机器学习实战1.2之逻辑回归之是否成功申请高校

导入库和数据集

import pandas as pd
import matplotlib.pyplot as plt

admissions = pd.read_csv('./data/admissions.csv')
print(admissions.head())

   admit       gpa         gre
0      0  3.177277  594.102992
1      0  3.412655  631.528607
2      0  2.728097  553.714399
3      0  3.093559  551.089985
4      0  3.141923  537.184894

可视化数据

plt.scatter(admissions['gpa'], admissions['admit'])
plt.show()

positive = admissions[admissions['admit'] == 1]
negative = admissions[admissions['admit'] == 0]
fig, ax = plt.subplots(figsize=(10, 5))
ax.scatter(
    positive['gpa'],
    positive['gre'],
    s=30,
    c='b',
    marker='o',
    label='Admitted')
ax.scatter(
    negative['gpa'],
    negative['gre'],
    s=30,
    c='r',
    marker='x',
    label='Not admitted')
plt.legend()
ax.set_xlabel('gpa')
ax.set_ylabel('gre')
plt.show()

sigmoid函数

import numpy as np

def logit(x):
    return 1 / (1 + np.exp(-x))
x = np.linspace(-6,6,50,dtype=float)
y = logit(x)
plt.plot(x, y)
plt.ylabel('Probability')
plt.show()

创建逻辑回归模型并进行预测

from sklearn.linear_model import LogisticRegression
logistc_model = LogisticRegression()
logistc_model.fit(admissions[['gpa']], admissions['admit'])

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.
  FutureWarning)





LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='warn',
          n_jobs=None, penalty='l2', random_state=None, solver='warn',
          tol=0.0001, verbose=0, warm_start=False)

预测

• 输出概率
• 输出分类结果

pred_probs = logistc_model.predict_proba(admissions[['gpa']])
plt.scatter(admissions['gpa'], pred_probs[:, 1])  # 1表示输出正确的分类取值，0表示输出错误的分类取值
plt.show()

fitted_labels = logistc_model.predict(admissions[['gpa']])
plt.scatter(admissions['gpa'], fitted_labels)
plt.show()