Support Vector Machine (SVM): Digit Classification with SVM Python using sklearn digits dataset

Question

Train SVM classifier using sklearn digits dataset (i.e. from sklearn.datasets import load_digits) and then,

1. Measure accuracy of your model using different kernels such as rbf and linear.
2. Tune your model further using regularization and gamma parameters and try to come up with highest accurancy score
3. Use 80% of samples as training data size

Answer 1

GO_STP_6266

https://www.linkedin.com/posts/sahil-parmar-4099391bb_google-colaboratory-activity-6810449047736975360-T7CN

Answer 2

import pandas as pd

import numpy as np

import sklearn

import matplotlib.pyplot as plt

from sklearn.datasets import load_digits

import seaborn as sns

digits=load_digits()

print(digits)

digits.keys()

df=pd.DataFrame(digits.data)

print(df.head())

print(df.shape)

df.columns

df.isnull().sum()

df['target']=digits.target

df.head()

print(digits.data.shape)

print(digits.target.shape)

df.target

df.values

from sklearn.model_selection import train_test_split

x=df.drop(['target'],axis='columns')

y=df.target

x_train,x_test,y_train,y_test= train_test_split(x,y,test_size=0.2,random_state=12)

print(len(x_train))

print(len(x_test))

from sklearn.metrics import accuracy_score

from sklearn.svm import SVC

model1=SVC(kernel='rbf',random_state=0, probability=True)

model1.fit(x_train,y_train)

y_pred_1=model1.predict(x_test)

print("Model Score of Kernal(rbf) :", model1.score(x_test,y_test))

model2=SVC(kernel='linear',random_state=0, probability=True)

model2.fit(x_train,y_train)

y_pred_2=model2.predict(x_test)

print("Model Score of Kernal(linear) :", model2.score(x_test,y_test))

model3=SVC(kernel='poly',random_state=0, probability=True)

model3.fit(x_train,y_train)

y_pred_3=model3.predict(x_test)

print("Model Score of Kernal(poly) :", model3.score(x_test,y_test))

accuracy=accuracy_score(y_test,y_pred_3)

print('ACCURACY is',accuracy)

from sklearn.metrics import confusion_matrix

cm=np.array(confusion_matrix(y_test,y_pred_3))

cm

from sklearn.metrics import mean_squared_error

mse=mean_squared_error(y_test,y_pred_3)

mse

model1_C=SVC(C=3)

model1_C.fit(x_train,y_train)

model1_C.score(x_test,y_test)

model2_C=SVC(C=3)

model2_C.fit(x_train,y_train)

model2_C.score(x_test,y_test)

model3_C=SVC(C=3)

model3_C.fit(x_train,y_train)

model3_C.score(x_test,y_test)

plt.figure(figsize=(5,5))

sns.heatmap(cm, annot=True, fmt=".2f", linewidths=.5, square = True, cmap = 'Blues_r')

plt.ylabel('Actual label')

plt.xlabel('Predicted label')

A=f'Accuracy Score :{accuracy:.2f}'

plt.title(A)

plt.show()