** Recognizing Handwritten Digits **

Hypothesis to be tested : The Digits data set of scikit-learn library provides numerous data-sets that are useful for testing many problems of data analysis and prediction of the results. Some Scientist claims that it predicts the digit accurately 95% of the times. Perform data Analysis to accept or reject this Hypothesis.

Steps :- 1. Load the  dataset from the package sklearn import svm .

2 . Explore the dataset by viewing its shape  , its dimension . So according to the data , each single data consist of 8x8 matrix which in whole represents a data .

3. Randomly select any of the data entry and load its pixel , and finds its actual value using function digits.target (data_entry).

4. Then predict your model by first using function fit() and predict() function . Thus the output is displayed on the screen which values is predicted

5. Compare the predicted values with the actual ones

Observation : 1. We loaded the data points from 200 to 206

2. After using digits.target[200 : 206] we get the output array([1,5,0,9,5,2]) and after predicting we get the same array as the output thus giving us the 100 % predicting accuracy .

3> Thus we can conclude that the we can obtain accuracy of 95 or more than 95 % as said by the Scientist .

I am thankful to mentors at suven consultants for providing awesome problem statements and giving many of us a Coding Internship Exprience. Thank you Rocky Jagtiani.