Digit Recognition

Here you can import digit dataset from scikit learn library which is in-built, So you don't need to download from other else

Note: If you use visual code, I recommend you to turn your color theme to Monokai because it has a few extra and important keyword and attractive colors than other theme.

 # %%  Import libraries

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import random 

# %%   Load dataset

from sklearn.datasets import load_digits

dataset = load_digits()

dataset.keys()

output: dict_keys(['data', 'target', 'target_names', 'images', 'DESCR'])

You have to check all to direct print them

Here DESCR is a description of dataset

# %%   divide the dataset into input and target

inputs = dataset.data

target = dataset.target

# %%   Visualization

images = dataset.images

for i in range(6):

    plt.figure(figsize=(6,4), num=0)

    plt.subplot(2,3, i+1)

    plt.axis('off')

    plt.imshow(images[i], cmap='gray')

    plt.title(dataset.target[i])

# %%   Split the dataset into training and testing set

from sklearn.model_selection import train_test_split

train_f, test_f, train_t, test_t = train_test_split(input, target, test_size=0.2, random_state=21)

# %%    model fitting

from sklearn.tree import DecisionTreeClassifier

model = DecisionTreeClassifier()

model.fit(train_f, train_t)

# %%   Score

model.score(test_f, test_t)

# %%    Prediction

num = 10

test_ar = test_f[num]

mark = model.predict([test_ar])

image = test_ar.reshape(8,8)

plt.imshow(image, cmap='gray')

plt.title('Digit is {}'.format(mark))

plt.show()

'''Now you can make real life application to saving model. There is the reason behind

save model is you don't have to run your already done model everytime. It consume your

important time and impairs the model performance.'''

# %%  Save the model

from sklearn.externals import joblib

joblib.dump(model, '../Digit_Recnogition_App')

You have to put your digit image in front of webcam and see result