fit_example.py

fit_example.py

"""
scikit-learn example to fit a SVC model for recognizing images of hand-written digits.

The images attribute of the dataset stores 8x8 arrays of grayscale values for each image. 
We will use these arrays to visualize the first 4 images. To apply a classifier on this data, 
we need to flatten the images, turning each 2-D array of grayscale values from 
shape (8, 8) into shape (64,). 

Reference: https://scikit-learn.org/stable/auto_examples/classification/plot_digits_classification.html
"""
from sklearn import datasets, svm
from sklearn.model_selection import train_test_split


# Load data 
digits_data = datasets.load_digits()

# Flatten images (see the comment on the top of the file to undestand why)
data_flattened = digits_data.images.reshape((len(digits_data.images), -1))

# Split data into training and testing sets (ratio 80:20)
X_train, X_test, y_train, y_test = train_test_split(
    data_flattened, 
    digits_data.target, 
    test_size=0.2, 
    shuffle=False
)

# Create a Support Vector Classifier
clf = svm.SVC(gamma=0.001)

# Fit the classifier to the input training data
clf.fit(X_train, y_train)