def selection_del(dataset, result=None):
feature_count = get_feature_count(dataset)
log = []
if result is None:
features_all = list(range(feature_count))
error = count_error(dataset, features_all)
log.append({"error": error, "feature_count": feature_count})
result = {"error": error, "features": features_all, "log": log}
while len(result["features"]) > 1:
result_cur = result
for feat in result["features"]:
features = result["features"][:]
features.remove(feat)
error = count_error(dataset, features)
log.append({"error": error, "feature_count": len(features)})
if error <= result_cur["error"]:
result_cur = {"error": error, "features": features, "log": log}
if result_cur == result:
break
result = result_cur
return result
def make_plot(dataset, result):
logs = result["log"]
if not logs:
return
feature_count = get_feature_count(dataset)
__set_labels()
__plot_all(dataset, logs, feature_count)
__plot_best_in_col(logs, feature_count)
__plot_best(result)
def __sort_features(dataset):
feature_count = get_feature_count(dataset)
feature_errors = list(
map(lambda i: {
"i": i,
"error": count_error(dataset, [i])
}, range(feature_count)))
features_sorted = list(sorted(feature_errors, key=lambda x: x["error"]))
return list(
map(lambda f, pos: {
"i": f["i"],
"pos": pos
}, features_sorted, range(feature_count)))
def selection_full_search(dataset):
feature_count = get_feature_count(dataset)
log = []
result = {"error": 9999, "features": [], "log": log}
for feat_cur in __feat_gen(feature_count):
error = count_error(dataset, feat_cur)
log.append({"error": error, "feature_count": len(feat_cur)})
if error < result["error"]:
result = {"error": error, "features": feat_cur, "log": log}
return result
def make_compare_plot(dataset, result, draw_ticks=False, **kwargs):
logs = result["log"]
if not logs:
return
feature_count = get_feature_count(dataset)
__set_labels()
if draw_ticks:
__draw_x_ticks(feature_count)
y_ticks = __plot_best_in_col(logs, feature_count, **kwargs)
__plot_best(result, **kwargs)
plot.yticks(y_ticks, __make_quality_tick_labels(dataset, y_ticks))
def selection_dfs(dataset):
feature_count = get_feature_count(dataset)
features = __sort_features(dataset)
logs = []
results = list(
map(lambda x: {
"error": 9999,
"features": []
}, range(feature_count + 1)))
__increase([], features, results, dataset, logs)
result = min(results, key=lambda x: x["error"])
result["features"] = sorted(__flatten_features(result["features"]))
result["log"] = logs
return result
def selection_bfs(dataset, iter_limit=1):
feature_count = get_feature_count(dataset)
logs = []
result_best = {
"error": 9999,
"features": [],
"log": logs
}
result = list(map(lambda i: {"features": [i]}, range(feature_count)))
for iteration in range(1, feature_count + 1):
for res in result:
res["error"] = count_error(dataset, res["features"])
logs.append({
"error": res["error"],
"feature_count": len(res["features"])
})
result.sort(key=lambda r: r["error"])
if len(result) > iter_limit:
result = result[:iter_limit]
if result[0]["error"] > result_best["error"]:
break
if result[0]["error"] < result_best["error"]:
result_best = result[0]
result_new = []
for res in result:
for i in range(feature_count):
if i not in res["features"]:
result_new.append({"features": res["features"] + [i]})
result = result_new
result_best["features"].sort()
result_best["log"] = logs
return result_best
def selection_add(dataset, result=None):
feature_count = get_feature_count(dataset)
log = []
if result is None:
result = {
"error": 9999,
"features": [],
"log": log
}
while True:
result_cur = result
for feat in range(feature_count):
if feat in result["features"]:
continue
features = result["features"] + [feat]
features.sort()
error = count_error(dataset, features)
log.append({
"error": error,
"feature_count": len(features)
})
if error <= result_cur["error"]:
result_cur = {
"error": error,
"features": features,
"log": log
}
if result_cur == result:
break
result = result_cur
return result