diff --git a/skrypt.py b/skrypt.py index 6fb0b0b..045b382 100644 --- a/skrypt.py +++ b/skrypt.py @@ -21,7 +21,12 @@ train, test = train_test_split(results, test_size= 1 - 0.6) valid, test = train_test_split(test, test_size=0.5) -train.to_csv("train.csv", index=False) -valid.to_csv("valid.csv",index=False) -test.to_csv("test.csv",index=False) +print("All data: ", results.size) +print("Train size: ", train.size) +print("Test size: ", test.size) +print("Validate size: ", valid.size) +print(results.describe(include='all')) + +# sprawdzenie czy cały dataset oraz podział na podzbiory jest równy +print(train.size+test.size+valid.size) diff --git a/skrypt_download.py b/skrypt_download.py index 6e8715d..2dfa1c5 100644 --- a/skrypt_download.py +++ b/skrypt_download.py @@ -21,11 +21,6 @@ train, test = train_test_split(results, test_size= 1 - 0.6) valid, test = train_test_split(test, test_size=0.5) -print("All data: ", results.size) -print("Train size: ", train.size) -print("Test size: ", test.size) -print("Validate size: ", valid.size) -print(results.describe(include='all')) - -# sprawdzenie czy cały dataset oraz podział na podzbiory jest równy -print(train.size+test.size+valid.size) +train.to_csv("train.csv", index=False) +valid.to_csv("valid.csv",index=False) +test.to_csv("test.csv",index=False)