《机器学习100天》学习笔记——Day 4-6_Logistic_Regression(逻辑回归）
100-Days-Of-ML-Code
中文版《机器学习100天》
GitHub ：https://github.com/MLEveryday/100-Days-Of-ML-Code
数据集 | 社交网络
部分数据集如下图所示：
该数据集包含了社交网络中用户的信息。这些信息涉及用户ID,性别,年龄以及预估薪资。一家汽车公司刚刚推出了他们新型的豪华SUV，我们尝试预测哪些用户会购买这种全新SUV。并且在最后一列用来表示用户是否购买。我们将建立一种模型来预测用户是否购买这种SUV，该模型基于两个变量，分别是年龄和预计薪资。因此我们的特征矩阵将是这两列。我们尝试寻找用户年龄与预估薪资之间的某种相关性，以及Ta是否购买SUV的决定。
第一步：数据预处理
（1）导入库
# Importing the Libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
（2）导入数据集
# Importing the dataset
dataset = pd.read_csv('D:/PycharmProjects/DataSet/Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values
y = dataset.iloc[:, 4].values
（3）将数据集划分为训练集和测试集
# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
（4）特征量化
# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
第二步：将逻辑回归应用于训练集
# Fitting Logistic Regression to the Training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression()
classifier.fit(X_train, y_train)
第三步：预测测试集结果
# Predicting the Test set results
y_pred = classifier.predict(X_test)
第四步：评估预测
我们已经预测了测试集，现在将评估逻辑回归模型是否正确的学习和理解。因此这个混淆矩阵将包含模型的正确和错误的预测。
（1）生成混淆矩阵
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
cm = confusion_matrix(y_test, y_pred)
print(cm) # print confusion_matrix
print(classification_report(y_test, y_pred)) # print classification report
结果如下：
（2）可视化
from matplotlib.colors import ListedColormap
X_set,y_set=X_train,y_train
X1,X2=np. meshgrid(np. arange(start=X_set[:,0].min()-1, stop=X_set[:, 0].max()+1, step=0.01),
np. arange(start=X_set[:,1].min()-1, stop=X_set[:,1].max()+1, step=0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(),X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(),X1.max()) #设定坐标上下限
plt.ylim(X2.min(),X2.max())
for i,j in enumerate(np. unique(y_set)):
plt.scatter(X_set[y_set==j,0],X_set[y_set==j,1],
c = ListedColormap(('red', 'green'))(i), label=j)
plt. title(' LOGISTIC(Training set)')
plt. xlabel(' Age')
plt. ylabel(' Estimated Salary')
plt. legend() #显示图中的标签
plt. show()
X_set,y_set=X_test,y_test
X1,X2=np. meshgrid(np. arange(start=X_set[:,0].min()-1, stop=X_set[:, 0].max()+1, step=0.01),
np. arange(start=X_set[:,1].min()-1, stop=X_set[:,1].max()+1, step=0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(),X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(),X1.max())
plt.ylim(X2.min(),X2.max())
for i,j in enumerate(np. unique(y_set)):
plt.scatter(X_set[y_set==j,0],X_set[y_set==j,1],
c = ListedColormap(('red', 'green'))(i), label=j)
plt. title(' LOGISTIC(Test set)')
plt. xlabel(' Age')
plt. ylabel(' Estimated Salary')
plt. legend()
plt. show()
结果如下图所示：
完整代码及学习图谱如下：
# Importing the Libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('D:/PycharmProjects/DataSet/Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values
y = dataset.iloc[:, 4].values
# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# Fitting Logistic Regression to the Training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression()
classifier.fit(X_train, y_train)
# Predicting the Test set results
y_pred = classifier.predict(X_test)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
cm = confusion_matrix(y_test, y_pred)
print(cm) # print confusion_matrix
print(classification_report(y_test, y_pred)) # print classification report
#Visualization
from matplotlib.colors import ListedColormap
X_set,y_set=X_train,y_train
X1,X2=np. meshgrid(np. arange(start=X_set[:,0].min()-1, stop=X_set[:, 0].max()+1, step=0.01),
np. arange(start=X_set[:,1].min()-1, stop=X_set[:,1].max()+1, step=0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(),X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(),X1.max())
plt.ylim(X2.min(),X2.max())
for i,j in enumerate(np. unique(y_set)):
plt.scatter(X_set[y_set==j,0],X_set[y_set==j,1],
c = ListedColormap(('red', 'green'))(i), label=j)
plt. title(' LOGISTIC(Training set)')
plt. xlabel(' Age')
plt. ylabel(' Estimated Salary')
plt. legend()
plt. show()
X_set,y_set=X_test,y_test
X1,X2=np. meshgrid(np. arange(start=X_set[:,0].min()-1, stop=X_set[:, 0].max()+1, step=0.01),
np. arange(start=X_set[:,1].min()-1, stop=X_set[:,1].max()+1, step=0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(),X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(),X1.max())
plt.ylim(X2.min(),X2.max())
for i,j in enumerate(np. unique(y_set)):
plt.scatter(X_set[y_set==j,0],X_set[y_set==j,1],
c = ListedColormap(('red', 'green'))(i), label=j)
plt. title(' LOGISTIC(Test set)')
plt. xlabel(' Age')
plt. ylabel(' Estimated Salary')
plt. legend()
plt. show()
