دسته بندی داده ها با پایتون — راهنمای کاربردی

1%matplotlib inline
2import pandas as pd
3import matplotlib.pyplot as plt
4fruits = pd.read_table('fruit_data_with_colors.txt')
5fruits.head()

1print(fruits.shape)

1print(fruits['fruit_name'].unique())

1print(fruits.groupby('fruit_name').size())

1import seaborn as sns
2sns.countplot(fruits['fruit_name'],label="Count")
3plt.show()

1fruits.drop('fruit_label', axis=1).plot(kind='box', subplots=True, layout=(2,2), sharex=False, sharey=False, figsize=(9,9), 
2                                        title='Box Plot for each input variable')
3plt.savefig('fruits_box')
4plt.show()

1import pylab as pl
2fruits.drop('fruit_label' ,axis=1).hist(bins=30, figsize=(9,9))
3pl.suptitle("Histogram for each numeric input variable")
4plt.savefig('fruits_hist')
5plt.show()

1from pandas.tools.plotting import scatter_matrix
2from matplotlib import cm
3feature_names = ['mass', 'width', 'height', 'color_score']
4X = fruits[feature_names]
5y = fruits['fruit_label']
6cmap = cm.get_cmap('gnuplot')
7scatter = pd.scatter_matrix(X, c = y, marker = 'o', s=40, hist_kwds={'bins':15}, figsize=(9,9), cmap = cmap)
8plt.suptitle('Scatter-matrix for each input variable')
9plt.savefig('fruits_scatter_matrix')

1from sklearn.model_selection import train_test_split
2X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
3from sklearn.preprocessing import MinMaxScaler
4scaler = MinMaxScaler()
5X_train = scaler.fit_transform(X_train)
6X_test = scaler.transform(X_test)

1from sklearn.linear_model import LogisticRegression
2logreg = LogisticRegression()
3logreg.fit(X_train, y_train)
4print('Accuracy of Logistic regression classifier on training set: {:.2f}'
5     .format(logreg.score(X_train, y_train)))
6print('Accuracy of Logistic regression classifier on test set: {:.2f}'
7     .format(logreg.score(X_test, y_test)))

1from sklearn.tree import DecisionTreeClassifier
2clf = DecisionTreeClassifier().fit(X_train, y_train)
3print('Accuracy of Decision Tree classifier on training set: {:.2f}'
4     .format(clf.score(X_train, y_train)))
5print('Accuracy of Decision Tree classifier on test set: {:.2f}'
6     .format(clf.score(X_test, y_test)))

1from sklearn.neighbors import KNeighborsClassifier
2knn = KNeighborsClassifier()
3knn.fit(X_train, y_train)
4print('Accuracy of K-NN classifier on training set: {:.2f}'
5     .format(knn.score(X_train, y_train)))
6print('Accuracy of K-NN classifier on test set: {:.2f}'
7     .format(knn.score(X_test, y_test)))

1from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
2lda = LinearDiscriminantAnalysis()
3lda.fit(X_train, y_train)
4print('Accuracy of LDA classifier on training set: {:.2f}'
5     .format(lda.score(X_train, y_train)))
6print('Accuracy of LDA classifier on test set: {:.2f}'
7     .format(lda.score(X_test, y_test)))

1from sklearn.naive_bayes import GaussianNB
2gnb = GaussianNB()
3gnb.fit(X_train, y_train)
4print('Accuracy of GNB classifier on training set: {:.2f}'
5     .format(gnb.score(X_train, y_train)))
6print('Accuracy of GNB classifier on test set: {:.2f}'
7     .format(gnb.score(X_test, y_test)))

1from sklearn.svm import SVC
2svm = SVC()
3svm.fit(X_train, y_train)
4print('Accuracy of SVM classifier on training set: {:.2f}'
5     .format(svm.score(X_train, y_train)))
6print('Accuracy of SVM classifier on test set: {:.2f}'
7     .format(svm.score(X_test, y_test)))

1from sklearn.metrics import classification_report
2from sklearn.metrics import confusion_matrix
3pred = knn.predict(X_test)
4print(confusion_matrix(y_test, pred))
5print(classification_report(y_test, pred))

1import matplotlib.cm as cm
2from matplotlib.colors import ListedColormap, BoundaryNorm
3import matplotlib.patches as mpatches
4import matplotlib.patches as mpatches
5X = fruits[['mass', 'width', 'height', 'color_score']]
6y = fruits['fruit_label']
7X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
8def plot_fruit_knn(X, y, n_neighbors, weights):
9    X_mat = X[['height', 'width']].as_matrix()
10    y_mat = y.as_matrix()
11# Create color maps
12    cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF','#AFAFAF'])
13    cmap_bold  = ListedColormap(['#FF0000', '#00FF00', '#0000FF','#AFAFAF'])
14clf = neighbors.KNeighborsClassifier(n_neighbors, weights=weights)
15    clf.fit(X_mat, y_mat)
16# Plot the decision boundary by assigning a color in the color map
17    # to each mesh point.
18    
19    mesh_step_size = .01  # step size in the mesh
20    plot_symbol_size = 50
21    
22    x_min, x_max = X_mat[:, 0].min() - 1, X_mat[:, 0].max() + 1
23    y_min, y_max = X_mat[:, 1].min() - 1, X_mat[:, 1].max() + 1
24    xx, yy = np.meshgrid(np.arange(x_min, x_max, mesh_step_size),
25                         np.arange(y_min, y_max, mesh_step_size))
26    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
27# Put the result into a color plot
28    Z = Z.reshape(xx.shape)
29    plt.figure()
30    plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
31# Plot training points
32    plt.scatter(X_mat[:, 0], X_mat[:, 1], s=plot_symbol_size, c=y, cmap=cmap_bold, edgecolor = 'black')
33    plt.xlim(xx.min(), xx.max())
34    plt.ylim(yy.min(), yy.max())
35patch0 = mpatches.Patch(color='#FF0000', label='apple')
36    patch1 = mpatches.Patch(color='#00FF00', label='mandarin')
37    patch2 = mpatches.Patch(color='#0000FF', label='orange')
38    patch3 = mpatches.Patch(color='#AFAFAF', label='lemon')
39    plt.legend(handles=[patch0, patch1, patch2, patch3])
40plt.xlabel('height (cm)')
41plt.ylabel('width (cm)')
42plt.title("4-Class classification (k = %i, weights = '%s')"
43           % (n_neighbors, weights))    
44plt.show()
45plot_fruit_knn(X_train, y_train, 5, 'uniform')

1k_range = range(1, 20)
2scores = []
3for k in k_range:
4    knn = KNeighborsClassifier(n_neighbors = k)
5    knn.fit(X_train, y_train)
6    scores.append(knn.score(X_test, y_test))
7plt.figure()
8plt.xlabel('k')
9plt.ylabel('accuracy')
10plt.scatter(k_range, scores)
11plt.xticks([0,5,10,15,20])