def get_predictions(df: pd.DataFrame, model: lgbm.LGBMRanker):
"""
:param df:
:return:
"""
print(f'\tPredicting relevance')
test_pred = model.predict(df)
df['relevance'] = test_pred
df.sort_values(by=['srch_id', 'relevance'],
ascending=[True, False],
inplace=True)
kaggle_answer = pd.DataFrame({
'srch_id': df['srch_id'],
'prop_id': df['prop_id']
})
print(f'\t Writing answers to csv')
kaggle_answer.to_csv('expedia_answer.csv', index=False)
# Convert to numpy
groups = np.array(groups)
y = np.array(y)
X = np.array(X)
unique_groups = np.unique(groups)
# Rank data
ranked_y = np.zeros_like(y)
for g in unique_groups:
indices = groups == g
ranks = rankdata(y[indices])
ranked_y[indices] = np.array(ranks / np.max(ranks) * 1000).astype(int)
# Ranker
ranker = LGBMRanker(n_estimators=500,
learning_rate=0.05,
num_leaves=16,
label_gain=np.arange(0, 1001, 1))
logo = LeaveOneGroupOut()
correlations = []
for train_index, test_index in tqdm(logo.split(X, y, groups)):
unique, counts = np.unique(groups[train_index], return_counts=True)
ranker.fit(X[train_index], ranked_y[train_index], group=counts)
predictions = ranker.predict(X[test_index])
correlation, p_value = kendalltau(ranked_y[test_index], predictions)
print(np.unique(groups[test_index]), correlation)
correlations.append(correlation)
print("Mean correlation: ", np.mean(correlations))
train_ind = np.where((meta.is_val == 0)
& (meta.is_test == 0))[0][:split_idx]
# val_ind = np.where((meta.is_val == 1) & (meta.is_test == 0))[0]
val_ind = np.arange(split_idx, 4868466)
print("train_ind: {} / val_ind: {}".format(train_ind, val_ind))
logger.info(
f"Train shape {train_ind.shape[0]} Val shape {val_ind.shape[0]}")
meta_train = meta.iloc[train_ind]
meta_val = meta.iloc[val_ind]
X_train = mat[train_ind.min():(train_ind.max() + 1)]
X_val = mat[val_ind.min():(val_ind.max() + 1)]
del mat
gc.collect()
with timer("model fitting"):
model = LGBMRanker(**BEST_PARAMS)
model.fit(X_train,
meta_train["was_clicked"].values,
group=group_lengths(meta_train["clickout_id"].values))
val_pred = model.predict(X_val)
train_pred = model.predict(X_train)
logger.info("Train AUC {:.4f}".format(
roc_auc_score(meta_train["was_clicked"].values, train_pred)))
logger.info("Val AUC {:.4f}".format(
roc_auc_score(meta_val["was_clicked"].values, val_pred)))
meta_val["click_proba"] = val_pred
logger.info("Val MRR {:.4f}".format(mrr_fast(meta_val, "click_proba")))
githash = get_git_hash()
meta_val.to_csv(f"predictions/model_val_{githash}.csv", index=False)
joblib.dump(model, "model_val.joblib")
def mrr_metric(train_data, preds):
mrr = mrr_fast_v2(train_data, preds, df_val["clickout_id"].values)
return "error", mrr, True
model = LGBMRanker(learning_rate=0.05,
n_estimators=900,
min_child_samples=5,
min_child_weight=0.00001,
n_jobs=-2)
model.fit(
mat_train,
df_train["was_clicked"],
group=group_lengths(df_train["clickout_id"]),
# sample_weight=np.where(df_train["clickout_step_rev"]==1,2,1),
verbose=True,
eval_set=[(mat_val, df_val["was_clicked"])],
eval_group=[group_lengths(df_val["clickout_id"])],
eval_metric=mrr_metric,
)
df_train["click_proba"] = model.predict(mat_train)
df_val["click_proba"] = model.predict(mat_val)
print(mrr_fast(df_val, "click_proba"))
print("By rank")
for n in range(1, 10):
print(n, mrr_fast(df_val[df_val["clickout_step_rev"] == n], "click_proba"))