购买意向预测与其他预测

今天使用逻辑回归做了个购买意向的预测。

数据集如下

4个特征，这里我们不使用ID和性别，只使用年龄和收入两个特征）：

代码如下

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
#import matplotlib.pyplot as plt
from sklearn.metrics import accuracy_score
 
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[ : ,2:4].values
Y = dataset.iloc[ : ,4].values
 
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2)
 
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test )
 
classifier = LogisticRegression()
classifier.fit(X_train, Y_train)
 
y_pred = classifier.predict(X_test)
 
acc = accuracy_score(Y_test, y_pred)
print("准确率为：", acc)

还有一个其他方面的预测代码示例如下:

# encoding: utf-8
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
 
dataset = pd.read_csv('dataset.csv', delimiter=',')
X = np.asarray(dataset.get(['x1', 'x2']))
y = np.asarray(dataset.get('y'))
 
# 划分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)
 
# 使用 sklearn 的 LogisticRegression 作为模型，其中有 penalty，solver，dual 几个比较重要的参数，不同的参数有不同的准确率，这里为了简便都使用默认的，详细的请参考 sklearn 文档
model = LogisticRegression(solver='liblinear')
 
# 拟合
model.fit(X, y)
 
# 预测测试集
predictions = model.predict(X_test)
 
# 打印准确率
print('测试集准确率：', accuracy_score(y_test, predictions))
 
weights = np.column_stack((model.intercept_, model.coef_)).transpose()
 
n = np.shape(X_train)[0]
xcord1 = []
ycord1 = []
xcord2 = []
ycord2 = []
for i in range(n):
    if int(y_train[i]) == 1:
        xcord1.append(X_train[i, 0])
        ycord1.append(X_train[i, 1])
    else:
        xcord2.append(X_train[i, 0])
        ycord2.append(X_train[i, 1])
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(xcord1, ycord1, s=30, c='red', marker='s')
ax.scatter(xcord2, ycord2, s=30, c='green')
x_ = np.arange(-3.0, 3.0, 0.1)
y_ = (-weights[0] - weights[1] * x_) / weights[2]
ax.plot(x_, y_)
plt.xlabel('x1')
plt.ylabel('x2')
plt.show()

 3. 癌症预测数据集实践

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import classification_report

# 加载数据
breast = load_breast_cancer()
print(breast)
# 数据拆分
X_train, X_test, y_train, y_test = train_test_split(
    breast.data, breast.target)

# 数据标准化
std = StandardScaler()
X_train = std.fit_transform(X_train)
X_test = std.transform(X_test)

# 训练预测
lg = LogisticRegression()

lg.fit(X_train, y_train)

y_predict = lg.predict(X_test)

# 查看训练准确度和预测报告
print(lg.score(X_test, y_test))
print("="*20)
print(classification_report(
    y_test, y_predict, labels=[0, 1]))