machinelearning_notebook/1_knn/knn_classification.py

# ---
# jupyter:
#   jupytext_format_version: '1.2'
#   kernelspec:
#     display_name: Python 3
#     language: python
#     name: python3
#   language_info:
#     codemirror_mode:
#       name: ipython
#       version: 3
#     file_extension: .py
#     mimetype: text/x-python
#     name: python
#     nbconvert_exporter: python
#     pygments_lexer: ipython3
#     version: 3.5.2
# ---

# # KNN Classification
#
#
#

# +
% matplotlib inline

import matplotlib.pyplot as plt
from sklearn import datasets, neighbors, linear_model

# load data
digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target

print("Feature dimensions: ", X_digits.shape)
print("Label dimensions:   ", y_digits.shape)


# +
# plot sample images
nplot = 10
fig, axes = plt.subplots(nrows=1, ncols=nplot)

for i in range(nplot):
    img = X_digits[i].reshape(8, 8)
    axes[i].imshow(img)
    axes[i].set_title(y_digits[i])


# +
# split train / test data
n_samples = len(X_digits)
n_train = int(0.4 * n_samples)

X_train = X_digits[:n_train]
y_train = y_digits[:n_train]
X_test = X_digits[n_train:]
y_test = y_digits[n_train:]


# +
# do KNN classification
knn = neighbors.KNeighborsClassifier()
logistic = linear_model.LogisticRegression()

print('KNN score: %f' % knn.fit(X_train, y_train).score(X_test, y_test))
print('LogisticRegression score: %f' % logistic.fit(X_train, y_train).score(X_test, y_test))
# -

# ## References
# * [Digits Classification Exercise](http://scikit-learn.org/stable/auto_examples/exercises/plot_digits_classification_exercise.html)
#