["user_answer", "tags", "type_of", "bundle_id", "previous_5_ans"],
axis=1)
df.columns = [
x.replace("[", "_").replace("]", "_").replace("'", "_").replace(
" ", "_").replace(",", "_") for x in df.columns
]
df = df[df["answered_correctly"].notnull()]
print(df.columns)
print(df.shape)
categorical_feature = ["content_id"]
print(model_id)
train_lgbm_cv_newuser(df,
categorical_feature=categorical_feature,
params=params,
output_dir=output_dir,
model_id=model_id,
exp_name=model_id,
is_debug=is_debug,
drop_user_id=True)
"""
params = {
'n_estimators': 12000,
'learning_rate': 0.1,
'eval_metric': 'AUC',
'loss_function': 'Logloss',
'random_seed': 0,
'metric_period': 50,
'od_wait': 400,
'task_type': 'GPU',
'max_depth': 8,
"verbose": 100
'metric': 'auc',
'verbosity': -1,
"n_estimators": 10000,
"early_stopping_rounds": 50
}
df.tail(1000).to_csv("exp028.csv", index=False)
df = df.drop([
"user_answer", "tags", "type_of", "bundle_id", "previous_3_ans"
],
axis=1)
df.columns = [
x.replace("[",
"_").replace("]", "_").replace("'", "_").replace(
" ", "_").replace(",", "_") for x in df.columns
]
df = df[df["answered_correctly"].notnull()]
categorical_feature = ["tags1", "tags2", "content_id"]
print(df.shape)
print(model_id)
train_lgbm_cv_newuser(
df,
categorical_feature=categorical_feature,
params=params,
output_dir=output_dir,
model_id=model_id,
exp_name=f"{model_id}_w2v_window{window}_size{size}",
is_debug=is_debug,
drop_user_id=True)
break
os.makedirs(output_dir, exist_ok=True)
params = {
'objective': 'binary',
'num_leaves': 32,
'min_data_in_leaf': 15, # 42,
'max_depth': -1,
'learning_rate': 0.1,
'boosting': 'gbdt',
'bagging_fraction': 0.7, # 0.5,
'feature_fraction': 0.5,
'bagging_seed': 0,
'reg_alpha': 0.1, # 1.728910519108444,
'reg_lambda': 1,
'random_state': 0,
'metric': 'auc',
'verbosity': -1,
"n_estimators": 10000,
"early_stopping_rounds": 100
}
df = df.drop(["user_answer"], axis=1)
print(df.columns)
train_lgbm_cv_newuser(df,
params=params,
output_dir=output_dir,
model_id=model_id,
exp_name="exp003",
new_user_ratio=0.01)
# break
df = df.drop(
["user_answer", "tags", "type_of", "bundle_id", "previous_3_ans"],
axis=1)
df.columns = [
x.replace("[", "_").replace("]", "_").replace("'", "_").replace(
" ", "_").replace(",", "_") for x in df.columns
]
df = df[df["answered_correctly"].notnull()]
print(df.columns)
print(df.shape)
print(model_id)
train_lgbm_cv_newuser(df,
params=params,
output_dir=output_dir,
model_id=model_id,
exp_name=model_id,
is_debug=is_debug,
drop_user_id=True)
if is_debug:
break
# fit
df_question = pd.read_csv(
"../input/riiid-test-answer-prediction/questions.csv",
dtype={
"bundle_id": "int32",
"question_id": "int32",
"correct_answer": "int8",
"part": "int8"
})
df.columns = [
x.replace("[", "_").replace("]", "_").replace("'", "_").replace(
" ", "_").replace(",", "_") for x in df.columns
]
df = df[df["answered_correctly"].notnull()]
print(df.columns)
print(df.shape)
categorical_feature = ["tags1", "tags2", "content_id"]
print(model_id)
use_columns = pd.read_csv("../output/ex_131/20201125230514/imp_train_0.csv"
)["feature"].values[:40].tolist()
train_lgbm_cv_newuser(df[["answered_correctly", "user_id"] + use_columns],
categorical_feature=categorical_feature,
params=params,
output_dir=output_dir,
model_id=model_id,
exp_name=model_id,
is_debug=is_debug,
drop_user_id=True)
params = {
'n_estimators': 12000,
'learning_rate': 0.1,
'eval_metric': 'AUC',
'loss_function': 'Logloss',
'random_seed': 0,
'metric_period': 50,
'od_wait': 400,
'task_type': 'GPU',
'max_depth': 8,
"verbose": 100
}
