s464913/ium_464913
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Dockerfile

Browse Source
This commit is contained in:
Mateusz 2024-04-01 19:33:15 +02:00
parent 182be399ac
commit b946aaf7cc
1 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
dataset-stats.py
View File

@ -24,7 +24,7 @@ def write_to_file(file_name):
f.write("\n\n")
f.write("Size of the dataset\n")
f.write(str(df.info()))
print(df.info(), file=f)
f.write("\n\n")
@ -39,7 +39,7 @@ def write_to_file(file_name):
f.write("\n\n")
f.write("Size of undersampled dataset\n")
f.write(str(undersample_data.info()))
print(undersample_data.info(), file=f)
f.write("\n\n")
@ -56,7 +56,7 @@ def write_to_file(file_name):
f.write("\n\n")
f.write("Statistical measures of the training dataset of whole data\n")
f.write(str(pd.concat([X_train, y_train], axis=1).info()))
print(pd.concat([X_train, y_train], axis=1).info(), file=f)
f.write("\n")
f.write(str(pd.concat([X_train, y_train], axis=1).describe()))
f.write("\n")
@ -65,7 +65,7 @@ def write_to_file(file_name):
f.write("\n\n")
f.write("Statistical measures of the test dataset of whole data\n")
f.write(str(pd.concat([X_test, y_test], axis=1).info()))
print(pd.concat([X_test, y_test], axis=1).info(), file=f)
f.write("\n")
f.write(str(pd.concat([X_test, y_test], axis=1).describe()))
f.write("\n")
@ -74,8 +74,8 @@ def write_to_file(file_name):
f.write("\n\n")
f.write("Statistical measures of the training dataset of undersampled data\n")
f.write(
str(pd.concat([X_train_undersample, y_train_undersample], axis=1).info())
print(
pd.concat([X_train_undersample, y_train_undersample], axis=1).info(), file=f
)
f.write("\n")
f.write(
@ -95,7 +95,9 @@ def write_to_file(file_name):
f.write("\n\n")
f.write("Statistical measures of the test dataset of undersampled data\n")
f.write(str(pd.concat([X_test_undersample, y_test_undersample], axis=1).info()))
print(
pd.concat([X_test_undersample, y_test_undersample], axis=1).info(), file=f
)
f.write("\n")
f.write(
str(pd.concat([X_test_undersample, y_test_undersample], axis=1).describe())