Examples of classification using Python

Use the MNIST dataset as an example.

The methods used here are Nearest Neighbour, Bayesian, Decision Tree, Logistic Regression, KNN

import numpy as np
import pandas as pd
#from keras.utils import np_utils
# 匯入資料
from keras.datasets import mnist
(x_train_image,y_train_label),(x_test_image,y_test_label)=mnist.load_data()
print('train data= ',len(x_train_image))
print('test data=', len(x_test_image))

train data=  60000
test data= 10000

import matplotlib.pyplot as plt

# 建立函數要來畫多圖的
def plot_images_labels_prediction(images,labels,prediction,idx,num=10):
  # 設定顯示圖形的大小
  fig= plt.gcf()
  fig.set_size_inches(12,14)
  # 最多25張
  if num>25:num=25
  # 一張一張畫
  for i in range(0,num):
    # 建立子圖形5*5(五行五列)
    ax=plt.subplot(5,5,i+1)
    # 畫出子圖形
    ax.imshow(images[idx],cmap='binary')
    # 標題和label
    title="label=" +str(labels[idx])
    # 如果有傳入預測結果也顯示
    if len(prediction)>0:
      title+=",predict="+str(prediction[idx])
    # 設定子圖形的標題大小
    ax.set_title(title,fontsize=10)
    # 設定不顯示刻度
    ax.set_xticks([]);ax.set_yticks([])
    idx+=1
  plt.show()
plot_images_labels_prediction(x_train_image,y_train_label,[],0,10)

# 影像資料--------------------------------------
# 代表 train image 總共有6萬張，每一張是28*28的圖片
# label 也有6萬個
# 所以要把二維的圖片矩陣先轉換成一維
# 這裡的784是因為 28*28
x_Train=x_train_image.reshape(60000,784).astype('float32')
x_Test=x_test_image.reshape(10000,784).astype('float32')


# 由於是圖片最大的是255，所以全部除以255，使其變成0-1的數值
x_Train_normalize=x_Train/255
x_Test_normalize=x_Test/255

# 標註資料--------------------------------------
#y_TrainOneHot=np_utils.to_categorical(y_train_label)
#y_TestOneHot=np_utils.to_categorical(y_test_label)

# Standard scientific Python imports
import matplotlib.pyplot as plt

# Import datasets, classifiers and performance metrics
from sklearn import datasets, svm, metrics
from sklearn.model_selection import train_test_split
from sklearn.neighbors import NearestCentroid, KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier

model=NearestCentroid()
#model = GaussianNB()
#model = DecisionTreeClassifier()
#model = LogisticRegression()
# fit the model
model.fit(x_Train_normalize, y_train_label)

# Predict the value of the digit on the test subset
predicted = model.predict(x_Test_normalize)
# Display the confusion matrix
disp = metrics.ConfusionMatrixDisplay.from_predictions(y_test_label, predicted,cmap='CMRmap_r')
accu = metrics.accuracy_score(y_test_label, predicted)
disp.figure_.suptitle("Confusion Matrix of Nearest Neighbour Method")
#print(f"Confusion matrix:\n{disp.confusion_matrix}")
print('Overall Acuracy:{:.3}'.format(accu))

Overall Acuracy:0.82

model = GaussianNB()
#model = DecisionTreeClassifier()
#model = LogisticRegression()
# fit the model
model.fit(x_Train_normalize, y_train_label)

# Predict the value of the digit on the test subset
predicted = model.predict(x_Test_normalize)
# Display the confusion matrix
disp = metrics.ConfusionMatrixDisplay.from_predictions(y_test_label, predicted,cmap='CMRmap_r')
accu = metrics.accuracy_score(y_test_label, predicted)
disp.figure_.suptitle("Confusion Matrix of Bayesian")
#print(f"Confusion matrix:\n{disp.confusion_matrix}")
print('Overall Acuracy:{:.3}'.format(accu))

Overall Acuracy:0.556

model = DecisionTreeClassifier()
#model = LogisticRegression()
# fit the model
model.fit(x_Train_normalize, y_train_label)

# Predict the value of the digit on the test subset
predicted = model.predict(x_Test_normalize)
# Display the confusion matrix
disp = metrics.ConfusionMatrixDisplay.from_predictions(y_test_label, predicted,cmap='CMRmap_r')
accu = metrics.accuracy_score(y_test_label, predicted)
disp.figure_.suptitle("Confusion Matrix of Decision Tree Classifier")
#print(f"Confusion matrix:\n{disp.confusion_matrix}")
print('Overall Acuracy:{:.3}'.format(accu))

Overall Acuracy:0.877

model = LogisticRegression()
# fit the model
model.fit(x_Train_normalize, y_train_label)

# Predict the value of the digit on the test subset
predicted = model.predict(x_Test_normalize)
# Display the confusion matrix
disp = metrics.ConfusionMatrixDisplay.from_predictions(y_test_label, predicted,cmap='CMRmap_r')
accu = metrics.accuracy_score(y_test_label, predicted)
disp.figure_.suptitle("Confusion Matrix of Logistic egression")
#print(f"Confusion matrix:\n{disp.confusion_matrix}")
print('Overall Acuracy:{:.3}'.format(accu))

/usr/local/lib/python3.10/dist-packages/sklearn/linear_model/_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(

Overall Acuracy:0.926

model=KNeighborsClassifier(n_neighbors=10)

# fit the model
model.fit(x_Train_normalize, y_train_label)

# Predict the value of the digit on the test subset
predicted = model.predict(x_Test_normalize)
# Display the confusion matrix
disp = metrics.ConfusionMatrixDisplay.from_predictions(y_test_label, predicted,cmap='CMRmap_r')
accu = metrics.accuracy_score(y_test_label, predicted)
disp.figure_.suptitle("Confusion Matrix of Nearest Neighbour Method")
#print(f"Confusion matrix:\n{disp.confusion_matrix}")
print('Overall Acuracy:{:.3}'.format(accu))

Overall Acuracy:0.967