Doctorado-ML/benchmark
1
0
Fork 0
mirror of https://github.com/Doctorado-ML/benchmark.git synced 2025-08-16 16:05:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add Dataset load return a pandas dataframe

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2022-11-04 18:40:50 +01:00
parent 0d87e670f7
commit feaf85d0b8
1 changed files with 9 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
benchmark/Datasets.py
View File

@@ -24,14 +24,16 @@ class DatasetsArff:
def folder(): def folder():
return "datasets" return "datasets"
def load(self, name, class_name): def load(self, name, class_name, dataframe):
file_name = os.path.join(self.folder(), self.dataset_names(name)) file_name = os.path.join(self.folder(), self.dataset_names(name))
data = arff.loadarff(file_name) data = arff.loadarff(file_name)
df = pd.DataFrame(data[0]) df = pd.DataFrame(data[0])
df = df.dropna() df = df.dropna()
X = df.drop(class_name, axis=1).to_numpy() X = df.drop(class_name, axis=1)
self.features = X.columns
self.class_name = class_name
y, _ = pd.factorize(df[class_name]) y, _ = pd.factorize(df[class_name])
return X, y return df if dataframe else (X.to_numpy(), y)
class DatasetsTanveer: class DatasetsTanveer:
@@ -43,7 +45,7 @@ class DatasetsTanveer:
def folder(): def folder():
return "data" return "data"
def load(self, name, _): def load(self, name, *args):
file_name = os.path.join(self.folder(), self.dataset_names(name)) file_name = os.path.join(self.folder(), self.dataset_names(name))
data = pd.read_csv( data = pd.read_csv(
file_name, file_name,
@@ -64,7 +66,7 @@ class DatasetsSurcov:
def folder(): def folder():
return "datasets" return "datasets"
def load(self, name, _): def load(self, name, *args):
file_name = os.path.join(self.folder(), self.dataset_names(name)) file_name = os.path.join(self.folder(), self.dataset_names(name))
data = pd.read_csv( data = pd.read_csv(
file_name, file_name,
@@ -115,10 +117,10 @@ class Datasets:
self.data_sets = result self.data_sets = result
self.class_names = class_names self.class_names = class_names
def load(self, name): def load(self, name, dataframe=False):
try: try:
class_name = self.class_names[self.data_sets.index(name)] class_name = self.class_names[self.data_sets.index(name)]
return self.dataset.load(name, class_name) return self.dataset.load(name, class_name, dataframe)
except (ValueError, FileNotFoundError): except (ValueError, FileNotFoundError):
raise ValueError(f"Unknown dataset: {name}") raise ValueError(f"Unknown dataset: {name}")