水果分類器採用機器學習的技巧來實作,因此可以看出所有的演算法都是把資料分成訓練組和測試組,大家不妨找出那一種分類法,所得到分數最高,就是比較適合水果分類的方法。
求邏輯迴歸(Logistic Regression)值:
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 | import pandas as pd import matplotlib.pyplot as plt fruits = pd.read_table('fruit_data_with_colors.txt') from pandas.tools.plotting import scatter_matrix from matplotlib import cm feature_names = ['mass', 'width', 'height', 'color_score'] X = fruits[feature_names] y = fruits['fruit_label'] from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) from sklearn.preprocessing import MinMaxScaler scaler = MinMaxScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) from sklearn.linear_model import LogisticRegression logreg = LogisticRegression() logreg.fit(X_train, y_train) print('Accuracy of Logistic regression classifier on training set: {:.2f}' .format(logreg.score(X_train, y_train))) print('Accuracy of Logistic regression classifier on test set: {:.2f}' .format(logreg.score(X_test, y_test))) |
執行結果:
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 | import pandas as pd import matplotlib.pyplot as plt fruits = pd.read_table('fruit_data_with_colors.txt') from pandas.tools.plotting import scatter_matrix from matplotlib import cm feature_names = ['mass', 'width', 'height', 'color_score'] X = fruits[feature_names] y = fruits['fruit_label'] from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) from sklearn.preprocessing import MinMaxScaler scaler = MinMaxScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) from sklearn.tree import DecisionTreeClassifier clf = DecisionTreeClassifier().fit(X_train, y_train) print('Accuracy of Decision Tree classifier on training set: {:.2f}' .format(clf.score(X_train, y_train))) print('Accuracy of Decision Tree classifier on test set: {:.2f}' .format(clf.score(X_test, y_test))) |
執行結果:
設置最大決策樹深度有助於避免過度擬合(Overfitting):
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 | import pandas as pd import matplotlib.pyplot as plt fruits = pd.read_table('fruit_data_with_colors.txt') from pandas.tools.plotting import scatter_matrix from matplotlib import cm feature_names = ['mass', 'width', 'height', 'color_score'] X = fruits[feature_names] y = fruits['fruit_label'] from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) from sklearn.preprocessing import MinMaxScaler scaler = MinMaxScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) from sklearn.tree import DecisionTreeClassifier clf2 = DecisionTreeClassifier(max_depth=3).fit(X_train, y_train) print('Accuracy of Decision Tree classifier on training set: {:.2f}' .format(clf2.score(X_train, y_train))) print('Accuracy of Decision Tree classifier on test set: {:.2f}' .format(clf2.score(X_test, y_test))) |
K-最近鄰居法(K-Nearest Neighbors):
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 | import pandas as pd import matplotlib.pyplot as plt fruits = pd.read_table('fruit_data_with_colors.txt') from pandas.tools.plotting import scatter_matrix from matplotlib import cm feature_names = ['mass', 'width', 'height', 'color_score'] X = fruits[feature_names] y = fruits['fruit_label'] from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) from sklearn.preprocessing import MinMaxScaler scaler = MinMaxScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) from sklearn.neighbors import KNeighborsClassifier knn = KNeighborsClassifier() knn.fit(X_train, y_train) print('Accuracy of K-NN classifier on training set: {:.2f}' .format(knn.score(X_train, y_train))) print('Accuracy of K-NN classifier on test set: {:.2f}' .format(knn.score(X_test, y_test))) |
執行結果:
線性區別分析(
Linear Discriminant Analysis):1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 | import pandas as pd import matplotlib.pyplot as plt fruits = pd.read_table('fruit_data_with_colors.txt') from pandas.tools.plotting import scatter_matrix from matplotlib import cm feature_names = ['mass', 'width', 'height', 'color_score'] X = fruits[feature_names] y = fruits['fruit_label'] from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) from sklearn.preprocessing import MinMaxScaler scaler = MinMaxScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) from sklearn.discriminant_analysis import LinearDiscriminantAnalysis lda = LinearDiscriminantAnalysis() lda.fit(X_train, y_train) print('Accuracy of LDA classifier on training set: {:.2f}' .format(lda.score(X_train, y_train))) print('Accuracy of LDA classifier on test set: {:.2f}' .format(lda.score(X_test, y_test))) |
執行結果:
單純貝氏分類器(Gaussian Naive Bayes):
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 | import pandas as pd import matplotlib.pyplot as plt fruits = pd.read_table('fruit_data_with_colors.txt') from pandas.tools.plotting import scatter_matrix from matplotlib import cm feature_names = ['mass', 'width', 'height', 'color_score'] X = fruits[feature_names] y = fruits['fruit_label'] from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) from sklearn.preprocessing import MinMaxScaler scaler = MinMaxScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) from sklearn.naive_bayes import GaussianNB gnb = GaussianNB() gnb.fit(X_train, y_train) print('Accuracy of GNB classifier on training set: {:.2f}' .format(gnb.score(X_train, y_train))) print('Accuracy of GNB classifier on test set: {:.2f}' .format(gnb.score(X_test, y_test))) |
執行成果:
支撐向量機(support vector machine, SVM):
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 | import pandas as pd import matplotlib.pyplot as plt fruits = pd.read_table('fruit_data_with_colors.txt') from pandas.tools.plotting import scatter_matrix from matplotlib import cm feature_names = ['mass', 'width', 'height', 'color_score'] X = fruits[feature_names] y = fruits['fruit_label'] from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) from sklearn.preprocessing import MinMaxScaler scaler = MinMaxScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) from sklearn.svm import SVC svm = SVC() svm.fit(X_train, y_train) print('Accuracy of SVM classifier on training set: {:.2f}' .format(svm.score(X_train, y_train))) print('Accuracy of SVM classifier on test set: {:.2f}' .format(svm.score(X_test, y_test))) |
執行結果: