diff --git a/logistic-regression-wdbc.py b/logistic-regression-wdbc.py
index b0ec4e7..820006e 100644
--- a/logistic-regression-wdbc.py
+++ b/logistic-regression-wdbc.py
@@ -43,9 +43,6 @@ if __name__ == "__main__":
     for col in num_cols:
         df = df[df[col] >= 0]
 
-    df['Diagnosis'] = df['Diagnosis'].map({'M': 1, 'B': 0})   # making diagnosis numeric
-    df['Diagnosis'] = df['Diagnosis'].astype('category')
-
     # sanity checks for data validity
     df = df[(df['radius_mean'] > 0) & (df['radius_mean'] <= 30)]
     df = df[(df['radius_worst'] > 0) & (df['radius_worst'] <= 30)]
@@ -59,4 +56,5 @@ if __name__ == "__main__":
     # check if there are still null values
     assert df.isna().sum().sum() == 0, "There are still some null values."
 
+    df['Diagnosis'] = df['Diagnosis'].map({'M': 1, 'B': 0})  # making diagnosis numeric
     df['Diagnosis'] = df['Diagnosis'].astype('category')
\ No newline at end of file
diff --git a/mini-batch-sgd-logistic-regression-wdbc.py b/mini-batch-sgd-logistic-regression-wdbc.py
index b0ec4e7..820006e 100644
--- a/mini-batch-sgd-logistic-regression-wdbc.py
+++ b/mini-batch-sgd-logistic-regression-wdbc.py
@@ -43,9 +43,6 @@ if __name__ == "__main__":
     for col in num_cols:
         df = df[df[col] >= 0]
 
-    df['Diagnosis'] = df['Diagnosis'].map({'M': 1, 'B': 0})   # making diagnosis numeric
-    df['Diagnosis'] = df['Diagnosis'].astype('category')
-
     # sanity checks for data validity
     df = df[(df['radius_mean'] > 0) & (df['radius_mean'] <= 30)]
     df = df[(df['radius_worst'] > 0) & (df['radius_worst'] <= 30)]
@@ -59,4 +56,5 @@ if __name__ == "__main__":
     # check if there are still null values
     assert df.isna().sum().sum() == 0, "There are still some null values."
 
+    df['Diagnosis'] = df['Diagnosis'].map({'M': 1, 'B': 0})  # making diagnosis numeric
     df['Diagnosis'] = df['Diagnosis'].astype('category')
\ No newline at end of file