Doctorado-ML/stree_datasets
1
0
Fork 0
mirror of https://github.com/Doctorado-ML/Stree_datasets.git synced 2025-08-15 15:36:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix normalization & standard. columnwise

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2021-04-15 00:30:16 +02:00
parent 59f59e6c4f
commit 84795b4c43
4 changed files with 109 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
checknormalize.py
View File

@@ -24,21 +24,20 @@ def header():
print("Processing Datasets with stree default.\n")
print(
f"{'Dataset':30s} {'No Norm.':9s} {'Normaliz.':9s} "
f"{'Col.Norm.':9s} {'Best score in crossval':25s}"
f"{'Col.Norm.':9s} {'Context B':9s} {'Best score in crossval':25s}"
)
print("=" * 30 + " " + ("=" * 9 + " ") * 3 + "=" * 25)
print("=" * 30 + " " + ("=" * 9 + " ") * 4 + "=" * 25)
def process_dataset(X, y):
def process_dataset(X, y, normalize):
scores = []
# return random.uniform(0, 1)
# Get the optimized parameters
for random_state in random_seeds:
random.seed(random_state)
clf_test = Stree(random_state=random_state, normalize=normalize)
np.random.seed(random_state)
kfold = KFold(shuffle=True, random_state=random_state, n_splits=5)
clf = Stree(random_state=random_state)
res = cross_validate(clf, X, y, cv=kfold, return_estimator=True)
res = cross_validate(clf_test, X, y, cv=kfold, return_estimator=True)
scores.append(res["test_score"])
return np.mean(scores)
@@ -58,7 +57,7 @@ database = dbh.get_connection()
random_seeds = [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]
dt = Datasets(normalize=False, standardize=False, set_of_files="tanveer")
header()
total = [0, 0, 0]
total = [0, 0, 0, 0]
line = TextColor.LINE1
for data in dt:
name = data[0]
@@ -66,22 +65,31 @@ for data in dt:
record = dbh.find_best(name, models_tree, "crossval")
X2 = normalize(X)
X3 = normalize_rows(X)
clf = Stree(random_state=1)
ac1 = process_dataset(X, y)
ac2 = process_dataset(X2, y)
ac3 = process_dataset(X3, y)
max_value = max(ac1, ac2, ac3)
ac1 = process_dataset(X, y, False)
ac2 = process_dataset(X2, y, False)
ac3 = process_dataset(X3, y, False)
ac4 = process_dataset(X, y, True)
max_value = round(max(ac1, ac2, ac3, ac4), 6)
line = TextColor.LINE2 if line == TextColor.LINE1 else TextColor.LINE1
print(line + f"{name:30s} ", end="", flush=True)
total[np.argmax([ac1, ac2, ac3])] += 1
total[np.argmax([ac1, ac2, ac3, ac4])] += 1
color1 = TextColor.SUCCESS if ac1 == max_value else line
color2 = TextColor.SUCCESS if ac2 == max_value else line
color3 = TextColor.SUCCESS if ac3 == max_value else line
color4 = TextColor.SUCCESS if ac4 == max_value else line
print(color1 + f"{ac1:9.6f} " + TextColor.ENDC, end="", flush=True)
print(color2 + f"{ac2:9.6f} " + TextColor.ENDC, end="", flush=True)
print(color3 + f"{ac3:9.6f}" + TextColor.ENDC, end="", flush=True)
print(line + f"{record[5]:9.6f} {record[3]}" + TextColor.ENDC)
print(f"{'Total':30s} {total[0]:9d} {total[1]:9d} {total[2]:9d}")
print(color3 + f"{ac3:9.6f} " + TextColor.ENDC, end="", flush=True)
print(color4 + f"{ac4:9.6f}" + TextColor.ENDC, end="", flush=True)
best_accuracy = round(record[5], 6)
best_color = TextColor.UNDERLINE if best_accuracy >= max_value else ""
print(
line
+ best_color
+ f"{best_accuracy:9.6f} {record[3]}"
+ TextColor.ENDC
)
print(f"{'Total':30s} {total[0]:9d} {total[1]:9d} {total[2]:9d} {total[3]:9d}")
stop = time.time()
hours, rem = divmod(stop - start, 3600)
minutes, seconds = divmod(rem, 60)