generated from LufsX/Experiment-LogReg
79 lines
2.6 KiB
Python
79 lines
2.6 KiB
Python
import numpy as np
|
|
from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score
|
|
from sklearn.preprocessing import StandardScaler
|
|
from sklearn.metrics import accuracy_score, roc_auc_score, f1_score
|
|
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier, VotingClassifier
|
|
from sklearn.linear_model import LogisticRegression
|
|
|
|
"""
|
|
请在这里填写学号和姓名，不填写即成绩无效。
|
|
"""
|
|
id = "202210423221"
|
|
name = "廖子豪"
|
|
|
|
def load_data(filepath):
|
|
"""Load and preprocess data from specified file."""
|
|
with open(filepath) as file:
|
|
fr = file.readlines()
|
|
|
|
data_list = []
|
|
y = []
|
|
|
|
for data in fr:
|
|
data = data.strip().split(' ')
|
|
|
|
# Keep the necessary fields
|
|
y.append(data[22]) # Target value
|
|
# Remove unnecessary columns
|
|
data = [data[i] for i in range(len(data)) if i not in [2, 22, 24, 25, 26]]
|
|
|
|
# Convert to float, replacing '?' with 0
|
|
data_processed = [0 if elem == '?' else float(elem) for elem in data]
|
|
data_list.append(data_processed)
|
|
|
|
y_train = np.array([1 if label in ['2', '3'] else 0 for label in y])
|
|
X = np.array(data_list)
|
|
|
|
# Add bias term (intercept)
|
|
X = np.insert(X, 0, 1, axis=1)
|
|
scaler = StandardScaler()
|
|
X = scaler.fit_transform(X)
|
|
|
|
return X, y_train
|
|
|
|
def train_logreg(X, y, numIter=1000, learning_rate=0.01, batch_size=128, lambda_reg=0.01):
|
|
"""Train a logistic regression model using mini-batch gradient descent."""
|
|
m, n = X.shape
|
|
weights = np.zeros(n)
|
|
|
|
for j in range(numIter):
|
|
# Shuffle data indices
|
|
dataIndex = np.random.permutation(m)
|
|
|
|
for i in range(0, m, batch_size):
|
|
end = min(i + batch_size, m)
|
|
batch_X = X[dataIndex[i:end]]
|
|
batch_y = y[dataIndex[i:end]]
|
|
|
|
# Compute predictions
|
|
z = np.dot(batch_X, weights)
|
|
h = 1 / (1 + np.exp(-z)) # Sigmoid
|
|
|
|
# Compute gradient
|
|
error = batch_y - h
|
|
gradient = np.dot(batch_X.T, error) / len(batch_y)
|
|
reg_term = 2 * lambda_reg * weights
|
|
gradient -= reg_term / len(batch_y) # Regularization
|
|
|
|
# Update weights
|
|
weights += learning_rate * gradient
|
|
|
|
return weights
|
|
|
|
def predict_logreg(inX, weights):
|
|
"""Make a prediction using the logistic regression model."""
|
|
z = np.dot(inX, weights)
|
|
prob = 1 / (1 + np.exp(-z))
|
|
return 1 if prob >= 0.5 else 0
|
|
|