From 3a9ca8cbc1af9131d98aab540b999f545498e2ad Mon Sep 17 00:00:00 2001
From: Mateusz <matpiw1@st.amu.edu.pl>
Date: Mon, 1 Apr 2024 19:39:09 +0200
Subject: [PATCH] Dockerfile

---
 create-dataset.py |  1 +
 dataset-stats.py  | 22 ++++++++++++----------
 2 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/create-dataset.py b/create-dataset.py
index eb10e44..4903d69 100644
--- a/create-dataset.py
+++ b/create-dataset.py
@@ -89,6 +89,7 @@ def save_whole_data(df, X_train, X_test, y_train, y_test):
 
 def main():
     os.makedirs("data", exist_ok=True)
+    os.system("rm -rf data/*")
 
     df = load_data("creditcard.csv")
     df = normalize_data(df)
diff --git a/dataset-stats.py b/dataset-stats.py
index 5a3510f..7cb9d2a 100644
--- a/dataset-stats.py
+++ b/dataset-stats.py
@@ -1,4 +1,5 @@
 import os
+import sys
 import pandas as pd
 
 
@@ -18,13 +19,15 @@ def write_to_file(file_name):
     y_train = pd.read_csv("data/y_train.csv")
 
     with open("stats_data/" + file_name, "w") as f:
+        sys.stdout = f
+
         f.write("Check missing values\n")
         f.write(str(df.isnull().sum()))
 
         f.write("\n\n")
 
         f.write("Size of the dataset\n")
-        print(df.info(), file=f)
+        df.info()
 
         f.write("\n\n")
 
@@ -39,7 +42,7 @@ def write_to_file(file_name):
         f.write("\n\n")
 
         f.write("Size of undersampled dataset\n")
-        print(undersample_data.info(), file=f)
+        undersample_data.info()
 
         f.write("\n\n")
 
@@ -56,7 +59,7 @@ def write_to_file(file_name):
         f.write("\n\n")
 
         f.write("Statistical measures of the training dataset of whole data\n")
-        print(pd.concat([X_train, y_train], axis=1).info(), file=f)
+        pd.concat([X_train, y_train], axis=1).info()
         f.write("\n")
         f.write(str(pd.concat([X_train, y_train], axis=1).describe()))
         f.write("\n")
@@ -65,7 +68,7 @@ def write_to_file(file_name):
         f.write("\n\n")
 
         f.write("Statistical measures of the test dataset of whole data\n")
-        print(pd.concat([X_test, y_test], axis=1).info(), file=f)
+        pd.concat([X_test, y_test], axis=1).info()
         f.write("\n")
         f.write(str(pd.concat([X_test, y_test], axis=1).describe()))
         f.write("\n")
@@ -74,9 +77,7 @@ def write_to_file(file_name):
         f.write("\n\n")
 
         f.write("Statistical measures of the training dataset of undersampled data\n")
-        print(
-            pd.concat([X_train_undersample, y_train_undersample], axis=1).info(), file=f
-        )
+        pd.concat([X_train_undersample, y_train_undersample], axis=1).info()
         f.write("\n")
         f.write(
             str(
@@ -95,9 +96,7 @@ def write_to_file(file_name):
         f.write("\n\n")
 
         f.write("Statistical measures of the test dataset of undersampled data\n")
-        print(
-            pd.concat([X_test_undersample, y_test_undersample], axis=1).info(), file=f
-        )
+        pd.concat([X_test_undersample, y_test_undersample], axis=1).info()
         f.write("\n")
         f.write(
             str(pd.concat([X_test_undersample, y_test_undersample], axis=1).describe())
@@ -111,9 +110,12 @@ def write_to_file(file_name):
             )
         )
 
+        sys.stdout = sys.__stdout__
+
 
 def main():
     os.makedirs("stats_data", exist_ok=True)
+    os.system("rm -rf stats_data/*")
     write_to_file("stats.txt")