batuhan-basoglu/Mini-Project-of-Machine-Learning
1
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Fixed the comments.

Browse source
This commit is contained in:
Batuhan Berk Başoğlu 2025-09-26 21:27:52 -04:00
parent 670c0c9869
commit a79c30f0d3
Signed by: batuhan-basoglu
SSH key fingerprint: SHA256:kEsnuHX+qbwhxSAXPUQ4ox535wFHu/hIRaa53FzxRpo
2 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

8
logistic-regression-wdbc.py
View file

@ -142,10 +142,10 @@ if __name__ == "__main__":
# ____________________________________________________________________________________ # ____________________________________________________________________________________
# separate dependent VS independent variables # separate dependent VS independent variables
X = cancer.drop(cancer.columns[0], axis=1) x = cancer.drop(cancer.columns[0], axis=1)
y = cancer[1] y = cancer[1]
# print(X.head().to_string()) # print(x.head().to_string())
# normalize data # normalize data
# normalize = cancer.drop(cancer.columns[0], axis=1) # normalize = cancer.drop(cancer.columns[0], axis=1)
@ -154,14 +154,14 @@ if __name__ == "__main__":
# print(cancer.head().to_string()) # print(cancer.head().to_string())
# turn into array for regression # turn into array for regression
X = X.to_numpy() x = x.to_numpy()
y = y.to_numpy() y = y.to_numpy()
# cancer_y = np.asarray(cancer2[0].tolist()) # cancer_y = np.asarray(cancer2[0].tolist())
# cancer2.drop(cancer2[0], axis = 1, inplace = True) # cancer2.drop(cancer2[0], axis = 1, inplace = True)
# split data into train / tests datasets # split data into train / tests datasets
X_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y) x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
''' '''
missing_rows = df[df.isin(['?', 'NA', 'na', '']).any(axis=1)] # checks null values missing_rows = df[df.isin(['?', 'NA', 'na', '']).any(axis=1)] # checks null values
print(f"Rows with null values: {len(missing_rows)}") print(f"Rows with null values: {len(missing_rows)}")

6
mini-batch-sgd-logistic-regression-wdbc.py
View file

@ -158,7 +158,7 @@ if __name__ == "__main__":
# ____________________________________________________________________________________ # ____________________________________________________________________________________
# separate dependent VS independent variables # separate dependent VS independent variables
X = cancer.drop(cancer.columns[0], axis=1) x = cancer.drop(cancer.columns[0], axis=1)
y = cancer[1] y = cancer[1]
# print(X.head().to_string()) # print(X.head().to_string())
@ -170,14 +170,14 @@ if __name__ == "__main__":
# print(cancer.head().to_string()) # print(cancer.head().to_string())
# turn into array for regression # turn into array for regression
X = X.to_numpy() x = x.to_numpy()
y = y.to_numpy() y = y.to_numpy()
# cancer_y = np.asarray(cancer2[0].tolist()) # cancer_y = np.asarray(cancer2[0].tolist())
# cancer2.drop(cancer2[0], axis = 1, inplace = True) # cancer2.drop(cancer2[0], axis = 1, inplace = True)
# split data into train / tests datasets # split data into train / tests datasets
X_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y) x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42, stratify=y)
''' '''
missing_rows = df[df.isin(['?', 'NA', 'na', '']).any(axis=1)] # checks null values missing_rows = df[df.isin(['?', 'NA', 'na', '']).any(axis=1)] # checks null values
print(f"Rows with null values: {len(missing_rows)}") print(f"Rows with null values: {len(missing_rows)}")