dataset update

app.py

@@ -112,14 +112,15 @@ shape, loc, scale = gamma_params["shape"], gamma_params["loc"], gamma_params["sc
 max_dist, precision_cdf = gamma_params["max_dist"], gamma_params["precision_cdf"]
 y_cdf, _ = dh_app.configura_distr_prob(shape, loc, scale, max_dist, precision_cdf)
 
-# Parámetros de la de búsqueda VSS:
+# Parámetros de búsqueda VSS:
 k = semantic_search_params["k"]
 brevity_penalty = semantic_search_params["brevity_penalty"]
 min_length = semantic_search_params["min_length"]
 reward_for_literal = semantic_search_params["reward_for_literal"]
 first_term_reward = semantic_search_params["first_term_reward"]
 partial_match_factor = semantic_search_params["partial_match_factor"]
-print(f"VSS params: k={k}, brevity_penalty={brevity_penalty}, reward_for_literal={reward_for_literal}, partial_match_factor={partial_match_factor}")
+print(f"VSS params: k={k}, brevity_penalty={brevity_penalty}, reward_for_literal={reward_for_literal}, partial_match_factor={partial_match_factor}", end="")
+print(f", min_length={min_length}, first_term_reward={first_term_reward}")
 
 filtros_keys = caracteristicas[2:]
 

json/semantic_search_params.json

@@ -2,7 +2,7 @@
     "semantic_search_params": {
         "k": 2000,
         "brevity_penalty": 0.1,
-		"min_length": 131,
+		"min_length": 190,
         "reward_for_literal": 0.03,
 		"first_term_reward": 20,
         "partial_match_factor": 0.8

parquet/app_dataset.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996f7b9f19f47e37e478ddf6c4b34b7a7612b8bbf9a27b2f7e6ae4af774552e5
-size 48114046
+oid sha256:fb2afe670c420f911f7f408c16a0d9121fb4b0ce54ede29fc83e0676e2063106
+size 48140762