def ejemplo_clasificacion(): from sklearn.datasets import make_classification from sklearn.neighbors import KNeighborsClassifier from adspy_shared_utilities import plot_two_class_knn X,y=make_classification(n_samples=300,n_features=2,n_redundant=0,n_informative=2,n_clusters_per_class=1,flip_y=0.1,class_sep=0.5,random_state=0) X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0) plot_two_class_knn(X_train,y_train,3,'uniform',X_test,y_test)
def binary_data():
plt.figure()
plt.title(
'Sample binary classification problem with two informative features')
X_C2, y_C2 = make_classification(n_samples=100,
n_features=2,
n_redundant=0,
n_informative=2,
n_clusters_per_class=1,
flip_y=0.1,
class_sep=0.5,
random_state=0)
plt.scatter(X_C2[:, 0],
X_C2[:, 1],
c=y_C2,
marker='o',
s=50,
cmap=cmap_bold)
plt.show()
X_train, X_test, y_train, y_test = train_test_split(X_C2,
y_C2,
random_state=0)
plot_two_class_knn(X_train, y_train, 1, 'uniform', X_test, y_test)
plot_two_class_knn(X_train, y_train, 3, 'uniform', X_test, y_test)
plot_two_class_knn(X_train, y_train, 11, 'uniform', X_test, y_test)
plt.show()
(X_cancer, y_cancer) = load_breast_cancer(return_X_y=True)
# Communities and Crime dataset
(X_crime, y_crime) = load_crime_dataset()
# ## K-Nearest Neighbors
# ### Classification
# In[ ]:
from adspy_shared_utilities import plot_two_class_knn
X_train, X_test, y_train, y_test = train_test_split(X_C2, y_C2, random_state=0)
plot_two_class_knn(X_train, y_train, 1, 'uniform', X_test, y_test)
plot_two_class_knn(X_train, y_train, 3, 'uniform', X_test, y_test)
plot_two_class_knn(X_train, y_train, 11, 'uniform', X_test, y_test)
# ### Regression
# In[ ]:
from sklearn.neighbors import KNeighborsRegressor
X_train, X_test, y_train, y_test = train_test_split(X_R1, y_R1, random_state=0)
knnreg = KNeighborsRegressor(n_neighbors=5).fit(X_train, y_train)
print(knnreg.predict(X_test))
print('R-squared test score: {:.3f}'.format(knnreg.score(X_test, y_test)))
# Breast cancer dataset for classification
cancer = load_breast_cancer()
X_cancer, y_cancer = load_breast_cancer(return_X_y=True)
# Communities and Crime dataset
X_crime, y_crime = load_crime_dataset()
# Target valuje to predict: per capita violent crime rate.
""" ====K-Nearest Neighbors==== """
# Classification
from adspy_shared_utilities import plot_two_class_knn
X_train, X_test, y_train, y_test = train_test_split(X_C2, y_C2, random_state=0)
# Figures 5-7
plot_two_class_knn(X_train, y_train, 1, "uniform", X_test, y_test) # Overfitting for complex model b/c too much variance.
plot_two_class_knn(X_train, y_train, 3, "uniform", X_test, y_test) # General trend more properly captured. Less accuracy in training set,
plot_two_class_knn(X_train, y_train, 11, "uniform", X_test, y_test) # But more accuracy in test set.
# Regression
from sklearn.neighbors import KNeighborsRegressor
X_train, X_test, y_train, y_test = train_test_split(X_R1, y_R1, random_state=0)
knnreg = KNeighborsRegressor(n_neighbors=5).fit(X_train, y_train)
print(knnreg.predict(X_test))
print("R-squared test score:{:.3f}\n".format(knnreg.score(X_test, y_test)))
fig, subaxes = plt.subplots(1, 2, figsize=(8,4))
X_predict_input = np.linspace(-3, 3, 50).reshape(-1, 1) # Linspace uses # of samples instead of step size, then reshapes it to (inferred, 1 column)
X_train, X_test, y_train, y_test = train_test_split(X_R1[0::5], y_R1[0::5], random_state=0) # Only take a sample amount of the data.
