Doctorado-ML/fimdlp
1
1
Fork 0
mirror of https://github.com/Doctorado-ML/FImdlp.git synced 2025-08-17 16:35:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Change arff library to sample.py

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2023-04-14 11:20:48 +02:00
parent 25d341aee5
commit 878cd379ee
1 changed files with 17 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
samples/sample.py
View File

@@ -5,6 +5,7 @@ from scipy.io import arff
import pandas as pd import pandas as pd
from sklearn.ensemble import RandomForestClassifier from sklearn.ensemble import RandomForestClassifier
from fimdlp.mdlp import FImdlp from fimdlp.mdlp import FImdlp
from fimdlp.cppfimdlp import CArffFiles
datasets = { datasets = {
"mfeat-factors": True, "mfeat-factors": True,
@@ -29,13 +30,15 @@ relative = "" if os.path.isdir("src") else ".."
file_name = os.path.join( file_name = os.path.join(
relative, "src", "cppmdlp", "tests", "datasets", args.dataset relative, "src", "cppmdlp", "tests", "datasets", args.dataset
) )
data = arff.loadarff(file_name + ".arff") arff = CArffFiles()
df = pd.DataFrame(data[0]) arff.load(bytes(f"{file_name}.arff", "utf-8"))
class_column = -1 if datasets[args.dataset] else 0 X = arff.get_X()
class_name = df.columns.to_list()[class_column] y = arff.get_y()
X = df.drop(class_name, axis=1) attributes = arff.get_attributes()
y, _ = pd.factorize(df[class_name]) attributes = [x[0].decode() for x in attributes]
X = X.to_numpy() df = pd.DataFrame(X, columns=attributes)
class_name = arff.get_class_name().decode()
df[class_name] = y
test = FImdlp( test = FImdlp(
min_length=args.min_length, min_length=args.min_length,
max_depth=args.max_depth, max_depth=args.max_depth,
@@ -48,7 +51,13 @@ print(f"Fitting ....: {fit_time - now:7.5f} seconds")
now = time.time() now = time.time()
Xt = test.transform(X) Xt = test.transform(X)
print(f"Transforming: {time.time() - now:7.5f} seconds") print(f"Transforming: {time.time() - now:7.5f} seconds")
print(test.get_cut_points()) cut_points = test.get_cut_points()
for i, cuts in enumerate(cut_points):
print(f"Cut points for feature {attributes[i]}: {cuts}")
print(f"Min: {min(X[:, i]):6.4f} Max: {max(X[:, i]):6.4f}")
num_cuts = sum([len(x) for x in cut_points])
print(f"Total cut points ...: {num_cuts}")
print(f"Total feature states: {num_cuts + len(attributes)}")
clf = RandomForestClassifier(random_state=0) clf = RandomForestClassifier(random_state=0)
print( print(
"Random Forest score with discretized data: ", clf.fit(Xt, y).score(Xt, y) "Random Forest score with discretized data: ", clf.fit(Xt, y).score(Xt, y)