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

removed unnecessary comments

Browse source
This commit is contained in:
ShaaniBel 2025-09-30 18:59:15 -04:00
parent 193dcabbff
commit 91e98ba8bc
4 changed files with 0 additions and 117 deletions
Download patch file Download diff file Expand all files Collapse all files

25
linear-regression-parkinsons.py
View file

@ -169,31 +169,6 @@ if __name__ == "__main__":
print("\nCorrelation with target variable descending order:")
print(target_corr)
'''
# repeated fields —> for now I removed them since might not be too relevant (need testing to see if we keep it later)
Parkinson = Parkinson.drop(Parkinson.columns[0:3], axis=1)
# ____________________________________________________________________________________
# HANDLE OUTLIERS AND INCONSISTENCIES
# https://medium.com/@heyamit10/pandas-outlier-detection-techniques-e9afece3d9e3
# if z-score more than 3 --> outllier
# print(Parkinson.head().to_string())
# ____________________________________________________________________________________
# normalize / scale features? if not already done
# !!!!!!!!!!only for X not y!!!!!!!!!!!
# normalize = Parkinson.drop(Parkinson.columns[0:6], axis=1)
# normalize = (normalize - normalize.mean()) / normalize.std()
# Parkinson[Parkinson.columns[6:]] = normalize
# turn into array for regression
x = x.to_numpy()
y = y.to_numpy()
# split data into train 80% / tests datasets 20%
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42, stratify=y)
'''
for col in df:
df[col] = pd.to_numeric(df[col], errors='coerce') # convert columns to numeric values

34
logistic-regression-wdbc.py
View file

@ -200,10 +200,6 @@ class LogisticRegression:
"""
if isinstance(x, pd.DataFrame):
x = x.values
if self.w is None:
raise ValueError("Model not fitted yet")
# Add bias term if needed
if x.shape[1] == len(self.w) - 1:
x = np.column_stack([np.ones(x.shape[0]), x])
@ -250,37 +246,7 @@ if __name__ == "__main__":
df = df.drop_duplicates()
# check data types: --> everything is good
# print(df.dtypes)
'''
# ____________________________________________________________________________________
# HANDLE OUTLIERS AND INCONSISTENCIES
# https://medium.com/@heyamit10/pandas-outlier-detection-techniques-e9afece3d9e3
# if z-score more than 3 --> outllier
# print(cancer.head().to_string())
# ____________________________________________________________________________________
# separate dependent VS independent variables
x = cancer.drop(cancer.columns[0], axis=1)
y = cancer[1]
# print(x.head().to_string())
# normalize data
# normalize = cancer.drop(cancer.columns[0], axis=1)
# normalize = (normalize - normalize.mean()) / normalize.std()
# cancer[cancer.columns[1:]] = normalize
# print(cancer.head().to_string())
# turn into array for regression
x = x.to_numpy()
y = y.to_numpy()
# cancer_y = np.asarray(cancer2[0].tolist())
# cancer2.drop(cancer2[0], axis = 1, inplace = True)
# 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)
'''
missing_rows = df[df.isin(['?', 'NA', 'na', '']).any(axis=1)] # checks null values
print(f"Rows with null values: {len(missing_rows)}")

24
mini-batch-sgd-linear-regression-parkinsons.py
View file

@ -171,31 +171,7 @@ if __name__ == "__main__":
print("\nCorrelation with target variable descending order:")
print(target_corr)
'''
# repeated fields —> for now I removed them since might not be too relevant (need testing to see if we keep it later)
Parkinson = Parkinson.drop(Parkinson.columns[0:3], axis=1)
# ____________________________________________________________________________________
# HANDLE OUTLIERS AND INCONSISTENCIES
# https://medium.com/@heyamit10/pandas-outlier-detection-techniques-e9afece3d9e3
# if z-score more than 3 --> outllier
# print(Parkinson.head().to_string())
# ____________________________________________________________________________________
# normalize / scale features? if not already done
# !!!!!!!!!!only for X not y!!!!!!!!!!!
# normalize = Parkinson.drop(Parkinson.columns[0:6], axis=1)
# normalize = (normalize - normalize.mean()) / normalize.std()
# Parkinson[Parkinson.columns[6:]] = normalize
# turn into array for regression
x = x.to_numpy()
y = y.to_numpy()
# split data into train 80% / tests datasets 20%
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42, stratify=y)
'''
for col in df:
df[col] = pd.to_numeric(df[col], errors='coerce') # convert columns to numeric values

34
mini-batch-sgd-logistic-regression-wdbc.py
View file

@ -219,9 +219,6 @@ class LogisticRegression:
if isinstance(x, pd.DataFrame):
x = x.values
if self.w is None:
raise ValueError("Model not fitted yet")
# Add bias term if needed
if x.shape[1] == len(self.w) - 1:
x = np.column_stack([np.ones(x.shape[0]), x])
@ -259,37 +256,6 @@ if __name__ == "__main__":
# check data types: --> everything is good
# print(df.dtypes)
'''
# ____________________________________________________________________________________
# HANDLE OUTLIERS AND INCONSISTENCIES
# https://medium.com/@heyamit10/pandas-outlier-detection-techniques-e9afece3d9e3
# if z-score more than 3 --> outllier
# print(cancer.head().to_string())
# ____________________________________________________________________________________
# separate dependent VS independent variables
x = cancer.drop(cancer.columns[0], axis=1)
y = cancer[1]
# print(X.head().to_string())
# normalize data
# normalize = cancer.drop(cancer.columns[0], axis=1)
# normalize = (normalize - normalize.mean()) / normalize.std()
# cancer[cancer.columns[1:]] = normalize
# print(cancer.head().to_string())
# turn into array for regression
x = x.to_numpy()
y = y.to_numpy()
# cancer_y = np.asarray(cancer2[0].tolist())
# cancer2.drop(cancer2[0], axis = 1, inplace = True)
# 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)
'''
missing_rows = df[df.isin(['?', 'NA', 'na', '']).any(axis=1)] # checks null values
print(f"Rows with null values: {len(missing_rows)}")