,
virtual_batch_size=256,
max_epochs=MAX_EPOCH,
drop_last=True,
pin_memory=True,
patience=10,
)
val_preds = model.predict_proba(X_valid)[:, -1]
print('auc:', roc_auc_score(y_true=y_valid, y_score=val_preds))
data['oof_preds'].iloc[valid_index] = val_preds
test_preds = model.predict_proba(X_test)[:, -1]
df_sub[f"fold_{fold_nb+1}"] = test_preds
df_sub["target"] = df_sub.filter(like="fold_").mean(axis=1).values
df_sub.to_csv("Analysis/submission_5_tabnet.csv", index=False)
df_sub = pd.read_csv("Analysis/submission_5_tabnet.csv")
# df_sub.target = df_sub.target.map(lambda x: 0 if x<=0.5 else 1)
df_sub.loc[:,
["id", "target"]].to_csv("Analysis/submission_5_2_tabnet.csv",
index=False)
y_test = y_all[d_train.shape[0]:(d_train.shape[0]+d_test.shape[0])]
cat_idxs = [ i for i, col in enumerate(X_all.columns) if col in vars_cat]
cat_dims = [ len(np.unique(X_all.iloc[:,i].values)) for i in cat_idxs]
cat_emb_dim = np.floor(np.log(cat_dims)).astype(int)
md = TabNetClassifier(cat_idxs=cat_idxs,
cat_dims=cat_dims,
cat_emb_dim=cat_emb_dim,
## optimizer_fn=torch.optim.Adam,
## optimizer_params=dict(lr=2e-2),
## mask_type='sparsemax',
n_steps=1,
)
%%time
md.fit( X_train=X_train, y_train=y_train,
eval_set=[(X_train, y_train), (X_test, y_test)],
eval_name=['train', 'test_EVIL'],
eval_metric=['auc'],
max_epochs=100, patience=100,
## batch_size=1024, virtual_batch_size=128,
## weights=0,
)
y_pred = md.predict_proba(X_test)[:,1]
print(metrics.roc_auc_score(y_test, y_pred))
X_train=X_trn,
y_train=y_trn,
eval_set=[(X_trn, y_trn), (X_vld, y_vld)],
eval_name=["train", "valid"],
eval_metric=["logloss"],
max_epochs=max_epochs,
patience=50,
batch_size=128,
virtual_batch_size=128,
num_workers=0,
weights=1,
drop_last=False,
from_unsupervised=loaded_pretrain,
)
fold_preds = clf.predict_proba(X_vld).astype(np.float64)[:, 1]
_test_preds.append(clf.predict_proba(X_tst)[:, 1])
oof[vld_index] = fold_preds
scores.append(log_loss(y_vld, fold_preds))
importances = pd.concat(
[
importances,
pd.DataFrame({"feature": feat_cols, "importance": clf.feature_importances_}),
],
axis=0,
)
oof_preds.append(oof)
test_preds.append(np.mean(_test_preds, axis=0))
fig, ax = plt.subplots(figsize=(6, 18))
X_train=X_trn,
y_train=y_trn,
eval_set=[(X_trn, y_trn), (X_vld, y_vld)],
eval_name=["train", "valid"],
eval_metric=["logloss"],
max_epochs=max_epochs,
patience=25,
batch_size=128,
virtual_batch_size=128,
num_workers=0,
weights=1,
drop_last=False,
from_unsupervised=loaded_pretrain,
)
fold_preds = clf.predict_proba(X_vld).astype(np.float64)
preds[vld_index] = fold_preds[:, 1]
scores.append(log_loss(y_vld, fold_preds[:, 1]))
importances = pd.concat(
[
importances,
pd.DataFrame({
"feature": feat_cols,
"importance": clf.feature_importances_
})
],
axis=0,
)
fig, ax = plt.subplots(figsize=(6, 18))
sns.barplot(
#we separe between categorical variables and date variables to preprocess it separately
categorical_val.remove('answer_creation_date')
categorical_val.remove('group_creation_date')
categorical_val.remove('request_creation_date')
categorical_val.remove('victim_of_violence_type')
date_columns = [
'answer_creation_date', 'group_creation_date', 'request_creation_date'
]
X_test, y_test = preprocess(requests_test, categorical_val, date_columns)
# Drop Nan value because otherwise there are memory errors
X_test['granted_number_of_nights'] = y_test
X_test = X_test.dropna()
y_test = X_test['granted_number_of_nights']
X_test = X_test.drop(columns=['granted_number_of_nights'])
#preprocess the datasets for TabNet
X_test_tab, y_test_tab = preprocess_for_tabnet(X_test, y_test)
# retrieve model
# Not working with version <3.7
PATH = '../model_zoo/TabNet_model.zip'
clf = TabNetClassifier()
clf.load_model(PATH)
#run inference
start = time.time()
preds = clf.predict_proba(X_test_tab)
end = time.time()
score = competition_scorer(y_test_tab, preds)
print('time per prediction:', (end - start) / len(X_test))
print('The competition score on test data', score)
class TabNetCv1(TabNetBase):
def act_init_ai(self, is_test=False):
if is_test is True:
_TPI(self, locals())
else:
MATCH = self.env.match_loader
self.ai = TabNetClassifier(n_steps=10,
input_dim=MATCH.count_cols *
MATCH.count_players,
cat_dims=self.cat_dims,
cat_emb_dim=self.cat_emb_dim,
cat_idxs=self.cat_idxs,
device_name='cuda')
def act_modify_data(self, is_test=False):
if is_test is True:
_TPI(self, locals())
else:
MATCH = self.env.match_loader
for i in range(len(self.y_train)):
result = MATCH.train_plus[i] - MATCH.train_minus[i]
if result < 0:
result = 0
elif result == 0:
result = 1
else:
result = 2
self.y_train[i] = result
for i in range(len(self.y_valid)):
result = MATCH.valid_plus[i] - MATCH.valid_minus[i]
if result < 0:
result = 0
elif result == 0:
result = 1
else:
result = 2
self.y_valid[i] = result
for i in range(len(self.y_valid)):
result = MATCH.test_plus[i] - MATCH.test_minus[i]
if result < 0:
result = 0
elif result == 0:
result = 1
else:
result = 2
self.y_test[i] = result
def load_model(self):
print("Loading Model")
print(self.save_name + ".zip")
self.ai.load_model(self.save_name + ".zip")
def get_result(self, my_team: list, your_team: list):
# tmp
'''
MATCH = self.env.match_loader
self.act_register_data(data=MATCH.act_get(is_flat=True))
self.act_modify_data()
self.ai = TabNetClassifier(
n_steps=10,
input_dim=MATCH.count_cols * MATCH.count_players,
cat_dims=self.cat_dims,
cat_emb_dim=self.cat_emb_dim,
cat_idxs=self.cat_idxs,
device_name='cuda'
)
self.ai.fit(
X_train=self.X_train, y_train=self.y_train,
X_valid=self.X_valid, y_valid=self.y_valid,
max_epochs=self.epochs,
patience=500,
batch_size=512,
drop_last=False
)
'''
try:
x = list()
for player in my_team:
x.append(0)
x.extend(player)
for player in your_team:
x.append(1)
x.extend(player)
x = np.array(x)
x = np.array([x])
print(x.shape)
# predictions = self.ai.predict(x)
probability = self.ai.predict_proba(x)
print(probability)
return probability[0][2]
except Exception as e:
print(e)
"gamma": 0.9
},
scheduler_fn=torch.optim.lr_scheduler.StepLR,
mask_type='entmax' # "sparsemax"
)
clf.fit(X_train=X_tr,
y_train=y_tr,
X_valid=X_val,
y_valid=y_val,
max_epochs=epoch,
patience=epoch,
batch_size=1024,
virtual_batch_size=128,
num_workers=0,
weights=1,
drop_last=False)
test_pred += clf.predict_proba(X_test)[:, 1]
test_pred /= 5
test_auc = roc_auc_score(y_test, test_pred)
print('test auc:', test_auc)
res[data_name] = test_auc
print(res)
with open("tabnet_result.pickle", "wb") as f:
pickle.dump(res, f)