Criminal/learning_curve.py

import sys
import numpy as np
import matplotlib.pyplot as plt
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.model_selection import ShuffleSplit
from sklearn.linear_model import LinearRegression
from sklearn.learning_curve import learning_curve
from sklearn.metrics import explained_variance_score, make_scorer
from sklearn.cross_validation import KFold


def set_trace():
    """A Poor mans break point"""
    # without this in iPython debugger can generate strange characters.
    from IPython.core.debugger import Pdb
    Pdb().set_trace(sys._getframe().f_back)

print(__doc__)

import numpy as np
import matplotlib.pyplot as plt
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.datasets import load_digits
from sklearn.model_selection import learning_curve
from sklearn.model_selection import ShuffleSplit


def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
    plt.figure()
    plt.title(title)
    if ylim is not None:
        plt.ylim(*ylim)
    plt.xlabel("Training examples")
    plt.ylabel("Score")
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
    train_scores_mean = np.mean(train_scores, axis=1)
    train_scores_std = np.std(train_scores, axis=1)
    test_scores_mean = np.mean(test_scores, axis=1)
    test_scores_std = np.std(test_scores, axis=1)
    plt.grid()

    plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
                     train_scores_mean + train_scores_std, alpha=0.1,
                     color="r")
    plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
                     test_scores_mean + test_scores_std, alpha=0.1, color="g")
    plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
             label="Training score")
    plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
             label="Cross-validation score")

    plt.legend(loc="best")
    return plt


def get_learning_curve(X, y):
    title = "Learning Curves (Naive Bayes)"
    # Cross validation with 100 iterations to get smoother mean test and train
    # score curves, each time with 20% data randomly selected as a validation set.
    title = "Learning Curves (SVM, RBF kernel, $\gamma=0.001$)"
    # SVC is more expensive so we do a lower number of CV iterations:
    cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
    estimator = SVC(gamma=0.001)
    plt = plot_learning_curve(estimator, title, X, y, cv=None, n_jobs=1)
    plt.show()    
    set_trace()

'''    
def plot_learning_curve(x_std, y):
    size = 1000
    cv = KFold(size, shuffle=True)
    X = np.reshape(np.random.normal(scale=2, size=size), (-1, 1))
    X.shape
    y = np.array([[1 - 2 * x[0] + x[0]**2] for x in X])
    y.shape
    
    lg = LinearRegression()
    lg.fit(X, y)
    train_sizes, train_scores, test_scores = learning_curve(
        lg, X, y, n_jobs=-1, cv=cv, train_sizes=np.linspace(.1, 1.0, 5), verbose=0)

    train_scores_mean = np.mean(train_scores, axis=1)
    train_scores_std = np.std(train_scores, axis=1)
    test_scores_mean = np.mean(test_scores, axis=1)
    test_scores_std = np.std(test_scores, axis=1)

    plt.figure()
    plt.title("Linear Regression")
    plt.legend(loc="best")
    plt.xlabel("Training examples")
    plt.ylabel("Score")
    plt.gca().invert_yaxis()

    # box-like grid
    plt.grid()

    # plot the std deviation as a transparent range at each training set size
    plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
                     train_scores_mean + train_scores_std, alpha=0.1, color="r")
    plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
                     test_scores_mean + test_scores_std, alpha=0.1, color="g")

    # plot the average training and test score lines at each training set size
    plt.plot(train_sizes, train_scores_mean, 'o-',
             color="r", label="Training score")
    plt.plot(train_sizes, test_scores_mean, 'o-',
             color="g", label="Cross-validation score")

    # sizes the window for readability and displays the plot
    # shows error from 0 to 1.1
    plt.ylim(-.1, 1.1)
    plt.show()
'''



'''

def plot_learning_curve(estimator, title, x_std, y, ylim=None, cv=None, n_jobs=1):

    train_sizes = 100
    plt.figure()
    plt.title(title)
    if ylim is not None:
        plt.ylim(*ylim)
    plt.xlabel("Training examples")
    plt.ylabel("Score")
    set_trace()
    train_sizes, train_scores, test_scores = learning_curve(estimator, x_std, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
    train_scores_mean = np.mean(train_scores, axis=1)
    train_scores_std = np.std(train_scores, axis=1)
    test_scores_mean = np.mean(test_scores, axis=1)
    test_scores_std = np.std(test_scores, axis=1)
    plt.grid()

    plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
                     train_scores_mean + train_scores_std, alpha=0.1,
                     color="r")
    plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
                     test_scores_mean + test_scores_std, alpha=0.1, color="g")
    plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
             label="Training score")
    plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
             label="Cross-validation score")

    plt.legend(loc="best")
    return plt



 

    title = "Learning Curves (Naive Bayes)"
     # Cross validation with 100 iterations to get smoother mean test and train
     # score curves, each time with 20% data randomly selected as a validation set.
    #cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)

    cv = KFold(train_sizes, shuffle=True)
    estimator = GaussianNB()
    plot_learning_curve(estimator, title, x_std, y, ylim=(0.7, 1.01), cv=cv, n_jobs=4)

    title = "Learning Curves (SVM, RBF kernel, $\gamma=0.001$)"
    # SVC is more expensive so we do a lower number of CV iterations:
    cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
    estimator = SVC(gamma=0.001)
    plot_learning_curve(estimator, title, x_std, y, (0.7, 1.01), cv=cv, n_jobs=4)

    plt.show()
'''