学习目标
- 掌握什么是逻辑回归
- 逻辑回归能够处理哪些问题
步骤讲解
逻辑回归
逻辑回归是一个线性分类器,在二维空间中模型中点存在两个状态。
step = "Step 2 | Logistic Regression Model"
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression()
classifier.fit(x_train, y_train)
源代码
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
step = "Step 1 | Data Pre-Processing"
# Importing the dataset
dataset = pd.read_csv("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)
step = "Step 2 | Logistic Regression Model"
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression()
classifier.fit(x_train, y_train)
step = "Step 3 | Predection"
y_pred = classifier.predict(x_test)
step = "Step 4 | Evaluating The Predection"
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
step = "Step 5 | 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()