from sklearn.datasets import fetch_openml
mnist = fetch_openml('mnist_784',version=1, as_frame=False)
mnist.keys()
X, y = mnist["data"], mnist["target"]
X.shape
y.shape
%matplotlib inline
import matplotlib as mpl
import matplotlib.pyplot as plt
some_digit = X[0]
some_digit_image = some_digit.reshape(28,28)
plt.imshow(some_digit_image, cmap=mpl.cm.binary)
plt.axis("off")
plt.show()
import sklearn
assert sklearn.__version__ >= "0.20"
import numpy as np
import os
np.random.seed(42)
def plot_digits(instances, images_per_row=10, **options):
size = 28
images_per_row = min(len(instances), images_per_row)
n_rows = (len(instances) - 1) // images_per_row + 1
n_empty = n_rows * images_per_row - len(instances)
padded_instances = np.concatenate([instances, np.zeros((n_empty, size * size))], axis = 0)
image_grid = padded_instances.reshape((n_rows, images_per_row, size, size))
big_image = image_grid.transpose(0,2,1,3).reshape(n_rows * size,
images_per_row * size)
plt.imshow(big_image, cmap = mpl.cm.binary, **options)
plt.axis("off")
plt.figure(figsize=(9,9))
example_images = X[:100]
plot_digits(example_images, images_per_row=10)
plt.show()
import numpy as np
y = y.astype(np.uint8)
X_train, X_test, y_train, y_test = X[:60000], X[60000:], y[:60000], y[60000:]
y_train_5 = (y_train ==5)
y_test_5 = (y_test ==5)
from sklearn.linear_model import SGDClassifier
sgd_clf = SGDClassifier(max_iter=1000, tol=1e-3, random_state=42)
sgd_clf.fit(X_train, y_train_5)
sgd_clf.predict([some_digit])
from sklearn.model_selection import cross_val_score
cross_val_score(sgd_clf, X_train, y_train_5, cv=3, scoring="accuracy")
from sklearn.model_selection import StratifiedKFold
from sklearn.base import clone
skfolds = StratifiedKFold(n_splits=3, shuffle=True, random_state=42)
for train_index, test_index in skfolds.split(X_train, y_train_5):
clone_clf = clone(sgd_clf)
X_train_folds = X_train[train_index]
y_train_folds=y_train_5[train_index]
X_test_fold = X_train[test_index]
y_test_fold = y_train_5[test_index]
clone_clf.fit(X_train_folds, y_train_folds)
y_pred = clone_clf.predict(X_test_fold)
n_correct = sum(y_pred == y_test_fold)
print(n_correct / len(y_pred))
from sklearn.model_selection import cross_val_predict
y_train_pred = cross_val_predict(sgd_clf, X_train, y_train_5, cv=3)
from sklearn.metrics import confusion_matrix
confusion_matrix(y_train_5, y_train_pred)
y_train_perfect_predictions = y_train_5
confusion_matrix(y_train_5, y_train_perfect_predictions)
from sklearn.metrics import precision_score, recall_score
precision_score(y_train_5, y_train_pred)
cm = confusion_matrix(y_train_5, y_train_pred)
cm[1,1] / (cm[0,1] + cm[1,1])
recall_score(y_train_5, y_train_pred)
cm[1, 1] / (cm[1, 0] + cm[1, 1])
from sklearn.metrics import f1_score
f1_score(y_train_5, y_train_pred)
cm[1, 1] / (cm[1, 1] + (cm[1, 0]+cm[0, 1])/2)
y_scores = sgd_clf.decision_function([some_digit])
y_scores
threshold = 0
y_some_digit_pred = (y_scores > threshold)
y_some_digit_pred
threshold = 8000
y_some_digit_pred = (y_scores > threshold)
y_some_digit_pred
y_scores = cross_val_predict(sgd_clf, X_train, y_train_5, cv=3,
method="decision_function")
from sklearn.metrics import precision_recall_curve
precisions, recalls, thresholds = precision_recall_curve(y_train_5, y_scores)
def plot_precision_recall_vs_threshold(precisions, recalls, thresholds):
plt.plot(thresholds, precisions[:-1], "b--", label="Precision", linewidth=2)
plt.plot(thresholds, recalls[:-1], "g-", label="Recall", linewidth=2)
plt.legend(loc="center right", fontsize=16)
plt.xlabel("Threshold", fontsize=16)
plt.grid(True)
plt.axis([-50000,50000,0,1])
recall_90_precision = recalls[np.argmax(precisions >= 0.90)]
threshold_90_precision = thresholds[np.argmax(precisions >= 0.90)]
plt.figure(figsize=(8,4))
plot_precision_recall_vs_threshold(precisions, recalls, thresholds)
plt.plot([threshold_90_precision, threshold_90_precision], [0., 0.9], "r:")
plt.plot([-50000, threshold_90_precision], [0.9, 0.9], "r:")
plt.plot([-50000, threshold_90_precision], [recall_90_precision, recall_90_precision], "r:")
plt.plot([threshold_90_precision], [0.9], "ro")
plt.plot([threshold_90_precision], [recall_90_precision], "ro")
plt.show()
y_scores = sgd_clf.decision_function([some_digit])
y_scores
threshold = 0
y_some_digit_pred = (y_scores > threshold)
y_some_digit_pred
threshold = 8000
y_some_digit_pred = (y_scores > threshold)
y_some_digit_pred
y_scores = cross_val_predict(sgd_clf, X_train, y_train_5, cv=3,
method="decision_function")
from sklearn.metrics import precision_recall_curve
precisions, recalls, thresholds = precision_recall_curve(y_train_5, y_scores)
def plot_precision_vs_recall(precisions, recalls):
plt.plot(recalls, precisions, "b-", linewidth=2)
plt.xlabel("Recall", fontsize=16)
plt.ylabel("Precision", fontsize=16)
plt.axis([0,1,0,1])
plt.grid(True)
plt.figure(figsize=(8,6))
plot_precision_vs_recall(precisions, recalls)
plt.plot([recall_90_precision, recall_90_precision], [0.,0.9], "r:")
plt.plot([0.0, recall_90_precision], [0.9,0.9], "r:")
plt.plot([recall_90_precision], [0.9], "ro")
plt.show()
from sklearn.metrics import roc_curve
fpr, tpr, thresholds = roc_curve(y_train_5, y_scores)
def plot_roc_curve(fpr, tpr, label=None):
plt.plot(fpr, tpr, linewidth=2, label=label)
plt.plot([0,1], [0,1], 'k--')
plt.axis([0,1,0,1])
plt.xlabel('False Positive Rate (Fall-Out)', fontsize=16)
plt.ylabel('True Positive Rate (Recall)', fontsize=16)
plt.grid(True)
plt.figure(figsize=(8,6))
plot_roc_curve(fpr, tpr)
fpr_90 = fpr[np.argmax(tpr >= recall_90_precision)]
plt.plot([fpr_90, fpr_90], [0, recall_90_precision], "r:")
plt.plot([0.0, fpr_90], [recall_90_precision, recall_90_precision], "r:")
plt.plot([fpr_90], [recall_90_precision], "ro")
plt.show()
from sklearn.metrics import roc_auc_score
roc_auc_score(y_train_5, y_scores)
from sklearn.neighbors import KNeighborsClassifier
knn_clf = KNeighborsClassifier()
noise = np.random.randint(0, 100, (len(X_train), 784))
X_train_mod = X_train + noise
noise = np.random.randint(0, 100, (len(X_test), 784))
X_test_mod = X_test + noise
y_train_mod = X_train
y_test_mod = X_test
def plot_digit(data):
image = data.reshape(28, 28)
plt.imshow(image, cmap=mpl.cm.binary, interpolation="nearest")
plt.axis("off")
some_index = 0
plt.subplot(121); plot_digit(X_test_mod[some_index])
plt.subplot(122); plot_digit(y_test_mod[some_index])
plt.show()
knn_clf.fit(X_train_mod, y_train_mod)
clean_digit=knn_clf.predict([X_test_mod[some_index]])
plot_digit(clean_digit)
plt.show()