機器學習100天系列學習筆記 機器學習100天(中文翻譯版)機器學習100天(英文原版）
代碼閱讀：

第一步：導包

#Step 1: Importing the Libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd

第二步：導入數據

#Step 2: Importing the dataset dataset = pd.read_csv('D:/daily/機器學習100天/100-Days-Of-ML-Code-中文版本/100-Days-Of-ML-Code-master/datasets/Social_Network_Ads.csv') X = dataset.iloc[:, [2, 3]].values y = dataset.iloc[:, 4].values

第三步：劃分訓練集、測試集

#Step 3: 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)

第四步：特征縮放

#Step 4: Feature Scaling from sklearn.preprocessing import StandardScaler sc = StandardScaler() X_train = sc.fit_transform(X_train) X_test = sc.transform(X_test)

經過特征縮放后的X_train:

[[ 0.58164944 -0.88670699][-0.60673761 1.46173768][-0.01254409 -0.5677824 ][-0.60673761 1.89663484][ 1.37390747 -1.40858358][ 1.47293972 0.99784738][ 0.08648817 -0.79972756][-0.01254409 -0.24885782][-0.21060859 -0.5677824 ]...]

對于進行特征縮放這一步，個人認為是非常重要的，它可以加快計算速度，在深度學習中間尤為重要（梯度爆炸問題）。

第五步：Logistic Regression

#Step 5: Fitting Logistic Regression to the Training set from sklearn.linear_model import LogisticRegression classifier = LogisticRegression() classifier.fit(X_train, y_train)

第六步：預測

#Step 6: Predicting the Test set results y_pred = classifier.predict(X_test)

第七步：混淆矩陣

#Step 7: 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

混淆：簡單理解為一個class被預測成另一個class。
給一個參考鏈接 混淆矩陣

第八步：可視化

#Step 8: 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()

可視化這一部分代碼可能比較難理解，函數meshgrid是生成一個二維矩陣，大小為X*Y數據個數，這里為(592, 616)；函數ravel將矩陣X1（二維）矩陣展開為一維矩陣（364672，）；函數reshape將（364672，）轉為跟矩陣X1大小一致的二維矩陣；
參數alpha為透明度；函數unique返回參數數組y_set中所有不同的值，并按照從小到大排序，這里返回（0，1）；函數enumerate() 用于將一個可遍歷的數據對象enumerate；這里循環i，j取0或1，
標簽y_setj成立，True=1，標簽y_setj不成立，Flase=0，所以0為紅色點，1為綠色點。
做出的圖為：

全部代碼：

#Day 4: Simple Linear Regression 2022/4/7 #Step 1: Importing the Libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd#Step 2: Importing the dataset dataset = pd.read_csv('D:/daily/機器學習100天/100-Days-Of-ML-Code-中文版本/100-Days-Of-ML-Code-master/datasets/Social_Network_Ads.csv') X = dataset.iloc[:, [2, 3]].values y = dataset.iloc[:, 4].values#Step 3: 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)#Step 4: Feature Scaling from sklearn.preprocessing import StandardScaler sc = StandardScaler() X_train = sc.fit_transform(X_train) X_test = sc.transform(X_test) #print(X_train)#Step 5: Fitting Logistic Regression to the Training set from sklearn.linear_model import LogisticRegression classifier = LogisticRegression() classifier.fit(X_train, y_train)#Step 6: Predicting the Test set results y_pred = classifier.predict(X_test)#Step 7: 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#Step 8: 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()

總結

以上是生活随笔為你收集整理的ML_Logistic_Regression的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。