学生成绩预测模型_逻辑回归实战练习——根据学生成绩预测是否被录取，使用sigmoid函数

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# 导入数据集
data = pd.read_csv('admission.csv')

# 数据探索
data.head()

# 绘制图表，可以直观的显示数据
fig, ax = plt.subplots(figsize=(10,5))
ax.scatter(data['GPA'], data['admit'])
ax.set_xlabel('GPA')
ax.set_ylabel('admit')
plt.show()

# 数据预处理
X = data.iloc[:, :-1] # 取数据的前三列作为特征向量
y = data.iloc[:, -1] # 取数据的最后一列作为标签向量

# 将数据集拆分为训练集和测试集
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

# 模型训练
from sklearn.linear_model import LogisticRegression
logreg = LogisticRegression()
logreg.fit(X_train, y_train)

# 模型预测
y_pred = logreg.predict(X_test)

# 模型评估
from sklearn.metrics import accuracy_score
accuracy_score(y_test, y_pred)

# 绘制决策边界
plt.scatter(X_test.iloc[:, 0], X_test.iloc[:, 1], c=y_pred)
x_min, x_max = X_test.iloc[:, 0].min() - .5, X_test.iloc[:, 0].max() + .5
y_min, y_max = X_test.iloc[:, 1].min() - .5, X_test.iloc[:, 1].max() + .5
xx, yy = np.meshgrid(np.arange(x_min, x_max, .2), np.arange(y_min, y_max, .2))
Z = logreg.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.contour(xx, yy, Z, cmap=plt.cm.Paired)
plt.xlabel('GPA')
plt.ylabel('GRE')
plt.show()