# Get the data
from sklearn.datasets import load_digits
digits = load_digits()
X = digits.data
y = digits.target

# Instantiate and train the classifier
from sklearn.neighbors import KNeighborsClassifier
clf = KNeighborsClassifier(n_neighbors=1)
clf.fit(X, y)

# Check the results using metrics
from sklearn import metrics
y_pred = clf.predict(X)

print(metrics.confusion_matrix(y_pred, y))

%matplotlib inline
from matplotlib import pyplot as plt
import numpy as np

from sklearn.datasets import load_boston
from sklearn.tree import DecisionTreeRegressor

data = load_boston()
clf = DecisionTreeRegressor().fit(data.data, data.target)
predicted = clf.predict(data.data)
expected = data.target

plt.scatter(expected, predicted)
plt.plot([0, 50], [0, 50], '--k')
plt.axis('tight')
plt.xlabel('True price ($1000s)')
plt.ylabel('Predicted price ($1000s)')

from sklearn import cross_validation
X = digits.data
y = digits.target

X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.25, random_state=0)

print("%r, %r, %r" % (X.shape, X_train.shape, X_test.shape))

clf = KNeighborsClassifier(n_neighbors=1).fit(X_train, y_train)
y_pred = clf.predict(X_test)

print(metrics.confusion_matrix(y_test, y_pred))

print(metrics.classification_report(y_test, y_pred))

metrics.f1_score(y_test, y_pred)

metrics.f1_score(y_train, clf.predict(X_train))

data = load_boston()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = cross_validation.train_test_split(
    X, y, test_size=0.25, random_state=0)

print("%r, %r, %r" % (X.shape, X_train.shape, X_test.shape))

est = DecisionTreeRegressor().fit(X_train, y_train)

validation_score = metrics.explained_variance_score(
    y_test, est.predict(X_test))

print("validation: %r" % validation_score)

training_score = metrics.explained_variance_score(
    y_train, est.predict(X_train))

print("training: %r" % training_score)

from sklearn.ensemble import GradientBoostingRegressor
est = GradientBoostingRegressor().fit(X_train, y_train)

validation_score = metrics.explained_variance_score(
    y_test, est.predict(X_test))

print("validation: %r" % validation_score)

training_score = metrics.explained_variance_score(
    y_train, est.predict(X_train))

print("training: %r" % training_score)

from sklearn.svm import LinearSVC
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier




%load solutions/05C_validation_exercise.py